EP4732289A1

EP4732289A1 - Method for determining a target synthesis specification of a polymer foam

Info

Publication number: EP4732289A1
Application number: EP23942714.9A
Authority: EP
Inventors: Volker SETTELS; Ning Wang; Sandra GONZALEZ MALDONADO; Maximilian JOOST; Robert Frenzel; Holger Haschke; Richard Igor LINDER; Mengmeng ZHAO; Berend Eling
Original assignee: BASF SE
Current assignee: BASF SE
Priority date: 2023-06-26
Filing date: 2023-06-26
Publication date: 2026-04-29
Also published as: WO2025000185A1; CN121399691A

Abstract

The invention refers to a method for determining a target polymer foam. A target property and a digital representation of a potential target synthesis specification indicative of characterizing parameters of the polymer forming the polymer foam and foam characteristics are provided. A property model adapted to determine a property of a polymer foam based on the characterizing parameters of the polymer forming the polymer foam and the foam characteristics is provided. The property model is a data-driven model parameterized such that it can determine a property of a polymer foam based on characterizing parameters of the polymer forming the polymer foam and based on foam characteristics. The property of the potential target polymer foam is determined based on the provided property model and the digital representation. The determined property of the potential target polymer foam is compared with the target property to determine the target polymer foam.

Description

Method for determining a target synthesis specification of a polymer foam

FIELD OF THE INVENTION

The invention relates to a method, an apparatus and a computer program product for determining a target synthesis specification indicative of a target polymer foam comprising a target technical application property. Moreover, the invention refers to a training method, a training apparatus and a training computer program product for training a data-driven property model usable for determining the properties of a polymer forming a polymer foam. Furthermore, the invention refers to an interface method, an interface apparatus and an interface computer program product for providing an interface for interfacing with any of the above methods, apparatuses and computer program products.

BACKGROUND OF THE INVENTION

Generally, polymer foams are widely used in industrial and/or daily use products due to their broad range of application properties. The use of polymer foams encompasses amongst others damping materials, thermal and acoustic insulation, coatings, furniture and beddings, packaging materials and absorbents. Typically, the efficient determina-tion of technical application properties of the polymer is a challenging problem with high industrial relevance. Moreover, since for a specific application it is often required that a polymer foam provides very specific predetermined properties, there is not only a need for polymer foams with desired properties to be found, but also a need to take into account knowledge about the properties of a polymer foam in early stages of a product design process.

SUMMARY OF THE INVENTION

It is an object of the present invention to provide a method, an apparatus and a computer program product for determining a target synthesis specification indicative of a target polymer foam comprising a target technical application property that allows for an accurate determination and is computationally inexpensive. Moreover, it is further an object of the invention to provide a training method, a training apparatus and a computer program product that allow to provide a property model that is usable in the method, apparatus and computer program product and that can be trained to provide a good determination accuracy by utilizing less computational resources.
In a first aspect of the present invention a computer-implemented method for determin-ing a target synthesis specification indicative of a target polymer foam comprising a target technical application property is presented, wherein the method comprises a) providing a target technical application property, wherein the target technical applica-tion property is indicative of a technical characteristic of a polymer foam, b) providing a digital representation of a potential target synthesis specification indicative of or associated with characterizing parameters of the polymer forming the polymer foam and foam characteristics of the polymer foam, wherein the characterizing parameters are indicative of characteristics of a polymer and/or are derivable from one or more characteristics of the polymer and the foam characteristics are indicative of characteris-tics of the foam structure of the polymer foam, c) providing a property model adapted to determine a technical application property of a polymer foam based on the characteriz-ing parameters of the polymer forming the polymer foam and the foam characteristics of the polymer foam, wherein the property model is a data-driven model parameterized such that it can determine a technical application property of a polymer foam based on characterizing parameters of the polymer forming a polymer foam and based on foam characteristics, d) determining the technical application property of the potential target polymer foam based on the provided property model and the digital representation, and e) comparing the determined technical application property of the potential target polymer foam with the target technical application property and, based on the compari-son, either i) determining the potential target polymer foam as the target polymer foam and the potential target synthesis specification as the target synthesis specification, or ii) providing a new potential target synthesis specification of a new potential target polymer foam and repeating the determination of the technical application property utilizing the new potential target synthesis specification of the new potential target polymer foam.
Since the property model is configured to determine a technical application property of a polymer foam based on provided characterizing parameters of the polymer forming the polymer foam and the foam characteristics of the polymer foam, the technical application property can be learned very accurately. Moreover, since the property model can be trained for a specific technical application property of a polymer foam with respective characteristics of the polymer forming the polymer foam and foam characteristics of the polymer foam, less training data becomes necessary and the property model becomes more flexible with respect to determining the technical application property of a new polymer foam not being part of the training dataset. Thus, the method allows for an accurate determination of a technical application property indicative of technical characteristics of a polymer foam that is computationally inexpensive and can be applied flexibly also to determining and/or creating new polymer foams, wherein new polymer foams can comprise or consist of new polymers. Thus, the property model becomes more robust for determining a target synthesis specification indicative of a target polymer foam comprising a target technical applica-tion property.
Moreover, since the characterizing parameters are utilized that contain physicochemi-cal information of the polymer forming the polymer foam, e.g. glass transition tempera-ture of the polymer, and foam characteristics, e.g. structural information of the foam like a foam density, the training of a respective property model can be improved. In particular, utilizing the characterizing parameters and foam characteristics allows training of such models with less training data, because some of the correlation information that needs to be learned is already presented to the model by using the characterizing parameters and foam characteristics. This further allows to reduce required tests and experiments necessary for providing the training data set.
Generally, companies developing new polymer foams need to invest significant resources in self-assessing product properties and often also in certification of such properties, for example, burning properties. The overall technical application property assessment, including the elaborate experiments, sample preparation, standard measurements and testing of polymers and polymer foams for specific properties desired for specific applications, laboratory spaces and equipment, becomes costly and time consuming. Thus, it is of great interest to substitute this assessment with well-designed digital tools to help user, for example a technical product engineer to early identify the technical application properties of a new material in the development process. The proposed method of determining technical application properties as disclosed herein enables a faster and more efficient way of developing new materials. In an early phase, even before synthesis of the polymer foam, the technical application properties can be determined. This allows to determine whether the polymer foam is suited for market entry. This leads to a faster time to market. This also allows to reduce waste production, because the polymer foam does not need to be synthesized to determine technical application properties and the number of required mechanical and processing tests during development is reduced. The proposed method provides a digital twin of measuring the technical application property of a polymer foam and leads to recipe for how to produce the associated polymer foam.
Moreover, due to the incredibly high number of possible, often not even fully explored polymers and respective polymer foams, potentially suitable for a specific application, today a technical product engineer, given the technical task of finding a polymer foam that is not only suitable for a specific application, but also fulfills respective target properties, as for example, a rebound, has to synthesize and test huge amounts of possible polymer foams, or go through huge datasets and libraries in which potential polymers and foam structures are stored in order to find a respective polymer foam that might fit the application. Even when utilizing sophisticated design of experiment methods, still a very high number of possible polymer foams has to be synthesized and experimentally tested. In this context the above described method allows to assist a user, for instance, a technical product engineer, to find potentially suitable polymers automatically and much faster. In particular, by utilizing the above method the user only has to synthesize and test potentially suitable polymer foams for which it has been determined that it is very likely that they fulfill the respective target property, as for example, a target rebound. Accordingly, unnecessary synthesizing and testing of polymer foams can be avoided. Thus, the method allows a user to perform a technical task of finding a polymer foam suitable for a technical application faster and more efficient.
In many of the applications of the polymer foam some foam properties are more desirable than others by the end user. Also, in addition to the properties of the polymer forming the polymer foam, the foam properties of the polymer foam have to be taken into account. In some cases, it is desirable by the user to find a polymer foam that meets a certain technical application property, like rebound, and also meets another technical application property like tear-strength. The method disclosed in this applica-tion utilizes the property model that helps to find and to focus on a potential polymer with promising properties fitting for production of a polymer foam with features suitable for a specific application.
The method refers to a computer implemented method and can thus be performed by a general or dedicated computer adapted to perform the method, for instance, by executing a respective computer program. The method is adapted to determine, in particular, predict, a target synthesis specification indicative of a target polymer foam comprising a target technical application property. Generally, a synthesis specification includes instructions on how a specific associated polymer foam can be produced. For example, a synthesis specification can refer to starting products and production conditions that, if applied, lead to a synthesis of the polymer foam in the production process. Thus, a synthesis specification is associated always with the polymer foam that is produced when performing the synthesis specification, for instance, utilizing suitable laboratory or industrial equipment. In particular, a synthesis specification can also be regarded as a recipe for how to produce the associated polymer foam. Since the target synthesis specification and the target polymer foam correspond to each other, i.e. the target synthesis specification, when executed accordingly, produces the target polymer foam, in the following both terms can be utilized concurrently, for example, when a target synthesis specification is determined the target polymer foam is also determined and vice versa. The synthesis specification can be utilized for generating control data for controlling a chemical plant for producing the polymer foam including, but not limited to determining, raw materials, temperatures, e.g. temperatures of storage tanks, piping, molds, etc., flow rates, mixing head rotation speed, cycle times.
A polymer foam refers to a polymer comprising the shape of a foam. The shape of the polymer foam refers to a polymer matrix consisting of a polymeric base material, i.e. base polymer and herein also only referred to as polymer, and a plurality of voids dispersed within the polymer matrix. Generally, the polymer foam comprising a technical application property can be any polymer foam. In addition, the polymeric base material can be any suitable polymer. Preferably, the polymer foam is a synthetic polymer foam. In particular, the synthetic polymer foam comprises a synthetic polymer. The voids dispersed within the polymer matrix can be formed by a foaming agent that is added to the composition and subsequently is activated by an external stimulus. The foaming agent can be a reactive component, which chemically reacts by forming a gas. The foaming agent can be any suitable chemical compound or physical agent that is capable of generating gas bubbles within the polymer matrix. The gas bubbles generated by the foaming agent create voids, also referred to as pockets, filled with gas. The bubbles could be connected resulting in an open celled foam. However, the voids can also be generated by a foaming process in which the base polymer and potential additives and other components are heated and subjected to pressurized gas causing a foaming of the base polymer and resulting in a respective polymer foam. An example of such a process is any polymer extrusion process.
Generally, the base polymer can be any polymer. Preferably, the base polymer is a synthetic polymer. In an embodiment, a synthetic polymer may be a chemical com-pound which is produced by a chemical production from one or more starting materi-al(s) , such as monomers, and which comprises at least two monomer units. The monomer may be already a polymer itself. The monomer units may be regarded as subunits of the polymer. The base polymer may be prepared from the monomers by commonly known polymerization reactions. The base polymer may be produced from a single type of monomers or from different monomers. The monomer units may be distributed randomly or may be present as blocks within the base polymer. The base polymer may be a linear polymer. The base polymer may be a branched polymer. The base polymer may be a crosslinked polymer.
In a first step, the method comprises providing a target technical application property indicative of a technical characteristic of a polymer foam. In particular, the providing can refer to receiving the target technical application property from an input of a user using, for instance, a respective input unit and providing the received target technical application property for further processing. Moreover, the providing can also refer to accessing a storage unit in which a target technical application property is already stored and providing the same for further processing. Further, the providing can also comprise receiving a target technical application property, for instance, via a network connection from other sources and providing the received target technical application property. Generally, the target technical application property is associated or indicative of one or more target technical characteristic of a polymer foam. For example, the target technical application property can be directly provided such that respective target values or target ranges for the target technical characteristic are provided. For example, the target technical application property can be provided in form of any kind of identifi-cation, for instance, a short description of the target technical application property, or an intended application of the target technical application property, wherein in this case a look-up table can be provided, for instance, on a storage, such that the providing can comprise accessing the look-up table and determining target values or target value ranges of target technical characteristic associated in the look-up table with the respective target technical application property. However, the target technical applica-tion property can also directly comprise the target technical characteristic of a polymer foam.
In particular, the technical application property can refer to any property of a polymer foam that allows to assess a technical applicability of the respective polymer foam as provided after its synthesis. The technical application property of a polymer foam is indicative of a technical property of a polymer foam. Assessing may involve testing the polymer foam in relevant conditions as defined for example in the standard specifica-tions or norm of a given test of the respective technical application property. The technical property is evaluated based on specific output parameters as defined in the respective norm describing the test. Finally, the technical property of the polymer foam may be compared to the requirements of the technical application.
In particular, a target technical application property is indicative of a technical charac-teristic of a polymer foam. Generally, the technical characteristic of a polymer foam can refer to any characteristic that allows for a quantification of the technical application property, for example, to determine how the polymer foam will react in a certain situation and can be evaluated to determine its suitability for a specific technical application. The determined one or more technical characteristic can refer only to one value, for instance, to a rebound, but can also refer to more than one value, for instance, can refer to a range of values. The technical characteristic of a polymer foam is indicative of the performance and behavior of the polymer foam in a particular technical application or environment, and can help to determine whether the foam is suitable for use in that application by, for example, determining how the polymer foam will behave in a certain situation. The determined technical characteristic of a polymer foam then allows to evaluate the technical application property. This evaluation of the technical application property also allows to estimate the suitability of the polymer for a certain application situation, for example, when provided as a part of a predetermined product and subjected to an impact by an object that will or will not rebound. In a preferred embodiment, the technical characteristic of a polymer foam is a characteristic associated with the foam nature of the polymer foam, even more preferably with a mechanical characteristic of the polymer foam that is caused by the foam nature of the polymer foam. Preferably, one or more technical characteristic of a polymer foam indicative of the technical application property comprises at least one of mechanical properties, optical properties, physicochemical properties, chemical properties and biological properties. Generally, mechanical properties can refer to, but are not limited to, any of adhesion, stiffness, hardness, shore hardness, compression hardness, compression set, compressive strength, shrinkage, elongation, split tear strength, tear-strength, rebound, compressibility, abrasion, spillage, morphology, haptic properties, stress at break, tensile strength, elongation at break, shock attenuating characteristics, e.g. absorbed energy loss during hysteresis cycle, peak pressure, maximum strain, and average stiffness, air permeability, granulometry and a degree of filling. An optical property can generally comprise any of coloration, turbidity, opaqueness, lucidity, reflection, appearance, absorption, scattering, color strength, cloud point, matting degree, optical density, spectra, refractive index. Moreover, a physicochemical property can refer to any of density, molar weight, molar mass distribution, particle size distribu-tion, solubility, storage stability, odor, segregation, coagulation, electric conductivity, electric capacity, surface area, vapor pressure, VOC, solid content, hygroscopicity, magnetism, miscibility, phase transition properties, glass transition temperature, corrosion inhibition, aggregation, self-heating ability, impact sensitivity, angle of response, electrostatic charge, and charge density. The chemical property can comprise any of chemical resistance, reaction timing, demolding time, growing, hard/soft segment content, crystallinity, reaction temperature, reaction pressure, decomposition, thermal decomposition, photodegradation, flammability, burning rate, selfignition, flash point, formation of flammable gases, reaction to fire, deflagration rate, residual monomer count, side product formation, degree of polymerization, salt content, temperature tolerance, oxidizing properties, reduction properties, reactivity, ash content, nonvolatile matter content, stability, chelating ability, calorific value, saponification value, raw material recovery rate, depolymerization rate, recycling rate, environmental impact of end of life scenarios, impact on circular economy, re-usage abilities. The thermal property can comprise any of thermal conductivity, thermal stability, thermal degradation, thermal load, specific heat capacity and thermal resistance. Further, the biological property can comprise any of biodegradability, biological resistance, toxicity, biotransformation, ecotoxicology, sensitization, bacterial count, enzyme activity, distribution in environment, bioaccumulation, biological exposure.
In a second step, the method comprises providing a digital representation of the potential target synthesis specification of a potential target polymer foam. In particular, the providing can refer to receiving the digital representation from an input of a user using, for instance, a respective input unit. Moreover, the providing can also refer to accessing a storage unit on which the digital representation is already stored. Further, the providing can also comprise receiving characterizing parameters of the polymer forming the polymer foam and foam characteristics of the polymer foam, for instance, via a network connection from other sources and providing the received characterizing parameters of the polymer forming the polymer foam and foam characteristics of the polymer foam as digital representation. The digital representation can be any represen-tation, for example, any data format or structure, that allows a respective computer system performing the method to read the digital representation.
In particular, the digital representation is indicative of or associated with the character-izing parameters of the polymer forming the polymer foam and foam characteristics of the polymer foam. The “indicative of or associated” is defined herein as providing a relation between the digital representation and the characterizing parameters and foam characteristics such that the characterizing parameters and the foam characteristics can be derived from the digital representation. For example, providing as digital representation an ID of a specific polymer foam allows to access respective databases to receive further information on the polymer foam, that can also be represented by a respective synthesis specification, like at least some of the characterizing parameters, at least some of the foam characteristics, synthesis specifications, structural formulas, etc. If not already present, this information allows to derive the respective characteriz-ing parameters and foam characteristics of the polymer foam, for instance, utilizing respective calculation methods. Thus, an ID of the polymer foam allows to derive the characterizing parameters of the polymer forming the polymer foam and foam charac-teristics of the polymer foam and is thus associated with or indicative of characterizing parameters of the polymer forming the polymer foam and foam characteristics of the polymer foam. Preferably, the digital representation refers to at least one of a recipe, a structural formula, a brand name, an IUPAC name, a chemical identifier and a CAS number of the polymer foam.
The characterizing parameters of the polymer are preferably indicative of physicochem-ical parameters. Preferably, the digital representation is indicative of and/or comprises polymer physicochemical parameters quantifying the characterizing parameters of the polymer forming the polymer foam, preferably, referring to polymer descriptors. The digital representation can also be provided such that it allows to derive physicochemi- cal characteristics, for example, in form of polymer descriptors, for instance, by providing a representation of the polymer for which respective physicochemical characteristics are already stored or can be determined, for instance, by respective polymer descriptor calculations.
The digital representation can also refer to or comprise directly a potential target synthesis specification of potential target polymer foam, wherein at least some of the characterizing parameters and foam characteristics can then be derived from the synthesis specification. The synthesis specification, for example, may refer to process parameters, like a temperature, pressure, moisture or other environmental specifica-tions for synthesizing the polymer foam, recipe parameters indicative of substances and/or amounts of substances that are utilized in the synthesis, wherein the recipe parameters can comprise an amount of certain prepolymers, an amount of a catalyst, an amount of fire protective additives, respective foaming agents, etc.
In an embodiment, the digital representation can also be provided such that it allows to derive the polymer characterizing parameters of the polymer forming the polymer foam by determining subgroups of the polymer and to determine the polymer characterizing parameters based on characterizing parameters of the determined subgroups. Generally, a subgroup refers to a part of the polymer, wherein all subgroups of a polymer together form the polymer. For example, a subgroup can refer to a part of the polymer, wherein the subgroups are linked together successively along a chain or network to form the polymer. Preferably, the subgroups of the polymer refer to repeat-ing units that describe a part of the polymer which when repeated produces the complete polymer chain. However, in some cases, a subgroup can also refer to a single part of the polymer that is not repeated. Moreover, it is preferred that the subgroups comprise parts that are repeated, for example, a subgroup of a polymer can comprise a repeating core also present in other subgroups and further additional parts that are not present in other subgroups. Preferably, the subgroups refer to at least one of polymerized monomers or oligomer fragments. More preferably, the subgroups refer to polymerized monomers. In this context, polymerized monomers refer to monomers after their polymerization sometimes also called “mer unit” or “mer” . In particular, polymerized monomers do not refer to monomers, i.e. raw materials, as present in a reaction mixture before polymerization, but refer to repeating units derived from monomers that have been changed during or after the polymerization. Thus, subgroup descriptors determined for polymerized monomers are different from subgroup descriptors determined for unreacted monomers before polymerization.
In an embodiment, the digital representation of the polymer comprises subgroups provided as molecular model which is indicative of its chemical structure of the subgroup after its polymerization. Preferably, the molecular model of a subgroup is determined in a way that is suited for quantum chemical computations regarding a number and type of atoms and their connectivity that is representative of the properties of the subgroup within the polymer. Moreover, additionally and alternatively to a molecular model of a subgroup treating the subgroup as a monomer structure, also a molecular model referring to an oligomer model can be utilized that takes into account effects of neighboring molecular structures of the subgroup in the polymer.
Generally, if the digital representation of polymer foam does not directly comprise the polymer characterizing parameters, in particular, the physicochemical parameters, it is preferred that the polymer characterizing parameters are determined by determining the subgroups of the polymer. For example, respective subgroups of the polymer can be determined utilizing known methods. However, it is preferred that the determination of the subgroups of the polymer is performed in accordance with later described embodiments of the invention. In particular, it is preferred that the subgroups are determined such that between atoms of different subgroups in the polymer the bond is as least polarized as possible and, preferably, with a bond order as small as possible (e.g. a CC single bond) . Additionally, it is preferred that the subgroups representing a polymer comprise the same number of active non-hydrogen-atoms then as the polymer. Besides the active atoms, a subgroup can also contain further atoms, which can be ignored during computing the descriptors of the subgroup. Further, it is preferred that the subgroups are determined in a way that polymers comprising parts, which were built up with different polymerization techniques, are well covered and fulfil the foresaid conditions. An example is a polyether used as ingredient for a polyurethane. Generally, a database or archive with a plurality of reactions between polymer parts can be generated and the subgroups can be derived from the respective structure of the reactions. For example, specific chemical languages like SMILES (Simplified Molecular Input Line Entry Specification) and SMARTS (SMILES arbitrary target specification) can be utilized to easily derive the subgroup of a polymer. For example, a database of reaction SMARTS can be generated and then based on the polymerization of the respective polymer a corresponding reaction SMARTS can be selected. From the selected reaction SMARTS then the SMILES of monomers of the polymer are directly derivable and, for example, RDkit can be used to determine from the SMILES of the monomers the SMILES, i.e. the number and connectivity of the atoms, of the sub-groups.
The determined subgroups of the polymer are associated with subgroup characterizing parameters quantifying physicochemical characteristics of the subgroups in the polymer, preferably, also the subgroup characterizing parameters refer to subgroup descriptors. In particular, it is preferred that if the polymer characterizing parameters are not directly provided by the digital representation, the polymer characterizing parameters are determined by determining a respective subgroup characterizing parameter for each of the subgroups and to determine the polymer characterizing parameters based on the subgroup characterizing parameters of the subgroups, for instance, by averaging. Thus, the method preferably comprises first providing or determining for the polymer the subgroups from the digital representation of the polymer, then to determine or provide the subgroup characterizing parameters, i.e. values of the parameters quantifying the physicochemical characteristics, of the subgroups, and then to determine the polymer characterizing parameters based on the subgroup characterizing parameters of each polymer.
Preferably, the polymer characterizing parameters refer to polymer descriptors referring to at least one of constitutional descriptors, count descriptors, list of structural frag-ments, fingerprints, graph invariants, 3D-descriptors and/or higher dimensional descriptors that are indicative of parameters quantifying characterizing parameters of the polymer. In a preferred embodiment the polymer descriptors refer to constitutional and count descriptors. Moreover, it is preferred that process parameters indicative of the synthesis of the polymer are also utilized.
Generally, polymer characterizing parameters can be derived from the subgroup physicochemical parameters, thus, also the subgroup characterizing parameters can refer to the same descriptors as stated above. However, the characterizing parameters can also be derived without utilizing subgroups, for instance, by quantum chemical simulations of the whole polymer. In the following the possible characterizing parame-ters are defined in more detail. Also in these cases the defined characterizing parame-ters can refer directly to the polymer characterizing parameters or, optionally, to the subgroup characterizing parameters.
A constitutional descriptor can refer to any of a potential, average molecular weight, polydispersity, charge, spin, boiling point, melting point, enthalpy of fusion, dissociation constant, Hansen parameter, protic, polar and dispersive contributions, Abraham parameter, retention index, TPSA (topological polar surface area) , receptor binding constant, Michaelis-Menten constant, inhibitor constant, mutagenicity, LD50 (lethal dose, 50%) , bioconcentration, toxicity, biodegradation profile and viscosity.
A count descriptor can refer to any of a sum of atomic electro negativities, a sum of atomic polarizabilities, an amount of ingredients, a ratio of amounts of ingredients, a number of atoms and non H-atoms, a number of H, B, C, N, O, P, S, Hal and heavy atoms, a number of H-donor and H-acceptor atoms, a number of bonds, non-H or multiple bonds, a number of double, triple and aromatic bonds, a number of functional groups, a ratio of functional groups, a sum of bond orders, an aromatic ratio, a number of rings or circuits, a number of unpaired electrons, a number of rotatable bonds, rotatable bond fractions, and a number of conformers.
Polymer descriptors referring to a list of structural fragment descriptors can refer to at least one of a list of molecular fractions, a list of functional groups, a list of bonds, and a list of atoms. Fingerprint descriptors comprise preferably, at least one of MACCS (Molecular ACCess System) keys, preferably, in bit format or total amount format, Morgan and other circular fingerprints, preferably, in bit format or total amount format, topological torsion, atom pairs, infrared and related spectra, fingerprint count, Pub-Chem fingerprint, substructure fingerprint, and Klekota-Roth fingerprint. Graph invari-ants/topological indices descriptors comprise preferably at least one of topostructural indices and topochemical indices.
In a preferred embodiment the polymer characterizing parameters are 3D descriptors comprising at least one of a volume as sum overall atoms, a mean volume per atom, an area as sum overall atoms, an area as mean per atom, an area over all atoms, an area as mean per atom, a solvent accessible surface, a dispersion energy, a dielectric energy, a H-donor, H-acceptor, polar and non-polar surface area, an atom resolved H-donor, H-acceptor, polar and non-polar surface area, a shape, a sphericity, dipole and higher electric moments, polarizability, dielectric energy, protic, polar and non-polar surface area, orbital energies and orbital gaps, ionization energy, electron affinity, hardness, electronegativity, electrophilicity, excitation energies and intensities, infrared and ultraviolet absorption bands, reactivity measurements, redox potential, bond criterial points, partial charges, charge surface areas, atomic orbital contributions, bond orders, atom radius.
In particular, it is preferred that the polymer characterizing parameters refer to 3D descriptors comprising at least one of a sum of a volume over all atoms, a mean of a volume per atom, a sum of the area over all atoms, a mean of an area per atom, a solvent accessible surface, a dispersion energy, a dielectric energy, a H-donor, H-acceptor, polar and/or non-polar surface area, atom resolved H-donor, H-acceptor, polar and/or non-polar surface area, shape, sphericity, cone angles, polarizability, dielectric energy, protic, polar and/or non-polar surface area, excitation energies and intensities, infrared and/or UV absorption bands, reactivity measurements, particle charges and/or charge surface areas. A preferably utilized higher dimensional de-scriptor can comprise at least one of a conformational partition function, solubility, vapor pressure, activity coefficient, diffusion coefficient, partition coefficient, interfacial activity, rotational constant, moment of inertia, radius of gyration, compositional drift of polymer, density, viscosity, conformer weighted volume and area, conformer weighted H-donor, H-acceptor, protic, polar and/or non-polar surface area, charge distribution, conformational dipole moment and molecular refraction. Preferably higher dimensional descriptors are utilized that comprise at least one of solubilities, vapor pressure and activity coefficients, interfacial activity, conformer weighted H-donor, H-acceptor, protic, polar and non-polar surface area, and charge distribution.
Generally, foams refer to materials that are formed by trapping pockets of gas in a liquid or solid base material. Thus, a polymer foam refers to a polymeric base material in which pockets of gas have been trapped. Thus, generally the characteristics of a foam are defined by characteristics of the base material, in particular, by mechanical characteristics of the base material, and further the characteristics provided by the specific structure of the foam, in particular, by the structure of the gas pockets within the foam. For example, a size, distribution and density of the cavities, i.e.gas pockets, within the foam not only influence the mechanical structure of the foam but can also influence the technical application properties of the foam. Moreover, the gas filling the cavities can also provide an additional influence, for example, on burning properties, e.g., if the gas comprises a fire retarding characteristic, a high inflammability of a polymer forming the foam can in some cases be compensated leading to an overall acceptable inflammability. Moreover, polymer foams are used in a wide variety of applications since the foaming of the polymer allows to further alter the characteristics of the polymer, in particular, the mechanical characteristics, advantageously reduce the weight of respective foam products compared to a non-foaming material and to reduce the amount of resources used for a product. Thus, taking the foam characteristics quantifying the characteristics of the foam aspect of the polymer foam into account allows for a more accurate description of the polymer foam and thus also for a more accurate determination of respective technical application properties.
In particular, the digital representation of the polymer foam is indicative of or associated with foam characteristics. Foam characteristics are indicative of characteristics of the foam structure. Preferably, foam characteristics of the polymer foam can be quantified by foam parameters indicative of characteristics of the foam structure of the polymer foam, for example, the foam parameters can be processing conditions associated with and defining the forming of the polymer foam. In an embodiment, the foam characteris-tics are indicative of structural characteristics, compositional characteristics, topology characteristics, and foaming process characteristics. In a preferred embodiment, foam characteristics can be derived from the provided digital representation of a polymer foam. However, the foam characteristics can also be part of the digital representation, e.g. the digital representation can comprise the foam characteristics.
In particular, structural characteristics of the polymer foam can, for instance, refer to the structure of the polymer foam like a size, distribution or density of the cavities provided in the foam. Compositional characteristics of the polymer foam can refer to the composition of the polymer foam, in particular, to the polymeric base material and to the gas trapped in the cavities of the foam. The gas trapped in the cavities indicates what blowing agent has been used during processing of the polymer foam. In particular, the gas trapped in the cavities indicates interactions during the forming of the cavities. Preferably, the foam characteristics comprise at least one of information on a gas filling cavities of the foam and an average size of the cavities in the foam. Topology charac-teristics can refer to a 3D model of the shape of the formed foam structure, for instance, of the cavities. Generally, the foaming process characteristics can be provided for any form of production of the polymer foam. In particular, foaming process characteristics can refer to processing conditions of polymer foam or to processing conditions of already produced polymer during the foaming process. Processing conditions provide for a suitable polymer base material a foaming agent chosen based on an intended technical application property of a polymer foam. Foaming agents can be selected based on the desired technical application property of the resulting polymer foam, e.g. density, porosity, or average void size. The amount and type of foaming agent used can also affect the processing conditions required to create the polymer foam, e.g. temperature. A foaming agent can be a chemical foaming agent or physical foaming agent.
Generally, the polymer foam can be produced utilizing a respective synthesis specifica-tion that utilizes chemical reactions with chemical foaming agents within the used base materials to produce gas and thus initiate the foaming process of the polymer foam. Thus, the foaming processes can be part of the processing conditions of a base materials. However, the polymer foam can also be produced from any already pro-duced base polymer, for instance, provided in the form of polymer pellets, in a foaming process in which the base polymer is heated and a respective blowing agent, referred to as physical foaming agent, is utilized for mixing gas into the polymer to form the polymer foam.
In particular, the foaming process characteristics refer, for example, to process parameters of the foaming process, for example, to utilized blowing agents, foam temperature profiles, pressure profiles, foam cream time, gel time, start time, foam rise time, foam rise speed, free-rise density, demold time, etc. Preferably, foaming process parameters are utilized as foam characteristics, wherein the foaming process parame-ters can be derived, for example, from a synthesis specification provided as part of the digital representation. In particular, a blowing agent is a substance which is capable of producing a gaseous part of the foam structure that is producing voids in the polymer matrix via a foaming process. Thus, blowing agents may also be referred to as foaming agents. Foaming agents can be divided into physical foaming agents and chemical foaming agents.
A chemical foaming agent is a foaming agent that comprises a suitable chemical compound requiring a chemical reaction as an external stimulus for activation of processes generating voids in a polymer matrix is a chemical foaming agent. In particular, the chemical foaming agents typically consists of a chemical compound that releases gas when heated or reacted with another chemical component in the polymer matrix consisting of the polymer base material. The gas generated by the chemical foaming agent creates voids within the polymer matrix, resulting in a foam structure. The created voids are filled with the gas. The chemical foaming agents are for example azodicar-bonamide, sodium bicarbonate, and citric acid.
A physical foaming agent is a foaming agent that consists of a suitable chemical compound not requiring a chemical reaction but instead a physical stimulus for activation of processes generating voids in a polymer matrix consisting of polymer base material. The physical stimulus can be for instance heat, pressure, or mechanical mixing to create voids within the polymer matrix. The physical foaming agent can for example be a blowing agent such as carbon dioxide or nitrogen that injected into the polymer matrix under high pressure create voids and thus creates a polymer foam structure. The created polymer foam structure and the gas filling the voids together build the polymer foam.
In a preferred embodiment the foam characteristics comprise at least one of a foam cream time, foam rise time, tack-free time, foam rise speed, foam temperature, free-rise density, and demold time.
In a third step, the method comprises providing a property model adapted to determine a technical application property of a polymer foam, wherein the property model is based on the provided characterising parameters of the polymer forming the polymer foam and the foam characteristics of the polymer foam. In particular, it is preferred that the providing of the property model refers to a selecting of a property model based on the provided characterizing parameters of the polymer forming the polymer foam and the foam characteristics of the polymer foam. For example, a plurality of property models can be stored on a property model storage, wherein each property model has been trained for specific characterizing parameters of the polymer forming the polymer foam and the foam characteristics of the polymer foam. In particular, each property model has been trained for a specific technical application property. Based on the provided characterizing parameters of the polymer forming the polymer foam and the foam characteristics of the polymer foam indicative of the technical application property of a polymer foam, a respective suitable property model can then be selected from the plurality of property models. However, in another embodiment the providing of a property model based on the provided characterizing parameters of the polymer forming the polymer foam and the foam characteristics of the polymer foam can also refer to a user selection of the property model. For instance, the user can be provided with a preselection of property models that are commonly utilized or are used for a specific application of a polymer foam and then be allowed to select the respective property model that should be utilized.
The provided property model is then adapted to determine a technical application property of a polymer foam. In particular, the property model is a data-driven model that is parameterized such that it can determine a technical application property of a polymer foam based on the characterizing parameters of the polymer forming the polymer foam and the foam characteristics of the polymer foam, preferably, based on the characterizing parameters of the polymer forming the polymer foam and the foam characteristics of the polymer foam indicated by the digital representation. The property model relates the characterizing parameters of the polymer forming the polymer foam and the foam characteristics of the polymer foam of historic digital representations of synthesis specification and historic digital representations of characteristics of the foam structure of the polymer to respective technical application properties. The term “data-driven” is used here to emphasize that the model is mainly based on respective data input and not, for instance, on intuition, personal experience or knowledge. Preferably, the property model refers to a machine learning based model that is based on known machine learning algorithms, like neural networks, regression models, classification algorithms, etc. It has been found that for most applications in this context, in particular, regression models based on Linear Regression, Random Forests, Boosted Trees, LASSO, Ridge Regression and MARS algorithms are suitable, whereas for classifica-tion models, in particular, Random Forests, Logistic Regression and SVM algorithms are suitable. Generally, the property model is parameterized during a training process in which the characterizing parameters of the polymer forming the polymer foam and the foam characteristics of the polymer foam are utilized together with corresponding technical characteristic of a polymer foam. Based on such a training data set that is specific for characterizing parameters of the polymer forming the polymer foam and the foam characteristics of the polymer foam the respective parameters of the data-driven model can be determined utilizing known training methods such that the property model is also able to determine technical characteristics of a polymer foam that are not part of the training data set.
The method further comprises determining the technical application property of the potential target polymer foam based on the provided property model and the digital representation. In particular, if the digital representation of the polymer foam comprises the polymer characterizing parameters and polymer foam characteristics, the polymer characterizing parameters and polymer foam characteristics are provided as input to the property model, wherein the property model then provides the determined technical application property of the polymer foam as output. If the digital representation does not directly comprise the polymer characterizing parameters, and polymer foam characteristics, the determining of the technical application property of the polymer foam can comprise also determining firstly the polymer characterizing parameters and polymer foam characteristics, for instance, as described above. The such determined polymer characterizing parameters, and polymer foam characteristics can then be provided to the property model as input.
The determination of the technical characteristics of a polymer foam utilizing the property model can be regarded as a virtual measurement of the technical application property. In particular, the property model is based on measurement data, for example, measured properties of polymer foams utilized for the training of the property model. Thus, the property model comprises the information provided by these previous measurements. Moreover, the characterizing parameters can in some cases also refer to measured characteristics of the polymer foam. Accordingly, also the determined property of a new polymer foam determined utilizing the property model can be regarded as being based at least partly on measurement results.
In a following step, the determined technical application property of the potential target polymer foam is compared with the respective target technical application property. Based on the comparison it is decided if the potential target polymer foam is deter-mined as the target polymer foam and the potential target synthesis specification is determined as the target synthesis specification, wherein in this case the iteration can stop at this point. Moreover, based on the comparison it can also be determined to provide a new potential target synthesis specification of a new potential target polymer foam and to repeat the determination of the technical application property utilizing the new potential target synthesis specification of the new potential target polymer foam. Thus, at this point an iteration is performed in which the determination of the technical application property using the property model, the polymer characterizing parameters and the foam characteristics of potential target polymer foams is repeated until a potential target polymer foam is determined as the target polymer foam. In particular, the comparison can comprise determining whether the determined technical application property of a potential target polymer foam lies within a predetermined range around the respective target technical application property, wherein in this case the target can be regarded as being fulfilled and the potential target polymer foam is determined as target polymer foam. If the determined technical application property lies outside of the predetermined range around the technical application property, it can be determined that the target is not fulfilled and a new potential target synthesis specification of a new potential target polymer foam is provided that might fulfil the target technical application property.
Generally, the performed iteration can refer to an arbitrary search of the potential target polymer foam space or to a directed search. For example, a new potential target synthesis specification or a new potential target polymer foam can simply be selected arbitrarily from a huge amount of in-silico generated potential target polymer foams. However, also specific rules for generating a new potential target polymer foam and thus a new potential target synthesis specification can be applied based on the comparison between the determined technical application property and the target technical application property of the target polymer foam, with or without considering the simultaneous optimization of additional target properties of the polymer foam. Generally, known methods for generating new target polymer foams can be utilized, for example, evolutional algorithms or Bayesian optimizers can be used.
The iteration can then be performed over the steps of determining the technical application property of the new potential target polymer foam by utilizing the respective foam characteristics and the polymer characterizing parameters of the new potential target polymer foam as described above. Optionally, also a determination of polymer characterizing parameters and foam characteristics from the digital description of the new potential target synthesis specification can be part of the iteration, if the polymer characterizing parameters and foam characteristics are not already provided with the digital representation of the new potential target synthesis specification. Moreover, it is preferred that the same property model is used in all iteration steps for determining the technical application property. However, in some cases also different property models can be used in different iteration steps. For example, if other polymer characterizing parameters and foam characteristics for the new potential target polymer foam are utilized also another property model can be more suitable.
After the iteration has stopped, for instance, after the potential target polymer foam has been determined as the target polymer foam, or if no new potential target polymer foam can be selected or generated, the result of the iteration can be provided to a user. For example, if none of the possible potential target polymer foams has met the technical application property, the user can be notified of the failure of determining a target polymer foam. In case a target polymer foam can be determined, the target polymer foam can be provided to the user as output. For example, the determined target polymer foam and target synthesis specification can then be provided to an output unit or to a computing unit for further processing. Preferably, the providing of the target synthesis specification and the target polymer foam leads to a further processing utilizing the target synthesis specification.
In a preferred embodiment the method further comprises providing as digital represen-tation of the potential target polymer foam a synthesis specification and determining the characterizing parameters, for example, in form of polymer characterizing parameters, preferably, as polymer descriptors, and the foam characteristics from the synthesis specification. In particular, the synthesis specification, i.e. recipe, comprises infor-mation on the polymer synthesis of the potential target polymer foam, for instance, on the starting substance and process by which respective starting substances are covalently bonded to form the polymer chain or network of the polymer forming the polymer foam. The method then comprises determining characterizing parameters, for instance, the polymer descriptors, and the foam characteristics from the synthesis specification. Optionally, from a synthesis specification the subgroups can be deter-mined and the polymer characterizing parameters can then be determined based on subgroup characterizing parameters of the subgroups, for instance, from a database or utilizing known characterizing parameter determination algorithms. In a preferred embodiment, further from the synthesis specification utilized catalysts and/or non- reactive process ingredients are determined. In this case it is preferred that this information is also utilized together with the characterizing parameters, in particular, the polymer characterizing parameters, by the property model for determining the technical application property. Preferably, characterizing parameters are also determined for the catalysts and/or non-reactive process ingredients and the respective characterizing parameters are also used for determining the physicochemical parameters of the polymer. Preferably, the characterizing parameter for the catalysts and/or non-reactive process ingredients refers to an amount of the respective ingredient, for example, a molar mass, a molar percentage, etc. and is taken into account for determining a polymer characterizing parameter for the potential targe polymer foam.
In a preferred embodiment, the determining of polymer characterizing parameters from the synthesis specification comprises identifying types and amounts of subgroups based on the synthesis specification, for instance, as characterizing parameters of the subgroups, and determining the polymer characterizing parameters based on the identified types and amounts of subgroups. Generally, the types of subgroups can refer to predetermined types or classes that are associated with specific characterizing parameters, e.g. physicochemical parameters, of the subgroups, and thus with specific characterizing parameters of a polymer comprising these subgroups. However, since the general characterizing parameters of a polymer and hence the polymer characteriz-ing parameters can also depend on the amount of a subgroup present in the polymer that amount can also be taken into account. In a preferred embodiment the determina-tion of the type and amount of subgroups takes into account information provided by the synthesis specification indicative of the type of polymerization. The information on the type of polymerization that can be utilized can refer, for instance, to whether the polymerization refers to a polycondensation, polyaddition, radical polymerization, cationic polymerization, anionic polymerization, or coordinative chain-polymerization. Preferably, for each type of polymerization rules are predetermined that can be applied to determine the subgroups of the polymer. For example, rules can be predetermined that determine which functional groups of monomers in the synthesis specification react with which prioritization to which functional groups of the synthesized polymer foam. The rules can be based, for instance, on kinetic considerations. Based on the number and type of polymerized functional groups the subgroups can be determined and a number and type of the subgroups can be calculated.
In an embodiment the determination of the amount of subgroups comprises determin-ing the amount of at least one of, amide, ester, thioester, carbonate, ether, amine, urea, urethane, thiourethane, isocyanurate, biuret, allophanate, acetal, Michael-adduct, radically polymerized double bond, siloxane, silane, silazane, phosphazene groups as well as residual amine, aldehyde, ketone, epoxide, aziridine, isocyanate, alcohol, thiol, carboxylic acid, acyl halogenide, α, β-unsaturated carbonyl groups, α, β-unsaturated carboxyl and double bond groups in the polymer based on the synthesis specification.
In an embodiment, the providing of the target synthesis specification of the target polymer comprises providing control signals adapted for controlling an industrial plant for producing the target polymer foam in accordance with the target synthesis specifi-cation. Preferably, the control signals are configured for controlling a production process based on the determined target synthesis specification. Preferably, the production process refers to a production process of the target polymer foam utilizing the target synthesis specification. Moreover, it is preferred that the target synthesis specification refers to a machine executable synthesis specification of the target polymer foam such that the control signals can directly refer to a controlling of respec-tive laboratory or process equipment allowing to execute the synthesis specification to produce the target polymer foam. In an embodiment, the providing of the target synthesis specification of the target polymer foam comprises providing control signals adapted for controlling an industrial plant for producing the target polymer in accord-ance with the target synthesis specification.
In an embodiment, the method further comprises providing an additional target technical application property for the target polymer foam and providing the potential target synthesis specification based on the provided additional target technical application property such that the potential target polymer foam fulfils the provided additional target technical application property. In particular, the additional technical application property can refer to any property of a polymer foam and/or a product consisting at least partly of the polymer foam, that allows to assess a technical applicability of the respective polymer foam as provided after its synthesis. Preferably, the additional target application property, i.e. second application property is at least one of an insulation property, a burning behavior, a rebound, a tear strength, a mechanical property, an aging property, and a biodegradability. More preferably, the technical application property, i.e. first application property, and the second application property refer to specific combination of properties that are important for a respective application of the polymer foam. Preferably, the first and the second application property refer to a least one of the following combinations an insulation property and a burning behavior, a rebound and a tear strength, and a mechanical property and an aging property.
The potential target synthesis specification is provided such that the associated potential target polymer foam fulfils the provided additional target technical application property. For example, a database can be utilized on which polymer foams and corresponding technical application properties are already stored and from the database target polymer foams and associated synthesis specifications can be selected that fulfil the provided additional target technical application property. General-ly, the polymer foams fulfilling the additional target technical application property can be regarded as forming the potential target polymer foam space that can be explored during the iteration process for finding the target polymer foam. From the selected target polymer foams fulfilling the additional target technical application property the first potential target polymer foam and thus the first potential target synthesis specifica-tion can be then be selected.
In an embodiment, the providing of a new potential target synthesis specification is based on amending the provided additional target technical application property and providing the new potential target synthesis specification such that the potential target polymer foam fulfils the amended additional target technical application property. In particular, if the new potential target synthesis specification has to be provided, the comparison of the determined technical application property and the target technical application property indicates that the determined technical application property of the current potential target polymer foam does not fulfil the target technical application property. In such a case, a new potential target synthesis specification and thus a new potential target polymer foam can be provided such that the new potential target polymer foam still fulfils the additional target technical application property, if such a respective polymer foam exists. However, in many cases it will not be possible to provide such a new potential target polymer foam or it might not be technically sensible to provide such a new potential target polymer foam that still fulfils the additional target technical application property. In these cases it is advantageous to amend the addi-tional target application property, for instance, by utilizing a less strict additional target technical application property, like amending the additional target technical application property such that it now refers instead of one specific value to a value range or if it refers to a value range to a wider value range. The new potential target polymer foam can then be selected or generated such that it fulfils the amended additional target application property.
In an embodiment, the providing of the potential target synthesis specification based on the provided additional target technical application property comprises utilizing a determination model adapted to determine a technical application property of a polymer foam based on the digital representation of the polymer foam, wherein the determina-tion model is a data driven model parameterized such that it determines based on the digital representation of the polymer foam the technical application property associated with the polymer foam. The determination model can refer to any known data-driven determination model that allows to determine a technical application property based on a digital representation of a polymer foam comprising polymer characterising parame-ters and foam characteristics. Generally, it is preferred that the determination model follows the same principles as described above with respect to the property model. In fact, the determination model can be based on or utilize the same machine learning algorithms and training methods, only utilizing different training data, i.e. training data comprising instead of the technical application property another respective technical application property of a polymer. Thus, all embodiments described above with respect to the property model can also be realized with respect to the determination model for determining the additional technical application property. Utilizing such a determination model has the advantage that an iteration can be performed not only over the technical application property of a polymer foam but also over the additional technical application property in a fast and computationally inexpensive manner leading to a target polymer foam that not only fulfils one target technical application property but also the additional target technical application property.
In an embodiment, the method further comprises providing test information indicative or associated with a technical application property test method, wherein the technical application property test method is indicative of a standardized test method for determining experimentally a respective technical application property of a polymer foam, wherein the property model is provided based on the technical application property test method. Generally, the test information can be provided such that it allows to derive the technical application property test method and the technical application property test parameters or such that it directly comprises the technical application property test method and the technical application property test parameters. For example, the test information can be provided in a form of an identifier of a technical application property test method, wherein based on the identifier a storage unit can be accessed comprising the technical application property test method and the technical application property test parameters. The identifier can, for example, be a name or identification number of the technical application property test as provided by a standard. Additionally the test information can be also referred to as the technical application property test information. However, the test information can also be directly provided, for instance, by a user utilizing an input unit, such that the technical applica-tion property test method and the technical application property test parameters are provided. For example, a user can be provided with a selection of known technical application property test methods and can then select the respective technical applica-tion property test method.
Preferably, the technical application property test method is indicative of a standardized test method for determining experimentally a technical application property of a polymer foam. Preferably, a plurality of such standardized test methods for a technical application property are known and can be referred to by a respective identifier. Moreover, in a preferred embodiment, the property model can also be adapted to determine the target technical characteristic of a polymer foam further based on test parameters as input.
The test parameters are further indicative of a specific test procedure of the technical application property test method, for instance, of one or more process parameters specifying the technical application property test method. In particular, the test parame-ters are specific to each technical application property test method and thus depend on the definition of the technical application property test method. However, even in a standardized test procedure the test parameters can be varied in some cases such that it is possible that for the same technical application property test method different test parameters can be specified within a range of possible test parameters defined by the technical application property test method.
Generally, in most cases technical application property test method will only test for a specific technical application property. Thus it is preferred that the technical application property and the test method are provided accordingly. For example, if the user inputs a respective target technical application property, he/she can be provided with a selection of possible test methods testing for the provided technical application properties and can the select the respective test method. However, the user can also provide the test method as input and then the user only has to determine the value or value range for the target technical application property, since the target technical application property is already determined by the provided test method.
Preferably, the technical application property is a mechanical property and the test method refers to a mechanical property test method. Exemplary tests to quantify potential representations of mechanical properties may be, but are not limited to ASTM D2632 -15 (Standard Test Method for Rubber Property-Resilience by Vertical Rebound) for rebound; ISO 8307: 2007 (Flexible cellular polymeric materials –Determi-nation of resilience by ball rebound) for rebound; ISO/DIS 20875: 2016 (Footwear – Test methods for outsoles –Determination of split tear strength and delamination resistance) for split tear strength; ISO 48-4: 2018 (Rubber, vulcanized or thermoplastic –Determination of hardness –Part 4: Indentation hardness by durometer method (Shore hardness) ) for shore hardness; ISO 3386-1: 1986 + Amd 1: 2010 (Polymeric materials, cellular flexible –Determination of stress-strain characteristics in compres-sion –Part 1: Low-density materials) for compression hardness; ISO 1856: 2018 (Flexible cellular polymeric materials –Determination of compression set) for compres-sion set; ISO 844: 2021 (Rigid cellular plastics –Determination of compression properties) for compressive strength; DIN EN ISO 527-1 (Plastics –Determination of tensile properties –Part 1: General principles) for tensile strength, and elongation at break; ASTM F1614 -99 (Standard Test Method for Shock Attenuating Properties of Materials Systems for Athletic Footwear) for shock attenuating characteristics, e.g. absorbed energy loss during hysteresis cycle, peak pressure, maximum strain, and average stiffness; ISO 7231: 2010 (Polymeric materials, cellular, flexible –Determina-tion of air flow value at constant pressure-drop) for air permeability. Generally, all tests are characterized in that they provide specific test conditions as defined for example in the respective standard specifications and that the mechanical property is evaluated based on specific output parameters as defined in the respective norm.
In a preferred embodiment the determined property is a rebound and the test method is ASTM D2632-2001, wherein in the test method a resilience is determined as the ratio of rebound height to drop height of a metal plunger of prescribed mass and the resilience is a function of both dynamic modulus and internal friction of the respective polymer foam. Since the rebound and the resilience are sensitive to temperature changes and to depth of penetration of the utilized experimental plunger, preferably, both variables, i.e. temperature and utilized plunger, are utilized as test parameters. Thus the property model can be trained in this case to determined rebound according to this test based on respective quantified test parameters.
In a preferred embodiment a split tear strength is determined for the test method DIN EN ISO 20875 EN, wherein the split tear strength is defined in this method as the force required to propagate a cut in a test piece by tearing. The method uses a splitting jig and knife to split one end of each of three test piece half-way between the top and bottom surfaces for a distance of approximately 30 mm. The two tongues are then folded back at one end of the test piece and inserted and clamped one in each jaw of a machine defined in the definition of the test method. The machine is then started so that the jaws separate at 100 mm/min, and a trace of the force is recorded as the test continues. The split tear strength STs is then expressed in newton per millimetre of width and is given by the formula STs = F/d, where F is the median force in newton d is the width of the test piece in millimetres. The resulting split tear strength is then the median of three values obtained. In this case the property model can be trained to determine the resulting split tear strength of the polymer foam based on respective training data acquired utilizing this test method on a plurality of different polymer foams with respective polymer characterizing parameters and foam parameters. For laminat-ed polymer foams further the method refers to determining a delamination resistance defined as the force, required to propagate delamination of an adhesive layer or joint interface if a multilayer polymer foam is composed of an adhesive layer, divided by the width of the test pieces. In this case of multilayer polymer foams the method separates the layers of the sole for a length of 10 mm, by inserting a heated knife in the adhesive layer. The two tongues are folded back at one end of the test piece and insert and clamp one in each jaw of the machine. Then the machine defined in the test method is utilized such that the jaws separate at 100 mm/min, and a trace of the force is recorded as the test continues. The delamination resistance Ds is then expressed in newton per millimetre of width and is given by the formula Ds = F/d, where F is the average force in newton and d is the width of the test piece in millimetres. Also in this case the resulting delamination resistance is the average of the values obtained from three test pieces. In this case the property model can be trained to determine the resulting delamination resistance of the polymer foam based on respective training data acquired utilizing this test method on a plurality of different polymer foams with respective polymer character-izing parameters and foam parameters. Moreover, the lamination characteristics, for example, a utilized adhesive, an adhesive strength, etc. between polymer foam layers and the layer characteristics, like layer depth, utilized polymer foam, etc. can be used as further test parameters and the property model can be trained further based on these test parameters.
In a preferred embodiment, shock attenuating properties are determined based on the test method F1614 -99 (Reapproved 2006) . The polymer foam is in this case utilized at least as part of a midsole of an athletic footwear. However, the test can also be applied to a polymer foam that is not configured to be utilized in form of an athletic footwear. The test method covers the measurement of predefined shock attenuating characteristics, rapid rate force-displacement relationships, of materials systems employed in the midsole of athletic footwear intended for use in normal running movements. In test method three different procedures are described for performance of an rapid rate force application. Procedure A utilizes falling weight impact machines, Procedure B utilizes compression force controlled machines, and Procedure C utilizes compression displacement controlled machines. Since the result for rapid rate force application may be different for each of the three procedures of this test method it is preferred that the respective test method is a further test parameter in the property model.
In a preferred embodiment, stress-strain characteristics in compression are determined based on the test method DIN EN ISO 3386-1, in particular, ISO 3386-1: 1986 + Amd 1:2010 (German version EN ISO 3386-1: 1997 + A1: 2010) . In this case the property model can be further trained based on test parameters comprising at least, a tempera-ture, a humidity, dimension of test pieces, number of layers, if applicable,
For a polymer foam being a ridged foam it is further preferred that the determined property is pressure hardness according to DIN EN 826. Further, in a preferred embodiment for ridged foams the determined property is the number of open and closed cells of the foam according to DIN EN ISO 4590. Moreover, it is preferred that the determined property is a thermal conductivity according to DIN EN 12667. If the technical application property is a thermal application property then an exemplary test to quantify potential representation of thermal property may be, but is not limited to ASTM C177 for measuring the thermal conductivity. Generally, all test methods are described by test information characterized in that it provides specific test conditions as defined for example in the respective standard specifications. The mechanical or thermal property is evaluated based on specific output parameters as defined in the respective norm or standard. In a preferred embodiment, the property is a burning behavior under predetermined conditions. In this case preferably a test to quantify a burning behavior is a respective burning test method.
Preferably, in this embodiment the burning test methods refer to at least one of, but are not limited to, single burning item (EN 13823: 2015) , single-flame source test (EN ISO 11925-2: 2020) , UL94 and UL 94 HB (EN 60695-11-10: 2014 and EN 60695-11–20: 2016, respectively) , an ASTM E84 test, as well as cone calorimeter (ISO 5660-1: 2015) . All these burning test methods are characterized in that they require specific test conditions as defined in the respective norm and that the burning behavior is evaluated based on specific burning properties that are measured during the burning test as defined in the respective burning test method norm, wherein the property model can then be trained to either determine the respective specific burning properties or directly the burning behavior.
In the following some further possible burning test methods are described that can be selected as burning test method for respective applications in the method described above for determining a target polymer foam with respective one or more target properties. In EN ISO 4589-2 a burning behavior is determined by determining an oxygen index. ISO 5658-2 determines a flame growth by measuring a critical flux at extinguishment. For a target application referring to a polymer foam utilized as or as part of a building material also ISO 5660-1 can be selected for determining a maximal heat release rate per surface area. For a target application referring to a polymer foam utilized as or as part of a flooring also EN ISO 9239-1 can be selected for determining a critical heat flux at extinguishment. In EN ISO 11925-2 an ignitability when directly subjected to a flame is determined. For a target application referring to a polymer foam utilized as or as part of a furniture, in particular, a seat, ISO/TR 9705-2 can be utilized to determine a mean heat release. For a target application referring to a polymer foam utilized as or as part of textile, in particular, bedding, EN ISO 12952-2 can be used to determine an afterglow time. In ISO 2592/ISO 2719 a flash point and combustion point is determined. For a target application referring to a polymer foam utilized as or as part of an electric cable EN 60332-1-2 can be utilized for determining a length of a burned and unburned part of the cable and EN 60332-3-24 can be utilized to determining a height of burned and unburned area. For a target application referring to a polymer foam utilized as or as part of a plastic EN ISO 5659-2 can be selected for determining a maximal optical density of fumes. Further, EN 45545-2: 2013+A1: 2015 can be utilized to determine a conventional index of toxicity. Also NF X70-100-1 and NF X70-100-2 can be utilized for determining toxicity parameters. For a target application referring to a polymer foam utilized as or as part of an electric cable EN 61034-2 can be used to determine a transmission or EN 50305 can be utilized to determine an ITC parameter for cables used in rail vehicles. For a target application referring to a polymer foam utilized as or as part of a building material EN 13501-1 can be utilized to determine a plurality of burning properties. Also EN 60695-2-11 and EN 60695-11-10 can utilized for determining respective burning properties.
In particular for target polymers foam that are to be utilized in or as part of upholstered furniture at least one of the following test methods can be selected EN ISO 12952-1, EN ISO 12952-2, EN 597-1, EN 597-2, NF P92501, NF P92507 M3, EN 1021-1, EN 1021-2, BS 5852, CSE RF 4/83. For target polymer foams that are to be utilized in or as part of a textile at least one of the following test methods can be selected EN 469, EN ISO 14460: 1999, EN 340, ISO 694d2: 2002, EN 367, EN 470, EN 533, EN ISO 11612: 2008, EN ISO 15025: 2002, EN 1103, EN 13772, EN ISO 13772, EN ISO 12952-1, EN ISO 12952-2, EN 597-1, EN 597-2, EN 1021-1, EN 1021-2, EN 597-1, EN 597-2, DIN 4102, UNI 9175, NFP 92 501-507, Italian UNI 9175.
Generally, for each of the above described burning test methods a respective property model can be trained that is adapted to determined the burning properties of a specific burning test method based on the respective polymer characteristics and/or foam characteristics of the polymer foam and optionally further based on the test parameters of the respective test, if these parameters are variable. Preferably, the property model is provided based on the technical application property test method. In an embodiment, the method for determining a technical application property of a polymer foam compris-es the providing of the property model that preferably refers to a selecting of a property model based on the provided technical application property test method of the polymer foam. For example, a plurality of property models can be stored on a property model storage, wherein each property model is associated with a specific technical application property test method.
In an embodiment the test information is further indicative of or associated with one or more test method parameters, wherein the property model is adapted to further determine the technical application property based on the test method parameters and wherein the determining of the technical application property is based further on the test method parameters. For example, in cases in which the test parameters can vary within certain ranges during the standardized test method, the property model can be trained to take the specific test parameters, i.e. the specific test parameter values, provided by the test conditions into account. In particular, the property model can be trained by utilizing a training data set comprising characterizing parameters of the polymer forming the polymer foam and foam characteristics of the polymer foam associated with different test parameters for a specific test method, as described above, leading to a property model that takes the test parameter variations of the test method indirectly into account. However, the training data set can optionally also comprise specific test parameter values of a respective test method. In this case, the property model can be trained such that in addition to the polymer foam characterizing parame-ters also test parameter values can be provided as input, wherein the property model then determines the one or more properties further based on the test parameter values. This has the advantage that the technical application property can be determined even more accurately, in particular, in cases in which the property strongly depend on the specific test parameter values of a test method.
In an embodiment, the provided test information is indicative of an intended application of the polymer foam and the technical application property test method and the test parameters are determined based on the intended application. The intended applica-tion can refer to any intended application of a product in which the polymer foam should be utilized. For example, the intended application can refer to an intended application in a seat in a public transport, as construction material in a building construction, as material in an automotive context, etc. Generally, each intended application of a polymer is associated with different performance and/or safety requirements of the utilized materials. In most cases, the respective technical applica-tion characteristic and safety requirements for the respective applications are standard-ized or regulated by respective authorities. Thus, from the intended application the respective technical application property test methods and test parameters can directly be derived. For example, for common intended applications a respective list of associated technical application property test methods and test parameters can be stored and the provided test information indicating the intended application can then be utilized to access the stored technical application property test method and test parameters associated with the intended application.
In a preferred embodiment the technical application property is at least one of a rebound, a tensile strength, a hardness, and a reactivity of a flexible foam. In this embodiment it is preferred that the physicochemical characteristics of the polymer forming the polymer foam and foam characteristics of the polymer foam comprise at least one of a mixing ratio, a moulded density, an amount of ingredients, an amount of repeating units, an amount blowing agent, and a stirring power.
In a preferred embodiment the technical application property is at least one of a heat release, flame hight, burning time, mass loss, smoke production and ignition time of a hard foam. In this embodiment it is preferred that the physicochemical characteristics of the polymer forming the polymer foam and foam characteristics of the polymer foam comprise at least one of a mixing ratio, amount of ingredients, atom count, amount of repeating units, amount of blowing agent and stirring power.
In a preferred embodiment the polymer foam is configured to be utilized as or as part of a shoe sole. In this embodiment it is preferred that the technical application property is at least one of a rebound, split tear strength, and G-peak. The rebound of the polymer foam is directly related to the comfort characteristics of the shoe, the split tear strength is related to the durability and wear characteristics of the shoe and the G-peak is related to the shock absorption and thus also to the comfort characteristics of the shoe. Determining these technical application properties, preferably, with respect to one of the tests described above, thus has the advantage that a shoe sole can be developed in a fast and easy manner. In particular, a customer can preferred values for the above technical application properties and polymer foam shoe sole can be determined that fulfills the desired characteristics and is thus customized to the customer.
In a further aspect of the present invention an interface method for providing an interface is presented, wherein the interface method comprises i) receiving as input a digital representation and a target technical application property via a user interface and providing the received digital representation and the target technical application property to a processor performing the method as described above, and ii) providing the determined target synthesis specification of the polymer foam to a user via a user interface as result, wherein the result is received from the processor performing the method as described above.
In a further aspect of the present invention a computer-implemented training method for training a data-driven based property model for parameterizing the property model is presented, wherein the training method comprises i) providing training data compris-ing a) digital representations of a plurality of training polymer foams indicative of characterizing parameters and foam characteristics of each of the training polymer foams, and b) a technical application property associated with each training polymer foam, ii) providing a data-driven based trainable property model, iii) training the provided data-driven based property model based on the provided training data such that the trained property model is adapted to determine a technical application property of a polymer foam based on characterizing parameters of the polymer forming the polymer foam and foam characteristics of the polymer foam, and iv) providing the trained property model.
In a further aspect of the present invention an apparatus for determining a target synthesis specification indicative of a target polymer foam comprising a target technical application property is presented, wherein the apparatus comprises one or more processors configured for performing the functions i) providing a target technical application property, wherein the target technical application property is indicative of a technical characteristic of a polymer foam, ii) providing a digital representation of a potential target synthesis specification indicative of or associated with characterizing parameters of the polymer forming the polymer foam and foam characteristics of the polymer foam, wherein the characterizing parameters are indicative of characteristics of a polymer and/or are derivable from one or more characteristics of the polymer and the foam characteristics are indicative of characteristics of the foam structure of the polymer foam, iii) providing a property model adapted to determine a technical applica-tion property of a polymer foam based on the characterizing parameters and the foam characteristics of the polymer foam, wherein the property model is a data-driven model parameterized to determine a technical application property of a polymer foam based on characterizing parameters and based on foam characteristics, iv) determining the technical application property of the potential target polymer foam based on the provided property model and the digital representation, and v) comparing the deter-mined technical application property of the potential target polymer foam with the target technical application property and, based on the comparison, either i) determining the potential target polymer foam as the target polymer foam and the potential target synthesis specification as the target synthesis specification, or ii) providing a new potential target synthesis specification of a new potential target polymer foam and repeating the determination of the technical application property utilizing the new potential target synthesis specification of the new potential target polymer foam.
In a further aspect of the present invention an interface apparatus for providing an interface is presented, wherein the interface apparatus comprises one or more processors configured for performing the functions a) receiving as input a digital representation and a target technical application property via a user interface and providing the received digital representation and the target technical application property to a processor performing the method as described above, and b) providing the determined target synthesis specification of the polymer foam to a user via a user interface as result, wherein the result is received from the processor performing the method as described above.
In a further aspect of the present invention a training apparatus for training a data-driven based property model for parameterizing the property model is presented, wherein the training apparatus comprises one or more processors configured for performing the functions i) providing training data comprising a) digital representations of a plurality of training polymer foams indicative of characterizing parameters and foam characteristics of each of the training polymer foams, and b) a technical applica-tion property associated with each training polymer foam, ii) providing a data-driven based trainable property model, iii) training the provided data-driven based property model based on the provided training data such that the trained property model is adapted to determine a technical application property of a polymer foam based on characterizing parameters and foam characteristics of the polymer, and iv) providing the trained property model.
In a further aspect, a computer program product for determining a target synthesis specification indicative of a target polymer foam comprising a target technical applica-tion property is presented, wherein the computer program product comprises program code means for causing the apparatus as described above to execute the method as described above.
In a further aspect, a computer program product for training a data-driven based property model is presented, wherein the computer program product comprises program code means for causing the training apparatus as described above to execute the training method as described above.
It shall be understood that the methods as described above, the apparatuses as described above and the computer program products as described above have similar and/or identical preferred embodiments, in particular, as defined in the dependent claims. Moreover, also the training method as described above, the training apparatus as described above and the training computer program product as described above have similar and/or identical preferred embodiments, in particular, as defined in the dependent claims.
It shall be understood that a preferred embodiment of the present invention can also be any combination of the dependent claims or above embodiments with the respective independent claim.
These and other aspects of the present invention will be apparent from and elucidated with reference to the embodiments described hereinafter.

BRIEF DESCRIPTION OF THE DRAWINGS

In the following drawings:
Fig. 1 shows schematically and exemplarily an embodiment of a system comprising an apparatus for determining a target synthesis specification indicative of a target polymer foam comprising a target technical applica-tion property and a training apparatus for training a data-driven based property model,
Fig. 2 shows schematically and exemplarily a flow chart of a method for determining a target synthesis specification indicative of a target polymer foam comprising a target technical application property,
Fig. 3 shows schematically and exemplarily a flow chart of a training method for training a data-driven based property model for parametrizing the property model,
Figs. 4 and 5 show schematically and exemplarily a flow chart of preferred more detailed embodiments of a method for determining a target synthesis specification indicative of a target polymer foam comprising a target technical application property,
Fig. 6 shows schematically and exemplarily an optional extension of a method for determining a target synthesis specification indicative of a target pol-ymer foam comprising a target technical application property,
Figs. 7 to 9 show schematically and exemplarily a block diagram of a system architecture of a system and apparatus for determining a target synthe-sis specification indicative of a target polymer foam comprising a target technical application property, and
Fig. 10 shows schematically and exemplarily an output and input screen of an exemplary user interface.

DETAILED DESCRIPTION OF EMBODIMENTS

Fig. 1 shows schematically and exemplarily an embodiment of a system 100 compris-ing an apparatus 110 for determining a target synthesis specification indicative of a target polymer foam comprising a target technical application property. Further, the system 100 comprises a training apparatus 130 for training a data-driven based property model utilized in the apparatus 110, a database 140 on which results of the determining of the target synthesis specification can be stored and a production system 120 for producing a product, in particular, comprising the determined target polymer foam that can be controlled utilizing the determined target synthesis specification.
The apparatus 110 comprises a target technical application property providing unit 111, a digital representation providing unit 112, a model providing unit 113, a technical application property determination unit 114, an iteration control unit 115 and optionally an output and/or control unit 116 that can be adapted to output the determined target synthesis specification and/or to provide control signals for controlling a production process of the production system 120 based on the determined synthesis specification.
The target technical application providing unit 111 is adapted to provide a target technical application property indicative of a technical characteristic of a polymer foam. The target technical application providing unit 111 can refer, for instance, to an input unit into which a user can input a respective target technical application property. Moreover, the target technical application property providing unit 111 can refer to or can be part of a user interface that allows the user to interact with the apparatus 110 for providing the target technical application property. However, the target technical application property providing unit 111 can also refer to or be communicatively coupled with a storage unit on which a target technical application property, for instance, for a specific application, is already stored.
The digital representation providing unit 112 is adapted to provide a digital representa-tion indicative of characterizing parameters of the polymer forming the polymer foam and foam characteristics of the polymer foam. In particular, the characterizing parame-ters are indicative of characteristics of a polymer and/or are derivable from one or more characteristics of the polymer and the foam characteristics are indicative of characteris-tics of the foam structure of the polymer foam. The digital representation providing unit 112 can refer, for instance, to an input unit into which a user can input the respective digital representation. Moreover, the digital representation providing unit 112 can refer to or be part of a user interface that allows the user to interact with the apparatus 110 and/or the database 140. However, the digital representation providing unit 112 can also refer to or be communicatively coupled with a storage unit on which the digital representation of the polymer foam is already stored. Generally, the digital representa-tion can directly comprise the characterizing parameters of the polymer forming the polymer foam and foam characteristics of the polymer foam. However, a synthesis specification of the polymer foam can be provided instead of directly providing the characterizing parameters of the polymer forming the polymer foam and foam charac-teristics of the polymer foam. In this case, it is preferred that the digital representation providing unit 112 is further adapted to determine the polymer characterizing parame-ters of the polymer forming the polymer foam and the foam characteristic parameters of the polymer foam from the synthesis specification.
However, instead of directly providing the polymer characterizing parameters also a synthesis specification of the polymer foam can be provided. In this case, it is preferred that the digital representation providing unit 112 is further adapted to determine the polymer characterizing parameters from the synthesis specification. In particular, it is preferred that the digital representation providing unit 112 is adapted to identify from the synthesis specification types and amounts of subgroups of the polymer and to determine the polymer characterizing parameters based on the identified types and amounts of subgroups. In particular, the digital representation providing unit 112 can be adapted to determine for each identified subgroup respective subgroup characterizing parameters, for instance, by accessing a database on which for a plurality of the most relevant subgroups respective characterizing parameters are stored. The characteriz-ing parameters of the polymer forming the polymer foam can then be determined based on the subgroup characterizing parameters of the subgroups and preferably, also on the determined amount and type of the subgroups, for example, by weighted averaging of the subgroup characterizing parameters of the subgroups.
Further, it is preferred that the digital representation also comprises the foam charac-teristics. However, also the digital representation providing unit 113 can also be adapted to derive the foam characteristics from the digital representation, for instance, from a synthesis specification. For example, the digital representation can comprise a 3D simulation or model of the polymer foam allowing to derive respective foam characteristics, like, a density of the cavities in the foam, a distribution of the cavities or the sizes of the cavities, etc. However, the digital representation can also comprise a synthesis specification of the polymer foam and can be adapted to derive the foam characteristics from the synthesis specification, for example, process conditions, additives, activation conditions, etc. as foam characteristics that lead to the formation of the foam when executing the synthesis specification. The digital representation providing unit 113 is then adapted to provide the digital representation comprising the characterizing parameters of the polymer forming the polymer foam and foam charac-teristics of the polymer foam, for instance, to the determination unit 114.
The property model providing unit 113 is adapted to provide a property model adapted to determine a technical application property of a polymer foam based on the charac-terizing parameters and the foam characteristics of the polymer foam. The property model providing unit 113 can comprise or refer to an input unit through which the property model can be received, for instance, by a user that inputs or indicates which property model should be used. Moreover, the property model providing unit 113 can refer to or be communicatively coupled with a storage unit 140 on which the property model is already stored. In a preferred embodiment, the property model providing unit 113 further refers to a selection unit that is adapted to access, for instance, a storage unit 140, on which a plurality of property models are stored and to select a respective property model for the technical application property of interest.
The property model is a data-driven model parameterized such that it can determine a technical application property of a polymer foam based on the digital representation, in particular, based on the characterizing parameters quantifying the characterizing parameters associated with the polymer forming the polymer foam, and based on foam characteristics. In a preferred embodiment, the data-driven model refers to a machine learning model, for instance, utilizing regression model based algorithms or classifier model based algorithms. A regression model based algorithm can be based on any of a neural network algorithm, a Linear Regression algorithm, a LASSO algorithm, a Ridge Regression algorithm, a MARS algorithm, a Random Forest algorithm, and a Boosted Trees algorithm. A classifier based model algorithm can be based on any of a Random Forest algorithm, a Logistic Regression algorithm, and a SVM algorithm. The inventors have found that for most applications, in particular, Linear Regression, Random Forest and MARS based algorithms are suitable.
The property model can be trained, for instance, utilizing training apparatus 130. In particular, the training apparatus 130 comprises a training data providing unit 131 for providing training data for training the data-driven based property model. The training data comprises a) digital representations of a plurality of training polymer foams indicative of characterizing parameters of the polymer and foam characteristics of each of the training polymer foams, and b) a technical application property associated with each training polymer foam. Optionally, if a technical application property test method should also be taken into account, it is preferred that the technical application proper-ties of the training data are measured utilizing the respective test method and that the property model is then identified as being trained for the respective test method. If the test method allows for a variation of test parameters characterizing the test method, then the training data can also comprise for each polymer foam the test parameter values for which the properties have been measured. Generally, the training data can be designed to cover predetermined polymer types or different foam characteristics for one or more technical application properties, optionally, for a predetermined technical application test method, as application space. Known methods for designing and optimizing training data for a predetermined application space can be utilized such that the application space is well covered with training data and that random outliers are avoided. In normal application scenarios the inventors have found that with training data comprising approximately 50 training polymer foams an acceptable accuracy of the determined properties can be achieved, wherein the accuracy can be increased if more training polymers are provided in the training data. Preferably, more than 100 training polymer foams are utilized.
Further, the training apparatus 130 comprises a model providing unit 132 adapted to provide a data-driven based trainable property model, for instance, a property model comprising parameters that can be set during the training process for training the property model. For example, a trainable property model can already be stored on a storage unit to which the model providing unit 132 can have access for providing the same. Moreover, the training apparatus 130 comprises a training unit 133 for training the provided data-driven based property model based on the provided training data. In particular, the training can refer to varying the parameters of the property model based on the respective training data until the property model is adapted to determine a technical application property of a polymer foam based on characterizing parameters of the polymer and foam characteristics of the polymer foam. In particular, the property model is adapted to determine a technical application property of a polymer foam based on a digital representation indicative of characterizing parameters of the polymer forming the polymer foam and foam characteristics of the polymer foam. Generally, any known training algorithms for training data-driven, in particular, machine learning based models can be utilized. Preferably, during the training of the property model also the characterizing parameters of the polymer forming the polymer foam and foam charac-teristic of the polymer foam that have the most influence on the technical application property are determined and the model is then trained based on these most influential characteristics. For determining these most influential characteristics, for example, feature-selection or statistical-hypothesis-test tools can be utilized. In particular, the characterizing parameters of the polymer forming the polymer foam and the foam characteristics of the polymer foam can be utilized to represent the application space, wherein the application space is then defined by the characterizing parameters of the polymer forming the polymer foam and the foam characteristics of the polymer foam. Then algorithms for proposing new experimental runs for generating one or more additional training data can be applied in the application space, for instance, space-filling design methods to cover the application space with as few training data as possible or active learning methods to search for the optimal polymer foams iteratively can be utilized.
The training apparatus 130 then comprises a trained model providing unit 134 that is adapted to provide the trained property model, for instance, to a storage unit on which respectively trained property models for different technical application properties, test methods and/or different types of polymers forming polymer foams and/or different types of polymer foams are stored. However, the trained model providing unit 134 can also be adapted to directly provide the trained property model, for instance, to the property model providing unit 113 of apparatus 110. In all cases, the property model providing unit 113 is then adapted to provide a suitable trained property model to the property determination unit 114
The determination unit 114 can then utilize the property model and the provided digital representation for determining the technical application property. In particular, the determination unit 114 can be adapted to utilize the characterizing parameters of the polymer forming the polymer foam and the foam characteristics indicated by the digital representation as input to the property model that has, as already described above, been trained to then provide as output a determination for technical application properties of the polymer foam for which it has been trained.
Further, the apparatus comprises the iteration control unit 115 that is adapted to control an iteration process for determining the target synthesis specification. In particular, the iteration control unit 115 is adapted to compare the determined technical application property of the potential target polymer foam with the target technical application property. Based on this comparison, the iteration control unit 115 is then adapted to decide whether a further iteration step is necessary for determining a target synthesis specification or if the iteration has reached an end, in particular, if the potential target polymer foam can be set as the target polymer foam and thus the potential target synthesis specification as the target synthesis specification. Preferably, the comparing of the determined technical application property of the potential target polymer foam and the target technical application property refers to determining whether the deter-mined technical application property lies within a predetermined range around the target technical application property, for instance, by determining whether a difference between the determined technical application property and the target technical application property lies below a predetermined threshold. However, the comparison can also refer to a more complex mathematical function and the condition for which the potential target polymer foam is determined as the target polymer foam can refer to any condition that is based on the comparing of the determined technical application property with the target application property. If the above condition is not fulfilled, for instance, if the determined technical application property lies not within the predeter-mined range around the respective target technical application property, the iteration control unit 115 is adapted to decide that a further iteration step is necessary. In this case, the iteration control unit 115 is adapted to provide a new potential target synthe-sis specification of a potential target polymer foam and to repeat the determination of the technical application property utilizing the new potential target synthesis specifica-tion of the new potential target polymer foam.
For example, the new potential target polymer synthesis specification can be provided on a database 140 on which a plurality of potential target synthesis specifications are already stored and from which the iteration control unit 115 can select a new potential target synthesis specification arbitrarily or according to predetermined rules. Such rules can, for instance, be a function of the comparison of the determined technical applica-tion property with the target technical application property of the potential target polymer foam. For example, the function can refer to the size of the difference between, for example, a predetermined technical application property and the respective target technical application property, wherein the smaller the difference the more parts of the new potential target polymer foam are similar in the potential target polymer foam. In such a case, these rules can lead to the iteration control unit 115 being adapted to select new potential target polymer foams that are more similar to the potential target polymer foam if the determined technical application property for the potential target polymer is already similar to the target technical application property and that are less similar if the difference between the determined technical application property and the target technical application property is high. However, also completely different rules can be applied. Moreover, the iteration control unit 115 can also be adapted to generate a new potential target synthesis specification, for instance, based on the potential target synthesis specification and predetermined rules or arbitrarily. Also in this case for the rules the same principles as described above can be applied.
Moreover, the iteration control unit 115 can also be adapted to apply an abortion criterion for the iteration that indicates that for a respective target technical application property no suitable target synthesis specification can be found. For example, the iteration control unit 115 can be adapted to apply an abortion criterion that refers to a predetermined number of iteration steps, i.e. that refers to determine a predetermined number of new potential target synthesis specifications. However, also other abortion criteria can be utilized.
An output unit referring, for instance, to a display, can then be adapted to output the determined target synthesis specification or the target polymer, for instance, in form of a visual representation of the polymer foam, an identification of the polymer foam, a chemical formula representing the polymer forming the polymer foam, etc. Moreover, the output unit can additionally or alternatively be adapted to provide the determined target syntheses specification to a database 140 for storing the respective determined target syntheses specification in association with the respective target technical application property for a future usage. Optionally, the apparatus 110 can comprise the control unit 116 that is adapted to provide control signals based on the determined target synthesis specification for controlling a production process of the production system 120. In particular, it is preferred that the control signals are indicative of a machine executable synthesis specification of the target polymer which is generated based on the determined target synthesis specification for producing the target polymer foam fulfilling the target technical application property. However, the control unit 116 can also be adapted to control the production process of another product based on the determined target synthesis specification, for instance, to provide control signals indicative of a machine executable synthesis specification for another product utilizing or comprising the respective target polymer foam.
Fig. 2 shows schematically and exemplarily a method for determining a target synthe-sis specification indicative of a target polymer foam comprising a target technical application property. In particular, the method 200 can be performed in accordance with the principles and by the apparatus as described with respect to Fig. 1. In a first step 210, the method comprises providing a target technical application property indicative of or associated with technical characteristics of a polymer foam. In a next step 220, a digital representation of a potential target synthesis specification indicative of or associated with characterizing parameters of the polymer forming the polymer foam and foam characteristics of the polymer foam is provided. Further, a property model is provided in step 230. The property model is adapted to determine a technical application property of a polymer foam based on the characterizing parameters of the polymer forming the polymer foam and the foam characteristics of the polymer foam, wherein the property model is a data-driven model parameterized such that it can determine a technical application property of a polymer foam based on characterizing parameters of the polymer forming the polymer foam and based on foam characteris-tics of the polymer foam. Further, the method 200 comprises a step 240 of determining a technical application property of the potential target polymer foam based on the provided property model and the digital representation. In a last step 250, the method comprises comparing the determined technical application property of the potential target polymer foam with the target technical application property. Based on the comparison, it is either determined that the potential target polymer foam is the target polymer foam and the potential target synthesis specification is the target synthesis specification or a new potential target synthesis specification of a new potential target polymer foam is provided and the respective steps are repeated in an iterative manner. In an optional step 260, the target synthesis specification is further processed, in particular, by providing control signals adapted for controlling an industrial plant for producing the target polymer foam in accordance with the target synthesis specification.
Fig. 3 shows schematically and exemplarily a flow chart of a method for training the data-driven based property model utilized, for instance, in the method 200 discussed with respect to Fig. 2. Generally, the method 300 can be performed, for instance, by respective units of the training apparatus 130 as described with respect to Fig. 1. The method 300 comprises a step 310 of providing training data for training the data-driven based property model. The training data comprises a) digital representations of a plurality of training polymer foams indicative of characterizing parameters and foam characteristics of each of the training polymer foams, and b) a technical application property associated with each training polymer foam. The method comprises further a step 320 of providing a data-driven based trainable property model, for instance, a machine learning based property model like a neural network. Generally, the step 310 and the step 320 can be performed in arbitrary order or even at the same time. The method 300 then further comprises a step 330 of training the provided data-driven based property model based on the provided training data, for instance, by varying parameters in the data-driven based trainable property model, such that the trained property model is adapted to determine a technical application property of a polymer foam based on characterizing parameters of a polymer forming polymer foam and foam characteristics of the polymer foam. In step 340 the trained property model can then be provided, for instance, by storing the trained property model on a storage or by directly providing the trained property model to the apparatus 130 as described with respect to Fig. 1.
In the following, more detailed preferred examples of the above described method and the corresponding apparatus will be described. A schematic and exemplary flow chart of an exemplary and preferred embodiment of the method is provided by Fig. 4. In this exemplary embodiment, the method starts with requesting, for instance, via a user interface, a target value for a target application, in particular, a target technical application property. Moreover, in a next step, the optimization is initialized by providing a potential target synthesis specification, i.e. a start recipe. Optionally, constraints on the recipe, i.e. the synthesis specification, can be taken into account in this process, for instance, if a user provides such constraints. The constraints can refer, for instance, to constraints in the production of a polymer foam, in the starting substances that should be used for synthesizing the polymer foam, etc. Moreover, additional application conditions can be requested being in particular indicative of the test information for the target polymer foam. Moreover, additional application conditions can also be indicative of further information with respect to the target polymer foam that should be fulfilled. For example, the requested additional application conditions can refer to a test information indicating an intended application of the polymer foam, wherein based on the intended application a test method and the respective test parameters can be determined, for instance, by utilizing a database on which the respective associated test parameters are already stored. Based on the above steps, the optimization for determining the target polymer foam, i.e. the target synthesis specification, can be initialized. In a first step of the optimization, polymer characterizing parameter values and foam characteristic values can be derived from the provided start recipe, i.e. from the provided potential target synthesis specification. A more detailed, preferred possibility for deriving the characterizing parameter values is described with respect to Fig. 6. However, the deriving of the polymer characterizing parameters and the foam characteristics can also refer to accessing a storage on which respective characterizing parameter values and foam characteristic values for the respective potential target polymer foam are already stored. Moreover, if the provided digital representation of the potential target syntheses specification already comprises the polymer characterizing parameter and foam characteristics, this step can also be omitted. Based on the requested additional application conditions, in particular, based on the test information, a respective determination model, i.e. a property model, can be provided. Based on the provided determination model and the digital representation of the potential target synthesis specification, values for the target application, i.e. the technical application property, for the potential target polymer can be provided. In a next step it is deter-mined if the determined performance values, i.e. the determined technical application property, meets the target values, i.e. the target technical application property, within predetermined limits. If this is not the case, i.e. if this condition is not fulfilled, the formulation of the potential target synthesis specification is amended and a new target synthesis specification is determined optionally taking into account the constraints previously provided. The iteration can then start anew for the new potential target synthesis specification. If at one point the determined performance value meets the target value within limits, i.e. if the respective condition is fulfilled, the potential target synthesis specification is determined as the target synthesis specification and provided, for example, to a user or to a control unit for producing the respective determined target polymer foam.
Fig. 5 shows schematically and exemplarily a further preferred embodiment of the above method for determining a target synthesis specification with predetermined target technical application properties, wherein in this embodiment in addition to the target technical application property it is desired that the target polymer also fulfils a further target value, i.e. a further target technical application property. The additional target technical application property can refer to any technical application property, for instance, a biodegradability, or any other technical application property. In particular, the method follows the same principles as described above with respect to Fig. 4. However, due to the additional target value, additional conditions have to be met during the optimization. Thus, in the following only the main differences with respect to the method as described above will be pointed out. In particular, in this preferred embodi-ment, the optimizer module does not only optimize over the first target values, i.e. over the first target technical application property, but also over the second target values, i.e. over the additional target technical application property. Preferably, also for the second target values a determination model adapted for determining a value for the technical application property based on polymer characterizing parameters, for instance, based on physicochemical characteristics, and foam characteristics is utilized. Thus, in addition to the method as described above for the second target application a second determination model is provided that allows to determine an application property value based on the polymer characterizing parameters and the foam characteristics for the second target application. The second determination model can, for instance, be based on the same algorithm as the property model, and is only trained with a different data set such that it determines another property of the polymer foam. The comparison then refers to not only determining whether the determined technical application property meet the target technical application property within limits, but also whether the determined second application property value meets the target second application property value within limits. Predetermined rules can be utilized that determine for which cases the iteration is continued, i.e. a new formulation is provided as new potential target synthesis specification and for which conditions the potential target synthesis specification is determined as the target synthesis specification. For example, a user can predetermine weights for weighting to which extents which of the conditions has to be met. For instance, it can be more important for a user that the first technical application property is met, whereas the other target application property is not so important. In this case, either the limits within which the second target application property can be met can be set broader or the meeting of this condition can be weighted less strongly. In this context also Pareto optimization methods can be utilized to find an optimal trade of between the different targets. If at one point of the iteration it is then determined that the conditions are met and fulfil the predetermined rules the respective potential target synthesis specification can be determined as target synthe-sis specification and provided as output to a user or can be utilized to generate a control file for producing the respective target polymer foam.
Fig. 5 shows schematically and exemplarily a preferred method 500 for deriving characterizing parameter values, in this example referring to polymer descriptors, from a digital representation of a new polymer foam. In this example, the deriving of the foam characteristics is not shown for a better overview and the foam characteristics can be regarded as known. In a first step 510 a digital representation of the polymer foam is provided. The digital representation can directly comprise the polymer de-scriptors, wherein in this case the steps shown in Fig. 5 until step 550 can be omitted. However, in many cases the polymer descriptors first have to be determined based on the provided digital representation comprising in such a case, for example, to a recipe for the synthesis of the polymer foam, or to a chemical representation of the polymer forming the polymer foam indicating the chemical components and bonds in the polymer forming the polymer foam. In this step 510 the digital representation can comprise any one or more of the following information on the polymer forming the polymer foam: an amount of monomer components; an amount of non-monomer components, like initiators, fillers, additives; a reaction condition, like temperature, vessel, pressure, stirring rate; condition profile, e.g. temperature profile, pH value, solvents; feed profiles; type of polymerization, e.g. radical, cationic, anionic, polycon-densation, polyaddition, polyether formation; post-processing, like amount of compo-nents, conditions, as well as temperature and feed profiles; type of post-processing, e.g. radical, cationic, anionic, polycondensation, polyaddition, polyether formation; chemical information on components, like mixtures, connectivity of non-polymeric pure com-pounds, composition of polymeric pure compounds on the basis of subgroups, connectivity of the monomers associated to the subgroups in the polymeric pure components; for block-co-polymers also information, in which block each monomer and reactive prepolymer is incorporated; for structures/layered materials and composites also information in which phase/layer each component is included. If such information is not provided by the digital representation directly, in optional step 520, the reactive components and subgroups can also be derived from the digital representation, for example, from the recipe.
If the provided information indicates the presence of a mixture, then in a following step the mixture is decomposed into its pure components and each polymer component is treated as input polymer. Moreover, the polymer composition can also be transformed into mol%, wt%, vol%or, absolute mol, if necessary.
In the next step 530 the polymerizable components can be transformed into subgroups, e.g. repeating units, and the subgroups are determined as different types. For example, polymerizable subgroups can be determined based on connectivity information of non- polymeric pure compounds by using SMARTS, for instance, via KNIME workflow. Also connectivity information of all possible subgroups can be derived from connectivity information of non-polymeric pure compounds by using reaction SMARTS, for example, also via KNIME workflow
After the subgroups and their types have been determined, in step 540 the type of descriptors that should be utilized can be provided. However, the descriptors can also be determined without first selecting the type of the subgroups. In order to decrease the computational resources for the method it is preferred that in a step 541 it is determined whether subgroup descriptors associated with a respective type of subgroup are already stored in a database, for example, if entries for subgroups with identical connectivity information already exist in the database. If this is the case the respective associated subgroup descriptor can be directly downloaded, for example, in step 544. If the determined type of subgroup is not stored on the database the sub-group descriptors that are associated with a respective type of subgroup can be determined, for example, in step 542. For example, either a 3D structure of respective types of subgroups can be derived based on connectivity information and an automatic computation of subgroup descriptors can be started using, for instance, a computer cluster, or already existing machine-learning determinations can be utilized as sub-group descriptors. Generally, it is preferred that if computations on new subgroups are necessary, in step 543, the results are stored in the database after the computations are finished. Optionally further subgroup descriptors can be provided from a topological analysis of the subgroups, a quantum chemical computation, a molecular dynamics computation, coarse-grained methods, finite-element computations and kinetic simulations. In particular, polymer reaction engineering methods can be used to derive subgroup descriptors that allow to take into account a microstructure of the polymer.
In step 531 the amount of subgroups, i.e. of each type of subgroup, is determined, for example based on the provided recipe information for the polymer forming the polymer foam and provided in step 532. For example, the amount can be determined by counting an amount of polymerizable groups per polymerizable component, optionally, including prepolymers. In this case, information on polymerizable groups can be derived from non-polymeric components and the such determined amount can be added to a count of the number of, optionally, non-polymerized, polymerizable groups of the subgroups for polymeric components based on the composition of the polymeric components to determine a resulting amount. Further, it is preferred that the amount of polymerizable groups originating from agents used for post-processing after polymeri-zation is removed from the resulting amount.
However, although it is preferred that the polymer descriptors are derived from polymer subgroups, in other embodiments of the invention the polymer descriptors can also be derived in other ways, for instance, by directly determining the polymer descriptors from the complete polymer. Moreover, the polymer descriptors for respective polymers can also be already stored on a storage unit such that the deriving of the polymer descriptors from a digital representation of the polymer can refer to determining from the digital representation information on the polymer forming the polymer foam that allows to access the database and retrieve the corresponding polymer descriptors.
Optionally the derived amounts of subgroups can be used for a further interpretation of the polymer composition. For example, a total number of polymerized functional groups, e.g. double bonds, amine groups, alcohols groups, thiol groups, carboxylic acid groups, isocyanate groups, epoxide groups, and formed functional groups, e.g. amid groups, ester groups, thioester groups, urea groups, urethane groups, thiourethane groups, ether groups, can be determined. Also the molar weighted total number of polymerized functional groups, the mass weighted total number of polymerized functional groups, the total number of residual functional groups, e.g. double bonds, amine groups, alcohol groups, thiol, groups, carboxylic acid groups, isocyanate groups, epoxide groups, aromatic groups, isocyanurate groups, the molar weighted total number of residual functional groups, the mass weighted total number of residual functional groups, the sum of all residual functional groups, the ratio between functional groups after polymerization, the amount of atoms in a certain oxidation state in the polymer, amount of phosphorus atoms in the polymer, the amount of halogen atoms in the polymer, the number of crosslinks in polymer, the molar fraction of crosslinks in polymer, optionally, with mass-weighting as well, the average number of atoms per subgroup, optionally, per weight as well, the average number of non-H-atoms per subgroup, optionally, per weight as well, the average number of bonds per subgroup, optionally, per weight as well, the average number of bonds between non-H-atoms per subgroup, optionally, per weight as well, the average number of rotors per subgroup, optionally, per weight as well, the average number of rotors between non-H-atoms per subgroup, optionally, per weight as well, the average number of rings per subgroup, optionally, per weight as well, the average polar surface areas per subgroup, optionally, per weight as well, the average refractivity per subgroup, optionally, per weight as well, the total number of blocks, the molar size of first block, the molar size of last block, the HLB value of polymer, optionally, with area weighted HLB value, the HLB value of block with lowest HLB value, optionally, with area weighted HLB value, the HLB value of block with largest HLB value, optionally, with area weighted HLB value, the HLB value of first block, optionally, with area weighted HLB value, the HLB value of last block, optionally, with area weighted HLB value, the mass of first block, the mass of last block, the area of block with lowest HLB value, the area of block with largest HLB value, the difference of the HLB values of the blocks, optionally, with area weighted HLB value, the hydrophilic area of the polymer, the lipophilic area of the polymer, the number of arms for ring-opening-polymerization, or the length of arms for ring-opening-polymerization can be determined.
In step 550 the determined amount and type of the subgroups and the associated subgroup descriptors can be utilized to compute the polymer descriptors. For example, the polymer descriptors can be determined by one or more of molar weighted, e.g. arithmetic, harmonic or logarithmic, averaging, mass weighted, e.g. arithmetic, harmonic or logarithmic averaging, volume weighted, e.g. arithmetic, harmonic or logarithmic, averaging, surface area weighted, e.g. arithmetic, harmonic or logarithmic, averaging of the associated descriptors of the subgroups. Moreover, the polymer descriptors can be determined by determining from the associated subgroup de-scriptors one or more of a molar weighted standard deviation, a mass weighted standard deviation, a volume weighted standard deviation, a surface area weighted standard deviation, a molar weighted maximum value, a mass weighted maximum value, a volume weighted maximum value, a surface area weighted maximum value, a molar weighted minimum value, a mass weighted minimum value, a volume weighted minimum value, a surface area weighted minimum value, a molar weighted sum, a mass weighted sum, a volume weighted sum, a surface area weighted sum, and a maximal difference.
In step 560 the derived or provided polymer descriptors can then be provided together with the foam characteristics to the trained property model for determining a technical application property, for example, as described with respect to Fig. 4. The polymer descriptors can be all or partially used in the property model. If they are partially used, a descriptor selection step is needed, which is also called feature selection. For instance, by doing correlation analysis and clustering analysis, the highly correlated descriptor pairs or groups can be detected. The representative descriptors can then be selected from these descriptor pairs or groups. Optionally, the descriptors can then be further selected based on their predictive power or importance for a respective technical application property. Alternatively, a screening design of experiments can be performed to select the descriptors that are statistically significant. The same process can optionally be performed for the foam characteristics in order to select foam characteristics that are most relevant for the determination of a technical application property of the polymer foam. Based on the selected polymer descriptors and/or based on the foam characteristics, an application space can be determined and defined. More data points can be added to this space by space-filling design, optimal design, active learning, etc, which propose new lab runs for determining new training data. The property model is then trained based on the training data set in the application space. The property model can generally refer to sparse, e.g. splines, LASSO regression, PLS, and non-sparse, e.g. linear regression, ridge regression, tree methods, kernel based methods, statistical learning models for relating the polymer descriptors and foam characteristics to a technical application property. Moreover, the property model can further provide a reliability estimation of the determination. For example, kernel density estimation can be used to estimate the determination uncertainty. In step 570 the determined technical application property can then be provided to a user, for example, via a user interface.
In the following some possible test methods are described that can be selected as property test method, in particular, for mechanical properties of a polymer foam for respective applications in the method described above for determining a target polymer foam with respective one or more target properties. For quantifying a rebound of a polymer foam, preferably, tests as described in ASTM D2632 -15 (Standard Test Method for Rubber Property-Resilience by Vertical Rebound) or in ISO 8307: 2007 (Flexible cellular polymeric materials –Determination of resilience by ball rebound) are utilized. For quantifying a split tear strength preferably a test method as described in ISO/DIS 20875: 2016 (Footwear –Test methods for outsoles –Determination of split tear strength and delamination resistance) is utilized. Exemplary test methods to quantify a shore hardness are described in ISO 48-4: 2018 (Rubber, vulcanized or thermoplastic –Determination of hardness –Part 4: Indentation hardness by durometer method (Shore hardness) ) . For quantifying a compression hardness a preferred test method is described in ISO 3386-1: 1986 + Amd 1: 2010 (Polymeric materials, cellular flexible –Determination of stress-strain characteristics in compression –Part 1: Low-density materials) . For quantifying a compression set preferably a test method as described in ISO 1856: 2018 (Flexible cellular polymeric materials –Determination of compression set) is utilized. An exemplary test method to quantify a compressive strength is described in ISO 844: 2021 (Rigid cellular plastics –Determination of compression properties) . For quantifying a tensile strength or an elongation at break preferred test methods are described in DIN EN ISO 527-1 (Plastics –Determination of tensile properties –Part 1: General principles) . A shock attenuating characteristics, e.g. absorbed energy loss during hysteresis cycle, peak pressure, maximum strain, and average stiffness can be quantified utilizing test methods as described in ASTM F1614 -99 (Standard Test Method for Shock Attenuating Properties of Materials Systems for Athletic Footwear) . For quantifying an air permeability a test method as described in ISO 7231: 2010 (Polymeric materials, cellular, flexible –Determination of air flow value at constant pressure-drop) can be utilized.
Generally, for each of the above described burning test methods a respective property model can be trained that is adapted to determined the burning properties of a specific burning test method based on the respective polymer characteristics and/or foam characteristics of the polymer foam and optionally further based on the test parameters of the respective test, if these parameters are variable. All tests are characterized in that they can require specific test conditions as defined for example in the respective standard specifications and, if these are variable, can be utilized as test parameters and that the mechanical property is evaluated based on specific output parameters as defined in the respective norm. Fig. 7 illustrates a block diagram of an exemplarily system architecture of an automated laboratory system 1000 for synthesizing a polymer foam with a laboratory equipment control device 1102, a network 1150 and the synthesis specification, i.e. recipe, module 1100/1110, and a client device 1108. The automated laboratory system includes a laboratory equipment control device layer 1152 as part of the laboratory equipment control device 1102 as well as a synthesis specification module layer 1154 associated with the synthesis specification module and a remote control or client layer 1156 associated with the client device 1108. The laboratory equipment control device layer can be split into several hierarchical layers: the hardware, the middleware and the interface layer. The hardware layer relates to hardware resources such as sensors and actuators, in particular for controlling synthesis of a polymer foam. The middleware relates to any of the known middleware for laboratory or plant synthesis operations. One example is LABS/QM, providing different abstractions to hardware, network and operating system such as low-level device control and message passing. The communication layer relates to communica-tion protocols, wherein one of the protocol may be REST, which may be implemented over different transport protocols (i.e. UDP, TCP, Telemetry) that allow the exchange of messages between the laboratory equipment control device and laboratory equipment devices. Such software architecture allows to control and monitor laboratory equipment without having to interact with the hardware.
The synthesis specification module layer 1154 may include: a mass storage layer, the computing layer, the interface layer. The storage layer is configured to provide mass storage for the data-driven based property model for providing a recipe, i.e. synthesis specification, of a polymer foam that meets a target technical application property, as described in detail above. In particular, the functions performed by the apparatus, as described above, can be provided as program code means stored on the mass storage. Furthermore, synthesis specifications for a plurality of polymer foams can be stored in the mass storage. Such data may be stored in structured databases such as SQL databases or in a distributed file system such as HDFS, NoSQL databases such as HBase, MongoDB. The computing layer may include an application layer that allows to customize the functionalities provided by standard cloud services to perform computing processes based on target properties. Such functionalities can include determining based on a target technical application property and the property model a digital representation of a target polymer foam, generating a synthesis specification from the digital representation of the target polymer foam, and providing the synthesis specifica-tion as control data to the laboratory equipment control device. The interface layer may implement web services, network interfaces as UDP or TCP or Websocket interfaces. For communication with the laboratory equipment control device a REST API is implemented. The client layer 1156 provides interfaces for end-users. For end-users, the client layer 1156 can run client side Web applications, which provide interfaces to the synthesis specification module layer 1154 or the laboratory equipment control device layer 1152. Users may be provided with a UI for selecting target technical application property and in an embodiment a test method for the target technical application property, the target technical application property may also comprise a range of values of technical application property. In other examples, the users may be provided with a UI for selecting more than one respective target technical application property and their respective values. The applications may be configured for users to monitor and control the laboratory equipment control device and the operation remotely. In other examples, the client device layer and the synthesis specification module layer may be integrated into one device. The alternatives described here are only for illustration purposes and should not be considered limiting.
Fig. 8 illustrates a block diagram of an exemplarily system architecture of a system and apparatus for generating a property model for determining a technical application property, a network 2150 and a model generating module 2100/2110 that can be regarded as or comprising a training model apparatus, a synthesis specification module 1100/1110, and a client device 2108. The system for generating a property model includes a model generating module layer 2154 as part of a model generating module and a client layer 2156 associated with the client devices 2108.
The model generating module layer 2154 may include: a mass storage layer, a computing layer, an interface layer. The storage layer is configured to provide mass storage for the data-driven property model as described above. Furthermore, the mass storage is configured for storing data on synthesis specifications for polymer foams and measured one or more technical application properties. In an embodiment, for every technical application property there is a corresponding test method. Such data may be stored in structured databases such as SQL databases or in a distributed file system such as HDFS, NoSQL databases such as HBase, MongoDB. The computing layer may include an application layer that allows to customize the functionalities provided by standard cloud services to perform computing processes for generating a property model for determining a technical application property of a polymer foam. Such functionalities may include receiving for at least two previously measured polymer foams their respective digital representations associated with a synthesis specification, measurement data of at least one technical application property for each of the at least two previously measured polymer foams, receiving at the model generating module the digital representation of at least one unmeasured polymer foam, training the model according to the above described training principles based on the digital representation of the at least two previously measured polymer foams, the measurement data of the technical application property for each of the at least two previously measured polymer foams, and, preferably, a similarity measure between the digital representation associated with the synthesis specification of each of the at least two previously measured polymer foams and the respective digital representation associated with a synthesis specification of the at least one unmeasured polymer foam, and providing via an output interface the property model for the technical application property. The model generating module layer may be configured for deploying the generated model and the synthesis specification database to the synthesis specification module layer. This may include storing the generated model and the synthesis specification database in the mass storage devices associated with the synthesis specification module.
The model generating module layer may further be configured for determining a digital representation of the polymer foam associated with the synthesis specification from the synthesis specification. The digital representation may include a sets of polymer characterizing parameters and polymer characterizing parameter values and polymer foam characteristics and polymer foam characteristics values associated with a synthesis specification of each measured polymer foam. One way of deriving these polymer forming polymer foam characterizing parameters can be to apply the SMILES algorithm or any other already above described principle. In case, where the model is generated based on the digital representation derived from the recipe, a relation between the synthesis specification and the polymer characterising parameters and foam characteristics may be stored in the mass storage devices associated with the model generating module. In such cases, deploying the model comprises providing that relation.
The interface layer may implement web services, network interfaces as UDP or TCP or Websocket interfaces. For communication with the client device a REST API is implemented in this example. The client layer 2156 provides access to mass storage devices, that contain synthesis specifications for polymer foams, and for at least two polymer foams at least one technical application property. The client layer further provides an interface for end-users. For end-users, the client layer 2156 may run client side Web applications, which provide interfaces to the model generation module layer 2154 or the mass storage devices associated with the client layer. The user may be provided with a UI for selection of the synthesis specification data. The user interface may also provide an option for uploading the selected data to the model generating module layer and optionally an option to initiate model generation. In an embodiment the user may be provided with a UI for selecting technical application property test method and connected with it test parameters.
Fig. 9 shows an exemplary system 700 for producing a chemical product based on a synthesis specification generated according to the invention. In this example the system comprises a user interface 710 and a processor 720, associated with a control unit 740. The user interface 710 and the processor 720 can be associated with or realized in accordance with the principles described above, in particular, can be adapted to perform a computer implemented method to determine a target polymer foam and/or synthesis specification based on a determined technical application property, as described above. The control unit 740 is, for example, configured for receiving control data generated according to the invention as described above, in particular, to receiving control data generated based on a synthesis specification of a polymer foam comprising a target technical application property. In this example the control data is provided from a data base 730, in other examples, however the control data can also be provided from a server or any other computational unit for distributing data. Vessels 750, 752 each contain a component of the chemical product, for example, pre-polymers, catalysts, etc. In general more than two vessels are present, however, in this example for illustrative purposes only two are shown. Valves 760, 762 are associ-ated with vessels 750, 752. Valves 750 and 752 can be controlled to dose appropriate amounts of each component into reactor 770, according to the synthesis specification. A motor 800 of a mixer 780 may also be controlled by the control unit according to the synthesis specification. An optional heater 790 may also be controlled according to the synthesis specification. Finally, an exit valve 810 in fluid communication with the reactor may be controlled by the control unit to provide the chemical product to a container or test system 820.
Fig. 10 shows exemplarily and schematically a possible user interface for interfacing, for example, with a processor performing the above described method for determining a target polymer foam with a target technical application property. In this example, an input screen is shown at the upper part. The input screen allows for a definition of a target one or more technical application properties, for instance, in form of maximal respective value. In this example, a target rebound elasticity has been input with to a target value of 81%. Optionally, the input can also refer to another target application property, in this example, a target shock attenuation of 0.9kN. Further, the input screen can allow to provide constrains for the target polymer foam, for example, as shown, constraints to a polymer foam class that can also be selected via a drop down menu. Here as exemplary case the polymer foam is constrained to the class of polyurethane. Moreover, additional constrains for the polymer can be provided as shown in Fig. 10, like the intended application as footwear foam. However, this input option can also be omitted and as described above a general synthesis specifications can be provided by a database or can be generated by known methods. Moreover, the input screen can also allow to provide additional or other constrains with respect to the target polymer foam or the target synthesis specification. Further, the input screen can allow to select a respective test method and optionally also test parameters values. Here in this example the test methods for the respective technical application properties are also provided. The values for such polymer descriptors and foam descriptors can then be determined in accordance with the above described principles for a starting polymer foam and also for respective amended polymer foams until a target polymer foam can be found. An exemplary output screen is shown in the lower part of Fig. 10. In this example, the output screen provides a target polymer foam that fulfils the target technical application properties. Moreover, the respective components of the polymer foam are provided in form of ingredient types and associated names and amounts. Optionally, also further information on the determined target polymer foam could be provided, for example, an associated synthesis specification.
Other variations to the disclosed embodiments can be understood and effected by those skilled in the art in practicing the claimed invention, from a study of the drawings, the disclosure, and the appended claims.
For the processes and methods disclosed herein, the operations performed in the processes and methods may be implemented in differing order. Furthermore, the outlined operations are only provided as examples, and some of the operations may be optional, combined into fewer steps and operations, supplemented with further operations, or expanded into additional operations without detracting from the essence of the dis-closed embodiments.
In the claims, the word "comprising" does not exclude other elements or steps, and the indefinite article "a" or "an" does not exclude a plurality.
A single unit or device may fulfill the functions of several items recited in the claims. The mere fact that certain measures are recited in mutually different dependent claims does not indicate that a combination of these measures cannot be used to advantage. Procedures like the providing of the digital representation of the polymer foam, the providing the property model, the determining of the technical application property of the polymer foam, etc. performed by one or several units or devices can be performed by any other number of units or devices. These procedures can be implemented as program code means of a computer program and/or as dedicated hardware.
A computer program product may be stored/distributed on a suitable medium, such as an optical storage medium or a solid-state medium, supplied together with or as part of other hardware, but may also be distributed in other forms, such as via the Internet or other wired or wireless telecommunication systems.
Any units described herein may be processing units that are part of a classical compu-ting system. Processing units may include a general-purpose processor and may also include a field programmable gate array (FPGA) , an application specific integrated circuit (ASIC) , or any other specialized circuit. Any memory may be a physical system memory, which may be volatile, non-volatile, or some combination of the two. The term “memory” may include any computer-readable storage media such as a non-volatile mass storage. If the computing system is distributed, the processing and/or memory capability may be distributed as well. The computing system may include multiple structures as “executable components” . The term “executable component” is a structure well understood in the field of computing as being a structure that can be software, hardware, or a combination thereof. For instance, when implemented in software, one of ordinary skill in the art would understand that the structure of an executable component may include software objects, routines, methods, and so forth, that may be executed on the computing sys-tem. This may include both an executable component in the heap of a computing sys-tem, or on computer-readable storage media. The structure of the executable component may exist on a computer-readable medium such that, when interpreted by one or more processors of a computing system, e.g., by a processor thread, the computing system is caused to perform a function. Such structure may be computer readable directly by the processors, for instance, as is the case if the executable component were binary, or it may be structured to be interpretable and/or compiled, for instance, whether in a single stage or in multiple stages, so as to generate such binary that is directly interpretable by the processors. In other instances, structures may be hard coded or hard wired logic gates, that are implemented exclusively or near-exclusively in hardware, such as within a field programmable gate array (FPGA) , an application specific integrated circuit (ASIC) , or any other specialized circuit. Accordingly, the term “executable component” is a term for a structure that is well understood by those of ordinary skill in the art of computing, whether implemented in software, hardware, or a combination. Any embodiments herein are described with reference to acts that are performed by one or more pro-cessing units of the computing system. If such acts are implemented in software, one or more processors direct the operation of the computing system in response to having executed computer-executable instructions that constitute an executable component. Computing system may also contain communication channels that allow the computing system to communicate with other computing systems over, for example, network. A “network” is defined as one or more data links that enable the transport of electronic data between computing systems and/or modules and/or other electronic devices. When information is transferred or provided over a network or another communications connection, for example, either hardwired, wireless, or a combination of hardwired or wireless, to a computing system, the computing system properly views the connection as a transmission medium. Transmission media can include a network and/or data links which can be used to carry desired program code means in the form of computer-executable instructions or data structures and which can be accessed by a general-purpose or special-purpose computing system or combinations. While not all compu-ting systems require a user interface, in some embodiments, the computing system includes a user interface system for use in interfacing with a user. User interfaces act as input or output mechanism to users for instance via displays.
Those skilled in the art will appreciate that at least parts of the invention may be practiced in network computing environments with many types of computing system configurations, including, personal computers, desktop computers, laptop computers, message processors, hand-held devices, multi-processor systems, microprocessor- based or programmable consumer electronics, network PCs, minicomputers, main-frame computers, mobile telephones, PDAs, pagers, routers, switches, datacenters, wearables, such as glasses, and the like. The invention may also be practiced in distributed system environments where local and remote computing system, which are linked, for example, either by hardwired data links, wireless data links, or by a combina-tion of hardwired and wireless data links, through a network, both perform tasks. In a distributed system environment, program modules may be located in both local and remote memory storage devices.
Those skilled in the art will also appreciate that at least parts of the invention may be practiced in a cloud computing environment. Cloud computing environments may be distributed, although this is not required. When distributed, cloud computing environ-ments may be distributed internationally within an organization and/or have compo-nents possessed across multiple organizations. In this description and the following claims, “cloud computing” is defined as a model for enabling on-demand network access to a shared pool of configurable computing resources, e.g., networks, servers, storage, applications, and services. The definition of “cloud computing” is not limited to any of the other numerous advantages that can be obtained from such a model when deployed. The computing systems of the figures include various components or functional blocks that may implement the various embodiments disclosed herein as explained. The various components or functional blocks may be implemented on a local computing system or may be implemented on a distributed computing system that includes elements resident in the cloud or that implement aspects of cloud computing. The various components or functional blocks may be implemented as software, hardware, or a combination of software and hardware. The computing systems shown in the figures may include more or less than the components illustrated in the figures and some of the components may be combined as circumstances warrant.
Any reference signs in the claims should not be construed as limiting the scope.
The invention refers to a method for determining a target polymer foam. A target property and a digital representation of a potential target synthesis specification indicative of characterizing parameters of the polymer forming the polymer foam and foam characteristics are provided. A property model adapted to determine a property of a polymer foam based on the characterizing parameters of the polymer forming the polymer foam and the foam characteristics is provided. The property model is a data-driven model parameterized such that it can determine a property of a polymer foam based on characterizing parameters of the polymer forming the polymer foam and based on foam characteristics. The property of the potential target polymer foam is determined based on the provided property model and the digital representation. The determined property of the potential target polymer foam is compared with the target property to determine the target polymer foam.

Claims

A computer-implemented method for determining a target synthesis specifica-tion indicative of a target polymer foam comprising a target technical application property, wherein the method comprises:

providing a target technical application property, wherein the target technical ap-plication property is indicative of a technical characteristic of a polymer foam,

providing a digital representation of a potential target synthesis specification in-dicative of or associated with characterizing parameters of the polymer forming the polymer foam and foam characteristics of the polymer foam, wherein the characterizing parameters are indicative of characteristics of a polymer and/or are derivable from one or more characteristics of the polymer and the foam characteristics are indicative of characteristics of the foam structure of the polymer foam,

providing a property model adapted to determine a technical application property of a polymer foam based on the characterizing parameters of the polymer forming the polymer foam and the foam characteristics of the polymer foam, wherein the property model is a data-driven model parameterized such that it can determine a technical application property of a polymer foam based on characterizing parameters of the polymer forming the polymer foam and based on foam characteristics of the polymer foam,

determining the technical application property of the potential target polymer foam based on the provided property model and the digital representation, and

comparing the determined technical application property of the potential target polymer foam with the target technical application property and, based on the compari-son, either i) determining the potential target polymer foam as the target polymer foam and the potential target synthesis specification as the target synthesis specification, or ii) providing a new potential target synthesis specification of a new potential target polymer foam and repeating the determination of the technical application property utilizing the new potential target synthesis specification of the new potential target polymer foam.
The method according to claim 1, wherein the providing of the target synthesis specification of the target polymer foam comprises providing control signals adapted for controlling an industrial plant for producing the target polymer in accordance with the target synthesis specification.
The method according to any of claims 1 and 2, further comprising providing an additional target technical application property for the target polymer foam and providing the potential target synthesis specification based on the provided additional target technical application property such that the potential target polymer foam fulfils the provided additional target technical application property.
The method according to claim 3, wherein the providing of a new potential target synthesis specification is based on amending the provided additional target technical application property and providing the new potential target synthesis specifi-cation such that the potential target polymer foam fulfils the amended additional target technical application property.
The method according to any of claims 3 and 4, wherein the providing of the potential target synthesis specification based on the provided additional target technical application property comprises utilizing a determination model adapted to determine a technical application property of a polymer foam based on the digital representation of the polymer foam, wherein the property model is a data driven model parameterized such that it determines based on the digital representation of the polymer foam a technical application property associated with the polymer foam.
The method according to any of the preceding claims, wherein the method further comprises providing test information indicative or associated with a technical application property test method, wherein the technical application property test method is indicative of a standardized test method for determining experimentally a respective technical application property of a polymer foam, wherein the property model is provided based on the technical application property test method.
The method according to claim 6, wherein the test information is further indicative of or associated with one or more test method parameters, wherein the property model is adapted to further determine the technical application property based on the test method parameters and wherein the determining of the technical application property is based further on the test method parameters.
The method according to any of the preceding claims, wherein the technical application properties are mechanical application properties or thermal application properties.
An interface method for providing an interface, wherein the interface method comprises:

receiving as input a digital representation and a target technical application prop-erty via a user interface and providing the received digital representation and the target technical application property to a processor performing the method according to any of the preceding claims, and

providing the determined target synthesis specification of the polymer foam to a user via a user interface as result, wherein the result is received from the processor performing the method according to any of the preceding claims.
A computer-implemented training method for training a data-driven based property model for parameterizing the property model, wherein the training method comprises:

providing training data comprising a) digital representations of a plurality of train-ing polymer foams indicative of characterizing parameters and foam characteristics of each of the training polymer foams, and b) a technical application property associated with each training polymer foam,

providing a data-driven trainable property model,

training the provided data-driven based property model based on the provided training data such that the trained property model is adapted to determine a technical application property of a polymer foam based on characterizing parameters of polymer forming polymer foam and foam characteristics of the polymer foam, and

providing the trained property model.
An apparatus for determining a target synthesis specification indicative of a target polymer foam comprising a target technical application property, wherein the apparatus comprises one or more processors configured for performing the functions:

providing a target technical application property, wherein the target technical ap-plication property is indicative of a technical characteristic of a polymer foam,

providing a digital representation of a potential target synthesis specification in-dicative of or associated with characterizing parameters of the polymer forming the polymer foam and foam characteristics of the polymer foam, wherein the characterizing parameters are indicative of characteristics of a polymer and/or are derivable from one or more characteristics of the polymer and the foam characteristics are indicative of characteristics of the foam structure of the polymer foam,

providing a property model adapted to determine a technical application property of a polymer foam based on the characterizing parameters and the foam characteris-tics of the polymer foam, wherein the property model is a data-driven model parameter-ized such that it can determine a technical application property of a polymer foam based on characterizing parameters and based on foam characteristics,

determining the technical application property of the potential target polymer foam based on the provided property model and the digital representation, and

comparing the determined technical application property of the potential target polymer foam with the target technical application property and, based on the compari-son, either i) determining the potential target polymer foam as the target polymer foam and the potential target synthesis specification as the target synthesis specification, or ii) providing a new potential target synthesis specification of a new potential target polymer foam and repeating the determination of the technical application property utilizing the new potential target synthesis specification of the new potential target polymer foam.
An interface apparatus for providing an interface, wherein the interface appa-ratus comprises one or more processors configured for performing the functions:

receiving as input a digital representation and a target technical application prop-erty via a user interface and providing the received digital representation and the target technical application property to a processor performing the method according to any of claims 1 to 8, and

providing the determined target synthesis specification of the polymer foam to a user via a user interface as result, wherein the result is received from the processor performing the method according to any of claims 1 to 8.
A training apparatus for training a data-driven based property model for parameterizing the property model, wherein the training apparatus comprises one or more processors configured for performing the functions:

providing training data comprising a) digital representations of a plurality of train-ing polymer foams indicative of characterizing parameters and foam characteristics of each of the training polymer foams, and b) a technical application property associated with each training polymer foam,

providing a data-driven based trainable property model,

training the provided data-driven based property model based on the provided training data such that the trained property model is adapted to determine a technical application property of a polymer foam based on characterizing parameters and foam characteristics of the polymer, and

providing the trained property model.
A computer program product for determining a target synthesis specification indicative of a target polymer foam comprising a target technical application property, wherein the computer program product comprises program code means for causing the apparatus of claim 11 to execute the method according to any of claims 1 to 8.
A computer program product for training a data-driven based property model, wherein the computer program product comprises program code means for causing the apparatus of claim 13 to execute the method according to claim 10.