EP4732223A1

EP4732223A1 - Systems and methods for verification of data associated with supplied input materials

Info

Publication number: EP4732223A1
Application number: EP24733226.5A
Authority: EP
Inventors: Nicole Graf; Michael-georg SCHMIDT
Original assignee: BASF SE
Current assignee: BASF SE
Priority date: 2023-06-20
Filing date: 2024-06-20
Publication date: 2026-04-29
Also published as: CN121336223A; WO2024261108A1

Abstract

Disclosed are methods and apparatuses and associated computer elements for verifying input material data gathered via a decentral network and associated with one or more input material(s) entering a production to avoid storage of faulty data and all to ensure generation of reliable data when using the input material data in data processing operation(s). Further disclosed is the use of the verified input material data to control the production of further products.

Description

SYSTEMS AND METHODS FOR VERIFICATION OF DATA ASSOCIATED WITH SUPPLIED INPUT MATERIALS

TECHNICAL FIELD

TECHNICAL BACKGROUND

In the production, reuse, repair, refurbishing, remanufacturing, repurposing, recycling and/or recovery of products multiple regulatory requirements need to be met, which differ depending on the product and recycling chain. For instance, the producer of a product must provide product data to their customers and to recyclers to fulfil regulatory requirements. Such product data may be exchanged electronically and may be used to control the production of further products at the production sites of the product consumer to improve production efficiency or to determine compounds present within the end-of-life product to improve recycling efficiency. To allow such improved production and recycling efficiency, it must be ensured that the exchanged product data is not erroneous.

Hence, there is a need to avoid storage and transfer of erroneous product data within the product ecosystem.

SUMMARY

In an aspect, the disclosure relates to a computer-implemented method for verifying input material data associated with one or more input material(s) entering a production, wherein the production produces one or more product(s) from the one or more input material(s), the method comprising:

(a) providing one or more decentral input material identifier(s) associated with the one or more input material(s),

(b) gathering - via a decentral network - input material data associated with the provided decentral input material identifier(s) from decentral data providing network node(s) associated with the input material data,

(c) verifying at least part of the gathered input material data by using a rule-based engine including plausibility threshold(s) or by using a data-driven model trained on historical data sets including input material data and plausibility scores,

(d) based on the verified input material data, providing the verified input material data for processing the verified input material data. In a further aspect, the disclosure relates to an apparatus for verifying input material data associated with one or more input material(s) entering a production, wherein the production produces one or more product(s) from the one or more input material(s), the apparatus comprising:

(a) a decentral input material identifier provider configured to provide one or more decentral input material identifier(s) associated with the one or more input material(s),

(b) a decentral data consuming network node associated with the production configured to gather input material data associated with the provided decentral input material identifier(s) from decentral data providing network node(s) associated with the respective input material data

(c) a rule-based engine including plausibility threshold(s) or a data-driven model trained on historical data sets including input material data and plausibility scores, wherein the rule-based engine or the data-driven model is configured to verify at least part of the gathered input material data and configured to provide - based on the verified input material data - the verified input material data,

(d) optionally a data processor configured to process the provided verified input material data.

In yet a further aspect, the present disclosure relates to a use of input material data as verified by the computer-implemented methods as disclosed herein or by the apparatuses disclosed herein to control the production of product(s) at least in part produced from input material(s) associated with the verified input material data.

In a further aspect, the present disclosure relates to a computer element, such as a computer readable storage medium, a computer program or a computer program product, comprising instructions, which when executed by a computing node or a computing system, direct the computing node or computing system to carry out the steps of the computer-implemented methods disclosed herein.

In a further aspect, the present disclosure relates to a computer element, such as a computer readable storage medium, a computer program or a computer program product, comprising instructions, which when executed by the apparatuses or systems disclosed herein, direct the apparatuses or systems to carry out steps the apparatuses or systems disclosed herein are configured to execute.

Any disclosure, embodiments and examples described herein relate to the methods, the apparatuses, the systems, the uses and computer elements lined out above and below. Advantageously, the benefits provided by any of the embodiments and examples equally apply to all other embodiments and examples.

Embodiments

To avoid the storage and use of erroneous input material data gathered from input material data owners via a decentral network, methods and systems to verify gathered input material data associated with supplied input material prior to storing the gathered input material data or prior to further processing the gathered input material data is proposed. By using a decentral input material identifier associated with the input material data and by controlling access to such input material data via a decentral data providing network node associated with the data owner of the input material data, the input material data can be exchanged securely and efficiently over the decentral network under the control of the respective input material data owner. Hence, the input material data owner may control access to said input material data via multiple decentral data consuming services associated with input material consumers. This allows for simplified and customizable data sharing or exchange from input material suppliers to product producer(s) using the input material(s) to produce product(s). This way, a more reliable and efficient further processing of supplied input material(s) by upstream participants of the supply chain can be achieved, while the data remains in the ownership of the input material supplier supplying the upstream participant.

By using a rule-based engine or a trained data-driven model, the plausibility of individual data points, combinations of data points or whole input material data sets may be verified. This allows to determine whether the gathered input material data contains erroneous data points and/or data types and/or erroneous combinations of data points and/or all data required from a regulatory standpoint. Erroneous data points, data types and/or data combinations may include data points, data types and/or data combinations being implausible for the respective input material. Verification of the input material data set or a part thereof may further allow to verify the input material as such. For example, the result of the plausibility check may be used to determine whether data contained within the input material set and not having been verified using the rule-based engine or the trained data-driven model is implausible or not. For instance, an implausible data point may result in the determination that the input material cannot have the origin data included in the input material data set. The rule-based engine may operate on data point level, multiple data points level or whole data set level and may use plausibility threshold(s) to determine whether individual data point(s), multiple data points or the whole data set is plausible. The plausibility threshold(s) may include rule(s) defining threshold(s) for individual data point(s) and/or rule(s) defining allowable data point combination(s) and/or rule(s) defining the content of the whole data set. Rule(s) defining the whole data set may be associated with a location the respective rule is applicable. Usage of rule(s) associated with the respective location of the production using the input material(s) to produce product(s) allows to ensure, that all data required from regulations applicable to said location is contained within the input material data.

Verifying the gathered input material data allows to ensure a high data quality and avoids lack of required input material data. Verifying the gathered input material data allows that such input material data can be used to reliably control the production of the product to increase production efficiency. Verifying the gathered input material data ensures that no erroneous data is contained within digital twins of products of the product ecosystem, hence avoiding the use of erroneous data which may result in the determination of inefficient production or recycling processes using said erroneous data. Verifying the gathered input material data hence ensures a high data quality of the digital twins used within the product ecosystem and ensures that no erroneous data is entered into systems controlling the production of products or the recycling of end-of-life products. Verifying the gathered input material data allows to ensure compliance with regulatory requirements regulating the required data to be provided upon supply of a product to a product consumer and/or upon entry of an input material to the system boundary of the production using said input material to produce product(s).

In the following, embodiments of the present disclosure will be outlined by ways of examples. It is to be understood that the present disclosure is not limited to said embodiments and/or examples.

The input material may comprise any indiscrete material, e.g., may be a continuous volume of solid or liquid material, or any discrete material, e.g. may be a component or part or a component assembly. The input material may include starting material used in any process performed in the production to produce the product. The input material may be a virgin material, e.g. an input material that has not undergone a previous production-and-use cycle, in particular, has not been processed and/or used. The input material may be a recycled material having undergone at least one recycling step. The input material may comprise or be any input material entering the production and provided at any entry point of the production . The input material may be any material entering the system boundary of the production. The input material may be used as feedstock to produce one or more product(s). The product(s) may be produced via one or more intermediate product(s). Hence, the input material may be directly or indirectly used to produce the one or more product(s).

The product may be an indiscrete product. The product may be a chemical product. The product may be a discrete product. The product may be a component or part, a component assembly or an end product.

The production may be any production producing products. The production may comprise one or more production chain(s). A production chain may comprise one or more production step(s). A production step may be performed by a machine or apparatus or a collection of machines or apparatuses. The production may be any facility or plant performing at least one reuse, repair, refurbish, re manufacture, recycle or recover operation. The input material may be used in any of the production chain(s). The input material may be used in any of the production step(s).

The production may be a chemical production. In this case, the input material may be a chemical material. Likewise, the product produced by the chemical production may be a chemical product. Chemical products may include or be any material produced by the chemical production using at least one input material. The chemical product may comprise or be any chemical product produced by the chemical production and provided at any exit point of the chemical production. The chemical product or output material may be produced from input materials by the chemical production. The chemical product may be produced from the input material(s) via one or more chemical and/or physical processes. Hence, chemical intermediate products produced from input materials may be used to produce the chemical product(s) or output material(s). Chemical processes may include chemical reactions. Chemical reactions may include any chemical reaction commonly known in the state of the art in which the reactants are converted to one or more different chemical products. Chemical reactions may involve the use of catalysts, enzymes, bacteria, etc. to achieve the chemical reaction between the reactants. Physical processes may include mixing, separation and/or extrusion. The input material may be selected from petrochemical feedstocks, such as naphtha crude oil, and natural gas, or intermediates from such feedstocks that in turn require a certain amount of naphtha, crude oil, and natural gas. The input material may be selected from natural feedstocks, such as vegetable oils, biologicals like enzymes, and/or naturally occurring inorganic or organic chemical materials, or intermediates from such feedstocks that in turn require a certain amount of vegetable oils, biologicals and/or naturally occurring inorganic or organic chemical materials.

The chemical production may be a chemical production network. Chemical production networks may include multiple types of production processes for producing different chemical products from input materials. The chemical production network may include a complex production network producing multiple chemical products in multiple production or value chains. A production or value chain may include one or more process(es) configured to produce one chemical product or chemical product class from one or more input material(s). The chemical production network may include connected, interconnected and/or non-connected production chains. The production chains included in the chemical production network may be defined by the physical system boundary of the chemical production network. The system boundary may be defined by location or control over production processes. The system boundary may be defined by the site of the chemical production network. The system boundary may be defined by production processes controlled by one entity or multiple entities jointly. The system boundary may be defined by the value chain with staggered production processes to an end product, which may be controlled by multiple entities jointly or separately. The chemical production network may include a waste collection and sorting step, a recycling step such as pyrolysis, a cracking step such as steam cracking, a production step to produce chemical products or intermediates from provided inbound material(s), a separation step to separate intermediates of one process step and further processing steps to convert such outputs to chemical product(s) leaving the system boundary of the chemical production network. The chemical production network may produce from input materials multiple intermediates and from intermediates one or more chemical products. Input material may enter the chemical production network at entry points. Chemical products may leave the production network at exit points (or feed-out points).

The chemical production network may comprise one or more entry points at which input materials are provided to the chemical production network. Input material may include raw materials, or chemical intermediate products. Input material may be provided to a plant performing the first production step of the production chain associated with the chemical product.

The decentral input material identifier may comprise any unique identifier uniquely associated with the input material data and optionally a data owner of the input material data. The decentral input material identifier may connect the physical entity of the input material to the input material data. The decentral input material identifier may include one or more Universally Unique Identifier(s) (UUID(s)) and/or one or more Decentralized Identifier(s) (DID(s)). The one or more DID(s) and/or UUID(s) may further be associated with the input material. The decentral input material identifier may further include or be associated with an input material identifier associated with the input material. The decentral input material identifier may be issued by a central or decentral identity issuer. The decentral input material identifier may be generated by the data owner or on behalf of the data owner of the input material data. The decentral input material identifier may include authentication information. Via the decentral input material identifier and its unique association with the input material data associated with the input material and optionally the data owner of the input material data, access to the input material data may be controlled by the data owner of the input material data. The data owner of the input material data may be the input material producer. This contrasts with central authority schemes, where identifiers are provided by such central authority and access to input material data is controlled by such central authority. Decentral in this context refers to the usage of the decentral input material identifier in implementations as controlled by the data owner of the input material data. The decentral input material identifier may be a digital or virtual identifier, e.g. may not correspond to physical identifier(s) physically attached to the input material .

The decentral input material identifier may include or be associated with one or more identifier(s) used in the decentral network and allowing for exchange of input material data via the decentral network. For instance, the decentral input material identifier may include or be associated with identifier(s) of data sets included in the input material data. Data exchange may include discovery of the decentral input material identifier and optionally identifier(s) included in or be associated with said decentral input material identifier for participant nodes of the decentral network, authentication of participant nodes of the decentral network and/or authorization of data transfers via a peer-to-peer communication between participant nodes of the decentral network.

The decentral input material identifier may be associated with one or more decentral identifier(s) associated with materials used to produce the input material. This allows to determine the materials used to produce the input material based on the decentral input material identifier.

The gathered input material data may be part of a digital twin of the input material. The digital twin of the input material may be a digital representation of a physical entity of the input material with a defined semantic description of said physical entity of the input material. The digital twin of the physical entity of the input material is hence a digital version of said physical entity. Once created, the digital twin may be used to represent the physical entity of the input material in a digital representation of a real- world system. The digital twin may be uniquely linked to the physical input material via at least the decentral input material identifier. The digital twin may be created such that it is identical in form and behavior of the corresponding input material. Additionally, the digital twin may mirror the properties of the input material during its lifetime and/or events occurring with respect to the input material during its lifetime. For example, sensors may capture real-time (or near real-time) data, such as transport data or use data, and/or event-driven data, such as data captured in response to the occurrence of a predetermined event, such as an accident, of the physical input material to relay it back to its remote digital twin. The digital twin may then be updated to maintain its correspondence to the physical entity of the input material. Hence, the digital twin may at any time represent the current state of the physical entity of the input material. The digital twin may contain the decentral input material identifier. The decentral input material identifier may be associated with a physical entity of the input material the digital twin is associated with. The decentral input material identifier may be associated with the physical entity of the input material the digital twin is generated for. The decentral input material identifier may be associated with decentral identifiers of materials used to produce the input material. The decentral input material identifier may be associated with products, components, component assemblies and/or end products produced using the input material (e.g. the input material associated with the decentral input material identifier may be used in at least one production step of the production of the products, the components, the component assemblies and/or the end products). This allows to track the input material and its use within the product ecosystem. The decentral input material identifier may or may be assigned to a physical identifier connected to the input material. The physical identifier may be any identifier for the produced input material, such as a batch number or a part number. The physical identifier may comprise a passive or active element, e.g. bar code, QR-code, RFID-tag, but is not limited thereto. The physical identifier may include markers embedded in the input material or similar physical arrangement that allows to digitally identify the input material. The digital twin may further contain an input material identifier. The digital twin may contain one or more data sets (e.g. digital twin data set(s)). A data set(s) may hence represent a part of the digital twin.

The digital twin may be stored on a dedicated storage associated with the data owner of the digital twin. Access to the dedicated storage may be controlled by the data owner of the input material data or digital twin. Access to the dedicated storage and hence the input material data or digital twins stored therein may be controlled by the data owner via the decentral data providing network node associated with the dedicated storage. The data owner may be the input material producer. The digital twin or input material data may be stored in the dedicated storage for access by consumers of the input material, such as producer producers using the input material to produce product(s).

The input material data may be associated with one or more representation(s) for accessing the input material data or parts thereof. The representations may include a locator pointing to the decentral data providing network node associated with the dedicated storage storing the respective input material or the part thereof. The representation may be used by decentral data consuming network node(s) to request access to the input material data associated with such representation. The gathered input material data may correspond to one or more data sets included in the digital twin. The data set may be associated with or may include a data set identifier uniquely identifying the respective data set within the digital twin. The data set identifier may be associated with the decentral input material identifier. This allows to uniquely identify a given data set using the decentral input material identifier in combination with the data set identifier. The data set may contain different types of input material data. For instance, a first data set may include production data, a second data set may include emission data, a third data set may include composition data, a fourth data set may include material safety data and technical data, etc.

The digital twin may be generated by a decentral participant node. The decentral participant node may be in communication with the decentral data providing network node providing the input material data. The decentral participant node may be associated with the decentral data providing network node providing the input material data. The digital twin may be generated by the data owner of the input material data. The data owner of the input material data may be the production producing the input material. The data owner of the input material data may be the legal entity operating the production producing the input material. The data owner of the input material data may be the natural person operating the production producing the input material. The digital twin may be generated on behalf of the data owner of the input material data. For instance, the digital twin may be generated by a third party based on a service provided by the third party to the data owner.

Gathering may include receiving or retrieving data, such as input material data.

The producer operating the production producing the product and the input material supplier(s) supplying the input material(s) may be part of a product ecosystem. The product ecosystem may include different stages including manufacturing, use and re-use. In these stages one or more ecosystem participant(s) may contribute to the manufacture, use or re-use of a product. For example, the manufacturing stage may include raw material manufacturers, intermediate material manufactures and/or end-product manufacturers. Further for example, the use stage may include product user, product maintainers and/or product distributors. Further for example, the re-use stage may include collectors, sorters, dismantlers, recyclers, restorers and/or re-furbishers.

The participants of the product ecosystem may be connected via the decentral network. The decentral network may include computing nodes associated with participants of the product ecosystem and may be configured to perform data transactions. The computing nodes associated with participants of the product ecosystem may be associated with producers, users or re-users of physical products, such as chemical intermediate product producers, chemical product producers, intermediate product producers, end product producers, end product users, used product users or product re-users. The data transactions may be based on a transaction protocol including authentication and/or authorization mechanism(s). Based on the authentication and/or authorization mechanism(s) a peer-to-peer communication between computing nodes associated with participants of the product ecosystem may be established. The respective nodes of the decentral network associated with the participants of the product ecosystem may be configured as decentral data consuming network node(s) and/or decentral data providing network node(s).

The one or more authentication mechanism(s) may be associated with or linked to a decentral identifier associated with the physical entity of the respective raw material, chemical product, intermediate product, end-product or end-of life product. The decentral identifier may uniquely identify the respective physical entity within the decentral network. The decentral identifier may connect the physical entity of the respective raw material, chemical product, intermediate product, end-product or end-of life product data to respective raw material data, chemical product data, intermediate product data, end-product data, end-of-life product data, respectively. The decentral identifier may include one or more Universally Unique Identifier(s) (UUID(s)) and/or one or more Decentralized Identifier(s) (DID(s)). The one or more authentication mechanism(s) associated with the decentral identifier may be provided to participant node(s). The one or more authentication mechanism(s) associated with the decentral identifier may be accessible by the decentral data providing network node and/or the decentral data consuming network node. The decentral configuration allows for more efficient use of computing resources and strengthens control by the data owners of the decentral network.

The one or more authorization mechanism(s) may include at least one authorization rule for controlling access to data under control by the data owners. The computing nodes associated with participants of the product ecosystem may be configured to provide decentral data consuming network node(s) and/or decentral data providing network node(s). A decentral data providing network node may be configured to provide or send data to another participant node of the decentral network. A decentral data consuming network node may be configured to ingest or receive data from another participant node of the decentral network. Providing data to a decentral data providing network node for access by a decentral data consuming network node may include indirect or direct access of the decentral data consuming network node to the data.

The decentral data providing network node may comprise computer-executable instructions for providing and/or processing data within a decentral network, such as the input material data, requested by a decentral data consuming network node. The decentral data providing network node may be associated with or connected to one or more dedicated data storage(s) storing the input material data. The decentral data providing network node may be directly or indirectly connected to the data storage(s) storing the input material data. Hence, the decentral data providing network node may be associated with the input material data. The dedicated data storage(s) may be under control of the data owner of the input material data. The data owner may have access to the dedicated data storage(s). This way, the data owner of the input material data may control access to the input material data from various decentral data consuming network nodes. The decentral data consuming network node may comprise computer-executable instructions for accessing and/or processing data within a decentral network, such as input material data, provided by a decentral data providing network node. The decentral data consuming network node may be controlled or owned by or associated with a consumer of the input material data (e.g. the product producer). The consumer may be any entity processing the input material data. The consumer may be any entity operating a production configured to process the input material. Processing may include using the input material to produce products. Processing may include performing one or more recycling step(s) on the input material. The consumer may be an upstream participant of the input material supplier in the product ecosystem the produced product is associated with, e.g. the product is used in.

A rule-based engine may be used to verify at least part of the gathered input material data. The rulebased engine may be a software or software component that applies one or more rules to at least part of the gathered input material data. The rule-based engine used to verify at least part of the gathered input material data may include plausibility threshold(s). Plausibility threshold(s) may be associated with individual data point(s), multiple data points and/or the whole data set (e.g. the complete data contained in the gathered input material data associated with a defined input material). Plausibility thresholds associated with individual data point(s) may include one or more rule(s) defining threshold(s), such as minimum value(s) and/or maximum value(s), for individual data points present with the gathered input material data. The individual data points may correspond to values associated with a chemical and/or physical property of the input material. The individual data points may correspond to the value of key-value pair(s) defining chemical and/or physical properties of the input material. Use of such plausibility threshold(s) allows to identify unplausible data points, hence avoiding storage and processing of unplausible input material data points which may result in incorrect data, such as control data to control production of products using the input materials, obtained upon processing such input material data containing unplausible data points.

Plausibility thresholds associated with multiple data points may include one or more rules defining allowable combination of data points and optionally threshold(s) for data points contained in said combination. The threshold(s) may define minimum value(s) and/or maximum value(s) for data points present with the combination of data points. Use of such plausibility threshold(s) allows to identify unplausible data point combinations and optionally unplausible data points, hence avoiding storage and processing of unplausible input material data combinations which may result in incorrect data, such as control data to control production of products using the input materials, obtained upon processing such input material data containing unplausible data combinations.

Plausibility thresholds associated with the whole data set may include one or more rules defining data to be contained within the gathered input material data (e.g. the gathered input material data associated with a particular input material. The rules may further define one or more locations associated with the data to be contained in the gathered input material. This allows to consider different regulatory regulations associated with different locations and defining the data to be contained with the gathered input material. Use of such plausibility threshold(s) allows to ensure completeness of the gathered input material data, hence ensuring that regulatory regulations are complied with.

The rule-based engine may further be configured to compare data points, data types and/or data combinations contained in a plurality of input material data sets associated with a respective input material. The comparison may be performed for a defined time span, The defined time span may be a predefined time span. This may allow to detect deviations in data points and/or data types and/or data combinations. Such deviations may indicate that production conditions of the input material may have been changed without including an indication in the associated input material data set(s). The determined deviations may be provided by the rule-based engine. The determined deviations may trigger a warning message, for example if a persistent downwards or upwards trend for data point(s) is determined.

The trained data driven model may be trained on historical data sets including input material data and one or more plausibility score(s). The input material data may include individual input material data points, multiple input material data points, such as combinations of input material data points and whole input material data sets. The plausibility score may be indicative of the plausibility of respective individual data point, combination of data points or whole data set. For instance, a plausibility score of 1 indicates that the data point, combination of data points or whole data set is unplausible while a plausibility score of 5 indicates that the data point, combination of data points or whole data set is plausible. Scores between 1 and 5 may be used to indicate a finer degree of plausibility. Hence, the plausibility score may be regarded as the likelihood that a data point, combination of data points or a whole set is considered plausible or not.

The trained data driven model may be a trained machine learning algorithm. Machine learning may refer to computer algorithms that improve through experience and are built on a model based on sample data, often described as training data, utilizing supervised, unsupervised, or semi-supervised machine learning techniques. Supervised learning may include using training data having a known label or result and preparing a model through a training process in which it is required to make predictions and the model is corrected when those predictions are wrong. The training process may continue until the model achieves a desired level of accuracy on the training data. Semi-supervised learning may include using a mixture of labelled and unlabeled input data and preparing a model through a training process in which the model learns the structures to organize the data as well as to make predictions. Unsupervised learning may include using unlabeled input data not having a known result and preparing a model by deducing structures, such as general rules, similarity, etc., present in the input data. The data driven model may be trained by selecting inputs and outputs to define an internal structure of the machine learning algorithm, applying a collection of input and output data samples to train the machine learning algorithm, verifying the accuracy of the machine learning algorithm by applying material input data samples of known plausibility and comparing the produced output values with expected output values, and modifying the parameters of the machine learning algorithm using an optimizing algorithm in case the received output values are not corresponding to the known plausibility. As inputs, input material data points and/or combinations of input material data points and/or whole input material data sets being labelled with a respective plausibility score may be used. Hence, each input material data, each combination of input material data points and/or each whole input material data set may be labelled with an appropriate plausibility score indicating the degree of plausibility (e.g. plausible to unplausible) associated with the respective data point, combination of data points and/or whole data set. The input data may be selected randomly but with the proviso that the training data contains the complete spectra of plausibility scores.

In an embodiment, the input material data includes one or more input material data set(s). The input material data set(s) may include a data set identifier, the decentral input material identifier and a part of the input material data.

In an embodiment, the input material data includes at least one measured physical and/or chemical property of the input material and/or at least one physical and/or chemical property determined from collected data associated with a production and/or a use of the input material. The chemical property may be a property of the input material that becomes evident during, or after, a chemical reaction. Hence, the chemical property may be any quality that can be established only by changing the chemical identity of the input material. Examples of chemical properties include heat of combustion, enthalpy of formation, toxicity, chemical stability in a given environment, flammability, oxidation state(s), ability to corrode, combustibility, acidity and basicity, chemical product composition, recyclate content used for producing or manufacturing the input material, bio-based content used for producing or manufacturing the input material, renewable content used for producing or manufacturing the input material and/or pH value. Property may be any property that is measurable. Hence, the value of a physical property describes a state of the input material. Examples of physical properties include absorption, brittleness, boiling point, capacitance, color, concentration, density, ductility, distribution, efficacy, elasticity, electric charge, electrical conductivity, electrical impedance, electric potential, flow rate, fluidity, hardness, heat capacity, inductance, intrinsic impedance, luminance, luminescence, luster, mass, melting point, opacity, permeability, permittivity, plasticity, pressure, radiance, resistivity, reflectivity, refractive index, solubility, specific heat, strength, stiffness, temperature, tension, thermal conductivity, thermal resistance, viscosity, volume and/or wave impedance. The measured at least one physical and/or chemical property may be obtained by sensors configured to measure the physical and/or chemical property. The sensor may be included in a measuring device. The sensor may correspond to the measuring device. For example, the physical and/or chemical property may include a property provided by sensors of a mobile device such as a camera, or measurement devices configured to measure at least one physical and/or chemical property.

Data associated with the production of the input material may be collected before, during and/or after production of the input material. The collected data may be used to determine at least one physical and/or chemical property of the produced input material. For instance, emission data of the input material may be determined based on data collected during production of the input material. Data associated with the production of the input material may include production data from the production of the input material. Data associated with the production of the input material may include monitoring and/or control data associated with the production of the input material. Data associated with the use of the input material may be collected via at least one identifier associated with the input material. The data may be collected during and/or after use of the input material. Collected data may include at least one measured physical and/or chemical property of the used input material. The measured physical and/or chemical property may include the chemical and/or physical properties described previously. The data may be collected with a suitable sensor configured to measure the chemical and/or physical property. The sensor data may be interrelated with the identifier associated with the product. The chemical and/or physical property determined from the sensor data may be interrelated with the identifier associated with the input material. The identifier may be the input material identifier. The identifier may be the decentral input material identifier. The decentral input material identifier may be linked to other decentral identifier(s) according to a physical relation of the input material entity with other physical entities e.g. those produced using the input material or those produced from the input material. The linking of the decentral input material identifier with other decentral identifier(s) allows to determine the decentral participant node(s) storing the collected data associated with the use of the input material or the determined physical and/or chemical property. The collected data and/or the determined chemical and/or physical property may be provided by said decentral participant node(s) and may be stored within the input material data. For instance, a new data set may be generated by applying a data model associated with the use of the input material to the collected data and/or the determined property and said new data set may be used to update the input material data.

In an embodiment, the input material data further includes data related to the use of the input material, data related to the production of the input material, one or more input material identifiers, the input material name, the chemical composition of the input material, emission data of the input material, recyclate content data of the input material, bio-based content data of the input material, renewable content data of the input material, input material declaration data, input material safety data, certificate of analysis data associated with the input material, certificate data associated with the input material, or a combination thereof. In an embodiment, the decentral input material identifier is provided from a sensor reading an identifier element physically connected to the input material. The identifier element may be present on the packaging unit of the respective input material. The identifier element may be present on the input material. The identifier element may uniquely identify the respective input material. The identifier element may include any physical arrangement that associates the decentral input material identifier with the respective input material. The identifier element may include markers embedded in the input material, a bar code, a QR-Code, a tag like a RFID tag or similar physical arrangement that allows to digitally identify the input material. The identifier element may be a physical identifier physically connected to the input material, such as a packaging unit comprising the input material. The packaging unit may be any enclosure suitable to store the input material. Packaging units may depend on the type of input material as well as the amount of produced input material or the intended use of the input material at the production. Suitable packaging units for liquid input materials may include containers, bottles, tanks, etc. Suitable packaging units for solid input materials may include tanks, bags, bottles, containers, etc.. The size of the packaging unit may depend on the intended use at the production as well as the type of input material contained in said packaging unit.

In an embodiment, the input material data is stored in a dedicated storage associated with the each decentral data providing network node and access to the input material data stored in the dedicated storage is controlled by the data owner of the input material data via the decentral data providing network node. The dedicated storage may be associated with the data owner of the input material data. The dedicated storage may be a dedicated storage of the data owner of the input material data. The dedicated storage may be associated with the production. The dedicated storage may be associated with the decentral data providing network node. The input material data may hence be accessible for the data owner. The data owner may be the owner of the input material data or the input material data owner. The data owner may be the owner of the input material associated with said input material data. The dedicated storage may be accessible by the data owner and the decentral data providing network node. The data owner may be the entity operating the production producing the input material. The data owner may control access to the dedicated storage storing the input material data. Access to the dedicated storage may be controlled by the data owner using the decentral data providing network node associated with the dedicated storage.

In an embodiment, gathering input material data further includes determining decentral identifier(s) associated with material(s) used to produce the input material based on the provided decentral input material identifier and gathering material data from decentral data providing network node(s) associated with said material data using at least part of the determined decentral identifiers. Each decentral data providing network node may be associated with a data owner of the respective material data. The material data owner may be the producer of the material. The material data owner may be the owner of the material associated with said material data. The decentral data providing network node(s) may be associated with participants of the product ecosystem. For example, the decentral data providing network node(s) may be associated with providers of raw materials or intermediate products used to produce the input material(s) which in turn are used to produce the product. By way of identity-based access using decentral material identifier(s), material data may be provided under control of the data owner of the respective material data. In such embodiment, the material data may be provided by a storage environment associated with the decentral data providing network node as previously described. The use of decentral data providing network nodes enables the owner of the material data to control usage of material data. In addition, secure data sharing or exchanging across participants of the product ecosystem can be enabled.

Material(s) used to produce the input material may include any material(s) used during the production of the input material. This may include raw materials, chemical products, components and component assemblies.

The material data may be gathered by a decentral network node. The decentral network node may be an operating node of the decentral network. The decentral network node may be part of the infrastructure of the decentral network. The decentral network node may not be associated with a participant of the product ecosystem.

The decentral identifier(s) may be determined by the decentral network node. The decentral identifier(s) may be determined by a further decentral network node being in communication with the decentral network node gathering the material data. For instance, the further decentral network node may determine decentral identifier(s) and may provide the determined decentral identifier(s) to the decentral network node. The decentral network node may then gather material data based on the provided decentral identifier(s).

The decentral identifier(s) are determined using relationship representation(s) specifying relationship(s) between the input material and materials used to produce the input material. The relationship representation(s) may be directly or indirectly associated with the decentral input material identifier. This allows to determine the respective relationship representation(s) using the decentral input material identifier. The relationship representation(s) may specify that the materials may be used to product the input material and/or that the input material is produced using the materials. The relationship representation may be associated with a relationship between the input material and each material used to produce the input material , for example using the decentral input material identifier and material identifier(s) associated with all materials used to produce the input material. Hence, such relationship representations may also specify raw materials, intermediate products and components used in the production of the input material. The relationship representation may be associated with the relationship between input material(s) and output material(s) of a single production step within the input material production chain. The input material production chain may include one or more production steps. The input material production chain may cover all production steps necessary to produce the input material. Relationship representations associated with a single production step may be linked to each other to mirror the whole input material production chain. Linking may performed by using decentral identifier(s) associated with input material(s) used in the production step and decentral identifier(s) associated with output material(s) resulting from said production step. Since the input material of one production step is corresponding to an output material of a previous production step the relationship representation of the previous production step will be linked to the relationship representation of a subsequent production step via respective decentral material identifier(s). Linking of such relationship representations may be used to obtain a bill of material tree structure of the input material or the part thereof by recursively determining the linking contained in such relationship representations. Linking of such relationship representations may be used to recursively gather data associated with production input(s) used to produce the input material or the part thereof per production stage by recursively determining the linking contained in such relationship representations and gathering the respective data based on the decentral identifier(s) contained in said relationship representations.

The relationship representations may be accessed based on data related to the relationship representation(s). The data related to the relationship representation(s) may be stored on a decentral registry accessible by the decentral network node determining the decentral material identifier(s). The decentral network node may access said decentral registry using the decentral input material identifier to determine data related to relationship representation(s) associated with said decentral input material identifier. Data related to a relationship representation may include a decentral relationship representation identifier and a digital representation pointing to the respective relationship representation. The digital representation pointing to the relationship representation may comprise at least one interface to a decentral data consuming network node being associated with said relationship representation. It may further include at least one interface to a decentral data consuming network node being associated with said relationship representation. It may include an endpoint for data exchange or sharing (resource endpoint) or an endpoint for service interaction (service Endpoint), that is uniquely identified via a communication protocol. The digital representation(s) pointing to the relationship representation may hence be uniquely associated with the decentral relationship representation identifier and the decentral input material identifier. The digital representation pointing to the relationship representation may be regarded as locator indicating the location or dedicated data storage(s) where the respective relationship representation is stored.

This decentral network node may be configured to determine data related to the respective relationship representation based on the decentral input material identifier. For instance, the decentral network node may be configured to retrieve data related to the relationship representation based on the decentral input material identifier from a decentral registry storing said data related to the relationship representation associated with the decentral input material identifier. The decentral network node may be configured to access the relationship representation from a decentral data providing network node associated with said relationship representation. The decentral data providing network node associated with said relationship representation may be associated with the producer of the input material. The relationship representation may be stored in a storage environment associated with said decentral data providing network node. The relationship representation may be part of the input material data associated with the decentral input material identifier and stored in the storage environment associated with said decentral data providing network node. The decentral data providing network node may be associated with the data owner of the input material data. The decentral network node may be configured to determine decentral identifier(s) contained in the accessed relationship representation. In case relationship representations are linked, the decentral network node may be configured to determine at least part of the materials used to produce the input material by recursively determining data related to linked relationship representations, access respective relationship representations using the determined data and retrieve decentral identifiers associated with materials used to produce the input material based on the accessed relationship representations.

In an embodiment, the rule-based engine operates on individual data points present within at least part of the gathered input material data, multiple data points present within at least part of the gathered input material data and/or the whole gathered input material data. The rule-based engine may be configured to determine the plausibility of individual data point(s), combinations of data points and/or the whole data set. The rule-based engine may operate on the individual data point(s), combinations of data points and/or the whole data set using plausibility threshold(s) as previously described. For instance, the rule-based engine may apply plausibility threshold(s) to individual data point(s), multiple data point(s) and/or the whole data set to determine the plausibility of the individual data point(s), multiple data point(s) and/or the whole data set. If the rule-based engine determines that the individual data point(s), multiple data point(s) and/or the whole data set is plausible, said individual data point(s), multiple data point(s) and/or the whole data set may be regarded as verified.

In an embodiment, the trained data-driven model is a classifier model. The classifier model may classify the input data (e.g. at least part of the gathered input material data) into two classes, such as “plausible” and “not plausible”. The classifier model may be selected from Decision Trees, Naive Bayes Classifiers, K-Nearest Neighbors, Support Vector Machines and deep learning models. Deep learning may refer to methods based on artificial neural networks (ANNs) having an unbounded number of layers of bounded size, which permits practical application and optimized implementation, while retaining theoretical universality under mild conditions. Deep learning architectures implementing deep learning algorithms may include deep neural networks, deep belief networks (DBNs), recurrent neural networks (RNNs) and convolutional neural networks (CNNs) and feed-forward networks.

In an embodiment, providing the verified input material data for processing includes storing at least part of the verified input material data in a data storage. The data storage may be associated with the production. The data storage may be associated with the entity operating the production, such as the product producer. The data storage may be associated with an operating system controlling and/or monitoring the production. The stored input material data may be used to generate control data to control the production of product(s) using the input material. The stored input material data may be used to generate a digital twin of a product produced using the input material. Hence, the digital twin of the product may, for example, include parts of the verified input material data.

In an embodiment, processing the verified input material data includes performing one or more data processing operation(s) on the verified input material data. Prior to performing said data processing operations, the data processing operations may be verified, e.g. it may be determined whether said data processing operations are allowed to be performed on the at least part of the verified input material data. Data processing operations may include data accumulation, generation of control data or the like. The data processing operations to be performed may be verified using the rule-based engine. The rule-based engine may be configured to determine usage policies associated with the verified input material data. The rule-based engine may be configured to compare usage conditions defined the usage policies with data processing operation(s) to be performed to determine whether the intended data processing operation(s) are in line with conditions defined in the usage policies.

BRIEF DESCRIPTION OF THE SEVERAL VIEWS OF THE DRAWINGS

In the following, the present disclosure is further described with reference to the enclosed figures. The same reference numbers in the drawings and this disclosure are intended to refer to the same or like elements, components, and/or parts.

FIG. 1 illustrates an example embodiment of a decentral network environment including decentral participant network nodes associated with participants of a product ecosystem involving various products.

FIG. 2 illustrates an example data structure of a digital twin of an input material including a plurality of digital twin data sets.

FIG. 3 shows a schematic illustration of providing access via a decentral data providing network node associated with a data owner to input material data associated with an input material using a decentral data consuming network node associated with an input material consumer.

FIG. 4 illustrates an example of a digital access element including DID owner data, DID document data and decentral identity infrastructure.

FIG. 5 and FIG. 6 illustrate examples of a production producing one or more product(s) from one or more input material(s) in connection with an operating system including an input material data verification system. FIG. 7A illustrates a diagram showing an example of gathering input material data and verifying at least part of the gathered input material data using a rule-based engine.

FIG. 7B illustrates a diagram showing an example of gathering input material data and verifying at least part of the gathered input material data using a trained data-driven model.

FIG. 8 illustrates an example method for verifying input material data associated with one or more input material(s) entering a production

FIG. 9 illustrates an example method for training a data-driven model to verify at least a part of gathered input material data.

DETAILED DESCRIPTION

The following embodiments are mere examples for implementing the method, the system or application device disclosed herein and shall not be considered limiting.

FIG. 1 illustrates an example embodiment of a decentral network environment. The decentral network environment may include a decentral participant network 134. The decentral participant network 134 may include one or more decentral network participants 102 to 112. The decentral network participants may be part of a product ecosystem including a variety of products, such as chemical products, components, part assemblies, end products and end-of-life products. The product ecosystem may include production chains to produce an end-product. The product ecosystem may include recycling chains to recycle at least a part of the end-of-life products originating from the use of the produced end-products. The product ecosystem may include an input material supplier(s) 106, a chemical product producer 102, a chemical product consumer 108, an OEM 112, an end-product user 114, an EOL product collector 116 and a recycler 118. The product ecosystem may allow to use materials resulting from recycling of end-of-life product to produce new end-products. The product ecosystem may be associated with the production of chemical products using one or more input materials and the use of the produced chemical products to produce further chemical products or discrete products.

The participant(s) of the decentral participant network 134 may be associated with the production of end-products and/or the recycling of end-of-life end products. The decentral network participant 102 to 118 may refer to a manufacturer of physical products, such as chemical product producer 102, chemical product consumer 108, OEM 112, end-product user 114, EOL product collector 116 and recycler 118. The decentral network participant may be associated with a decentral participant identifier. The decentral participant identifier may uniquely identify the decentral network participant within the decentral participant network 134.

The participant(s) of the decentral participant network 134 may be connected via material flow 140.

The material flow 140 may correspond to the flow of product(s) from an upstream participant of the decentral participant network 134 to the respective downstream participant of the decentral participant network 134. The material flow 140 may refer to a continuous or a discontinuous flow of product(s). The flow of product(s) may include any means of transportation suitable to transport the product(s) from an upstream participant to the respective downstream participant. The means of transportation may include pipes, containers, barrels, packages. The material flow 140 may be associated with raw materials, chemical products, chemical intermediate products, parts, part assemblies, end-products, end-of-life products, recycled material, etc..

The data flow 136 between decentral network participant nodes may be directly or indirectly associated with the material flow 140 between the decentral network participants. For instance, data flow 136 may be directly associated with material flow 140 if input material data associated with a physical entity of an input material provided from input material supplier 106 to chemical product producer 102 is accessed by a decentral data consuming network node associated with said chemical product producer 102. For instance, data flow 136 may be indirectly associated with material flow 140 if data associated with a chemical product produced by chemical product producer 102 is accessed by a decentral data consuming network node associated with end-product user 114 or recycler 118.

At least part of the participants of the decentral participant network 134 may be associated with decentral participant network nodes 120, 122, 124, 126, 128, 130, 132. The decentral participant nodes 120 to 132 may be under control of the respective decentral participant associated with the respective decentral participant node. The decentral participant nodes 120 to 132 may form decentral network 138. The decentral network 138 may be a peer-to-peer communication network. The decentral network 138 may be configured to perform data transactions 136. The data transactions 136 may be based on a transaction protocol including authentication and/or authorization mechanism(s). Based on the authentication and/or authorization mechanism(s) a peer-to-peer communication between decentral network nodes 120 to 132 associated with decentral network participants 102 to 118 may be established. The one or more authentication mechanism(s) may be associated with or linked to a decentral identifier as described in the context of FIG. 3. The one or more authentication mechanism(s) associated with the decentral identifier may be accessible by a decentral data providing network node and/or a decentral data consuming network node as described in the context of FIG. 3. The decentral configuration allows for more efficient use of computing resources and strengthens control by the data owners of the decentral network.

Data transactions between decentral network participant nodes may be based on a decentral identifier associated with the data to be accessed and/or decentral identifier(s) associated with material(s) used to produce the respective input material or output product. The decentral identifier may be uniquely associated with the physical entity of the input material and associated input material data. The decentral identifier may be uniquely associated with the physical entity of the output product and associated product data. The input material may be any raw material, chemical product, part, part assembly or end-of-life product. The output product may be any raw material, chemical product, part, part assembly, end-product, end-of-life product or recycled material. The decentral identifier may uniquely identify the respective input material or output product within the decentral network. The decentral identifier may be associated with further decentral identifier(s), such as decentral identifier(s) of material(s) used to produce the input material or output product. This may allow to track the materials(s) used to produce the input material or output product. The decentral identifier may be included in a digital access element associated with the input material or output product, for example as described in the context of FIG. 3 and FIG. 4.

The decentral participant nodes 120 to 132 may be decentral computing nodes. The decentral computing node may be any device or system that includes at least one physical and tangible processor, and a physical and tangible memory capable of having thereon computer-executable instructions that are executed by a processor. The memory may take any form and depends on the nature and form of the computing node.

At least part of the decentral participant nodes 120 to 132 may be decentral data providing network nodes. At least part of the participant nodes 120 to 132 may be decentral data consuming network nodes. A participant of the decentral participant network 134 may be associated with a decentral data providing network node and/or a decentral data consuming network node depending on whether data is provided to downstream participants and/or consumed from upstream participants. For instance, input material supplier(s) 106 may be associated with a decentral data providing network node configured to provide input material data associated with supplied input material(s) to a downstream participant (e.g. chemical product producer 102) for example as described in the context of FIG. 3. In addition to or alternatively, input material supplier(s) 106 may be associated with a decentral data consuming network node configured to receive input material data associated with supplied input material(s) from upstream participants (not shown) via a decentral data providing network node associated with said upstream participants.

The decentral network 138 may include further decentral network nodes. The further decentral network nodes may be decentral infrastructure service nodes (not shown in FIG. 1). The decentral infrastructure service nodes may not be associated with a participant of the product ecosystem. The decentral infrastructure service nodes may provide services for decentral participant nodes 120 to 132, such as verifying the identity of the decentral network participant nodes 120 to 132 prior to performing a data exchange. The decentral network participant nodes 120 to 132 may be associated with or include certificate(s), such as X.509 certificate(s). The certificate(s) may be associated with decentral infrastructure service node(s) including e.g. a certificate issuing service and/or a dynamic provisioning service providing dynamic attribute tokens (e.g. OAuth Access Tokens). This way the decentral network participant nodes 120 to 132 possess a unique identifier embedded in a X.509 certificate that identifies the respective decentral network participant node 120 to 132. The information required to verify the certificate may be provided via an authentication registry associated with the certificate issuing service and/or a dynamic provisioning service. For instance, in the IDSA Reference Architecture Model, Version 3.0 of April 2019, a decentral data providing network node associated with a data owner, a Certification Authority (CA), a Dynamic Attribute Provisioning Service (DAPS) and a decentral data consuming network node associated with a data consumer are used to verify the identity prior to performing a data exchange (not shown).

FIG. 2 illustrates an example data structure of a digital twin of an input material including a plurality of digital twin data sets. The gathered input material data may be part of such a digital twin. The example data structure may be stored in a dedicated storage associated with a decentral data providing network node providing access to said digital twin or parts thereof.

The exemplary data structure may include a decentral input material identifier. The decentral input material identifier may comprise any unique identifier uniquely associated with the digital twin and/or digital twin data set(s), and optionally the data owner. The decentral input material identifier may connect the physical entity of the input material to the digital twin. The decentral input material identifier may include one or more Universally Unique Identifier(s) (UUID(s)) or Digital Identifier(s) (DID(s)). The one or more DID(s) and/or UUID(s) may be associated with the digital twin and/or the digital twin data set. The one or more DID(s) and/or UUID(s) may further be associated with the input material. The decentral input material identifier may be generated by the data owner or on behalf of the data owner of the input material data. The decentral input material identifier may include authentication information. Via the decentral input material identifier, the data owner may control access to the input material data or a part thereof, such as input material data sets.

The exemplary data structure may include one or more data sets, such as data set 1 206, data set 2 208 and data set 3 210. The number of data sets shown in FIG. 2 is merely illustrative and should not be understood limiting. Hence, a digital twin may include more or less data sets than shown in FIG. 2. Such data sets may be denoted digital twin assets or aspects. Such data sets may be regarded as child nodes of the digital twin root node. Each data set may include a decentral data set identifier. The decentral data set identifier may include one or more UUID(s) and/or DID(s) as previously described. The decentral data set identifier may uniquely identify the data set within the digital twin. A combination of decentral input material identifier and decentral data set identifier allows to uniquely identify a data set within the decentral network, such as the decentral network of FIG. 1 . A combination of decentral input material identifier and decentral data set identifier may be used to access input material data as described in the context of FIG. 3.

Each data set may further include input material data. The input material data may include an individual data point or multiple data points. The input material data may include one or more key value pairs. The input material data may include a tree structure comprising a root node and one or more leaf nodes (e.g. nodes not having any child nodes). The tree structure may further comprise intermediate nodes (e.g. nodes neither being a root node nor a leaf node). Each data set may include different input material data. For instance, data set 1 206 may include production data, data set 2 208 may include emission data and data set 3 210 set may include input material composition data.

The exemplary digital twin data structure may be generated by applying one or more data models having a defined semantic description to data associated with an input material to generate one or more data sets. The generated data sets may be associated with the decentral input material identifier to generate the digital twin data structure.

Use of a digital twin data structure having a defined semantic description ensures that the input material data is provided in a uniform and harmonized data format, hence allowing to efficiently verify the received input material data without requiring data transformations to harmonize the received input material data to a uniform data format prior to verification.

FIG. 3 shows a schematic illustration of providing access via a decentral data providing network node associated with a data owner to input material data associated with an input material using a decentral data consuming network node associated with a data user, such as an input material consumer. The system shown in FIG. 3 may be used to exchange data, such as input material data associated with input materials supplied to participants of the product ecosystem to produce products and/or products produced by participants of the product ecosystem, within a decentral participant network, such as described in the context of FIG. 1. What is described in the context of FIG. 3 with respect to input material data hence equally applies to products produced from such input materials.

The input material 104 may be associated with a digital twin. The digital twin of the input material may include the decentral input material identifier and input material data. The input material data may include at least one measured chemical and/or physical property of the input material and/or at least one physical and/or chemical property determined from collected data associated with the production and/or the use of the input material. The digital twin may be generated by the data owner of the input material data, such as chemical product producer 102. The digital twin may be generated on behalf of the data owner of the chemical product data. The digital twin may be generated by gathering data associated with the input material and applying one or more data models to the gathered data to generate digital twin data set(s). The generated digital twin data set(s) may then be associated with the decentral input material identifier to generate the digital twin. The digital twin may include the decentral input material identifier. Via the decentral input material identifier and its unique association with the digital twin (and hence with the input material) and optionally the data owner, access to the digital twin generated from said data or access to parts of the digital twin, such as digital twin data set(s) contained in the digital twin, may be controlled by the data owner. This contrasts with central authority schemes, where identifiers are provided by such central authority and access to data is controlled by such central authority. Decentral in this context refers to the usage of the decentral identifier(s) in implementations as controlled by the data owner of the input material data. The decentral input material identifier may include or be associated with one or more identifier(s) used in the decentral network and allowing for data exchange via the decentral network. For instance, the decentral identifier may include or be associated with digital twin data set identifier(s) of digital twin data sets, such as UUID(s) of digital twin data set(s) (see for example FIG. 2). Any combination of UUID(s) and DID(s) may be possible. For instance, the decentral input material identifier may be a DID while the digital twin data set identifier(s) may be UUID(s). In another instance, the decentral input material identifier, and the digital twin set data identifier(s) may be UUlDs. Data exchange may include discovery of the decentral input material identifier and optionally identifier(s) associated with said decentral input material identifier for participant nodes of the decentral network, authentication of participant nodes of the decentral network and/or authorization of data transfers via a peer-to-peer communication between participant nodes of the decentral network. The digital twin may be stored in a dedicated storage (DT storage 320) associated with decentral data providing network node 120. The digital twin may be stored in the dedicated storage 320 for access by consumers of the input material associated with the input material data stored in such dedicated storage 320. Consumers of the input material data may be product producer(s) using the input material to produce one or more product(s). The dedicated storage may be accessible by the data owner of the digital twin. The dedicated storage may be associated with the data owner of the digital twin. Access to the dedicated storage 320 may be controlled by the data owner of the digital twin, for example via the decentral data providing network node 120. The data owner of the digital twin may be the input material producer.

The decentral input material identifier may be linked to other decentral identifier(s) according to a physical relation of the input material entity with other physical entities e.g. those used to produce using the input material or those produced from the input material. This way decentral participant node(s) of the decentral network may be able to interpret the relation of the decentral input material identifier corresponding to the physical relation of the physical input material entity to other physical entities. The linking of the decentral input material identifier with other decentral product identifier(s) allows to determine the decentral participant node(s) storing the collected data associated with the use of the input material or the determined physical and/or chemical property. The collected data and/or the determined chemical and/or physical property may be provided by said decentral participant node(s) and may be stored within the digital twin. For instance, a new data set may be generated by applying an aspect model associated with the use of the input material and said new data set may be used to update the digital twin. The decentral input material identifier may be digital or virtual identifier(s), e.g. may not correspond to physical identifier(s) physically attached to the input material.

The decentral input material identifier may or may be assigned to a physical identifier connected to the input material 104. The connection of the physical identifier with the input material may be provided by means of physical connection to the physical input material or physical entity. For instance, the physical identifier may be connected with the physical entity of the input material. The physical identifier may have one-to-one correspondence to a virtual identity or to a physical identity by means of a physical connection to the physical entity. The physical identifier may be physically attached to the input material via an identifier element. Physical identifier or physical identifier element may refer to any virtual or physical arrangement that associates the decentral identifier with the input material. The physical identifier may be any identifier for the produced input material, such as a batch number or a part number. The physical identifier element may comprise a passive or active element, e.g. QR- code, RFID-tag, but is not limited thereto. The physical identifier element may be a physical identifier physically connected to the input material. The identifier element may include markers embedded in the input material, a bar code, a QR-Code, a tag like a RFID tag or similar physical arrangement that allows to digitally identify the input material.

A digital access element may be generated for the produced input material 104. The digital access element may include a decentral access element identifier and access data. The decentral access element identifier may be associated with the decentral input material identifier. The decentral access element identifier may correspond to the decentral input material identifier. The access data may include a digital representation pointing to the decentral data providing network node associated with the digital twin of the input material. The access data may include a representation for accessing the input material data. The decentral input material identifier may be associated with the representation for accessing the input material data. An example of such a digital access element is illustrated in FIG. 4. The digital access element may further include or relate to authentication and/or authorization information linked to the decentral access element identifier. The authentication and/or authorization information may be provided for authentication and/or authorization of the decentral network node/decentral data consuming network nodes and decentral data providing network nodes. The digital access element may be provided to a decentral registry node, for example as described in the context of FIG. 3. The decentral registry node may store decentral access element identifier(s) and associated access data.

The physical entity of the input material 104 as produced by an input material supplier 106 may be physically provided from the input material supplier 106 to the chemical product producer 102. The input material may be provided in association with the digital access element to chemical product producer 102. The chemical product producer 102 may use the supplied input material to produce product(s) (e.g. output product(s)). Output products may be chemical product(s) or discrete product(s). The input material 104 may be connected to a code, such as a bar code or QR-code, having encoded the decentral access element identifier. The chemical product producer 102 receiving input material 104 may read the code through code reader 302. The code reader 302 may be a smartphone running a code reading application, such as a QR code reader app. The data obtained by the code reading application may be used to determine the decentral access element identifier. The data obtained by the code reading application may be used to determine the decentral input material identifier. The data obtained by the code reading application may be used to determine the input material identifier. The data obtained by the code reading application may be used to determine the access data. The decentral passport identifier, decentral input material identifier, input material identifier and access data may be determined by code reader 302. For instance, the decentral passport identifier determined by the code reader 302 may be a DID and the code reader 302 may be configured to retrieve the associated DID document containing the decentral input material identifier and the access data, for example using a DID resolver (see also FIG. 4). In another instance, the input material identifier is determined by code reader 302 and used to retrieve the decentral access element identifier and associated access data, for example from a database, such as decentral registry node 308. Hence, code reader 302 may be configured to retrieve the digital access element containing the decentral access element identifier and access data from decentral registry node 308. Code reader 302 may be configured to provide the decentral access element identifier and/or the decentral input material identifier to a database 306 associated with chemical product producer 102. Code reader 302 may be configured to provide the determined decentral access element identifier, decentral input material identifier and access data to decentral data consuming network node 122.

Code reader 302 may be configured to display determined/retrieved data on a user interface as illustrated by reference sign 304. The user interface may display the determined decentral access element identifier (PP identifier), the determined decentral input material identifier (DT identifier) and the determined access data (DT location). In this embodiment, the decentral access element identifier and the decentral input material identifier differ from each other. In another embodiment, the decentral access element identifier is equal to the decentral input material identifier. The user interface may further display the determined input material identifier (not shown). The user interface may also allow to initiate retrieval of the input material data based on the decentral access element identifier and the access data as described in the following. This process may be initiated by the button denoted “Access DT”. Upon pressing said button, code reader 302 may send a request to access the digital twin or a part thereof to decentral data consuming network node 120.

Decentral data consuming network node 122 may generate a request to access the digital twin or a part thereof. Decentral data consuming network node 122 may generate the request based on the data received from code reader 302. For instance, decentral data consuming network node 122 may generate the request based on the decentral input material identifier received from code reader 302. Decentral data consuming network node 122 may generate the request based on the decentral access element identifier and/or decentral input material identifier provided to database 306. For example, decentral data consuming network node 122 may be configured to retrieve the decentral input material identifier and access data from decentral registry node 308 based on the decentral access element identifier stored in database 306 or based on the input material identifier associated with the input material. The request generated by decentral data consuming network node 122 may include the decentral input material identifier and the decentral participant identifier of the chemical product producer 102 associated with decentral data consuming network node 122. The request may include digital twin data set identifier(s) of digital twin data set(s) (e.g. input material data) to be accessed. Decentral data consuming network node 122 may be configured to determine the decentral data providing network node 120 associated with the digital twin of the input material 104 based on the access data provided by code reader 302 or retrieved from decentral registry node 308 or based on the input material identifier.

Decentral data consuming network node 122 may sent the request to access the digital twin or the part thereof to the determined decentral data providing network node 120 as signified by arrow 310. The decentral data providing network node 120 may be associated with the input material supplier 106 supplying the input material 104 to chemical product producer 102. The decentral data providing network node 120 may be associated with the production producing the input material. The decentral data providing network node 120 may be associated with the data owner of the digital twin of the input material 104. The decentral data providing network node 120 may be associated with the entity operating the production producing input material 104. In addition to the request, authentication and/or authorization information may be provided by decentral data consuming network node 122.

The request may be authenticated. Access to the digital twin or the part thereof may be authorized based on access policy data associated with the digital twin or a part thereof. The access policy data may define decentral participant identifier(s) permitted to access the input material data. The access policy data may define one or more authorization rule(s) associated with the usage of the input material data. The access policy data may define one or more action(s) permitted to be performed on the input material data by decentral data consuming network nodes. This allows to filter decentral data consuming network nodes requesting access based on the decentral participant identifier(s) associated with said network nodes and requested actions to be performed on the accessed input material data. If the request is not authorized, e.g. if decentral data consuming network node 122 is not authorized to access the input material data, the peer-to-peer communication channel will be terminated by decentral data providing network node 120 and no input material data will be provided.

If the request is authorized, decentral data providing network node 120 may initiate contract negotiations with decentral data consuming network node 122 prior to providing the input material. Decentral data providing network node 120 may provide an electronic contract to decentral data consuming network node 122. The electronic contract may include one or more authorization rule(s) associated with the decentral identifier. This allows the data consumer to determine usage conditions associated with the provided input material data. Decentral data providing network node 120 and decentral data consuming network node 122 may be configured to negotiate an electronic contract and to sign the negotiated electronic contract. Use of the electronic contract ensures that the decentral data consuming network node 122 and further systems handling the input material data are complying to at least one authorization rule associated with the input material data. Upon signature of the electronic contract, the input material data may be gathered based on the provided decentral input material identifier and optionally the data set identifier(s) and access policy data may be applied to the gathered data as signified by arrows 312 and 314. The input material data resulting from applying access policy data to the gathered input material data may be provided by decentral data providing network node 120 to decentral data consuming network node 122 as signified by arrow 316.

The input material data provided by decentral data providing network node 120 may be stored in database storage 306 associated with the decentral data consuming network node 122 according to the access policy data as signified by arrow 318.

Through the decentral input material identifier, the input material data can be uniquely associated with the input material. Through the decentral network, the input material data may be transferred between an input material producer and an input material consumer in a standardized and secure way, allowing the input material producer to control access to the input material data by multiple decentral data consuming network nodes existing within the decentral network. This way, the input material data can be shared with unique association to the input material and without central intermediary directly between the participants of the product ecosystem in a reliable yet secure manner.

FIG. 4 shows an example of a digital access element including DID owner data, DID document data and decentral identity infrastructure. The digital access element may be associated with an input material. The digital access element may be associated with an output material. The digital access element may be associated with any input material and/or output material produced and transferred within a product ecosystem, such as described in FIG. 1. Output product(s) may also include output products resulting from recycling operation(s).

The decentral identifier may include a Decentralized Identifier (DID). The decentral identifier-based digital access element may in this case be a DID document 404 associated with the DID. Besides the DID document 404 serving as digital access element, FIG. 4 shows a DID owner data element 402 including decentral identifier-based owner data. Generally, the decentral identifier-based owner data may include the decentral identifier associated with a subject such as input material data and may include one or more authentication mechanism(s). The decentral identifier-based owner data 402 may include owner data that is electronically owned and controlled by the DID owner. In this context electronically owned may refer to data that is stored in an owner repository or wallet. Such data may be securely stored and/or managed on an organizational server or client device. The decentral identifier-based owner data 402 may include a DID, a private key and a public key. The DID owner may own and control the DID that represents an identity associated with the DID subject, a private key and public key pair that are associated with the DID. DID may be understood as an identifier and authentication information associated with or uniquely linked to the identifier. The DID subject may be an input material. The DID subject may be an output product. The DID subject may be a machine, a system, or a device used for producing the input material, or a collection of such machine(s), device(s) and/or system(s). The DID subject may be a machine, a system, or a device used for producing the output product, or a collection of such machine(s), device(s) and/or system(s). The DID owner may be a supply chain participant or a manufacturer such as an input material producer or an output product producer.

The DID may be any identifier that is associated with the DID subject and/or the DID owner. Preferably, the identifier is unique to the DID subject and/or DID owner. The identifier may be unique at least within the scope in which the DID is anticipated to be in use. The identifier may be a locally or globally unique identifier for the input material or output product; the machine, the system, or the device used for producing the input material or output product, or the collection of such machine(s), device(s) and/or system(s); the input material producer or the output product producer; any participant of the product ecosystem including raw chemical product supplier, intermediate chemical products manufacturer, intermediate part manufacturer, component manufacturer, component assembly manufacturer, end-product manufacturer, end-product user, EOL collector, recycler or a collection thereof.

The DID may be any identifier that is associated with the DID subject and the DID owner. Preferably, the DID is unique to the DID subject and/or DID owner. The DID may be unique at least within the scope in which the DID is anticipated to be in use. The DID may be a locally or globally unique identifier for any of the above mentioned possible DID subjects. The DID may also be a Uniform Resource Identifier (URI) such as a Uniform Resource Locator (URL). Moreover, the DID may be an Internationalized Resource Identifier (IRI). The DID may be a Uniform Resource Identifier (URI) such as a Uniform Resource Locator (URL). The DID may be an Internationalized Resource Identifier (IRI). The DID may be a random string of numbers and letters for increased security. In one embodiment, the DID may be a string of 128 letters and numbers e.g. according to the scheme did:method name: method specific-did such as did:example:ebfeb1f712ebc6f1 c276e12ec21 . The DID may be decentralized ID independent of a centralized, third party management system and under the control of the DID owner.

The digital access element as DID document data 404 may be associated with the DID, i.e. the DID included in the decentral identifier-based owner data 402. Accordingly, the digital access element may include a reference to the DID, which is associated with the DID subject that is described by the DID document 404 . The DID document 404 may also include an authentication information such as the public key. The public key may be used by third-party entities that are given permission by the DID owner/subject to access information and data owned by the DID owner/subject. The public key may also be used for verifying that the DID owner, in fact, owns or controls the DID. The DID document may include authentication information, authorization information e.g. to authorize third party entities to read the DID document or some part of the DID document e.g. without giving the third party the right to prove ownership of the DID.

The digital access element 404 may include one or more representations that digitally link to the digital twin or parts thereof the digital access element is associated with, e.g. by way of service endpoints. A service endpoint may include a network address at which a service operates on behalf of the DID owner. In particular, the service endpoints may refer to services, such as data providing network node(s), of the DID owner that provide access to the input material data.

The digital access element 404 may include further identifiers, such as digital twin data set identifier(s) and an input material or output product identifier.

The digital access element 404 may include various other information such metadata specifying when the digital access element was created, when it was last modified and/or when it expires.

The DID and digital access element 404 may be associated with a data registry node such as a centralized data service system or a decentralized data service system 406, e.g. a distributed ledger or blockchain or a decentralized file system. The distributed ledger or blockchain may be used to store a representation of the DID that points to the digital access element 404 . A representation of the DID may be stored on distributed computing nodes of the distributed ledger or blockchain 1906. For example, DID hash may be stored on multiple computing nodes of the distributed ledger and point to the location of the digital access element 404 . In some embodiments, the digital access element 404 may be stored on the distributed ledger 406. Each of the computing nodes may store a copy of the distributed ledger 406. In this way, each DID hash can be stored redundantly, thereby allowing for an increased data safety. DIDs associated with a plurality of different digital access element 404 may be included in the distributed ledger 406.

In some embodiments, the digital access element 404 may be stored on the distributed ledger 406, i.e. either additionally or alternatively to the associated DID representation being stored on the distributed ledger 406. In other embodiments, the digital access element 404 may be stored in a data storage (not illustrated) that is associated with the distributed ledger or blockchain or decentralized file system.

The distributed ledger or blockchain 406may be any decentralized, distributed network that includes various computing nodes that are in communication with each other. For example, the distributed ledger 406 may include a first distributed computing node, a second distributed computing node, a third distributed computing node, and any number of additional distributed computing nodes (not shown). The distributed ledger or blockchain 1806 may include known technology stacks like Bitcoin (see e.g. Bitcoin documentation of November 11 , 2022 published https://en.bitcoin.it/wiki/Protocol_documentation), Ethereum (see e.g. Ethereum documentation of August 15, 2022 published on https://ethereum.org/en/developers/docs/), Solana (see e.g. Solana documentation of November 11 , 2022 published on https://spl.solana.com/), Polygon (see e.g. Polygon documentation of November 11 , 2022 published on https://wiki. polygon. technology/) or other implementations with varying degree of data transactions performed on the distributed ledger. The description of the example framework is only for illustrative purposes and shall not be considered limiting.

FIG. 5 illustrates an example of a production producing one or more product(s) from one or more input material(s) in connection with an operating system including an input material data verification system. The production may be a chemical production 502. The product(s) may be chemical product(s) 142.

For producing one or more chemical product(s) 142 different input materials (feedstocks) 104 may be provided as physical inputs from material providers or suppliers 106 (see also FIG. 1). The chemical products 142 produced from the input materials 104 may be supplied to chemical product consumer 108, for example as described in the context of FIG. 1 . The chemical production 502 may be a chemical production network. The chemical production network may include multiple interlinked processing steps. The chemical production network may be an integrated chemical production network with connected or interconnected production chains. The chemical production network may include multiple different production chains that have at least one intermediate product in common. The chemical production network may include multiple stages of the chemical value chain. The chemical production network may include the producing, refining, processing and/or purification of chemical products. The chemical production network may include multiple production chains that produce from one or more input material(s) chemical products that exit the chemical production network4. The chemical production network may include multiple tiers of a chemical value chain. The chemical production network may include physically connected or interconnected supply chains and/or production sites. The production sites may be at the same location or at different locations. In the latter case, the production sites may be connected or interconnected by means of dedicated transportation systems such as pipelines, supply chain vehicles, like trucks, ships or other cargo transportation means.

The chemical production 502 may chemically convert input materials 104 via chemical intermediates to one or more chemical product(s) 142 that exit the chemical production 502. The chemical production 502 may convert input material(s) 104 by way of chemical conversion to one or more chemical product(s).

The input material(s) 142 may be fed into the chemical production 502 at any entry point. The input material(s) 142 may be fed into the chemical production 502 at the start of the chemical production 502. Input materials may for example make up the feedstock of the plant performing the first production step of the production chain associated with the chemical product. The chemical production 502 may product the chemical product 142 via multiple production steps. The production steps may be defined by the system boundary of the chemical production 502. The system boundary may be defined by location or control over production processes. The system boundary may be defined by the site of the chemical production 502. The system boundary may be defined by production processes controlled by one entity or multiple entities jointly. The system boundary may be defined by a value chain with staggered production processes to an end product, which may be controlled by multiple entities separately. The chemical production 502 may include at least one of a waste collection and sorting step, a recycling step such as pyrolysis, a cracking step such as steam cracking, a chemical reaction step, a separation step to separate outputs of one process step and further processing steps to convert such outputs to a chemical product leaving the system boundary of the chemical production 502.

The operating system 504 of the chemical production 502 may monitor and/or control the chemical production network 504 based on operating parameters of the different processes. One process step monitored and/or controlled may be the feed of input materials or the discharge of chemical products. Another process step monitored and/or controlled may be the gathering of input material data associated with input material(s) entering the system boundary of chemical production 502. Yet another process step monitored and/or controlled may be the verification of gathered input material data. Yet another process step monitored and/or controlled may be the processing of verified input material data.

The operating system 504 may be configured to perform at least part of the steps described in the context of FIG. 8 and FIG. 9. The operating system may include a data verification system as described in the context of FIG. 6 to FIG. 7B. The data verification system may be configured to verify gathered input material data as described in the context of FIG. 6 to FIG. 8. The data verification system may be configured to process verified input material data as described in the context of FIG. 6 to FIG. 8.

FIG. 6 illustrates an example of a production producing one or more product(s) from one or more input material(s) in connection with an operating system including an input material data verification system. The production may be chemical production 502 producing one or more chemical product(s) for the input material(s). Chemical production 502 is described above with reference to FIG. 5.

Operating system 504 may be a digital operating system configured to collect, store, manage and interpret a wide range of production and/or business data for chemical production 502. Operating system 504 may be part of an Enterprise Resource Planning (ERP) system. Alternatively, operating system 504 may be partly implemented in an ERP system and partly implemented in one or more additional systems coupled with an ERP system. Operating system 504 may also be implemented in one or more systems outside of an ERP system. Input materials 104 may be provided to chemical production 502 at the feed-in-point 602. The input materials may include raw materials. The input materials may include chemical intermediate products. The input materials may include recycled materials. After they are delivered to chemical production 502, the input materials 104 may be stored into input material storage(s), such as tanks, as they enter the chemical production process.

Chemical products 142 produced by chemical production 502 may be stored in chemical product storage(s), such as tanks, prior to providing such produced chemical products 142 to the feed-out- point 604. At the feed-out-point 604, the produced chemical products 142 may be provided to one or more chemical product consumers 108 (not shown, see for example FIG. 1). The chemical product consumers 108 may use the supplied chemical products 142 to produce further chemical products or discrete products.

Input materials 104 may comprise a physical identifier element as described in the context of FIG. 3. The physical identifier element may be scanned by code reader 302 to determine the decentral input material identifier(s) (denoted as ID1 , ID2 in FIG. 6), for example as described in the context of FIG. 3. With reference to FIG. 7A and FIG. 7B, the determined decentral input material identifier(s) may be used by data verification system 606 to initiate gathering of input material data via decentral data consuming network node 122 associated with operating system 504 (see operation 706 of FIG. 7A and FIG. 7B). Decentral data consuming network node may gather the input material data from decentral data providing network nodes 120a and 120b associated with input material suppliers 106, for example as described in the context of FIG. 3. The input material data gathered by decentral data consuming network node 122 may be provided to data verification system 606. With reference to FIG. 2, the input material data gathered by decentral data consulting network node 122 may comprise one or more data set(s). Each data set may include one or more data point(s).

In one embodiment and with reference to FIG. 7A, data verification system 606 may include a rulebased engine 704. The rule-based engine 704 may operate on individual data point(s), multiple data point(s) and/or a whole data set. The rule-based engine 704 may operate on each gathered data set individually. This allows to verify each data set individually, hence allowing a more granular verification of the input material data. Rule-based engine 704 may receive a request to verify obtained input material data. Rule-based engine 704 may be configured to determine data set identifier(s) associated with the received input material data. For instance, rule-based engine 704 may parse the received input material data to determine the data present within the respective data set(s). Afterwards, rulebased engine 704 may determine respective data set identifier(s). Rule-based engine 704 may formulate a request for rule(s) to obtain one or more rule(s) from rule DB 708. The request may contain data set identifier(s) and optionally location data. The location data may be associated with the location of chemical production 502. Rule DB 708 may store one or more rule(s). One or more rule(s) associated with the data set(s) to be verified may be provided to rule-based engine 704. The one or more rule(s) may define threshold(s) for individual data point(s), allowable data point combination(s) and/or required data points optionally associated with location data. The one or more rule(s) may be associated with data set identifier(s).

Rule-based engine 704 may be configured to apply the received rule(s) to the input material data to be verified (see operation 712) to verify the input material data. Verifying the input material data may include determining the plausibility of the input material data. Input material data may be considered plausible if one or more rule(s) applied by rule-based engine 704 are fulfilled. Applying the rule(s) to the input material data may include comparing the threshold(s) to individual data point(s) present within the input material data to be verified to determine whether individual data point(s) within the input material data are above or below threshold(s) defined by such rule(s). Applying the rule(s) to the input material data may include comparing data point combination(s) defined in the rule(s) to data point combination present within the input material data to be verified to determine whether the input material data contains unallowed data point combinations. Applying the rule(s) to the input material data may include comparing the data defined in the rule(s) to the whole input material data set to be verified to determine whether the input material data set contains all required data. Operations performed by rule-based engine 704 may be determined by rule(s) gathered from rule DB 708. For instance, rule(s) gathered from rule DB 708 may determine whether rule-based engine 704 operates on individual data point(s) and/or multiple data point(s) and/or the whole data set.

Rule-based engine 704 may be configured to determine whether the input material data to be verified fulfills one or more applied rule(s) (see operation 702). Rule-based engine 704 may provide at least part of the input material data to database 610 responsive to the part of the input material data being verified. Rule-based engine 704 may provide at least part of the input material data to data processor 612 responsive to the part of the input material data being verified. Data processor 612 may be configured to process at least a part of the received verified input material data. Data processor 612 may be configured to gather verified input material data from database 610. Processing may include generating control data based on the verified input material data to control the production of chemical product(s) using input material(s) associated with the verified input material data. Processing may include performing one or more data processing operation(s) on at least part of the verified input material data. Data processing operation(s) may include use of the verified input material data to generate further data, such as accumulated data emission data, accumulated recyclate content data, accumulated biobased content data, certificate data, or the like.

If at least a part of the received input material data is not verified, rule-based engine 704 may proceed to operation 714. In operation 714, rule-based engine 704 may generate message data indicating that at least part of the input material data could not be verified. The message data may include an indication which data point(s) of which input material data could not be verified. The message data may be provided to a display device configured to display data received from rule-based engine 704. The display device may comprise a graphical user interface 716. The display device may display the message in response to receiving message data from rule-based engine 704. This allows to trigger correction of data point(s) identified as unplausible or incorrect or to obtain missing input material data from the input material data owner. Correction of data points may include generating message data indicating the unplausible or missing input material data and providing the message data to the input material data owner. The message data may be provided to the input material data owner via decentral network 138. The message data may be provided to the input material data owner via common data transfer protocols.

In another embodiment and with reference to FIG. 7B, data verification system 606 may verify at least part of the gathered input material data using at least one trained data driven model 722. The data- driven model(s) may be trained as described in the context of FIG. 9. The data-driven model(s) may be stored on a data storage (not shown) associated with data verification system 606 and may be gathered by data verification system 606 upon verifying at least part of the input material data in operation 720.

The input material data may be obtained in operation 706 as described with respect to FIG. 7A above using the decentral input material identifier(s) associated with received input material(s). At least part of the input material data obtained in operation 706 may be verified using at least one trained data driven model 722 in operation 720. For this purpose, the input material data to be verified may be provided as input to at least one trained data driven model 722. The at least one trained data driven model 722 be a classifier model classifying the input into “plausible” and “not plausible”. The classification may be used in operation 702 to determine whether the input material data to be verified is plausible or not. Data verification system 606 may provide at least part of the input material data to database 610 responsive to the part of the input material data being verified. Data verification system 606 may provide at least part of the input material data to data processor 612 responsive to the part of the input material data being verified. Data processor 612 may process at least part of the verified material data as described in the context of FIG. 7A above.

If at least a part of the received input material data is not verified, data verification system 606 may proceed to operation 714 as described in the context of FIG. 7A.

FIG. 8 illustrates an example of a method for verifying input material data associated with one or more input material(s) entering a production. The production may be chemical production 502 producing one or more chemical product(s) for the input material(s). Chemical production 502 is described above with reference to FIG. 5. At least part of the method may be performed by operating system 504 described in the context of FIG. 5 and FIG. 6. In block 802, decentral input material identifier(s) associated with input material(s) entering the system boundary 608 of the chemical production 502 may be provided. The decentral input material identifier(s) may be provided as described in the context of FIG. 3 and FIG. 6.

In block 804, input material data associated with the provided decentral input material identifier(s) may be gathered by a decentral data consuming network node 122 associated with chemical production 502 from one or more decentral data providing network node(s) 120 associated with input material supplier(s) 106. The input material data may be gathered as described in the context of FIG. 3 and FIG. 6.

In block 806, at least part of the gathered input material data may be verified using a rule-based engine or at least one trained data driven model. Block 806 may be performed by rule-based engine 704 described in the context of FIG. 6 And FIG. 7A or by at least one trained data driven model 722 described in the context of FIG. 6 and FIG. 7B.

In block 808, it may be determined if the input material data is verified, for example as described in the context of FIG. 6. If all input material data to be verified is verified, the method may proceed to block 820. If only part of the input material data to be verified is verified, the method may proceed to block 810. If no input material data to be verified is verified, the method may proceed to block 816.

In block 810, at least part of the verified input material data may be provided for processing, for example as described in the context of FIG. 6. The method may then proceed to block 812, where message data is generated with respect to non-validated input material data, for example as described in the context of FIG. 6 and FIG. 7A/FIG. 7B (see operation 714). The generated message data may be provided, for example as described in the context of FIG. 6.

In block 816, message data may be generated as previously described. Afterwards, the method may proceed to block 818 and may provide the generated message data as described in the context of FIG. 6. The message data may be provided to the data owner of the input material data. This way, updating of the digital twin of the input material (e.g. the input material data) by the data owner of the digital twin can be triggered. Updating of the digital twin in response to message data received from data consumer allows the data owner of the digital twin to remove errors in the digital twin data, hence improving the data reliability within the decentral network. The message data may be provided to the data owner via the decentral network.

In block 820, at least part of the verified input material data may be provided for processing. Providing the verified input material data for processing may include storing said input material data in a database. The provided verified input material data may be processed (see optional block 822), for example as described in the context of FIG. 6 and FIG. 7A. FIG. 9 illustrates an example method for training a data-driven model to verify at least a part of gathered input material data. The method may be used to obtain trained data driven model 722 described in the context of FIG. 6 and FIG. 7B. The data-driven model may be a classifier model as described in the context of FIG. 6 and FIG. 7B.

In block 902, the input and outputs are selected. In case an artificial neural network (ANN) is used, the inputs and outputs may refer to the number of data points in each of the input and output layers which will be separated in the ANN model by one or more layers of neurons. Any number of input and output data points may be utilized. There may be numerous data inputs, such numerous input material data points and two data outputs, such as a classifier being “plausible” or “not plausible”.

In block 902, a training data set is developed and/or collected. A generally accepted practice is to divide the model training data sets into three portions: the training set, the validation set, and the verification (or “testing”) set. In case an ANN is used, the training set is used to adjust the internal weighting algorithms and functions of the hidden layers of the neural network so that the neural network iteratively “learns” how to correctly recognize and classify patterns in the input data. The validation set, however, is primarily used to minimize overfitting. The validation set typically does not adjust the internal weighting algorithms of the neural network as does the training set, but rather verifies that any increase in accuracy over the training data set yields an increase in accuracy over a data set that has not been applied to the neural network previously, or at least the network has not been trained on it yet (i.e. validation data set). If the accuracy over the training data set increases, but the accuracy over then validation data set remains the same or decreases, the process is often referred to be “overfitting” the neural network and training should cease. Finally, the verification set is used for testing the final solution in order to confirm the actual predictive power of the neural network.

In one example, approximately 70% of the developed or collected data model sets are used for model training, 15% are used for model validation, and 15% are used for model verification. These approximate divisions can be altered as necessary to reach the desired result.

The training data may be collected by gathering various input material data sets from various input materials (e.g. historical input material data) and annotating individual data points and/or combinations of data points and/or whole data set(s) with a plausibility score. The plausibility score may be indicative of the plausibility of respective individual data point, combination of data points or whole data set. For instance, a plausibility score of 1 indicates that the data point, combination of data points or whole data set is unplausible while a plausibility score of 5 indicates that the data point, combination of data points or whole data set is plausible. Scores between 1 and 5 may be used to indicate a finer degree of plausibility. Hence, the plausibility score may be regarded as the likelihood that a data point, combination of data points or a whole set is considered plausible or not. The training data set may include samples throughout a full range of plausibility scores. In block 906 a classifier model is selected. The classifier model may be selected from Decision Trees, Naive Bayes Classifiers, K-Nearest Neighbors, Support Vector Machines and deep learning models. Guidelines known to those skilled in the art and/or associated with specific algorithm software can aid in the initial selection of the model type and dimensions.

In block 908, the model selected in block 906 is pointed to the training and validation portions of the training data set. Training is an iterative process that - in case of ANNs - sets the internal weights, or weighting algorithms, between the ANN model neurons, with each neuron of each layer being connected to each neuron of each adjacent layer, and further with each connection represented by a weighting algorithm. With each iteration of training data to adjust the weights, the validation data is run on the ANN model and one or more measures of accuracy is determined by comparison of the model output for fill level with the actual measurement of fill level collected with the training data. For example, generally the standard deviation and mean error of the output will improve for the validation data with each iteration and then the standard deviation and mean error will start to increase with subsequent iterations. The iteration for which the standard deviation and mean error is minimized is the most accurate set of weights for that ANN model for that training set of data.

In block 910, the algorithm is pointed to the verification data set and a determination of whether the output of the algorithm is sufficiently accurate when compared to the actual plausibility of the respective input material data. If the accuracy is not sufficient, the method may return to block 906 or to block 904 to improve the algorithm accuracy. The method proceeds to block 806 if the model has been trained to sufficient accuracy.

The trained data driven model may be improved over time with additional data, such as operational data.

The present disclosure has been described in conjunction with preferred embodiments and examples as well. However, other variations can be understood and effected by those persons skilled in the art and practicing the claimed invention, from the studies of the drawings, this disclosure and the claims. Notably, in particular, the any steps presented can be performed in any order, i.e. the present invention is not limited to a specific order of these steps. Moreover, it is also not required that the different steps are performed at a certain place or at one node of a distributed system, i.e. each of the steps may be performed at different nodes using different equipment/data processing.

As used herein ..determining" also includes ..initiating or causing to determine", “generating" also includes ..initiating and/or causing to generate" and “providing” also includes “initiating or causing to determine, generate, select, send and/or receive”. “Initiating or causing to perform an action” includes any processing signal that triggers a computing node or device to perform the respective action. In the claims as well as in the description the word “comprising” does not exclude other elements or steps and the indefinite article “a” or “an” does not exclude a plurality. A single element or other unit may fulfill the functions of several entities or items recited in the claims. The mere fact that certain measures are recited in the mutual different dependent claims does not indicate that a combination of these measures cannot be used in an advantageous implementation. In the claims as well as in the description the word “comprising” or “including” or similar wording does not exclude other elements or steps and shall not be construed limiting to the elements or steps lined out. The indefinite article “a” or “an” does not exclude a plurality. A single element or other unit may fulfill the functions of several entities or items recited in the claims. The mere fact that certain measures are recited in the mutual different dependent claims does not indicate that a combination of these measures cannot be used in an advantageous implementation or further elements may be included.

Providing in the scope of this disclosure may include any interface configured to provide data. This may include an application programming interface, a human-machine interface such as a display and/or a software module interface. Providing may include communication of data or submission of data to the interface, in particular display to a user or use of the data by the receiving entity.

All terms and definitions used herein are understood broadly and have their general meaning.

Claims

1. A computer-implemented method for verifying input material data associated with one or more input material(s) entering a production, wherein the production produces one or more product(s) from the one or more input material(s), the method comprising:

(d) based on the verified input material data, providing the verified input material data for processing the verified input material data.

2. The computer-implemented method of claim 1 , wherein the input material data includes one or more input material data set(s).

3. The computer-implemented method of claim 1 or 2, wherein the input material data includes at least one measured physical and/or chemical property of the input material and/or at least one physical and/or chemical property determined from collected data associated with a production and/or a use of the input material.

4. The computer-implemented method of any one of claims 1 to 3, wherein the production is a chemical production and/or wherein the product is a chemical product.

5. The computer-implemented method of any one of claims 1 to 4, wherein the decentral input material identifier is provided from a sensor reading an identifier element physically connected to the input material.

6. The computer-implemented method of any one of claims 1 to 5, wherein the input material data is stored in a dedicated storage associated with the each decentral data providing network node and access to the input material data stored in the dedicated storage is controlled by the data owner of the input material data via the decentral data providing network node.

7. The computer-implemented method of any one of claims 1 to 6, wherein gathering input material data further includes determining decentral identifier(s) associated with material(s) used to produce the input material based on the provided decentral input material identifier and gathering material data from decentral data providing network node(s) associated with said material data using at least part of the determined decentral identifiers.

8. The computer-implemented method of claim 7, wherein the decentral identifier(s) are determined using relationship representation(s) specifying relationship(s) between the input material and materials used to produce the input material.

9. The computer-implemented method of any one of claims 1 to 8, wherein the rule-based engine operates on individual data points present within at least part of the gathered input material data, multiple data points present within at least part of the gathered input material data or the whole gathered input material data.

10. The computer-implemented method of any one of claims 1 to 8, wherein the trained data-driven model is a classifier model.

11 . The computer-implemented method of any one of claims 1 to 10, wherein providing the verified input material data for processing includes storing at least part of the verified input material data on a data storage.

12. The computer-implemented method of any one of claims 1 to 11 , wherein processing the verified input material data includes performing one or more data processing operation(s) on at least part of the verified input material data.

13. An apparatus for verifying input material data associated with one or more input material(s) entering a production, wherein the production produces one or more product(s) from the one or more input material(s), the apparatus comprising:

(b) a decentral data consuming network node associated with the production configured to gather input material data associated with the provided decentral input material identifier(s) from decentral data providing network node(s) associated with the input material data,

(c) a rule-based engine including plausibility threshold(s) or a data-driven model trained on historical data sets including input material data and plausibility scores, wherein the rulebased engine or the data-driven model is configured to verify at least part of the gathered input material data and configured to provide - based on the verified input material data - the verified input material data,

14. Use of input material data as verified by the computer-implemented method of any one of claims 1 to 12 or by the apparatus of claim 13 to control the production of product(s) at least in part produced from input material(s) associated with the verified input material data.

15. A computer element with instructions, which when executed on one or more computing node(s) are configured to carry out the steps of the method as claimed in any one of claims 1 to 12 or are configured to be carried out by the apparatus as claimed in claim 13.