CN114637257A - Foam production parameter adjustment, hardness conversion relation determination, foam production device and medium - Google Patents

Foam production parameter adjustment, hardness conversion relation determination, foam production device and medium Download PDF

Info

Publication number
CN114637257A
CN114637257A CN202011477997.1A CN202011477997A CN114637257A CN 114637257 A CN114637257 A CN 114637257A CN 202011477997 A CN202011477997 A CN 202011477997A CN 114637257 A CN114637257 A CN 114637257A
Authority
CN
China
Prior art keywords
foam
information
hardness
hardness information
predicted
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202011477997.1A
Other languages
Chinese (zh)
Inventor
张俊
杨追燕
高建伍
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Covestro Deutschland AG
Original Assignee
Covestro Deutschland AG
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Covestro Deutschland AG filed Critical Covestro Deutschland AG
Priority to CN202011477997.1A priority Critical patent/CN114637257A/en
Publication of CN114637257A publication Critical patent/CN114637257A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B19/00—Programme-control systems
    • G05B19/02—Programme-control systems electric
    • G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
    • G05B19/41865—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM] characterised by job scheduling, process planning, material flow
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B2219/00—Program-control systems
    • G05B2219/30—Nc systems
    • G05B2219/32—Operator till task planning
    • G05B2219/32252—Scheduling production, machining, job shop
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2111/00—Details relating to CAD techniques
    • G06F2111/10—Numerical modelling
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2113/00—Details relating to the application field
    • G06F2113/26—Composites
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
    • G06F2119/08—Thermal analysis or thermal optimisation
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Software Systems (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Artificial Intelligence (AREA)
  • Mathematical Physics (AREA)
  • Data Mining & Analysis (AREA)
  • Computing Systems (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biophysics (AREA)
  • Molecular Biology (AREA)
  • General Health & Medical Sciences (AREA)
  • Computational Linguistics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Biomedical Technology (AREA)
  • Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Automation & Control Theory (AREA)
  • Quality & Reliability (AREA)
  • Manufacturing & Machinery (AREA)
  • Geometry (AREA)
  • Computer Hardware Design (AREA)
  • Casting Or Compression Moulding Of Plastics Or The Like (AREA)

Abstract

The application relates to a foam production parameter adjusting method, a hardness conversion relation determination method, a foam production device and a medium. The production parameter adjusting method comprises the following steps: measuring section hardness information of foam on a conveyor belt of a foam production line; determining predicted hardness information of the cured foam according to the section hardness information based on a conversion relation, wherein the conversion relation is formed according to the section hardness information of the foam and historical data of the cured hardness information; and adjusting the production parameters of the foam according to the predicted hardness information. The method can predict the hardness of the cured foam on the production line in real time or quasi-real time and adjust the hardness adaptively.

Description

Foam production parameter adjustment, hardness conversion relation determination, foam production device and medium
Technical Field
The application relates to the field of foam processing, in particular to a foam production parameter adjusting method and system, a method for determining a hardness information conversion relation of foam, a neural network for determining foam hardness information, a foam production device and a computer readable storage medium.
Background
Common methods for producing flexible Polyurethane (PUR) foam include a large block foam process by which long, continuous flexible polyurethane block foam can be produced continuously or discontinuously. In a continuous process, the required raw materials, optionally including polyol, isocyanate, water and/or auxiliary blowing agents, catalysts, stabilizers and other additives, are delivered to the mixing head by precision pumps (e.g., piston pumps, gear pumps). The raw materials are then mixed by a mechanical stirrer and cast onto a substrate, which is transported by a conveyor through an exhaust channel. At the same time, the reaction mixture expands to the desired size and the foam block produced will then be cut into the desired shape.
Since the lateral pressure is generated immediately after the foam expands, the lateral surface is also often designed as a mobile conveyor. The process can produce foam blocks continuously by partially inhibiting the initial rise process.
Disclosure of Invention
The embodiment of the application provides a method and a system for adjusting foam production parameters, a method for determining a hardness information conversion relation of foam, a neural network for determining foam hardness information, a foam production device and a computer-readable storage medium, which are used for predicting the hardness of the cured foam on a production line in real time and further adjusting the hardness of the cured foam on the production line.
According to one aspect of the application, a foam production parameter adjusting method is provided, and comprises the following steps: measuring section hardness information of foam on a conveyor belt of a foam production line; determining predicted hardness information of the cured foam according to the section hardness information based on a conversion relation, wherein the conversion relation is formed according to the section hardness information of the foam and historical data of the cured hardness information; and adjusting the production parameters of the foam according to the predicted hardness information.
In some embodiments of the present application, optionally, the section stiffness information, the predicted stiffness information, and the ripeness stiffness information include: indentation hardness, compression hardness.
In some embodiments of the present application, optionally, the production parameters include: formulation parameters and process parameters.
In some embodiments of the present application, optionally, the recipe parameters include raw material ratios, and the process parameters include: charging temperature, fall plate angle, conveyor belt speed.
In some embodiments of the present application, optionally, the transformation relationship is formed according to a machine learning algorithm or a neural network algorithm.
According to another aspect of the present application, there is provided a method of determining a stiffness information conversion relation of foam, the method including: measuring section hardness information of at least one foam sample on a conveyor belt of a foam production line; measuring curing hardness information of the cured foam sample; and forming a conversion relation according to the section hardness information and the curing hardness information, wherein the conversion relation is used for determining cured predicted hardness information according to section hardness information of foam on a conveyor belt of a foam production line.
In some embodiments of the present application, optionally, the section hardness information is formed according to at least one position of at least one section of the foam sample, and the aging hardness information is formed according to at least one position of the foam sample after aging.
In some embodiments of the present application, optionally, measuring the section hardness information is close to or the same as measuring at least part of the ripeness information.
In some embodiments of the present application, optionally, the section stiffness information, the predicted stiffness information, and the ripeness stiffness information include: indentation hardness, compression hardness.
In some embodiments of the present application, optionally, the method comprises: and forming the conversion relation by using the machine learning algorithm or the neural network algorithm and the section hardness information of the foam sample as input and the curing hardness information of the foam sample as output.
According to another aspect of the application, a neural network for determining foam hardness information is provided, the neural network takes section hardness information of at least one foam sample on a conveyor belt of a foam production line as input, and takes cured hardness information of the cured foam sample as target output for training.
According to another aspect of the present application, there is provided a foam production parameter adjustment system, the system comprising: one or more sensors configured to measure cross-sectional stiffness information of the foam on the foam production line conveyor; a calculation unit configured to determine predicted hardness information after curing of the foam from the section hardness information based on a conversion relationship formed from history data of section hardness information and curing hardness information of the foam; and a transmitting unit configured to transmit the predicted hardness information.
In some embodiments of the application, optionally, the tangent stiffness information, the predicted stiffness information, and the cured stiffness information include: indentation hardness, compression hardness.
In some embodiments of the present application, optionally, the transformation relationship is formed according to a machine learning algorithm or a neural network algorithm.
In some embodiments of the present application, optionally, the computing unit comprises any one of the neural networks as described above.
In some embodiments of the present application, optionally, the system comprises 3 sensors.
In some embodiments of the present application, optionally, each sensor is ≧ 10 centimeters from each side of the rectangle of the foam.
In some embodiments of the present application, optionally, each sensor is ≧ 20 centimeters from each side of the rectangle of the foam.
In some embodiments of the present application, optionally, the sensor is configured to measure perpendicular to a tangent plane of the foam.
According to another aspect of the present application, there is provided a foam production apparatus comprising any one of the foam production parameter adjustment systems described above.
In some embodiments of the present application, optionally, the apparatus comprises a receiving unit configured to receive the predicted firmness information; and an adjusting unit configured to adjust a parameter of the device according to the predicted hardness information.
In some embodiments of the present application, optionally, the parameters include: formulation parameters and process parameters.
In some embodiments of the present application, optionally, the recipe parameters include raw material ratios, and the process parameters include: charging temperature, fall plate angle, conveyor belt speed.
According to another aspect of the present application, there is provided a computer-readable storage medium having stored therein instructions which, when executed by a processor, cause the processor to perform any of the methods described above.
Drawings
The above and other objects and advantages of the present application will become more apparent from the following detailed description when taken in conjunction with the accompanying drawings, in which like or similar elements are designated by like reference numerals.
Fig. 1 illustrates a foam production parameter adjustment method according to one embodiment of the present application.
Fig. 2 illustrates a method of determining stiffness information transformation relationship of foam according to an embodiment of the present application.
Figure 3 illustrates a foam production parameter adjustment system according to one embodiment of the present application.
Figure 4 shows a foam production apparatus according to one embodiment of the present application.
Figure 5 shows a foam production apparatus according to one embodiment of the present application.
FIG. 6 shows a sensor according to an embodiment of the present application.
Figure 7 shows a foam production apparatus according to one embodiment of the present application.
Detailed Description
For the purposes of brevity and explanation, the principles of the present application are described herein with reference primarily to exemplary embodiments thereof. However, those skilled in the art will readily recognize that the same principles are equally applicable to all types of foam production parameter adjustment methods and systems, methods of determining stiffness information transformation relationships for foam, neural networks for determining foam stiffness information, foam production devices, and computer readable storage media, and that these same or similar principles may be implemented therein, with any such variations not departing from the true spirit and scope of the present application.
Hardness is one of the most important quality indexes of the soft foam, so that the hardness is required to be within a specified range to meet the quality specification requirement. Otherwise, the foam would be down-rated and even considered a waste product in extreme cases. The limitation of the hardness measurement of polyurethane block foam production devices according to the prior art is that currently the measurement can only be carried out after curing (also referred to as curing in the present application) in the laboratory for about 24 hours. Therefore, there is no way to measure the hardness of foam during the manufacturing process well to prevent the production of foam with an unacceptable hardness. Some embodiments of the present invention provide a mechanism for obtaining hardness information of foam on a production line and further guiding the setting of foaming parameters, by which real-time quality control can be achieved.
Although the examples of the present application are developed with polyurethane block foam, the basic principles of the present invention are also applicable to other foams similar to the way existing polyurethane foam is produced. Some examples of the application do not require that the cut surface be rectangular, while other examples require a rectangular cut surface.
The various "information" in this application may be specific values or may be a hierarchy formed according to the values (for example, similar values are classified into the same hierarchy), so that the complexity of the processing can be reduced.
According to an aspect of the present application, a foam (e.g., polyurethane block foam) production parameter adjustment method is provided. As shown in fig. 1, the method for adjusting the production parameters includes the following steps: the section hardness information of the foam on the conveyor belt of the foam production line is measured in step S11. In step S12, predicted hardness information after curing of the foam is determined from the cut surface hardness information based on the conversion relationship. Wherein, the conversion relation is formed according to the historical data of section hardness information and curing hardness information of the foam. In step S13, the production parameters of the foam are adjusted according to the predicted hardness information.
The production parameter adjusting method measures section hardness information of foam on a conveyor belt of a foam production line in step S11. In step S11, the hardness of the section of the newly cut foam is measured, for example, and various hardness indexes of the foam may be measured by a sensor to form section hardness information.
In some examples of the present application, the cut stiffness information may be calculated from at least one location of at least one cut of the foam. The severed foam sample will include two sections, with some examples of this application preferably measuring the section along the back side of the belt in the direction of belt travel. The hardness information of the cut surface can be formed by measuring the hardness information at a plurality of positions of the cut surface before and after curing. For example, for the convenience of measurement, the hardness of the foam remaining on the conveyor belt after cutting is measured here, not the hardness of the foam dropped after cutting. Secondly, in the present application, a "new" cut-off generally means that a measurement is taken immediately after the cut-off, so that it is ensured that the normal transport of the conveyor belt is not affected. In other examples, the hardness of the foam after a short period of time (e.g., 0.5 seconds, 2 seconds) after cutting may also be measured subject to hardware constraints and/or a set time to stabilize the foam structure. In some examples, the stiffness information of the foam may be measured using a mechanical measurement device such as a pressure sensor. Although the specific manner of measurement (e.g., the number of sensors, the placement position, etc.) is not limited herein, the measurement of the cut-plane hardness information of the cut foam on the production line should be performed under the same conditions as the measurement of the cut-plane hardness information of the foam in the history data described below. Typical examples of pressure sensors include the LCMcKD series subminiature industrial load cells such as those available from OMEGA.
The production parameter adjustment method of the present application determines predicted hardness information after curing of foam according to the cut hardness information based on a conversion relationship in step S12, wherein the conversion relationship is formed according to the cut hardness information of the foam and the history data of the cured hardness information. Direct measurement of the section hardness information is described above, but the foam hardness after curing does not coincide with the measured section hardness. In experiments, the section hardness information and the predicted hardness information after curing have a corresponding relation, so the predicted hardness information after curing can be calculated according to the section hardness information of the information foam. The conversion relationship between the section hardness information and the predicted hardness information may be formed from historical data, such historical data including data obtained experimentally specifically to investigate the conversion relationship, the concept of "history" being relative to the current time at which the predicted hardness information after curing of the foam is determined. It should be noted that, in some examples, the conversion relationship may be a mathematical expression, such as a conversion table, a mapping function, or the like. In other examples, the translation relationship may be a mathematical abstraction that cannot or cannot be easily expressed in a specific mathematical form. The conversion relation of the invention refers to various feasible forms which take 'section hardness information' as an input parameter and 'predicted hardness information' as an output result.
The production parameter adjustment method of the present application adjusts the production parameters of the foam based on the predicted hardness information in step S13. It is stated above that the predicted hardness information can be determined in step S12, and the parameters of the foam production apparatus can be adjusted according to the difference between the predicted hardness information and the desired hardness information so that the predicted hardness information is close to or even equal to the desired hardness information. For example, if the predicted hardness information does not reach the hardness required for processing, the parameters of the foam production device can be adjusted to increase the hardness of the foam on the production line.
Various interference factors exist in the actual production process, and even if the foam produced at a certain moment meets the desired hardness information, the interference factors can cause the foam produced subsequently to be unsatisfactory due to error accumulation. Steps S11 to S13 may be repeated continuously during actual production, so that the hardness of the produced foam may be dynamically checked and the parameters of the foam production apparatus may be dynamically adjusted to eliminate accumulated errors.
In some embodiments of the present application, the hardness information described above refers to various indicators capable of evaluating hardness, for example, the hardness information (including section hardness information, predicted hardness information, and aging hardness information) may be Indentation hardness (e.g., IFD/ILD), compressive hardness (e.g., CFD, compressive Force Deflection), and the like. In some examples, it is preferable to measure, predict, and form the transformation relationship with the same hardness information. For example, if the sectional indentation hardness of the foam after cutting is measured, the predicted indentation hardness of the foam after aging is predicted, and the conversion relationship according to which the prediction is based is formed from the sectional indentation hardness and the aged indentation hardness in the history data. In other examples, the possibility of measuring, predicting with different hardness information is not excluded. For example, if the cut-surface compressive hardness of the foam after cutting is measured and the estimated indentation hardness of the foam after aging is predicted, the conversion relationship based on the prediction is formed from the cut-surface compressive hardness and the aged indentation hardness in the history data. That is, the scope of the claims of the present application extends to situations where measurements and predictions are made with different metrics.
In some embodiments of the present application, the production parameters of the foam that can be adjusted include formulation parameters and process parameters. Wherein, the formula parameters comprise raw material proportioning, and the process parameters comprise one or more of feeding temperature, falling plate angle and conveyor belt speed. The hardness of the produced foam can be respectively adjusted by controlling the raw material proportion, the feeding temperature, the falling plate angle and the conveyor belt speed of the production line, and various parameters can be adjusted simultaneously under some conditions, so that the produced foam can reach the desired hardness under the limitation of physical conditions. In the foaming process, the side face of the foam body can generate relative displacement with the side plate when the foam rises, so that larger friction and disturbance are caused, and the foam body is unstable and is easy to have defects. The displacement amplitude of the foam body and the side plate can be controlled and reduced at any time by adjusting the angle of the falling plate, so that the generation of foaming defects and the shape of the foam body are reduced.
In some embodiments of the present application, the transformation relationship is formed according to a machine learning algorithm (e.g., linear regression) or a neural network algorithm. The translation relationships may be attached to the neural network, for example, and although the translation relationships depend on the structure of the neural network, one skilled in the art may practice the invention without regard to the structure of the neural network, or how the neural network is trained and what form the neural network is after training.
While the foregoing describes determining predicted stiffness information for a foam after curing based on a conversion relationship, according to another aspect of the present application, a method is provided for determining a stiffness information conversion relationship for a foam (e.g., a polyurethane block foam). As shown in fig. 2, the method for determining the hardness information conversion relationship of the foam comprises the following steps: the section hardness information of at least one foam sample on the foam production line conveyor is measured in step S21. The ripened hardness information of the foam sample after the ripened is measured in step S22. In step S23, a conversion relationship is formed according to the section hardness information and the curing hardness information, and the conversion relationship is used for determining the cured predicted hardness information according to the section hardness information of the foam on the conveyor belt of the foam production line.
The method for determining the hardness information conversion relation of the foam measures the section hardness information of at least one foam sample on the conveying belt of the foam production line in step S21. The above describes that the conversion relationship can be formed from historical data of section stiffness information and maturation stiffness information of foam. In some examples, the conversion relationship may be determined experimentally, the subject of the experiment being referred to as a foam sample. It should be noted that the foam sample may also be a finished foam of an actual production process, which is not manufactured for the purpose of studying the conversion relationship, but may be used for studying the conversion relationship, and may be regarded as a foam sample in the study process.
At least one foam sample may not be continuously produced, for example, the foam samples may be produced on different production days, so that interference caused by accidental errors of a foam production device to research conversion relation can be avoided. The method for measuring section hardness information of the foam sample can refer to the method for measuring section hardness information of the foam sample, and is not described herein again.
The method for determining the conversion relation of the hardness information of the foam measures the aging hardness information of the aged foam sample in step S22. After the section hardness information of at least one of the samples is measured according to step S21, the samples may be moved to, for example, a laboratory for curing for about 12 hours before the cured hardness information of the foam samples after curing is measured. The hardness of the foam can be considered to be consistent with that of the foam which leaves the factory after the foam is cured for 12 hours in a laboratory.
In some examples of the application, the section stiffness information may be calculated from at least one position of at least one section of the foam sample. On the other hand, the curing hardness information may be calculated from at least one position of the cured foam sample. The severed foam sample will include two sections, with some examples of this application preferably measuring the section along the back side in the direction of belt travel. The hardness information can be measured at several positions of the section before and after curing, so as to respectively form section hardness information and curing hardness information.
In some examples of the present application, the measured section stiffness information is located close to or the same as at least a portion of the measured ripeness information, where "close" may be defined as no more than a set threshold (e.g., 2 centimeters) apart.
The method for determining the conversion relation of the hardness information of the foam forms the conversion relation according to the section hardness information and the curing hardness information in step S23, and the conversion relation is used for determining the predicted cured hardness information according to the section hardness information of the foam on the conveyor belt of the foam production line. The relationship between the section hardness information and the curing hardness information of the foam sample can form a conversion relation. In some examples, the conversion relationship may be in the form of a mathematical expression that may be embodied, for example, as a conversion table, a mapping function, or the like. In other examples, the translation relationship may be a mathematical abstraction that cannot or cannot be easily expressed in a specific mathematical form. The conversion relation of the invention refers to various feasible forms which take 'section hardness information' as an input parameter and 'predicted hardness information' as an output result.
Because the foam and the foam sample which are actually put into production have consistency in the change from the section hardness information to the curing hardness information, the predicted hardness information of the cured foam after being cut on the conveyor belt of the foam production line can be estimated by utilizing the conversion relation formed by the foam samples. The above process can be mathematically represented as:
f: Hfresh.Sample → HCured.Sample
HCured.Product = f(Hfresh.Product)
wherein f represents a conversion relationship, HfreshSample represents section hardness information of a foam Sample, HCuredSample represents the curing hardness information of the foam Sample; hfreshProduct represents section hardness information of produced foam, HCuredProduct represents the predicted hardness information of the produced foam after aging. The predicted hardness information H of the produced foam after curing can be determined through the mathematical relationshipCured.Product。
In some embodiments of the present application, the section hardness information, the predicted hardness information, and the curing hardness information may be indentation hardness, compression hardness, and the like. In some examples, it is preferable to form the conversion relationship with the same hardness information. For example, if the conversion relationship on which the prediction is based is formed from the cross-sectional indentation hardness and the aged indentation hardness of the foam sample, then the cross-sectional indentation hardness of the cut foam can be measured and the predicted indentation hardness of the foam after aging can be predicted. In other examples, forming the conversion relationship with different stiffness information is not excluded. For example, if the conversion relationship according to which the prediction is based is formed based on the section compressive hardness and the aged indentation hardness of the foam sample, the section compressive hardness of the cut foam can be measured and the predicted indentation hardness of the aged foam can be predicted.
In some embodiments of the present application, a method of determining a stiffness information transformation relationship of foam includes: and (3) forming a conversion relation by using a machine learning algorithm (such as linear regression) or a neural network algorithm and taking section hardness information of the foam sample as input and curing hardness information of the foam sample as output. Under the condition that the section hardness information of the foam sample is used as input and the curing hardness information of the foam sample is used as output to train the neural network, the conversion relation is attached to the neural network. Although the transformation relationships depend on the structure of the neural network, those skilled in the art may practice the present invention without paying attention to the structure of the neural network, how to train the neural network, and what form the neural network is after training.
According to another aspect of the present application, a neural network for determining hardness information of foam (e.g., polyurethane block foam) is provided, wherein the neural network is trained with section hardness information of at least one foam sample on a conveyor belt of a foam production line as an input and aging hardness information after aging of the foam sample as a target output. At this point, the translation relationships may be attached to the neural network. The specific configuration of the neural network is not limited herein as long as the predicted stiffness information can be determined after training.
According to another aspect of the present application, a foam (e.g., polyurethane block foam) production parameter adjustment system is provided. As shown in fig. 3, the production parameter adjustment system 30 includes one or more sensors 301, a calculation unit 302, and a transmission unit 303. Wherein one or more sensors 301 are configured to measure section hardness information of the foam on the conveyor belt of the foam production line, for example, various hardness indexes of the foam can be measured by the sensors 301 to form section hardness information.
In some examples of the present application, the cut stiffness information may be calculated from at least one location of at least one cut of the foam. The severed foam sample will include two sections, with some examples of this application preferably measuring the section along the back side in the direction of belt travel. The hardness information of the cut surface can be formed by measuring the hardness information at a plurality of positions of the cut surface before and after curing. For example, to facilitate sensor 301 placement, the hardness of the foam remaining on the conveyor belt after severing is measured here, rather than the hardness of the foam falling after severing. Secondly, in the present application, a "new" cut-off generally means that a measurement is taken immediately after the cut-off, so that it is ensured that the normal transport of the conveyor belt is not affected. In other examples, the hardness of the foam may be measured after a certain period of time (e.g., 0.5 seconds, 2 seconds) after cutting, subject to hardware constraints and/or a certain curing time to make the foam structure more stable. In some examples, the sensor 301 may be embodied as a mechanical measurement device such as a pressure sensor. Although the specific manner of measurement (e.g., the number, arrangement position, etc. of the sensors 301) is not limited herein, the section hardness information of the cut foam on the measurement line should be measured under the same condition as the section hardness information of the foam in the measurement history data (e.g., keeping the arrangement of the sensors 301 unchanged).
Referring to fig. 5, a cutting device 502 is arranged on the existing production line, foam 503 is cut after passing through the cutting device 502, and a sensor 501 can measure the section hardness information of the newly cut foam on the conveyor belt of the foam production line.
The calculation unit 302 is configured to determine predicted firmness information after curing of the foam from the section firmness information based on a conversion relationship formed from historical data of section firmness information and curing firmness information of the foam. The above describes that the section hardness information is directly measured by the sensor 301, but the cured (cured) foam hardness is not consistent with the measured section hardness, but the predicted hardness information after curing can be estimated from the section hardness information of the information foam. The conversion relationship between the section hardness information and the predicted hardness information may be formed from historical data, such historical data including data obtained experimentally specifically to investigate the conversion relationship, the concept of "history" being relative to the current time at which the predicted hardness information after curing of the foam is determined. It should be noted that, in some examples, the conversion relationship may be a mathematical expression, such as a conversion table, a mapping function, or the like. At this time, the calculation unit 302 may determine the predicted hardness information after the foam is ripened, based on, for example, a conversion table, a mapping function, or the like. In other examples, the translation relationship may be a mathematical abstraction that cannot or cannot be easily expressed in a specific mathematical form. At this time, the calculation unit 302 may determine the predicted hardness information after curing of the foam based on such mathematical abstractions without considering the expression form of the mathematical abstraction. The conversion relation of the invention refers to various feasible forms which take 'tangent plane hardness information' as an input parameter and 'predicted hardness information' as an output result.
The transmitting unit 303 is configured to transmit the predicted hardness information. It is stated above that the calculation unit 302 can determine the predicted stiffness information and, based on the difference between the predicted stiffness information and the desired stiffness information, can adjust the parameters of the foam production device such that the predicted stiffness information is close to or even equal to the desired stiffness information. For example, if the predicted hardness information does not reach the hardness required for processing, the parameters of the foam production device can be adjusted to increase the hardness of the foam on the production line. The transmitting unit 303 of the present application may transmit the predicted hardness information to the foam production apparatus so that the foam production apparatus adjusts parameters therein according to the predicted hardness information.
Various interference factors exist in the actual production process, and even if the foam produced at a certain moment meets the desired hardness information, the interference factors can cause the foam produced subsequently to be unsatisfactory due to error accumulation. The plurality of sensors 301, the calculation unit 302, and the transmission unit 303 may be continuously operated in actual production, so that the hardness of the produced foam may be dynamically checked and the predicted hardness information may be transmitted in real/near real time.
In some embodiments of the present application, the hardness information described above refers to various indexes capable of evaluating hardness, for example, the hardness information (including cut face hardness information, predicted hardness information, and aged hardness information) may be indentation hardness, compression hardness. In some examples, it is preferable to measure, predict, and form the conversion relationship with the same hardness information. For example, if the sensor 301 measures the sectional indentation hardness of the cut foam, the calculation unit 302 predicts the predicted indentation hardness of the cured foam, and the conversion relationship based on which the calculation unit 302 depends is formed based on the sectional indentation hardness and the cured indentation hardness in the history data. In other examples, the possibility of measuring, predicting with different hardness information is not excluded. For example, if the sensor 301 measures the section compression hardness of the foam after cutting and the calculation unit 302 predicts the predicted indentation hardness of the foam after aging, the conversion relationship based on the prediction is formed according to the section compression hardness and the aging indentation hardness in the history data.
In some embodiments of the present application, the transformation relationship is formed according to a machine learning algorithm (e.g., linear regression) or a neural network algorithm. The transformational relationships may be, for example, attached to a neural network, although the transformational relationships depend on the structure of the neural network, one skilled in the art may not be concerned with the structure of the neural network, nor how the neural network is trained and what form the neural network is in after training. In some embodiments of the present application, the computing unit 302 may retain a relationship to which the transformation is attached, such as a neural network.
In some embodiments of the present application, the foam may specifically be polyurethane block foam. As shown in fig. 6, the production parameter adjustment system 30 may include sensors 601 and 602, and each sensor 601 and 602 is more than 20 cm from each side of the rectangle of the block foam 603. In some examples, production parameter adjustment system 30 includes 3 sensors, and each sensor is more than 10 centimeters, and preferably may be more than 20 centimeters, from each side of the rectangle of foam. In general, the dimension of each dimension of the foam is larger than 40 cm, and if the edge hardness of the foam is detected, the measured value is not representative because the deformation is large. In experiments we found that arranging 3 sensors works best, a balance between measurement accuracy and cost can be struck. More accurate tangent plane hardness information can be determined according to the measured values of the 3 sensors, for example, the average value of the measured values of the 3 sensors can be taken as the tangent plane hardness information. In addition, obviously unreasonable measured values can be eliminated according to the measured values of the 3 sensors, and section hardness information can be determined according to the rest reasonable values. In some embodiments of the present application, each sensor may be set to be equidistant from the center of the rectangle of the foam, and the distance between the sensors is equal. In this way, the sensors 301 will be evenly distributed with respect to the rectangular cross section, and thus more general tangential plane hardness information can be measured. If the sensors 301 are arranged in a concentrated manner, hardness information of the same region is measured: in the presence of local processing flaws in this area, the measured values will clearly not be representative of the hardness of the cut surface.
In some embodiments of the present application, the sensor 301 is configured to measure perpendicular to the cut plane of the foam. It was stated in the foregoing that measuring the section hardness information of the foam after cutting on the production line should be performed under the same conditions as measuring the section hardness information of the foam in the history data described below (for example, keeping the arrangement of the sensors 301 unchanged). In particular, the detection directions of the sensors 301 can all be perpendicular to the section plane of the foam.
The foam production parameter adjusting system 30 of the present application can be used for, for example, being installed in an existing production line, and upgrading the existing production line.
According to another aspect of the present application, there is provided a foam (e.g., polyurethane block foam) production apparatus. As shown in fig. 4, the foam production apparatus 40 includes a foam production parameter adjustment system 30 as described above. Therefore, the foam production device 40 can adjust the production line parameters according to the predicted hardness information reported by the foam production parameter adjustment system 30, and further realize the hardness control of the foam on the production line.
In some embodiments of the present application, the foam production apparatus 40 specifically further includes a receiving unit 401 and an adjusting unit 402. Wherein the receiving unit 401 is configured to receive the predicted stiffness information and the adjusting unit 402 is configured to adjust the parameters of the foam production apparatus 40 according to the predicted stiffness information. The receiving unit 401 may receive the predicted hardness information reported from the production parameter adjusting system 30 and send the predicted hardness information to the adjusting unit 402, and the adjusting unit 402 adjusts the parameters of the foam production apparatus 40 according to the predicted hardness information. In particular, the adjustment unit 402 may send instructions to adjust parameters of the foam production apparatus 40 based on the difference between the predicted stiffness information and the desired stiffness information, the instructions being sent to various execution components (not shown) of the foam production apparatus 40 so that the predicted stiffness information is close to or even equal to the desired stiffness information. For example, if the hardness information is predicted not to reach the hardness required for processing, the adjustment unit 402 may send a command to adjust the parameters of the foam production apparatus 40 to increase the hardness of the foam on the production line.
In some embodiments of the present application, the parameters that can be adjusted include recipe parameters and process parameters. Wherein, the formula parameters comprise raw material proportioning, and the process parameters comprise one or more of feeding temperature, falling plate angle and conveyor belt speed. For example, the adjustment unit 402 may send instructions to a precision pump (e.g., piston pump, gear pump) to adjust the dosing composition, or may send instructions to a conveyor motor to adjust the speed.
More specifically, referring again to fig. 7, the foam production apparatus 70 includes an existing production line 701, and a sensor 7011 and an adjustment unit 7012 are added to the existing production line. In addition, the foam production apparatus 70 further includes a server 702, a memory 703, a database 704, and a processing unit 705. The sensor 7011 is configured to measure cut hardness information of, for example, freshly cut foam on the foam production line conveyor and send this information to the server 702. The cut foam may be cured in a laboratory environment and cured hardness information recorded in memory 703 after curing. Database 704 may collect foam section hardness information from server 702 and ripeness information from memory 703 and accumulate them to form a historical database. The processing unit 705 may train an algorithm according to the corresponding section hardness information and the curing hardness information stored in the database 704, and the trained algorithm may be used to predict the predicted hardness information. Processing unit 705 also receives foam tangent hardness information of server 702 and may determine predicted hardness information based on the tangent hardness information according to an algorithm. The predicted hardness information may be uploaded to adjusting unit 7012, and adjusting unit 7012 may transmit instructions to adjust parameters of foam production apparatus 70, which are transmitted to respective execution parts (not shown) of foam production apparatus 70, according to a difference between the predicted hardness information and the desired hardness information, so that the predicted hardness information is close to or even equal to the desired hardness information.
According to another aspect of the present application, there is provided a computer-readable storage medium having stored therein instructions, which, when executed by a processor, cause the processor to perform any one of the methods as described above. Computer-readable media, as referred to in this application, includes all types of computer storage media, which can be any available media that can be accessed by a general purpose or special purpose computer. By way of example, computer-readable media may include RAM, ROM, EPROM, E2PROM, registers, hard disk, removable disk, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other temporary or non-temporary medium that can be used to carry or store desired program code means in the form of instructions or data structures and that can be accessed by a general purpose or special purpose computer, or a general purpose or special purpose processor. A disk, as used herein, typically reproduces data magnetically, while a disk reproduces data optically with a laser. Combinations of the above should also be included within the scope of computer-readable media. An exemplary storage medium is coupled to the processor such the processor can read information from, and write information to, the storage medium. In the alternative, the storage medium may be integral to the processor. The processor and the storage medium may reside in an ASIC. The ASIC may reside in a user terminal. In the alternative, the processor and the storage medium may reside as discrete components in a user terminal.
The above are merely specific embodiments of the present application, but the scope of the present application is not limited thereto. Other possible variations or alternatives may occur to those skilled in the art based on the technical scope disclosed in the present application, and are all covered by the scope of the present application. In the present invention, the embodiments and features of the embodiments may be combined with each other without conflict. The scope of protection of the present application is subject to the description of the claims.

Claims (23)

1. A foam production parameter adjusting method is characterized by comprising the following steps:
measuring section hardness information of foam on a conveyor belt of a foam production line;
determining predicted hardness information of the cured foam according to the section hardness information based on a conversion relation, wherein the conversion relation is formed according to the section hardness information of the foam and historical data of the cured hardness information; and
and adjusting the production parameters of the foam according to the predicted hardness information.
2. The method of claim 1, wherein the tangent stiffness information, the predicted stiffness information, and the cured stiffness information comprise: indentation hardness, compression hardness.
3. The method of claim 1, the production parameters comprising: formulation parameters and process parameters.
4. The method of claim 3, the recipe parameters comprising raw material mix-ups, the process parameters comprising: charging temperature, fall plate angle, conveyor belt speed.
5. The method of any one of claims 1-4, the transformational relationship being formed according to a machine learning algorithm or a neural network algorithm.
6. A method for determining hardness information conversion relation of foam, which is characterized by comprising the following steps:
measuring section hardness information of at least one foam sample on a conveyor belt of a foam production line;
measuring curing hardness information of the cured foam sample; and
and forming a conversion relation according to the section hardness information and the curing hardness information, wherein the conversion relation is used for determining the cured predicted hardness information according to the section hardness information of the foam on the conveyor belt of the foam production line.
7. The method of claim 6, wherein the section stiffness information is formed from at least one location of at least one section of the foam sample, and the ripened stiffness information is formed from at least one location of the foam sample after it has been ripened.
8. The method of claim 7, wherein measuring the tangent plane stiffness information is at least partially located near or at the same location as measuring the curing stiffness information.
9. The method of any of claims 6-8, the tangent stiffness information, the predicted stiffness information, and the cured stiffness information comprising: indentation hardness, compression hardness.
10. The method according to any one of claims 6-8, the method comprising: and forming the conversion relation by using the machine learning algorithm or the neural network algorithm and the section hardness information of the foam sample as input and the curing hardness information of the foam sample as output.
11. The neural network is characterized in that the neural network takes section hardness information of at least one foam sample on a conveyor belt of a foam production line as input, and takes cured hardness information of the cured foam sample as target output for training.
12. A foam production parameter adjustment system, characterized in that, the system includes:
one or more sensors configured to measure section hardness information of foam on the foam production line conveyor;
a calculation unit configured to determine predicted hardness information after curing of the foam from the section hardness information based on a conversion relationship formed from history data of section hardness information and curing hardness information of the foam; and
a transmitting unit configured to transmit the predicted hardness information, wherein the predicted hardness information is used to adjust production parameters of foam.
13. The system of claim 12, the tangent stiffness information, the predicted stiffness information, and the cured stiffness information comprising: indentation hardness, compression hardness.
14. The system of claim 12 or 13, the computing unit comprising a neural network as claimed in claim 11.
15. The system of claim 12 or 13, comprising at least 3 sensors.
16. The system of claim 15, wherein each sensor is no less than 10 cm from each side of the rectangle of the foam.
17. The system of claim 16, wherein each sensor is spaced more than or equal to 20 cm from each side of the rectangle of foam.
18. The system of claim 12 or 13, the sensor configured to measure perpendicular to a tangent plane of the foam.
19. A foam production apparatus, characterized in that it comprises a system according to any one of claims 12-18.
20. The apparatus of claim 19, comprising a receiving unit configured to receive the predicted firmness information; and
an adjustment unit configured to adjust a parameter of the device according to the predicted hardness information.
21. The apparatus of claim 20, the parameters comprising: formulation parameters and process parameters.
22. The apparatus of claim 21, the recipe parameters comprising raw material mix ratios, the process parameters comprising: charging temperature, fall plate angle, conveyor belt speed.
23. A computer-readable storage medium having instructions stored therein, which when executed by a processor, cause the processor to perform the method of any one of claims 1-10.
CN202011477997.1A 2020-12-15 2020-12-15 Foam production parameter adjustment, hardness conversion relation determination, foam production device and medium Pending CN114637257A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011477997.1A CN114637257A (en) 2020-12-15 2020-12-15 Foam production parameter adjustment, hardness conversion relation determination, foam production device and medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011477997.1A CN114637257A (en) 2020-12-15 2020-12-15 Foam production parameter adjustment, hardness conversion relation determination, foam production device and medium

Publications (1)

Publication Number Publication Date
CN114637257A true CN114637257A (en) 2022-06-17

Family

ID=81945075

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011477997.1A Pending CN114637257A (en) 2020-12-15 2020-12-15 Foam production parameter adjustment, hardness conversion relation determination, foam production device and medium

Country Status (1)

Country Link
CN (1) CN114637257A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115113596A (en) * 2022-07-13 2022-09-27 浙江高裕家居科技股份有限公司 Polyurethane material production parameter adjusting method and system based on quality monitoring

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115113596A (en) * 2022-07-13 2022-09-27 浙江高裕家居科技股份有限公司 Polyurethane material production parameter adjusting method and system based on quality monitoring
CN115113596B (en) * 2022-07-13 2023-09-08 浙江高裕家居科技股份有限公司 Polyurethane material production parameter adjusting method and system based on quality monitoring

Similar Documents

Publication Publication Date Title
US8356957B2 (en) System and method of applying a road surface
US7138077B2 (en) Process and installation for the production of foam in a continuous slabstock foam process
US7644162B1 (en) Resource entitlement control system
US9581980B2 (en) Method and system for updating a model in a model predictive controller
US9513610B2 (en) Apparatus and methods for non-invasive closed loop step testing using a tunable trade-off factor
CN114637257A (en) Foam production parameter adjustment, hardness conversion relation determination, foam production device and medium
CN113677495A (en) Visual metal panel quality detection based on cut edges
KR100829706B1 (en) Method of predicting properties of polymer product
US20220284991A1 (en) Method of producing a chemical product using a regression model
US20040059694A1 (en) Method and apparatus for providing a virtual age estimation for remaining lifetime prediction of a system using neural networks
AU2008255635B2 (en) Monitoring methods and apparatus
US20030014226A1 (en) Method and apparatus for providing a polynomial based virtual age estimation for remaining lifetime prediction of a system
KR101985801B1 (en) Method for controlling viscosity of electrode active material slurry of the secondary battery and apparatus for manufacturing electrode active material slurry of the secondary battery
EP4075209A1 (en) Adjusting foam production parameter, determining hardness conversion relationship, device for foam production and medium
Steinwandter et al. Propagation of measurement accuracy to biomass soft-sensor estimation and control quality
JP2006168360A (en) Method and device for manufacturing foam in continuous foaming process
Kochetkov et al. Standardization of Roughness of Products of the Machine-Building Industry on the Basis of Variable Height Indicator of Ledges and Variable Depth Indicator of Hollows as an Extension of State Standard GOST 2789–73
US10775218B2 (en) Plant evaluation device and plant evaluation method
US20060128022A1 (en) Process control method and process control system
JP4820747B2 (en) TRAVEL TIME CALCULATION DEVICE, PROGRAM, AND RECORDING MEDIUM
US11044922B2 (en) Milk coagulation process control technology
RU2486227C1 (en) Method of catalytic reforming control
Han et al. Quality control during construction of the Green Heart Tunnel on the basis of service life design
WO2024079199A1 (en) Method and system for measuring the setting time of a gypsum board
RU2536822C1 (en) Method of controlling process of polymerisation of ethylene propylene synthetic rubbers

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication