CN117035200A - Optimized production control method and system for plastic products - Google Patents
Optimized production control method and system for plastic products Download PDFInfo
- Publication number
- CN117035200A CN117035200A CN202311295375.0A CN202311295375A CN117035200A CN 117035200 A CN117035200 A CN 117035200A CN 202311295375 A CN202311295375 A CN 202311295375A CN 117035200 A CN117035200 A CN 117035200A
- Authority
- CN
- China
- Prior art keywords
- performance
- batching
- plastic
- expected
- ingredient
- 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.)
- Granted
Links
- 239000004033 plastic Substances 0.000 title claims abstract description 314
- 229920003023 plastic Polymers 0.000 title claims abstract description 314
- 238000000195 production control method Methods 0.000 title claims abstract description 11
- 238000004519 manufacturing process Methods 0.000 claims abstract description 92
- 238000012216 screening Methods 0.000 claims abstract description 43
- 238000004458 analytical method Methods 0.000 claims abstract description 28
- 238000000034 method Methods 0.000 claims abstract description 26
- 239000004615 ingredient Substances 0.000 claims description 156
- 238000005457 optimization Methods 0.000 claims description 80
- 230000005284 excitation Effects 0.000 claims description 28
- 239000000463 material Substances 0.000 claims description 12
- 230000003213 activating effect Effects 0.000 claims description 9
- 238000009826 distribution Methods 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 9
- 238000013528 artificial neural network Methods 0.000 claims description 7
- 230000004044 response Effects 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 5
- 230000004927 fusion Effects 0.000 claims description 5
- 238000004891 communication Methods 0.000 claims description 4
- 238000010276 construction Methods 0.000 claims description 4
- 230000000694 effects Effects 0.000 abstract description 18
- 238000013329 compounding Methods 0.000 description 11
- 238000004806 packaging method and process Methods 0.000 description 2
- 239000004793 Polystyrene Substances 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000000071 blow moulding Methods 0.000 description 1
- 238000005034 decoration Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 229920001903 high density polyethylene Polymers 0.000 description 1
- 239000004700 high-density polyethylene Substances 0.000 description 1
- 238000001746 injection moulding Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000003754 machining Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000000465 moulding Methods 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- -1 polyethylene terephthalate Polymers 0.000 description 1
- 239000005020 polyethylene terephthalate Substances 0.000 description 1
- 229920000139 polyethylene terephthalate Polymers 0.000 description 1
- 229920002223 polystyrene Polymers 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 229920005989 resin Polymers 0.000 description 1
- 239000011347 resin Substances 0.000 description 1
- 239000000243 solution Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000003856 thermoforming Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- G06N3/0499—Feedforward networks
-
- 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
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06395—Quality analysis or management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/04—Manufacturing
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C60/00—Computational materials science, i.e. ICT specially adapted for investigating the physical or chemical properties of materials or phenomena associated with their design, synthesis, processing, characterisation or utilisation
Abstract
The invention discloses an optimized production control method and system for plastic products, and relates to the field of plastic product production, wherein the method comprises the following steps: carrying out associated batching index identification on W plastic performance expected characteristics to obtain a plurality of associated batching indexes; performing expected performance trigger prediction of an initialization batching space according to the expected performance trigger analysis function and the W plastic performance expected characteristics to obtain M expected performance triggers; screening the optimal expected performance triggering degree, and judging whether the optimal expected performance triggering degree meets the preset triggering degree or not; and if the optimal expected performance triggering degree does not meet the preset triggering degree, obtaining a screening initial batching result, and optimizing the screening initial batching result to obtain an optimal batching result. Solves the technical problems that the prior art can not carry out targeted batching according to the performance requirement of the plastic product, the batching accuracy of the plastic product is poor, and the production effect of the plastic product is poor.
Description
Technical Field
The invention relates to the field of plastic product production, in particular to an optimized production control method and system for plastic products.
Background
The plastic product is produced with plastic as main material and through injection molding, blow molding, thermoforming and other technological processes. Plastic bags, plastic cups, plastic packaging bottles, automobile plastic inner decorations and the like belong to plastic products. The production process of the plastic product comprises the steps of batching, molding, machining, jointing, decorating, assembling and the like. The ingredients have important influence on the performance and production quality of plastic products. In the prior art, the technical problems that the plastic product cannot be purposefully compounded according to the performance requirement of the plastic product, so that the compounding accuracy of the plastic product is poor and the production effect of the plastic product is poor exist.
Disclosure of Invention
The application provides an optimized production control method and system for plastic products. Solves the technical problems that the prior art can not carry out targeted batching according to the performance requirement of the plastic product, the batching accuracy of the plastic product is poor, and the production effect of the plastic product is poor. The technical effects of realizing targeted proportioning according to the performance requirements of plastic products, improving the proportioning accuracy of the plastic products, improving the proportioning effect of the plastic products and improving the production quality of the plastic products are achieved.
In view of the above, the present application provides a method and system for optimized production control of plastic products.
In a first aspect, the present application provides a method for controlling optimized production of plastic products, wherein the method is applied to a system for controlling optimized production of plastic products, and the method comprises: the plastic production management end is interacted to obtain a plastic production instruction, wherein the plastic production instruction comprises plastic type expected characteristics and W plastic performance expected characteristics, and W is a positive integer greater than 1; carrying out associated batching index identification on the W plastic performance expected characteristics according to a pre-constructed initial batching characteristic decision maker to obtain a plurality of associated batching indexes; initializing ingredients based on the expected characteristics of the plastic types and the plurality of associated ingredient indexes to obtain an initialized ingredient space, wherein the initialized ingredient space comprises M initial ingredient results, and M is a positive integer greater than 1; executing expected performance trigger prediction of the initialized material distribution space according to an expected performance trigger analysis function and the W plastic performance expected characteristics to obtain M expected performance trigger degrees; screening optimal expected performance trigger degrees according to the M expected performance trigger degrees, and judging whether the optimal expected performance trigger degrees meet preset trigger degrees or not; if the optimal expected performance trigger degree does not meet the preset trigger degree, matching the M initial batching results based on the optimal expected performance trigger degree to obtain screening initial batching results, and generating a batching optimization instruction; and activating an ingredient optimizing channel based on the ingredient optimizing instruction to optimize the screening initial ingredient result, obtaining an optimal ingredient result, and sending the optimal ingredient result to the plastic production management end.
In a second aspect, the present application also provides an optimized production control system for plastic products, wherein the system is in communication connection with a plastic production management end, and the system comprises: the production instruction obtaining module is used for interacting the plastic production management end to obtain a plastic production instruction, wherein the plastic production instruction comprises plastic type expected characteristics and W plastic performance expected characteristics, and W is a positive integer greater than 1; the associated batching index identification module is used for carrying out associated batching index identification on the W plastic performance expected characteristics according to a pre-built initial batching characteristic decision maker so as to obtain a plurality of associated batching indexes; the initialization batching module is used for performing initialization batching based on the expected characteristics of the plastic types and the plurality of associated batching indexes to obtain an initialization batching space, wherein the initialization batching space comprises M initial batching results, and M is a positive integer greater than 1; the expected performance trigger prediction module is used for executing expected performance trigger prediction of the initialized material distribution space according to an expected performance trigger analysis function and the W plastic performance expected characteristics to obtain M expected performance triggers; the trigger degree judging module is used for screening the optimal expected performance trigger degree according to the M expected performance trigger degrees and judging whether the optimal expected performance trigger degree meets the preset trigger degree or not; the optimization instruction generation module is used for matching the M initial batching results based on the optimal expected performance trigger degree if the optimal expected performance trigger degree does not meet the preset trigger degree, so as to obtain screening initial batching results and generate a batching optimization instruction; and the ingredient optimizing module is used for activating an ingredient optimizing channel to optimize the screening initial ingredient result based on the ingredient optimizing instruction, obtaining an optimal ingredient result and sending the optimal ingredient result to the plastic production management end.
One or more technical schemes provided by the application have at least the following technical effects or advantages:
obtaining a plastic production instruction through a plastic production management end, wherein the plastic production instruction comprises plastic type expected characteristics and W plastic performance expected characteristics; carrying out associated batching index identification on W plastic performance expected characteristics according to a pre-constructed initial batching characteristic decision maker to obtain a plurality of associated batching indexes; initializing ingredients based on the expected characteristics of the plastic types and a plurality of associated ingredient indexes to obtain an initialized ingredient space; performing expected performance trigger prediction of an initialization batching space according to the expected performance trigger analysis function and the W plastic performance expected characteristics to obtain M expected performance triggers; screening the optimal expected performance trigger degrees according to the M expected performance trigger degrees, and judging whether the optimal expected performance trigger degrees meet the preset trigger degrees or not; if the optimal expected performance trigger degree does not meet the preset trigger degree, matching M initial batching results based on the optimal expected performance trigger degree to obtain screening initial batching results, and generating batching optimization instructions; activating a batching optimizing channel according to a batching optimizing instruction to optimize a screening initial batching result, obtaining an optimal batching result, and sending the optimal batching result to a plastic production management end. The technical effects of realizing targeted proportioning according to the performance requirements of plastic products, improving the proportioning accuracy of the plastic products, improving the proportioning effect of the plastic products and improving the production quality of the plastic products are achieved.
The foregoing description is only an overview of the present application, and is intended to be implemented in accordance with the teachings of the present application in order that the same may be more clearly understood and to make the same and other objects, features and advantages of the present application more readily apparent.
Drawings
In order to more clearly illustrate the technical solution of the embodiments of the present application, the following description will briefly explain the drawings of the embodiments of the present application. It is apparent that the figures in the following description relate only to some embodiments of the application and are not limiting of the application.
FIG. 1 is a schematic flow chart of a method for optimizing production control of plastic products according to the present application;
FIG. 2 is a schematic flow chart of performing optimization constraints of a plurality of associated ingredient indexes in an optimized production control method of plastic products according to the present application;
FIG. 3 is a schematic diagram of a system for optimizing production control of plastic products according to the present application.
Detailed Description
The application provides a method and a system for controlling the optimized production of plastic products. Solves the technical problems that the prior art can not carry out targeted batching according to the performance requirement of the plastic product, the batching accuracy of the plastic product is poor, and the production effect of the plastic product is poor. The technical effects of realizing targeted proportioning according to the performance requirements of plastic products, improving the proportioning accuracy of the plastic products, improving the proportioning effect of the plastic products and improving the production quality of the plastic products are achieved.
Example 1
Referring to fig. 1, the present application provides a method for controlling optimized production of plastic products, wherein the method is applied to a system for controlling optimized production of plastic products, the system is in communication connection with a plastic production management end, and the method specifically comprises the following steps:
the plastic production management end is interacted to obtain a plastic production instruction, wherein the plastic production instruction comprises plastic type expected characteristics and W plastic performance expected characteristics, and W is a positive integer greater than 1;
and connecting with a plastic production management end to obtain a plastic production instruction. Wherein, the plastic production management end is in communication connection with an optimized production control system of plastic products. The plastic production management end has the functions of plastic product production control, data inquiry, information interaction, instruction receiving and the like. The plastic production instructions include plastic type desired characteristics and W plastic performance desired characteristics sent by any user. And W is a positive integer greater than 1. The plastic type desired characteristics include type information of the plastic article to be produced. For example, plastic types are desirably characterized as plastic packaging bottles, plastic cups, plastic cutlery boxes, and the like. The W plastic property desired characteristics include W plastic property desired intervals corresponding to W plastic property desired indicators of the plastic article to be produced. The plastic performance expected index is the performance requirement index of the plastic product to be produced. The expected plastic performance interval is the performance requirement range information corresponding to the performance requirement index. For example, when the plastic type desired feature is a plastic lunch box, the W plastic performance desired indexes include heat resistance indexes, impact resistance indexes, sealability indexes, and the like, and the W plastic performance desired sections include heat resistance-performance required ranges, impact resistance-performance required ranges, sealability-performance required ranges, and the like.
Carrying out associated batching index identification on the W plastic performance expected characteristics according to a pre-constructed initial batching characteristic decision maker to obtain a plurality of associated batching indexes;
based on big data, obtaining a plastic batching index record library;
obtaining a preset building operator, wherein the preset building operator comprises taking a sample plastic performance expected index record as a batching index characteristic and taking a sample plastic batching index record as a batching index response characteristic;
and carrying out data fusion on the plastic batching index record library based on the preset construction operator to obtain an associated batching index identification map, and embedding the associated batching index identification map into the initial batching characteristic decision maker.
And inquiring the plastic batching index record based on the big data to obtain a plastic batching index record library. The plastic ingredient index record library comprises a plurality of plastic ingredient index records. Each plastic compounding index record includes a sample plastic performance desired index record and a sample plastic compounding index record. The sample plastic performance desired index record includes a plurality of historical plastic performance desired characteristics. The sample plastic ingredient index record includes a plurality of historical plastic material indices corresponding to a plurality of historical plastic performance desired characteristics within the sample plastic performance desired index record. For example, a number of historical plastic material indicators include resins, polyethylene terephthalate, high density polyethylene, polystyrene, and the like.
The preset building operator comprises taking the expected index record of the sample plastic performance as the batching index feature and taking the batching index record of the sample plastic as the batching index response feature. And carrying out data fusion on the plastic batching index record library according to a preset construction operator, namely marking each plastic batching index record in the plastic batching index record library as an associated batching index identification node, setting a sample plastic performance expected index record in each plastic batching index record as a batching index feature, setting a sample plastic batching index record in each plastic batching index record as a batching index response feature, obtaining an associated batching index identification map, and embedding the associated batching index identification map into an initial batching feature decider. And then, inputting the W plastic performance expected characteristics into an initial batching characteristic decision maker, and performing plastic material index matching on the W input plastic performance expected characteristics by using an associated batching index identification map in the initial batching characteristic decision maker to obtain a plurality of associated batching indexes, thereby improving the batching reliability of the plastic product.
The initial ingredient feature determiner includes an associated ingredient index identification map. The associated ingredient index identification map includes a plurality of associated ingredient index identification nodes. And, each associated ingredient index identification node includes an ingredient index feature, an ingredient index response feature. The plurality of associated compounding indicia includes a plurality of plastic material indicia corresponding to the W plastic performance desired characteristics.
As shown in fig. 2, after obtaining the plurality of associated ingredient indexes, the method further includes:
carrying out batch sequence influence identification on the plurality of associated batch indexes to generate batch sequence influence degree;
judging whether the influence degree of the batching sequence meets a preset influence constraint;
if the batching sequence influence degree does not meet the preset influence constraint, a batching index constraint instruction is obtained;
and executing optimization constraints of the plurality of associated ingredient indexes based on the ingredient index constraint instructions.
And obtaining the influence degree of the batching sequence by identifying the batching sequence influence of a plurality of associated batching indexes. The identification of the distribution sequence influence refers to analysis of whether the distribution sequence of a plurality of associated distribution indexes can influence the production quality and the production safety of plastic products. The batching sequence influence degree is data information for representing the influence of the throwing sequence of a plurality of associated batching indexes on the production quality and the production safety of the plastic products. The higher the influence of the throwing sequence of a plurality of associated batching indexes on the production quality of plastic products, the stronger the influence of the production safety, and the larger the influence of the corresponding batching sequence.
Further, whether the influence degree of the batching sequence meets the preset influence constraint is judged. If the influence degree of the batching sequence does not meet the preset influence constraint, a batching index constraint instruction is obtained, and optimization constraint is carried out on a plurality of associated batching indexes according to the batching index constraint instruction. The preset influence constraint comprises a preset determined dosage sequence influence degree range by the optimized production control system of the plastic product. The batching index constraint instruction is instruction information used for representing that the batching sequence influence degree does not meet the preset influence constraint, the batching sequence influence degree is strong, and optimization constraint needs to be carried out on a plurality of associated batching indexes.
Preferably, when the plurality of associated batching indexes are subjected to optimization constraint according to the batching index constraint instruction, the plurality of associated batching indexes are subjected to throwing sequence constraint identification according to the throwing sequence, so that the production effect of plastic products is improved, and the batching control comprehensiveness of the plastic products is improved.
Initializing ingredients based on the expected characteristics of the plastic types and the plurality of associated ingredient indexes to obtain an initialized ingredient space, wherein the initialized ingredient space comprises M initial ingredient results, and M is a positive integer greater than 1;
and carrying out historical data query according to the expected characteristics of the plastic types and a plurality of associated batching indexes to obtain an initialized batching space. Wherein the initialization batching space comprises M initial batching results. And M is a positive integer greater than 1. Each initial compounding result includes a plurality of historical compounding index values corresponding to a plurality of associated compounding index values when producing a historical plastic product that meets the desired characteristics of the plastic type and whose material index is the plurality of associated compounding index. Each historical associated ingredient index value comprises a historical putting weight/historical putting volume and other putting quantity parameters corresponding to each associated ingredient index.
Executing expected performance trigger prediction of the initialized material distribution space according to an expected performance trigger analysis function and the W plastic performance expected characteristics to obtain M expected performance trigger degrees;
traversing the initialized batching space to obtain an mth initial batching result, wherein M is a positive integer, and M belongs to M;
based on the W plastic performance expected characteristics, W plastic performance expected indexes are obtained;
taking the mth initial batching result as an mth retrieval constraint and taking the W plastic performance expected indexes as retrieval targets;
big data matching is carried out according to the mth retrieval constraint and the retrieval target, and a batching performance index record library is obtained, wherein the batching performance index record library comprises J batching performance index records, and J is a positive integer greater than 1;
and randomly selecting M initial batching results in the initialized batching space to obtain an mth initial batching result. M is a positive integer, and M belongs to M. The mth initial ingredients result includes any one of the initial ingredients results in the initial ingredients space. Then, W plastic performance expectation indices are extracted from the W plastic performance expectation features. Setting the mth initial batching result as the mth retrieval constraint, and taking W plastic performance expected indexes as retrieval targets. And acquiring big data according to the mth retrieval constraint and the retrieval target to obtain a batch performance index record library. The ingredient performance index record library comprises J ingredient performance index records. J is a positive integer greater than 1. Each compounding performance index record includes W plastic performance desired index record values corresponding to W plastic performance desired indexes of the plastic article produced according to the mth initial compounding result. For example, when the plastic property desired index includes a heat resistance index, the plastic property desired index recorded value includes a historical heat resistance parameter of the plastic article produced according to the mth initial compounding result. The higher the historical heat resistance parameter, the stronger the heat resistance of the plastic article produced according to the mth initial formulation result.
Analyzing the expected performance triggering degree of the ingredient performance index record base based on the expected performance triggering analysis function to obtain J ingredient record performance triggering degrees;
wherein obtaining J ingredient record performance triggers comprises:
based on the batching performance index record library, a J-th batching performance index record is obtained, J is a positive integer, and J belongs to J;
inputting the J-th ingredient performance index record into the expected performance trigger analysis function, obtaining a J-th ingredient record performance trigger degree corresponding to the J-th ingredient performance index record, and adding the J-th ingredient record performance trigger degree to the J-th ingredient record performance trigger degrees, wherein the expected performance trigger analysis function is as follows:
；
；
wherein,characterizing the j-th ingredient recording performance trigger level, +.>Representing the performance triggering degree of an ith index corresponding to an ith plastic performance expected index in a jth ingredient performance index record, wherein i is a positive integer, and the ith plastic performance expected index belongs to W, and comprises any one of W plastic performance expected indexes>Characterizing an i-th plastic property expected index record value corresponding to the i-th plastic property expected index in the j-th ingredient property index record, >Characterizing the lower limit expectations corresponding to the ith plastic property expectations index,/->And characterizing the upper limit expectation corresponding to the ith plastic performance expectation index.
And randomly selecting J ingredient performance index records in the ingredient performance index record library to obtain J ingredient performance index records, wherein J is a positive integer, and J belongs to J. The j-th ingredient performance index record comprises any one ingredient performance index record in the ingredient performance index record library. And then inputting the J-th ingredient performance index record into an expected performance trigger analysis function, obtaining the J-th ingredient record performance trigger corresponding to the J-th ingredient performance index record, and adding the J-th ingredient record performance trigger to the J-th ingredient record performance trigger. The desired performance trigger analysis function is:
；
；
wherein,recording the corresponding j-th ingredient performance triggering degree for the output j-th ingredient performance index; />The method comprises the steps that the performance triggering degree of an ith index corresponding to an ith plastic performance expected index in a jth batching performance index record is obtained, i is a positive integer, and belongs to W, wherein the ith plastic performance expected index comprises any one of W plastic performance expected indexes; />Representing an i plastic performance expected index record value corresponding to the i plastic performance expected index in the j-th ingredient performance index record; / >Representing the lower limit expectation corresponding to the ith plastic performance expectation index, wherein the lower limit expectation corresponding to the ith plastic performance expectation index is the minimum value of the plastic performance expectation interval corresponding to the ith plastic performance expectation index; />And representing the upper limit expectation corresponding to the ith plastic performance expectation index, wherein the upper limit expectation corresponding to the ith plastic performance expectation index is the maximum value of the plastic performance expectation interval corresponding to the ith plastic performance expectation index.
And carrying out average calculation on the J ingredient record performance triggering degrees to obtain an mth expected performance triggering degree corresponding to the mth initial ingredient result, and adding the mth expected performance triggering degree to the M expected performance triggering degrees.
Screening optimal expected performance trigger degrees according to the M expected performance trigger degrees, and judging whether the optimal expected performance trigger degrees meet preset trigger degrees or not;
if the optimal expected performance trigger degree does not meet the preset trigger degree, matching the M initial batching results based on the optimal expected performance trigger degree to obtain screening initial batching results, and generating a batching optimization instruction;
and respectively analyzing J ingredient performance index records in the ingredient performance index record library according to the expected performance trigger analysis function to obtain J ingredient record performance triggers corresponding to the J ingredient performance index records in the ingredient performance index record library. The calculation mode of the J ingredient record performance trigger degrees is the same as that of the J ingredient record performance trigger degrees, and is not repeated here. Then, setting the average value of the J ingredient record performance triggers as the mth expected performance trigger corresponding to the mth initial ingredient result, and adding the mth expected performance trigger to the M expected performance triggers. The M expected performance triggers are in one-to-one correspondence with the M initial batch results. The M expected performance triggers are the same as the M expected performance triggers, and are not described herein.
Further, setting the maximum value of the M expected performance triggers as the optimal expected performance trigger, and judging whether the optimal expected performance trigger meets the preset trigger. The preset trigger level includes a desired performance trigger level range preset by the optimized production control system of the plastic product. And if the optimal expected performance trigger degree meets the preset trigger degree, setting an initial batching result corresponding to the optimal expected performance trigger degree as an optimal batching result. Otherwise, if the optimal expected performance trigger degree does not meet the preset trigger degree, setting an initial batching result corresponding to the optimal expected performance trigger degree as a screening initial batching result, and generating a batching optimization instruction. The batch optimization instruction is instruction information used for representing that the triggering degree of the optimal expected performance does not meet the preset triggering degree and needs to activate a batch optimization channel to optimize the screening initial batch results.
And activating an ingredient optimizing channel based on the ingredient optimizing instruction to optimize the screening initial ingredient result, obtaining an optimal ingredient result, and sending the optimal ingredient result to the plastic production management end.
Obtaining W index performance confidence values corresponding to the screening initial batching results;
Comparing the W index performance confidence values with the W plastic performance expected characteristics to obtain excitation optimization performance expected characteristics, and calculating excitation characteristic optimization coefficients corresponding to the excitation optimization performance expected characteristics;
clustering a plurality of plastic performance expected index record values corresponding to the screening initial batching result according to W plastic performance expected indexes, classifying the plurality of plastic performance expected index record values corresponding to the same plastic performance expected index into one class to obtain W index record value clustering results, and respectively carrying out average value calculation on the W index record value clustering results to obtain W index performance confidence values. Each index record value clustering result comprises a plurality of plastic performance expected index record values corresponding to the same plastic performance expected index in a plurality of plastic performance expected index record values corresponding to the initial batching result. Each index performance confidence value includes an average value of each index record value clustering result.
Further, the W index performance confidence values are compared with the W plastic performance expected features, i.e., it is determined whether each index performance confidence value is less than a minimum value of a plastic performance expected interval within the corresponding plastic performance expected feature, respectively. If the index performance confidence value is less than the minimum value of the plastic performance expected interval in the corresponding plastic performance expected characteristic, setting the plastic performance expected characteristic corresponding to the index performance confidence value as an excitation optimization performance expected characteristic, and recording the absolute value of the difference value between the index performance confidence value and the minimum value of the plastic performance expected interval in the corresponding plastic performance expected characteristic as an excitation characteristic optimization coefficient. The larger the excitation feature optimization coefficient is, the higher the degree of optimization to be of the corresponding excitation optimization performance expected feature is.
Inputting the excitation optimization performance expected characteristics, the excitation characteristic optimization coefficients and the screening initial batching results into the batching optimization channel to generate the optimal batching results.
Obtaining a sample batching optimization record;
based on the BP neural network, obtaining an ingredient optimizing network;
training the batching optimization network according to the sample batching optimization record, and generating an output accurate operator when training is performed for preset times;
and when the output accurate operator meets the preset output accurate operator, generating the batching optimization channel.
And carrying out historical data query based on the excitation optimization performance expected characteristics, the excitation characteristic optimization coefficients and the screening initial batching results to obtain a sample batching optimization record. The sample recipe optimization record includes a plurality of sets of sample recipe optimization data. Each set of sample ingredient optimization data comprises a historical excitation optimization performance expected characteristic, a historical excitation characteristic optimization coefficient, a historical screening initial ingredient result and a historical optimal ingredient result. The BP neural network is then a multi-layer feedforward neural network trained according to an error back propagation algorithm. The BP neural network comprises an input layer, a plurality of layers of neurons and an output layer. The BP neural network is set as an ingredient optimizing network. Training the batching optimization network according to the sample batching optimization record, testing the batching optimization network when the batching optimization network is trained for preset times, obtaining an output accurate operator, and judging whether the output accurate operator meets the preset output accurate operator or not. The preset times are training times preset and determined by the optimized production control system of the plastic product. And when the output accuracy operator is used for each training preset time, the output accuracy parameters of the network are optimized by batching. The preset output accuracy operator is an output accuracy range preset and determined by the optimized production control system of the plastic product.
And outputting the ingredient optimizing network as an ingredient optimizing channel if the output accurate operator meets the preset output accurate operator. If the output accurate operator does not meet the preset output accurate operator, continuing to train the batching optimization network until a batching optimization channel is generated. And inputting the excitation optimization performance expected characteristics, the excitation characteristic optimization coefficients and the screening initial batching results into a batching optimization channel, and adjusting the screening initial batching results by the batching optimization channel according to the excitation optimization performance expected characteristics and the excitation characteristic optimization coefficients to obtain optimal batching results. The batching optimization channel comprises an input layer, an implicit layer and an output layer. And then, sending the optimal batching result to a plastic production management end, and controlling batching according to the optimal batching result by the plastic production management end so as to improve batching quality of plastic products.
In summary, the optimized production control method for plastic products provided by the application has the following technical effects:
obtaining a plastic production instruction through a plastic production management end, wherein the plastic production instruction comprises plastic type expected characteristics and W plastic performance expected characteristics; carrying out associated batching index identification on W plastic performance expected characteristics according to a pre-constructed initial batching characteristic decision maker to obtain a plurality of associated batching indexes; initializing ingredients based on the expected characteristics of the plastic types and a plurality of associated ingredient indexes to obtain an initialized ingredient space; performing expected performance trigger prediction of an initialization batching space according to the expected performance trigger analysis function and the W plastic performance expected characteristics to obtain M expected performance triggers; screening the optimal expected performance trigger degrees according to the M expected performance trigger degrees, and judging whether the optimal expected performance trigger degrees meet the preset trigger degrees or not; if the optimal expected performance trigger degree does not meet the preset trigger degree, matching M initial batching results based on the optimal expected performance trigger degree to obtain screening initial batching results, and generating batching optimization instructions; activating a batching optimizing channel according to a batching optimizing instruction to optimize a screening initial batching result, obtaining an optimal batching result, and sending the optimal batching result to a plastic production management end. The technical effects of realizing targeted proportioning according to the performance requirements of plastic products, improving the proportioning accuracy of the plastic products, improving the proportioning effect of the plastic products and improving the production quality of the plastic products are achieved.
Example two
Based on the same inventive concept as the optimized production control method of a plastic product in the foregoing embodiment, the present invention further provides an optimized production control system of a plastic product, referring to fig. 3, the system is communicatively connected to a plastic production management end, and the system includes:
the production instruction obtaining module is used for interacting the plastic production management end to obtain a plastic production instruction, wherein the plastic production instruction comprises plastic type expected characteristics and W plastic performance expected characteristics, and W is a positive integer greater than 1;
the associated batching index identification module is used for carrying out associated batching index identification on the W plastic performance expected characteristics according to a pre-built initial batching characteristic decision maker so as to obtain a plurality of associated batching indexes;
the initialization batching module is used for performing initialization batching based on the expected characteristics of the plastic types and the plurality of associated batching indexes to obtain an initialization batching space, wherein the initialization batching space comprises M initial batching results, and M is a positive integer greater than 1;
The expected performance trigger prediction module is used for executing expected performance trigger prediction of the initialized material distribution space according to an expected performance trigger analysis function and the W plastic performance expected characteristics to obtain M expected performance triggers;
the trigger degree judging module is used for screening the optimal expected performance trigger degree according to the M expected performance trigger degrees and judging whether the optimal expected performance trigger degree meets the preset trigger degree or not;
the optimization instruction generation module is used for matching the M initial batching results based on the optimal expected performance trigger degree if the optimal expected performance trigger degree does not meet the preset trigger degree, so as to obtain screening initial batching results and generate a batching optimization instruction;
and the ingredient optimizing module is used for activating an ingredient optimizing channel to optimize the screening initial ingredient result based on the ingredient optimizing instruction, obtaining an optimal ingredient result and sending the optimal ingredient result to the plastic production management end.
Further, the system further comprises:
the first execution module is used for obtaining a plastic batching index record library based on big data;
The operator obtaining module is used for obtaining a preset building operator, wherein the preset building operator comprises a sample plastic batching index response characteristic which is obtained by taking a sample plastic performance expected index record as a batching index characteristic;
the record fusion module is used for carrying out data fusion on the plastic batching index record library based on the preset construction operator, obtaining an associated batching index identification map, and embedding the associated batching index identification map into the initial batching characteristic decision maker.
Further, the system further comprises:
the batching sequence influence identification module is used for carrying out batching sequence influence identification on the plurality of associated batching indexes and generating batching sequence influence degree;
the influence constraint judging module is used for judging whether the influence degree of the batching sequence meets a preset influence constraint or not;
the constraint instruction obtaining module is used for obtaining a constraint instruction of the batching index if the influence degree of the batching sequence does not meet the preset influence constraint;
and the optimization constraint module is used for executing optimization constraints of the plurality of associated ingredient indexes based on the ingredient index constraint instructions.
Further, the system further comprises:
the second execution module is used for traversing the initialized batching space to obtain an mth initial batching result, wherein M is a positive integer, and M belongs to M;
the third execution module is used for obtaining W plastic performance expected indexes based on the W plastic performance expected characteristics;
the retrieval setting module is used for taking the mth initial batching result as an mth retrieval constraint and taking the W plastic performance expected indexes as retrieval targets;
the big data matching module is used for carrying out big data matching according to the mth retrieval constraint and the retrieval target to obtain a batching performance index record library, wherein the batching performance index record library comprises J batching performance index records, and J is a positive integer greater than 1;
the batching recording performance trigger degree analysis module is used for analyzing the expected performance trigger degree of the batching performance index record base based on the expected performance trigger analysis function to obtain J batching recording performance trigger degrees;
the expected performance trigger degree obtaining module is used for carrying out average value calculation on the J ingredients record performance trigger degrees to obtain an mth expected performance trigger degree corresponding to the mth initial ingredients result, and adding the mth expected performance trigger degree to the M expected performance trigger degrees.
Further, the system further comprises:
the fourth execution module is used for obtaining J-th batching performance index records based on the batching performance index record library, J is a positive integer, and J belongs to J;
the fifth execution module is configured to input the J-th ingredient performance index record into the expected performance trigger analysis function, obtain a J-th ingredient record performance trigger corresponding to the J-th ingredient performance index record, and add the J-th ingredient record performance trigger to the J-th ingredient record performance trigger, where the expected performance trigger analysis function is:
；
；
wherein,characterizing the j-th ingredient recording performance trigger level, +.>Characterizing an ith index performance trigger degree corresponding to an ith plastic performance expected index in a jth ingredient performance index record, wherein i is a positive integer, and belongs to W, and the ith plastic performance expected index comprises W piecesAny one of the plastic performance desirability indexes, < >>Characterizing an i-th plastic property expected index record value corresponding to the i-th plastic property expected index in the j-th ingredient property index record,>characterizing the lower limit expectations corresponding to the ith plastic property expectations index,/- >And characterizing the upper limit expectation corresponding to the ith plastic performance expectation index.
Further, the system further comprises:
the index performance confidence value obtaining module is used for obtaining W index performance confidence values corresponding to the screening initial batching results;
the excitation analysis module is used for comparing the W index performance confidence values with the W plastic performance expected characteristics to obtain excitation optimization performance expected characteristics, and calculating excitation characteristic optimization coefficients corresponding to the excitation optimization performance expected characteristics;
and the sixth execution module is used for inputting the excitation optimization performance expected characteristics, the excitation characteristic optimization coefficients and the screening initial ingredient result into the ingredient optimization channel to generate the optimal ingredient result.
Further, the system further comprises:
the optimizing record obtaining module is used for obtaining sample batching optimizing records;
the seventh execution module is used for obtaining an ingredient optimization network based on the BP neural network;
the network training module is used for training the batching optimization network according to the sample batching optimization record, and generating an output accurate operator when the batching optimization network is trained for preset times;
And the eighth execution module is used for generating the batching optimization channel when the output accuracy operator meets the preset output accuracy operator.
The optimized production control system for the plastic product provided by the embodiment of the application can execute the optimized production control method for the plastic product provided by any embodiment of the application, and has the corresponding functional modules and beneficial effects of the execution method.
All the included modules are only divided according to the functional logic, but are not limited to the above-mentioned division, so long as the corresponding functions can be realized; in addition, the specific names of the functional modules are only for distinguishing from each other, and are not used for limiting the protection scope of the present application.
The application provides an optimized production control method of plastic products, wherein the method is applied to an optimized production control system of plastic products, and comprises the following steps: obtaining a plastic production instruction through a plastic production management end, wherein the plastic production instruction comprises plastic type expected characteristics and W plastic performance expected characteristics; carrying out associated batching index identification on W plastic performance expected characteristics according to a pre-constructed initial batching characteristic decision maker to obtain a plurality of associated batching indexes; initializing ingredients based on the expected characteristics of the plastic types and a plurality of associated ingredient indexes to obtain an initialized ingredient space; performing expected performance trigger prediction of an initialization batching space according to the expected performance trigger analysis function and the W plastic performance expected characteristics to obtain M expected performance triggers; screening the optimal expected performance trigger degrees according to the M expected performance trigger degrees, and judging whether the optimal expected performance trigger degrees meet the preset trigger degrees or not; if the optimal expected performance trigger degree does not meet the preset trigger degree, matching M initial batching results based on the optimal expected performance trigger degree to obtain screening initial batching results, and generating batching optimization instructions; activating a batching optimizing channel according to a batching optimizing instruction to optimize a screening initial batching result, obtaining an optimal batching result, and sending the optimal batching result to a plastic production management end. Solves the technical problems that the prior art can not carry out targeted batching according to the performance requirement of the plastic product, the batching accuracy of the plastic product is poor, and the production effect of the plastic product is poor. The technical effects of realizing targeted proportioning according to the performance requirements of plastic products, improving the proportioning accuracy of the plastic products, improving the proportioning effect of the plastic products and improving the production quality of the plastic products are achieved.
Although the invention has been described in more detail by means of the above embodiments, the invention is not limited to the above embodiments, but may comprise many other equivalent embodiments without departing from the inventive concept, the scope of which is determined by the scope of the appended claims.
Claims (8)
1. An optimized production control method for plastic products, which is characterized in that the method is applied to an optimized production control system for plastic products, the system is in communication connection with a plastic production management end, and the method comprises the following steps:
the plastic production management end is interacted to obtain a plastic production instruction, wherein the plastic production instruction comprises plastic type expected characteristics and W plastic performance expected characteristics, and W is a positive integer greater than 1;
carrying out associated batching index identification on the W plastic performance expected characteristics according to a pre-constructed initial batching characteristic decision maker to obtain a plurality of associated batching indexes;
initializing ingredients based on the expected characteristics of the plastic types and the plurality of associated ingredient indexes to obtain an initialized ingredient space, wherein the initialized ingredient space comprises M initial ingredient results, and M is a positive integer greater than 1;
Executing expected performance trigger prediction of the initialized material distribution space according to an expected performance trigger analysis function and the W plastic performance expected characteristics to obtain M expected performance trigger degrees;
screening optimal expected performance trigger degrees according to the M expected performance trigger degrees, and judging whether the optimal expected performance trigger degrees meet preset trigger degrees or not;
if the optimal expected performance trigger degree does not meet the preset trigger degree, matching the M initial batching results based on the optimal expected performance trigger degree to obtain screening initial batching results, and generating a batching optimization instruction;
and activating an ingredient optimizing channel based on the ingredient optimizing instruction to optimize the screening initial ingredient result, obtaining an optimal ingredient result, and sending the optimal ingredient result to the plastic production management end.
2. The method of claim 1, wherein the method comprises:
based on big data, obtaining a plastic batching index record library;
obtaining a preset building operator, wherein the preset building operator comprises taking a sample plastic performance expected index record as a batching index characteristic and taking a sample plastic batching index record as a batching index response characteristic;
And carrying out data fusion on the plastic batching index record library based on the preset construction operator to obtain an associated batching index identification map, and embedding the associated batching index identification map into the initial batching characteristic decision maker.
3. The method of claim 1, further comprising, after obtaining the plurality of associated ingredient indicators:
carrying out batch sequence influence identification on the plurality of associated batch indexes to generate batch sequence influence degree;
judging whether the influence degree of the batching sequence meets a preset influence constraint;
if the batching sequence influence degree does not meet the preset influence constraint, a batching index constraint instruction is obtained;
and executing optimization constraints of the plurality of associated ingredient indexes based on the ingredient index constraint instructions.
4. The method of claim 1, wherein performing the expected performance trigger prediction of the initialization recipe space based on an expected performance trigger analysis function and the W plastic performance expected characteristics to obtain M expected performance triggers comprises:
traversing the initialized batching space to obtain an mth initial batching result, wherein M is a positive integer, and M belongs to M;
based on the W plastic performance expected characteristics, W plastic performance expected indexes are obtained;
Taking the mth initial batching result as an mth retrieval constraint and taking the W plastic performance expected indexes as retrieval targets;
big data matching is carried out according to the mth retrieval constraint and the retrieval target, and a batching performance index record library is obtained, wherein the batching performance index record library comprises J batching performance index records, and J is a positive integer greater than 1;
analyzing the expected performance triggering degree of the ingredient performance index record base based on the expected performance triggering analysis function to obtain J ingredient record performance triggering degrees;
and carrying out average calculation on the J ingredient record performance triggering degrees to obtain an mth expected performance triggering degree corresponding to the mth initial ingredient result, and adding the mth expected performance triggering degree to the M expected performance triggering degrees.
5. The method of claim 4, wherein performing a desired performance trigger metric analysis on the ingredient performance index record library based on the desired performance trigger analysis function to obtain J ingredient record performance triggers comprises:
based on the batching performance index record library, a J-th batching performance index record is obtained, J is a positive integer, and J belongs to J;
inputting the J-th ingredient performance index record into the expected performance trigger analysis function, obtaining a J-th ingredient record performance trigger degree corresponding to the J-th ingredient performance index record, and adding the J-th ingredient record performance trigger degree to the J-th ingredient record performance trigger degrees, wherein the expected performance trigger analysis function is as follows:
；
；
Wherein,characterizing the j-th ingredient recording performance trigger level, +.>Representing the performance triggering degree of an ith index corresponding to an ith plastic performance expected index in a jth ingredient performance index record, wherein i is a positive integer, and the ith plastic performance expected index belongs to W, and comprises any one of W plastic performance expected indexes>Characterizing an i-th plastic property expected index record value corresponding to the i-th plastic property expected index in the j-th ingredient property index record,>characterizing the lower limit expectations corresponding to the ith plastic property expectations index,/->And characterizing the upper limit expectation corresponding to the ith plastic performance expectation index.
6. The method of claim 1, wherein obtaining optimal dosage results comprises:
obtaining W index performance confidence values corresponding to the screening initial batching results;
comparing the W index performance confidence values with the W plastic performance expected characteristics to obtain excitation optimization performance expected characteristics, and calculating excitation characteristic optimization coefficients corresponding to the excitation optimization performance expected characteristics;
inputting the excitation optimization performance expected characteristics, the excitation characteristic optimization coefficients and the screening initial batching results into the batching optimization channel to generate the optimal batching results.
7. The method of claim 6, wherein the method comprises:
obtaining a sample batching optimization record;
based on the BP neural network, obtaining an ingredient optimizing network;
training the batching optimization network according to the sample batching optimization record, and generating an output accurate operator when training is performed for preset times;
and when the output accurate operator meets the preset output accurate operator, generating the batching optimization channel.
8. An optimized production control system for plastic articles, characterized in that it is adapted to perform the method according to any one of claims 1 to 7, said system being in communicative connection with a plastic production management terminal, said system comprising:
the production instruction obtaining module is used for interacting the plastic production management end to obtain a plastic production instruction, wherein the plastic production instruction comprises plastic type expected characteristics and W plastic performance expected characteristics, and W is a positive integer greater than 1;
the associated batching index identification module is used for carrying out associated batching index identification on the W plastic performance expected characteristics according to a pre-built initial batching characteristic decision maker so as to obtain a plurality of associated batching indexes;
The initialization batching module is used for performing initialization batching based on the expected characteristics of the plastic types and the plurality of associated batching indexes to obtain an initialization batching space, wherein the initialization batching space comprises M initial batching results, and M is a positive integer greater than 1;
the expected performance trigger prediction module is used for executing expected performance trigger prediction of the initialized material distribution space according to an expected performance trigger analysis function and the W plastic performance expected characteristics to obtain M expected performance triggers;
the trigger degree judging module is used for screening the optimal expected performance trigger degree according to the M expected performance trigger degrees and judging whether the optimal expected performance trigger degree meets the preset trigger degree or not;
the optimization instruction generation module is used for matching the M initial batching results based on the optimal expected performance trigger degree if the optimal expected performance trigger degree does not meet the preset trigger degree, so as to obtain screening initial batching results and generate a batching optimization instruction;
and the ingredient optimizing module is used for activating an ingredient optimizing channel to optimize the screening initial ingredient result based on the ingredient optimizing instruction, obtaining an optimal ingredient result and sending the optimal ingredient result to the plastic production management end.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311295375.0A CN117035200B (en) | 2023-10-09 | 2023-10-09 | Optimized production control method and system for plastic products |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311295375.0A CN117035200B (en) | 2023-10-09 | 2023-10-09 | Optimized production control method and system for plastic products |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117035200A true CN117035200A (en) | 2023-11-10 |
| CN117035200B CN117035200B (en) | 2023-12-15 |
Family
ID=88641602
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311295375.0A Active CN117035200B (en) | 2023-10-09 | 2023-10-09 | Optimized production control method and system for plastic products |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117035200B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6757667B1 (en) * | 2000-04-12 | 2004-06-29 | Unilever Home & Personal Care Usa, Division Of Conopco, Inc. | Method for optimizing formulations |
| CN1520557A (en) * | 1999-09-03 | 2004-08-11 | Method of optimizing parameter values in process of producing product | |
| CN112101630A (en) * | 2020-08-19 | 2020-12-18 | 江苏师范大学 | Multi-target optimization method for injection molding process parameters of thin-wall plastic part |
| WO2022136228A1 (en) * | 2020-12-22 | 2022-06-30 | Sabic Global Technologies B.V. | Method for optimisation of the sustainability footprint of polymer formulations. |
| RU2776591C1 (en) * | 2012-07-04 | 2022-07-22 | Норск Хюдро Аса | Method for optimizing product properties and production costs in industrial processes |
-
2023
- 2023-10-09 CN CN202311295375.0A patent/CN117035200B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1520557A (en) * | 1999-09-03 | 2004-08-11 | Method of optimizing parameter values in process of producing product | |
| US6757667B1 (en) * | 2000-04-12 | 2004-06-29 | Unilever Home & Personal Care Usa, Division Of Conopco, Inc. | Method for optimizing formulations |
| RU2776591C1 (en) * | 2012-07-04 | 2022-07-22 | Норск Хюдро Аса | Method for optimizing product properties and production costs in industrial processes |
| CN112101630A (en) * | 2020-08-19 | 2020-12-18 | 江苏师范大学 | Multi-target optimization method for injection molding process parameters of thin-wall plastic part |
| WO2022136228A1 (en) * | 2020-12-22 | 2022-06-30 | Sabic Global Technologies B.V. | Method for optimisation of the sustainability footprint of polymer formulations. |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117035200B (en) | 2023-12-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Fei et al. | Practical applications of Taguchi method for optimization of processing parameters for plastic injection moulding: a retrospective review | |
| CN113119425B (en) | Injection product quality prediction method based on improved support vector machine | |
| CN108960303A (en) | A kind of unmanned plane during flying data exception detection method based on LSTM | |
| Abdul et al. | Shrinkage prediction of injection molded high density polyethylene parts with taguchi/artificial neural network hybrid experimental design | |
| CN106782510B (en) | Place name voice signal recognition method based on continuous Gaussian mixture HMM model | |
| CN111488946A (en) | Radar servo system fault diagnosis method based on information fusion | |
| CN117035200B (en) | Optimized production control method and system for plastic products | |
| CN111222575B (en) | KLXS multi-model fusion method and system based on HRRP target recognition | |
| CN113103535A (en) | GA-ELM-GA-based injection molding part mold parameter optimization method | |
| CN115237878A (en) | Process database construction method and medium based on additive manufacturing | |
| CN117140847B (en) | Packaging method and system for precision die | |
| Raissi | Developing new processes and optimizing performance using response surface methodology | |
| Shie | Optimization of injection molding process for contour distortions of polypropylene composite components by a radial basis neural network | |
| Post et al. | Determining damage initiation of carbon fiber reinforced polymer composites using machine learning | |
| CN116894379A (en) | Injection molding quality optimization method | |
| CN115762678A (en) | Polyester powder coating toughness classification prediction method based on material genome | |
| CN110245248A (en) | A kind of remote sensing image keyword query method | |
| CN107633009A (en) | A kind of Weakly supervised Document Classification Method based on mark confidence level | |
| CN108734213A (en) | A kind of batch process modal identification method based on bayesian statistical analysis | |
| CN111610514B (en) | Inversion method and device for propagation characteristics of evaporation waveguide | |
| Wang et al. | FCM algorithm and index CS for the signal sorting of radiant points | |
| CN110691319B (en) | Method for realizing high-precision indoor positioning of heterogeneous equipment in self-adaption mode in use field | |
| CN113780005B (en) | Semantic model-based Handle stock identification analysis method | |
| CN111695039A (en) | Personalized recommendation method based on multi-objective optimization | |
| CN109902378A (en) | Complex industrial process low cost modeling method based on multi-model migration and BMA theory |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |