CN114202262A - Prepreg process improvement method and system based on neural network and storage medium - Google Patents
Prepreg process improvement method and system based on neural network and storage medium Download PDFInfo
- Publication number
- CN114202262A CN114202262A CN202210154419.7A CN202210154419A CN114202262A CN 114202262 A CN114202262 A CN 114202262A CN 202210154419 A CN202210154419 A CN 202210154419A CN 114202262 A CN114202262 A CN 114202262A
- Authority
- CN
- China
- Prior art keywords
- raw material
- experiment
- neural network
- user side
- sheet
- 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
- 238000000034 method Methods 0.000 title claims abstract description 86
- 230000008569 process Effects 0.000 title claims abstract description 42
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 31
- 230000006872 improvement Effects 0.000 title claims abstract description 27
- 238000003860 storage Methods 0.000 title claims abstract description 22
- 239000002994 raw material Substances 0.000 claims abstract description 149
- 238000002474 experimental method Methods 0.000 claims abstract description 115
- 238000012545 processing Methods 0.000 claims abstract description 100
- 238000003062 neural network model Methods 0.000 claims abstract description 55
- 238000012549 training Methods 0.000 claims abstract description 50
- 238000004519 manufacturing process Methods 0.000 claims abstract description 49
- 230000005484 gravity Effects 0.000 claims description 7
- 238000005303 weighing Methods 0.000 claims description 7
- 230000000007 visual effect Effects 0.000 claims description 5
- 230000006978 adaptation Effects 0.000 abstract description 2
- 239000003795 chemical substances by application Substances 0.000 description 14
- 229920005989 resin Polymers 0.000 description 9
- 239000011347 resin Substances 0.000 description 9
- 238000002360 preparation method Methods 0.000 description 8
- 230000004044 response Effects 0.000 description 6
- 239000004744 fabric Substances 0.000 description 5
- 239000000835 fiber Substances 0.000 description 5
- 239000000463 material Substances 0.000 description 5
- 238000006243 chemical reaction Methods 0.000 description 4
- 239000003822 epoxy resin Substances 0.000 description 4
- 229920000647 polyepoxide Polymers 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 229920000049 Carbon (fiber) Polymers 0.000 description 3
- 229920006231 aramid fiber Polymers 0.000 description 3
- 239000004917 carbon fiber Substances 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000004069 differentiation Effects 0.000 description 3
- 239000003365 glass fiber Substances 0.000 description 3
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 239000002131 composite material Substances 0.000 description 2
- 238000004132 cross linking Methods 0.000 description 2
- 239000006185 dispersion Substances 0.000 description 2
- 230000008018 melting Effects 0.000 description 2
- 238000002844 melting Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 238000007711 solidification Methods 0.000 description 2
- 230000008023 solidification Effects 0.000 description 2
- 230000002950 deficient Effects 0.000 description 1
- 238000002715 modification method Methods 0.000 description 1
- 239000012779 reinforcing material Substances 0.000 description 1
- 229920005992 thermoplastic resin Polymers 0.000 description 1
- 229920001187 thermosetting polymer Polymers 0.000 description 1
Images
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
- G06Q10/06—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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/25—Integrating or interfacing systems involving database management systems
- G06F16/252—Integrating or interfacing systems involving database management systems between a Database Management System and a front-end application
-
- 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
- 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—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/04—Manufacturing
-
- 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
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Databases & Information Systems (AREA)
- Marketing (AREA)
- General Health & Medical Sciences (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Entrepreneurship & Innovation (AREA)
- Data Mining & Analysis (AREA)
- Primary Health Care (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Manufacturing & Machinery (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Moulding By Coating Moulds (AREA)
Abstract
The invention discloses a prepreg process improvement method, a prepreg process improvement system and a storage medium based on a neural network, and belongs to the field of prepreg processing, wherein the method comprises the following steps: acquiring user order information to match a raw material sheet, and generating an experiment data sheet and a processing data sheet based on the raw material sheet; extracting the experimental data list and outputting a training experiment table to a user; and extracting corresponding parameter values of the trained neural network model, and combining the processing data sheet to generate a processing production table to be output to the user side. The invention sets two categories of training experiment and processing production, utilizes the neural network model to carry out the training experiment to obtain each parameter up to the standard, further carries out specific processing production based on different parameters, can effectively guarantee the yield, and can carry out adaptation according to the requirements of different users.
Description
Technical Field
The invention relates to the technical field of prepreg processing, in particular to a prepreg process improvement method and system based on a neural network and a storage medium.
Background
The prepreg is an intermediate material for manufacturing a composite material, wherein resin is combined with fibers in advance before being cured, the service life of the prepreg is kept within a certain range, rows of layers can be laid and molded at any time within the service life range, and the prepreg is particularly used for manufacturing the composite material.
The prepreg is classified according to physical state, and is classified into unidirectional prepreg, unidirectional fabric prepreg and fabric prepreg; the prepreg is divided into thermosetting resin prepreg and thermoplastic resin prepreg according to different resin matrixes; according to different reinforcing materials, the prepreg is divided into carbon fiber (fabric) prepreg, glass fiber (fabric) prepreg and aramid fiber (fabric) prepreg; according to different fiber lengths, the prepreg is divided into short fiber prepreg, long fiber prepreg and continuous fiber prepreg; according to the curing temperature difference, divide into medium temperature solidification preimpregnation material, high temperature solidification preimpregnation material etc. and the different processing production standard of purchasing demand correspondence of user difference, but the majority is the manual differentiation among the prior art, and the defective percentage is difficult to can be ensured.
Disclosure of Invention
The invention aims to provide a prepreg process improvement method, a prepreg process improvement system and a storage medium based on a neural network, wherein a neural network model is used for training experiments to obtain various parameters reaching the standard, and further, specific processing production is carried out based on different parameters, so that the yield can be effectively guaranteed, and adaptation can be carried out according to the requirements of different users.
The invention provides a prepreg process improvement method based on a neural network, which comprises the following steps:
acquiring user order information to match a raw material sheet, and generating an experiment data sheet and a processing data sheet based on the raw material sheet;
extracting the experimental data list and outputting a training experiment table to a user side, wherein feedback data of the user side are obtained, and stress, temperature and curing parameters are changed by using a preset neural network model so as to update the training experiment table;
and after the output result of the training experiment reaches a preset standard, extracting the corresponding parameter values of the trained neural network model, and combining the processing data sheet to generate a processing production table to output the processing production table to the user side.
In this scheme, obtaining user order information and matching a raw material sheet, generating an experimental data sheet and a processing data sheet based on the raw material sheet, specifically include:
matching the user order information based on a preset raw material database and outputting the raw material list;
identifying the quantity grades of the raw materials of the current raw material list, wherein different quantity grades are matched with corresponding classification proportions;
and classifying the current raw material sheet according to the classification proportion to obtain the corresponding experimental data sheet and the corresponding processing data sheet.
In this scheme, the different quantity grades correspond to different classification proportions, and specifically include:
obtaining the raw material quantity grades based on the raw material type, the raw material specific gravity and the raw material weighing of the current raw material sheet, wherein the raw material quantity grades are divided into I grade, II grade and III grade;
the classification proportion corresponding to the raw material quantity grade I and the raw material quantity grade II is a first proportion, and the classification proportion corresponding to the raw material quantity grade III is a second proportion.
In this scheme, the extracting the experimental data list and outputting a training test table to a user side, wherein feedback data of the user side is obtained, and a preset neural network model is used to change stress, temperature and curing parameters, so as to update the training test table, and the method specifically includes:
outputting the corresponding training experiment table to the user side based on the experiment data sheet so as to carry out a prenatal experiment;
in the experimental process, the stress, the temperature and the curing parameters are updated by utilizing the neural network model through acquiring the feedback data of the user side, so that the training experiment table is continuously updated to be used by the user side for carrying out the prenatal experiment;
and stopping the prenatal experiment after the experiment result of the prenatal experiment is recognized to reach the preset standard, and recording the current parameter values of the neural network model.
In this scheme, after the output result of the experiment to be trained reaches the preset standard, extracting the corresponding parameter values of the trained neural network model, and generating a processing production table by combining the processing data sheet to output to the user side, specifically including:
when the antenatal experiment is ended, extracting each parameter value of the current neural network model as a first data packet;
and generating the processing production table based on the first data packet and the processing data sheet so as to output the processing production table to the user side for the user side to perform processing production.
In this scheme, the method further includes extracting the first data packet for visual display.
The second aspect of the present invention also provides a prepreg process improvement system based on a neural network, which includes a memory and a processor, wherein the memory includes a prepreg process improvement method program based on the neural network, and when executed by the processor, the prepreg process improvement method program based on the neural network realizes the following steps:
acquiring user order information to match a raw material sheet, and generating an experiment data sheet and a processing data sheet based on the raw material sheet;
extracting the experimental data list and outputting a training experiment table to a user side, wherein feedback data of the user side are obtained, and stress, temperature and curing parameters are changed by using a preset neural network model so as to update the training experiment table;
and after the output result of the training experiment reaches a preset standard, extracting the corresponding parameter values of the trained neural network model, and combining the processing data sheet to generate a processing production table to output the processing production table to the user side.
In this scheme, obtaining user order information and matching a raw material sheet, generating an experimental data sheet and a processing data sheet based on the raw material sheet, specifically include:
matching the user order information based on a preset raw material database and outputting the raw material list;
identifying the quantity grades of the raw materials of the current raw material list, wherein different quantity grades are matched with corresponding classification proportions;
and classifying the current raw material sheet according to the classification proportion to obtain the corresponding experimental data sheet and the corresponding processing data sheet.
In this scheme, the different quantity grades correspond to different classification proportions, and specifically include:
obtaining the raw material quantity grades based on the raw material type, the raw material specific gravity and the raw material weighing of the current raw material sheet, wherein the raw material quantity grades are divided into I grade, II grade and III grade;
the classification proportion corresponding to the raw material quantity grade I and the raw material quantity grade II is a first proportion, and the classification proportion corresponding to the raw material quantity grade III is a second proportion.
In this scheme, the extracting the experimental data list and outputting a training test table to a user side, wherein feedback data of the user side is obtained, and a preset neural network model is used to change stress, temperature and curing parameters, so as to update the training test table, and the method specifically includes:
outputting the corresponding training experiment table to the user side based on the experiment data sheet so as to carry out a prenatal experiment;
in the experimental process, the stress, the temperature and the curing parameters are updated by utilizing the neural network model through acquiring the feedback data of the user side, so that the training experiment table is continuously updated to be used by the user side for carrying out the prenatal experiment;
and stopping the prenatal experiment after the experiment result of the prenatal experiment is recognized to reach the preset standard, and recording the current parameter values of the neural network model.
In this scheme, after the output result of the experiment to be trained reaches the preset standard, extracting the corresponding parameter values of the trained neural network model, and generating a processing production table by combining the processing data sheet to output to the user side, specifically including:
when the antenatal experiment is ended, extracting each parameter value of the current neural network model as a first data packet;
and generating the processing production table based on the first data packet and the processing data sheet so as to output the processing production table to the user side for the user side to perform processing production.
In this scheme, the method further includes extracting the first data packet for visual display.
A third aspect of the invention provides a computer readable storage medium including a program of a neural network based prepreg process improvement method of a machine, which when executed by a processor implements the steps of a neural network based prepreg process improvement method as claimed in any one of the preceding claims.
The prepreg process improving method, the prepreg process improving system and the storage medium based on the neural network can automatically analyze raw material data based on user order information, classify the raw material data based on the raw material data, set two categories of a training experiment and a processing production, perform the training experiment by using the neural network model to obtain each parameter which reaches the standard, further perform the specific processing production based on different parameters, effectively guarantee the yield, and can be adapted according to the requirements of different users.
Drawings
FIG. 1 shows a flow diagram of a neural network based prepreg process modification method of the present invention;
fig. 2 shows a block diagram of a prepreg process improvement system based on a neural network according to the present invention.
Detailed Description
In order that the above objects, features and advantages of the present invention can be more clearly understood, a more particular description of the invention will be rendered by reference to the appended drawings. It should be noted that the embodiments and features of the embodiments of the present application may be combined with each other without conflict.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced in other ways than those specifically described herein, and therefore the scope of the present invention is not limited by the specific embodiments disclosed below.
Fig. 1 shows a flow chart of a prepreg process improvement method based on a neural network according to the present application.
As shown in fig. 1, the present application discloses a prepreg process improvement method based on a neural network, comprising the following steps:
s102, obtaining user order information to match a raw material sheet, and generating an experiment data sheet and a processing data sheet based on the raw material sheet;
s104, extracting the experimental data sheet and outputting a training experiment table to a user side, wherein feedback data of the user side are obtained, and stress, temperature and curing parameters are changed by using a preset neural network model so as to update the training experiment table;
and S106, after the output result of the training experiment reaches a preset standard, extracting corresponding parameter values of the trained neural network model, and combining the processing data sheet to generate a processing production table to be output to the user side.
According to the embodiment of the invention, the obtaining of the user order information matches with a raw material sheet, and the generating of the experimental data sheet and the processing data sheet based on the raw material sheet specifically comprises:
matching the user order information based on a preset raw material database and outputting the raw material list;
identifying the quantity grades of the raw materials of the current raw material list, wherein different quantity grades are matched with corresponding classification proportions;
and classifying the current raw material sheet according to the classification proportion to obtain the corresponding experimental data sheet and the corresponding processing data sheet.
It should be noted that after the user order information is obtained, the preset raw material database is used to match the order information to output the raw material sheet, the raw material sheet is made of, for example, glass fiber, carbon fiber or aramid fiber, and the corresponding classification proportion is matched based on the raw material quantity grade corresponding to the raw material sheet, wherein after the raw material sheet is classified based on the classification proportion, the experimental data sheet and the processing data sheet can be obtained by differentiation.
According to the embodiment of the present invention, the different quantity grades correspond to different classification proportions, and specifically include:
obtaining the raw material quantity grades based on the raw material type, the raw material specific gravity and the raw material weighing of the current raw material sheet, wherein the raw material quantity grades are divided into I grade, II grade and III grade;
the classification proportion corresponding to the raw material quantity grade I and the raw material quantity grade II is a first proportion, and the classification proportion corresponding to the raw material quantity grade III is a second proportion.
It should be noted that the raw material quantity grade may be specifically divided into the raw material type, the raw material specific gravity and the raw material weighing, and may be divided into a grade I, a grade II and a grade III based on different raw material quantity grades, where the classification ratio corresponding to the raw material quantity grade I and the raw material quantity grade II is a first ratio, for example, the ratio of the experimental raw material sheet to the processing raw material sheet is "1: 1000", and the classification ratio corresponding to the raw material quantity grade III is a second ratio, for example, the ratio of the experimental raw material sheet to the processing raw material sheet is "1: 800".
According to the embodiment of the invention, the extracting the experimental data list and outputting the training experiment table to a user side, wherein feedback data of the user side is obtained, and stress, temperature and curing parameters are changed by using a preset neural network model to update the training experiment table, and the method specifically comprises the following steps:
outputting the corresponding training experiment table to the user side based on the experiment data sheet so as to carry out a prenatal experiment;
in the experimental process, the stress, the temperature and the curing parameters are updated by utilizing the neural network model through acquiring the feedback data of the user side, so that the training experiment table is continuously updated to be used by the user side for carrying out the prenatal experiment;
and stopping the prenatal experiment after the experiment result of the prenatal experiment is recognized to reach the preset standard, and recording the current parameter values of the neural network model.
It should be noted that, during the prenatal experiment, the neural network model may be used to update various parameters in the experiment, including the stress, temperature and curing parameters, for example, the resin material is internally adjusted at 36-37 ℃ in summer and 30-32 ℃ in winter, the curing time does not exceed 90min, the results of the prenatal experiment are different by continuously adjusting parameters, then obtaining the feedback data of the user side after each update to continuously update until the experimental result of the prenatal experiment reaches the preset standard, the preset standard may be that the yield is higher than "98%", and therefore, when it is recognized that the yield in the experimental result of the pre-production experiment is higher than "98%", the pre-production experiment is stopped, and the current parameter values of the neural network model are recorded.
According to the embodiment of the present invention, after the output result of the experiment to be trained reaches the preset standard, extracting the corresponding parameter values of the trained neural network model, and generating a processing production table by combining the processing data sheet to output to the user side, specifically includes:
when the antenatal experiment is ended, extracting each parameter value of the current neural network model as a first data packet;
and generating the processing production table based on the first data packet and the processing data sheet so as to output the processing production table to the user side for the user side to perform processing production.
It should be noted that, in the prenatal experiment process, since each parameter value is to be adjusted after the feedback data is acquired, each parameter value is dynamically changed, and therefore, each parameter value corresponding to the termination of the prenatal experiment is a processing parameter that can match the requirement of the current user order information, and therefore, each parameter value of the current neural network model can be extracted and output as the first data packet, so that the user terminal performs processing and production based on the first data packet.
It is worth mentioning that the method further comprises extracting the first data packet for visual display.
It should be noted that, when the first data packet is output to the user side, it may also be visually displayed, and preferably, when the corresponding parameter is adjusted based on the neural network model, each parameter may also be visually displayed.
It should be noted that the method further includes identifying the processing response value in the user order information before the user order information is obtained and matched to the raw material sheet.
It should be noted that each factory distinguishes processing and preparation methods, wherein, the preparation method of the prepreg includes a dry method and a wet method, and therefore, before obtaining the user order information and matching the raw material sheet, a processing response value in the user order information needs to be identified, for example, a certain manufacturer a only has the capability of dry preparation and processing, but identifies that the corresponding processing response value is "dry + wet combination", so that the manufacturer a does not satisfy the processing and preparation conditions, that is, does not perform matching and output the corresponding raw material sheet.
It is worth mentioning that the method further comprises adjusting the curing parameters based on the user order information.
It should be noted that, when adjusting the curing parameters, not only the feedback data of the user terminal may be obtained to perform adjustment based on the neural network model, but also initial adjustment may be performed based on the user order information, for example: the prepreg required by a user needs to have a certain storage period at room temperature, so that a latent curing agent needs to be used as the curing agent corresponding to the curing parameter, so that the curing agent does not react with the resin at normal temperature and normal pressure, but under a special temperature and pressure, the resin is promoted to generate a crosslinking curing reaction so as to be beneficial to the storage of the prepreg at normal temperature, and further, the curing agent is usually a dispersion type curing agent, namely, the curing agent is solid at normal temperature, cannot be dissolved in the epoxy resin, but can be mixed with the epoxy resin when being heated to the vicinity of the melting point of the curing agent, so that the curing reaction can be rapidly generated.
Fig. 2 shows a block diagram of a prepreg process improvement system based on a neural network according to the present invention.
As shown in fig. 2, the present invention discloses a prepreg process improvement system based on a neural network, which includes a memory and a processor, wherein the memory includes a prepreg process improvement method program based on the neural network, and when executed by the processor, the prepreg process improvement method program based on the neural network implements the following steps:
acquiring user order information to match a raw material sheet, and generating an experiment data sheet and a processing data sheet based on the raw material sheet;
extracting the experimental data list and outputting a training experiment table to a user side, wherein feedback data of the user side are obtained, and stress, temperature and curing parameters are changed by using a preset neural network model so as to update the training experiment table;
and after the output result of the training experiment reaches a preset standard, extracting the corresponding parameter values of the trained neural network model, and combining the processing data sheet to generate a processing production table to output the processing production table to the user side.
According to the embodiment of the invention, the obtaining of the user order information matches with a raw material sheet, and the generating of the experimental data sheet and the processing data sheet based on the raw material sheet specifically comprises:
matching the user order information based on a preset raw material database and outputting the raw material list;
identifying the quantity grades of the raw materials of the current raw material list, wherein different quantity grades are matched with corresponding classification proportions;
and classifying the current raw material sheet according to the classification proportion to obtain the corresponding experimental data sheet and the corresponding processing data sheet.
It should be noted that after the user order information is obtained, the preset raw material database is used to match the order information to output the raw material sheet, the raw material sheet is made of, for example, glass fiber, carbon fiber or aramid fiber, and the corresponding classification proportion is matched based on the raw material quantity grade corresponding to the raw material sheet, wherein after the raw material sheet is classified based on the classification proportion, the experimental data sheet and the processing data sheet can be obtained by differentiation.
According to the embodiment of the present invention, the different quantity grades correspond to different classification proportions, and specifically include:
obtaining the raw material quantity grades based on the raw material type, the raw material specific gravity and the raw material weighing of the current raw material sheet, wherein the raw material quantity grades are divided into I grade, II grade and III grade;
the classification proportion corresponding to the raw material quantity grade I and the raw material quantity grade II is a first proportion, and the classification proportion corresponding to the raw material quantity grade III is a second proportion.
It should be noted that the raw material quantity grade may be specifically divided into the raw material type, the raw material specific gravity and the raw material weighing, and may be divided into a grade I, a grade II and a grade III based on different raw material quantity grades, where the classification ratio corresponding to the raw material quantity grade I and the raw material quantity grade II is a first ratio, for example, the ratio of the experimental raw material sheet to the processing raw material sheet is "1: 1000", and the classification ratio corresponding to the raw material quantity grade III is a second ratio, for example, the ratio of the experimental raw material sheet to the processing raw material sheet is "1: 800".
According to the embodiment of the invention, the extracting the experimental data list and outputting the training experiment table to a user side, wherein feedback data of the user side is obtained, and stress, temperature and curing parameters are changed by using a preset neural network model to update the training experiment table, and the method specifically comprises the following steps:
outputting the corresponding training experiment table to the user side based on the experiment data sheet so as to carry out a prenatal experiment;
in the experimental process, the stress, the temperature and the curing parameters are updated by utilizing the neural network model through acquiring the feedback data of the user side, so that the training experiment table is continuously updated to be used by the user side for carrying out the prenatal experiment;
and stopping the prenatal experiment after the experiment result of the prenatal experiment is recognized to reach the preset standard, and recording the current parameter values of the neural network model.
It should be noted that, during the prenatal experiment, the neural network model may be used to update various parameters in the experiment, including the stress, temperature and curing parameters, for example, the resin material is internally adjusted at 36-37 ℃ in summer and 30-32 ℃ in winter, the curing time does not exceed 90min, the results of the prenatal experiment are different by continuously adjusting parameters, then obtaining the feedback data of the user side after each update to continuously update until the experimental result of the prenatal experiment reaches the preset standard, the preset standard may be that the yield is higher than "98%", and therefore, when it is recognized that the yield in the experimental result of the pre-production experiment is higher than "98%", the pre-production experiment is stopped, and the current parameter values of the neural network model are recorded.
According to the embodiment of the present invention, after the output result of the experiment to be trained reaches the preset standard, extracting the corresponding parameter values of the trained neural network model, and generating a processing production table by combining the processing data sheet to output to the user side, specifically includes:
when the antenatal experiment is ended, extracting each parameter value of the current neural network model as a first data packet;
and generating the processing production table based on the first data packet and the processing data sheet so as to output the processing production table to the user side for the user side to perform processing production.
It should be noted that, in the prenatal experiment process, since each parameter value is to be adjusted after the feedback data is acquired, each parameter value is dynamically changed, and therefore, each parameter value corresponding to the termination of the prenatal experiment is a processing parameter that can match the requirement of the current user order information, and therefore, each parameter value of the current neural network model can be extracted and output as the first data packet, so that the user terminal performs processing and production based on the first data packet.
It is worth mentioning that the method further comprises extracting the first data packet for visual display.
It should be noted that, when the first data packet is output to the user side, it may also be visually displayed, and preferably, when the corresponding parameter is adjusted based on the neural network model, each parameter may also be visually displayed.
It should be noted that the method further includes identifying the processing response value in the user order information before the user order information is obtained and matched to the raw material sheet.
It should be noted that each factory distinguishes processing and preparation methods, wherein, the preparation method of the prepreg includes a dry method and a wet method, and therefore, before obtaining the user order information and matching the raw material sheet, a processing response value in the user order information needs to be identified, for example, a certain manufacturer a only has the capability of dry preparation and processing, but identifies that the corresponding processing response value is "dry + wet combination", so that the manufacturer a does not satisfy the processing and preparation conditions, that is, does not perform matching and output the corresponding raw material sheet.
It is worth mentioning that the method further comprises adjusting the curing parameters based on the user order information.
It should be noted that, when adjusting the curing parameters, not only the feedback data of the user terminal may be obtained to perform adjustment based on the neural network model, but also initial adjustment may be performed based on the user order information, for example: the prepreg required by a user needs to have a certain storage period at room temperature, so that a latent curing agent needs to be used as the curing agent corresponding to the curing parameter, so that the curing agent does not react with the resin at normal temperature and normal pressure, but under a special temperature and pressure, the resin is promoted to generate a crosslinking curing reaction so as to be beneficial to the storage of the prepreg at normal temperature, and further, the curing agent is usually a dispersion type curing agent, namely, the curing agent is solid at normal temperature, cannot be dissolved in the epoxy resin, but can be mixed with the epoxy resin when being heated to the vicinity of the melting point of the curing agent, so that the curing reaction can be rapidly generated.
A third aspect of the invention provides a computer readable storage medium, which includes a program of a method for improving a prepreg process based on a neural network, and when the program of the method is executed by a processor, the steps of the method for improving a prepreg process based on a neural network are realized.
The prepreg process improving method, the prepreg process improving system and the storage medium based on the neural network can automatically analyze raw material data based on user order information, classify the raw material data based on the raw material data, set two categories of a training experiment and a processing production, perform the training experiment by using the neural network model to obtain each parameter which reaches the standard, further perform the specific processing production based on different parameters, effectively guarantee the yield, and can be adapted according to the requirements of different users.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above-described device embodiments are merely illustrative, for example, the division of the unit is only a logical functional division, and there may be other division ways in actual implementation, such as: multiple units or components may be combined, or may be integrated into another system, or some features may be omitted, or not implemented. In addition, the coupling, direct coupling or communication connection between the components shown or discussed may be through some interfaces, and the indirect coupling or communication connection between the devices or units may be electrical, mechanical or other forms.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units; can be located in one place or distributed on a plurality of network units; some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, all the functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately regarded as one unit, or two or more units may be integrated into one unit; the integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional unit.
Those of ordinary skill in the art will understand that: all or part of the steps for realizing the method embodiments can be completed by hardware related to program instructions, the program can be stored in a computer readable storage medium, and the program executes the steps comprising the method embodiments when executed; and the aforementioned storage medium includes: a mobile storage device, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
Alternatively, the integrated unit of the present invention may be stored in a computer-readable storage medium if it is implemented in the form of a software functional module and sold or used as a separate product. Based on such understanding, the technical solutions of the embodiments of the present invention may be essentially implemented or a part contributing to the prior art may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the methods described in the embodiments of the present invention. And the aforementioned storage medium includes: a removable storage device, a ROM, a RAM, a magnetic or optical disk, or various other media that can store program code.
Claims (10)
1. A prepreg process improvement method based on a neural network is characterized by comprising the following steps:
acquiring user order information to match a raw material sheet, and generating an experiment data sheet and a processing data sheet based on the raw material sheet;
extracting the experimental data list and outputting a training experiment table to a user side, wherein feedback data of the user side are obtained, and stress, temperature and curing parameters are changed by using a preset neural network model so as to update the training experiment table;
and after the output result of the training experiment reaches a preset standard, extracting the corresponding parameter values of the trained neural network model, and combining the processing data sheet to generate a processing production table to output the processing production table to the user side.
2. The method according to claim 1, wherein the step of obtaining the user order information to match a raw material sheet, and the step of generating the experimental data sheet and the processing data sheet based on the raw material sheet specifically includes:
matching the user order information based on a preset raw material database and outputting the raw material list;
identifying the quantity grades of the raw materials of the current raw material list, wherein different quantity grades are matched with corresponding classification proportions;
and classifying the current raw material sheet according to the classification proportion to obtain the corresponding experimental data sheet and the corresponding processing data sheet.
3. The method according to claim 2, wherein the different number grades correspond to different classification ratios, and specifically comprises:
obtaining the raw material quantity grades based on the raw material type, the raw material specific gravity and the raw material weighing of the current raw material sheet, wherein the raw material quantity grades are divided into I grade, II grade and III grade;
the classification proportion corresponding to the raw material quantity grade I and the raw material quantity grade II is a first proportion, and the classification proportion corresponding to the raw material quantity grade III is a second proportion.
4. The method according to claim 2, wherein the extracting the experimental data list outputs a training experiment table to a user side, wherein feedback data of the user side is obtained, and the stress, the temperature and the curing parameters are changed by using a preset neural network model to update the training experiment table, and specifically comprises:
outputting the corresponding training experiment table to the user side based on the experiment data sheet so as to carry out a prenatal experiment;
in the experimental process, the stress, the temperature and the curing parameters are updated by utilizing the neural network model through acquiring the feedback data of the user side, so that the training experiment table is continuously updated to be used by the user side for carrying out the prenatal experiment;
and stopping the prenatal experiment after the experiment result of the prenatal experiment is recognized to reach the preset standard, and recording the current parameter values of the neural network model.
5. The method according to claim 4, wherein after the output result of the experiment to be trained reaches a preset standard, extracting corresponding parameter values of the trained neural network model, and generating a processing production table in combination with the processing data sheet to output the processing production table to the user side, specifically comprises:
when the antenatal experiment is ended, extracting each parameter value of the current neural network model as a first data packet;
and generating the processing production table based on the first data packet and the processing data sheet so as to output the processing production table to the user side for the user side to perform processing production.
6. The method for improving the prepreg technology based on the neural network as claimed in claim 5, wherein the method further comprises extracting the first data packet for visual display.
7. A prepreg process improvement system based on a neural network is characterized by comprising a memory and a processor, wherein the memory comprises a prepreg process improvement method program based on the neural network, and the prepreg process improvement method program based on the neural network realizes the following steps when being executed by the processor:
acquiring user order information to match a raw material sheet, and generating an experiment data sheet and a processing data sheet based on the raw material sheet;
extracting the experimental data list and outputting a training experiment table to a user side, wherein feedback data of the user side are obtained, and stress, temperature and curing parameters are changed by using a preset neural network model so as to update the training experiment table;
and after the output result of the training experiment reaches a preset standard, extracting the corresponding parameter values of the trained neural network model, and combining the processing data sheet to generate a processing production table to output the processing production table to the user side.
8. The prepreg process improvement system based on the neural network as claimed in claim 7, wherein the obtaining of the user order information matches a raw material sheet, and the generating of the experimental data sheet and the processing data sheet based on the raw material sheet specifically includes:
matching the user order information based on a preset raw material database and outputting the raw material list;
identifying the quantity grades of the raw materials of the current raw material list, wherein different quantity grades are matched with corresponding classification proportions;
and classifying the current raw material sheet according to the classification proportion to obtain the corresponding experimental data sheet and the corresponding processing data sheet.
9. The system of claim 8, wherein the extracting of the experimental data is performed to output a training experiment table to a user side, wherein feedback data of the user side is obtained, and the stress, temperature and curing parameters are changed by using a preset neural network model to update the training experiment table, and specifically comprises:
outputting the corresponding training experiment table to the user side based on the experiment data sheet so as to carry out a prenatal experiment;
in the experimental process, the stress, the temperature and the curing parameters are updated by utilizing the neural network model through acquiring the feedback data of the user side, so that the training experiment table is continuously updated to be used by the user side for carrying out the prenatal experiment;
and stopping the prenatal experiment after the experiment result of the prenatal experiment reaches the preset standard, and recording the current parameter values of the neural network model.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium comprises a neural network-based prepreg process improvement method program, which when executed by a processor, implements the steps of a neural network-based prepreg process improvement method as claimed in any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210154419.7A CN114202262B (en) | 2022-02-21 | 2022-02-21 | Prepreg process improvement method and system based on neural network and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210154419.7A CN114202262B (en) | 2022-02-21 | 2022-02-21 | Prepreg process improvement method and system based on neural network and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114202262A true CN114202262A (en) | 2022-03-18 |
| CN114202262B CN114202262B (en) | 2022-07-01 |
Family
ID=80645718
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210154419.7A Active CN114202262B (en) | 2022-02-21 | 2022-02-21 | Prepreg process improvement method and system based on neural network and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114202262B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115454171A (en) * | 2022-08-30 | 2022-12-09 | 海尔优家智能科技（北京）有限公司 | Intelligent device and defogging method, device and medium thereof |
| CN116797053A (en) * | 2023-08-25 | 2023-09-22 | 深圳普菲特信息科技股份有限公司 | Chemical production data analysis method, system and medium based on neural network |
Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105479771A (en) * | 2015-12-30 | 2016-04-13 | 吉林大学 | Manufacturing method for carbon fiber composite plate and self-punching riveting die and method for carbon fiber composite plate and aluminum alloy plate |
| CN106371409A (en) * | 2016-08-27 | 2017-02-01 | 绍兴兴明染整有限公司 | Dyeing and finishing production line management system and management method |
| CN109234661A (en) * | 2018-09-21 | 2019-01-18 | 北京联合涂层技术有限公司 | A kind of heat spraying method and system based on artificial neural network |
| CN109472358A (en) * | 2018-10-17 | 2019-03-15 | 深圳市微埃智能科技有限公司 | Welding condition recommended method, device and robot neural network based |
| CN110232255A (en) * | 2019-06-24 | 2019-09-13 | 南京航空航天大学 | A kind of method of carbon fibre reinforced composite drilling axial force prediction |
| CN111461398A (en) * | 2020-02-27 | 2020-07-28 | 季华实验室 | Welding process parameter optimization method and device and readable storage medium |
| US20200272129A1 (en) * | 2019-02-27 | 2020-08-27 | The Boeing Company | Object design using machine-learning model |
| CN112180720A (en) * | 2020-09-08 | 2021-01-05 | 武汉大学 | Fiber placement process parameter model construction method and system based on simulation learning |
| CN112257342A (en) * | 2020-10-20 | 2021-01-22 | 李�杰 | Neural network laser cutting quality prediction method |
| CN112529618A (en) * | 2020-12-02 | 2021-03-19 | 恒宝股份有限公司 | Intelligent manufacturing system and method for carbon fiber and composite material |
| CN112632813A (en) * | 2020-12-03 | 2021-04-09 | 浙江大学 | Optimization method of curing system of large-thickness resin-based composite material |
| CN113168891A (en) * | 2018-09-14 | 2021-07-23 | 西北大学 | Data-driven representation and clustering discretization method and system for design optimization and/or performance prediction of material systems and application thereof |
| WO2021191254A1 (en) * | 2020-03-27 | 2021-09-30 | Flooring Technologies Ltd. | Method for simultaneously determining parameters of at least one resin layer applied to at least one carrier material |
| CN113536619A (en) * | 2021-05-24 | 2021-10-22 | 天津中德应用技术大学 | Method for optimizing compression molding process parameters of carbon fiber reinforced composite material |
| CN113592288A (en) * | 2021-07-28 | 2021-11-02 | 成都飞机工业（集团）有限责任公司 | Blanking plan scheduling method based on non-equivalent parallel machine model |
| CN113761680A (en) * | 2021-09-01 | 2021-12-07 | 江苏科技大学 | Parameter design method for winding process of composite material vertical pipe |
| CN113919601A (en) * | 2021-12-09 | 2022-01-11 | 山东捷瑞数字科技股份有限公司 | Resin process prediction method and device based on product performance and process data model |
-
2022
- 2022-02-21 CN CN202210154419.7A patent/CN114202262B/en active Active
Patent Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105479771A (en) * | 2015-12-30 | 2016-04-13 | 吉林大学 | Manufacturing method for carbon fiber composite plate and self-punching riveting die and method for carbon fiber composite plate and aluminum alloy plate |
| CN106371409A (en) * | 2016-08-27 | 2017-02-01 | 绍兴兴明染整有限公司 | Dyeing and finishing production line management system and management method |
| CN113168891A (en) * | 2018-09-14 | 2021-07-23 | 西北大学 | Data-driven representation and clustering discretization method and system for design optimization and/or performance prediction of material systems and application thereof |
| CN109234661A (en) * | 2018-09-21 | 2019-01-18 | 北京联合涂层技术有限公司 | A kind of heat spraying method and system based on artificial neural network |
| CN109472358A (en) * | 2018-10-17 | 2019-03-15 | 深圳市微埃智能科技有限公司 | Welding condition recommended method, device and robot neural network based |
| CN111625898A (en) * | 2019-02-27 | 2020-09-04 | 波音公司 | Object design using machine learning models |
| US20200272129A1 (en) * | 2019-02-27 | 2020-08-27 | The Boeing Company | Object design using machine-learning model |
| CN110232255A (en) * | 2019-06-24 | 2019-09-13 | 南京航空航天大学 | A kind of method of carbon fibre reinforced composite drilling axial force prediction |
| CN111461398A (en) * | 2020-02-27 | 2020-07-28 | 季华实验室 | Welding process parameter optimization method and device and readable storage medium |
| WO2021191254A1 (en) * | 2020-03-27 | 2021-09-30 | Flooring Technologies Ltd. | Method for simultaneously determining parameters of at least one resin layer applied to at least one carrier material |
| CN112180720A (en) * | 2020-09-08 | 2021-01-05 | 武汉大学 | Fiber placement process parameter model construction method and system based on simulation learning |
| CN112257342A (en) * | 2020-10-20 | 2021-01-22 | 李�杰 | Neural network laser cutting quality prediction method |
| CN112529618A (en) * | 2020-12-02 | 2021-03-19 | 恒宝股份有限公司 | Intelligent manufacturing system and method for carbon fiber and composite material |
| CN112632813A (en) * | 2020-12-03 | 2021-04-09 | 浙江大学 | Optimization method of curing system of large-thickness resin-based composite material |
| CN113536619A (en) * | 2021-05-24 | 2021-10-22 | 天津中德应用技术大学 | Method for optimizing compression molding process parameters of carbon fiber reinforced composite material |
| CN113592288A (en) * | 2021-07-28 | 2021-11-02 | 成都飞机工业（集团）有限责任公司 | Blanking plan scheduling method based on non-equivalent parallel machine model |
| CN113761680A (en) * | 2021-09-01 | 2021-12-07 | 江苏科技大学 | Parameter design method for winding process of composite material vertical pipe |
| CN113919601A (en) * | 2021-12-09 | 2022-01-11 | 山东捷瑞数字科技股份有限公司 | Resin process prediction method and device based on product performance and process data model |
Non-Patent Citations (5)
| Title |
|---|
| BO DENG等: ""Modeling and Optimizing the Composite Prepreg Tape Winding Process Based on Grey Relational Analysis Coupled with BP Neural Network and Bat Algorithm"", 《NANOSCALE RESEARCH LETTERS》 * |
| JIATONG HOU等: ""Prediction of curing process for thermosetting prepreg compression molding process based on machine learning"", 《HTTPS://ONLINELIBRARY.WILEY.COM/DOI/ABS/10.1002/PC.26494》 * |
| 俞涛等: "复合材料带缠绕成型过程建模及工艺参数优化", 《固体火箭技术》 * |
| 元振毅等: ""基于多场耦合方法的厚截面复合材料固化过程的多目标优化"", 《复合材料学报》 * |
| 康超: ""预浸带缠绕成型筒形件关键性能建模及其工艺参数优化设计"", 《中国优秀硕士学位论文全文数据库 工程科技I辑》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115454171A (en) * | 2022-08-30 | 2022-12-09 | 海尔优家智能科技（北京）有限公司 | Intelligent device and defogging method, device and medium thereof |
| CN116797053A (en) * | 2023-08-25 | 2023-09-22 | 深圳普菲特信息科技股份有限公司 | Chemical production data analysis method, system and medium based on neural network |
| CN116797053B (en) * | 2023-08-25 | 2023-11-10 | 深圳普菲特信息科技股份有限公司 | Chemical production data analysis method, system and medium based on neural network |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114202262B (en) | 2022-07-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114202262B (en) | Prepreg process improvement method and system based on neural network and storage medium | |
| CN104978957A (en) | Voice control method and system based on voiceprint identification | |
| CN105301383A (en) | Vehicle detection method and system | |
| CN105024997A (en) | Method and device for associating control terminal with controlled terminal | |
| CN103150584A (en) | Communication resource motion processing method and system | |
| CN105243545A (en) | Multi-platform resource processing method and device | |
| CN104156796A (en) | Method and system for managing production line of MAC (Media Access Control) address on Internet set top box | |
| CN110322143B (en) | Model materialization management method, device, equipment and computer storage medium | |
| CN105045927A (en) | Automatic coding method and system for data of labor, materials and machines of construction project | |
| CN104898440A (en) | Household electrical appliance control method and apparatus | |
| CN106557410A (en) | User behavior analysis method and apparatus based on artificial intelligence | |
| CN109615196A (en) | A kind of production line administrative system | |
| CN107742520B (en) | Voice control method, device and system | |
| CN115600998A (en) | Process management method, system and readable storage medium based on production management platform | |
| CN113506016A (en) | Customized intelligent manufacturing service system based on Internet | |
| CN109427450A (en) | Dynamic print anti-fake two-dimension code production technology on cable | |
| CN109286928B (en) | Method for reasonably distributing virtual SIM cards for equipment | |
| CN112235602A (en) | Personalized screen protection system and method of smart television and smart television | |
| CN116915816A (en) | CAN signal data customized acquisition method and device | |
| CN110955165A (en) | Control method of cleaning equipment and cleaning equipment | |
| CN107681749A (en) | The recognition methods of mobile terminal safe charging and system | |
| CN115689403A (en) | Method and device for constructing risk evaluation model of distribution network equipment | |
| CN111580857B (en) | Equipment firmware online configuration method, device and system | |
| CN114239534A (en) | Document template selection method, device and equipment | |
| CN111703338A (en) | BIM-based catenary cantilever pre-configuration method and device |
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 |