CN118014442B - Quality evaluation method and system for blending type interpenetrating network thermoplastic elastomer - Google Patents
Quality evaluation method and system for blending type interpenetrating network thermoplastic elastomer Download PDFInfo
- Publication number
- CN118014442B CN118014442B CN202410416225.9A CN202410416225A CN118014442B CN 118014442 B CN118014442 B CN 118014442B CN 202410416225 A CN202410416225 A CN 202410416225A CN 118014442 B CN118014442 B CN 118014442B
- Authority
- CN
- China
- Prior art keywords
- quality
- sampling
- production
- historical
- sampling inspection
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 45
- 238000013441 quality evaluation Methods 0.000 title claims abstract description 44
- 229920002725 thermoplastic elastomer Polymers 0.000 title claims abstract description 42
- 238000002156 mixing Methods 0.000 title abstract description 18
- 238000005070 sampling Methods 0.000 claims abstract description 362
- 238000004519 manufacturing process Methods 0.000 claims abstract description 230
- 238000007689 inspection Methods 0.000 claims abstract description 226
- 238000001514 detection method Methods 0.000 claims abstract description 164
- 229920001971 elastomer Polymers 0.000 claims abstract description 67
- 239000000806 elastomer Substances 0.000 claims abstract description 67
- 238000012545 processing Methods 0.000 claims abstract description 36
- 238000004458 analytical method Methods 0.000 claims abstract description 27
- 230000002159 abnormal effect Effects 0.000 claims description 43
- 238000009966 trimming Methods 0.000 claims description 19
- 238000004364 calculation method Methods 0.000 claims description 13
- 238000005457 optimization Methods 0.000 claims description 12
- 238000001303 quality assessment method Methods 0.000 claims description 9
- 230000007423 decrease Effects 0.000 claims description 5
- 230000002452 interceptive effect Effects 0.000 claims description 5
- 230000006978 adaptation Effects 0.000 claims description 4
- 238000011077 uniformity evaluation Methods 0.000 claims description 4
- 230000000694 effects Effects 0.000 abstract description 8
- 238000012795 verification Methods 0.000 description 10
- 238000012549 training Methods 0.000 description 7
- 230000005856 abnormality Effects 0.000 description 6
- 238000013527 convolutional neural network Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 238000004220 aggregation Methods 0.000 description 3
- 230000002776 aggregation Effects 0.000 description 3
- 230000003247 decreasing effect Effects 0.000 description 3
- 239000000203 mixture Substances 0.000 description 3
- 238000012163 sequencing technique Methods 0.000 description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000011176 pooling Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000001816 cooling Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000001131 transforming effect Effects 0.000 description 1
- 239000002699 waste material Substances 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
- G06Q10/06—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
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- 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
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/27—Regression, e.g. linear or logistic regression
-
- 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)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Strategic Management (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- General Health & Medical Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Primary Health Care (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Manufacturing & Machinery (AREA)
- Biomedical Technology (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Automatic Analysis And Handling Materials Therefor (AREA)
Abstract
The application provides a quality evaluation method and a system of a blending type interpenetrating network thermoplastic elastomer, which relate to the technical field of quality evaluation, and the method comprises the following steps: obtaining M elastomer production data sets; traversing production and processing data of M production lines, and configuring a historical quality sampling inspection scheme library; fine tuning and optimizing the historical quality sampling inspection scheme library to obtain a target quality sampling inspection scheme; sampling quality detection is carried out on the production products of the current production task by utilizing a target quality sampling detection scheme, and a sampling quality detection result is obtained; and carrying out bias analysis on the sampling quality detection result to obtain a quality evaluation result of the target elastomer. The application can solve the technical problem of inaccurate quality detection result obtained by sampling detection caused by poor coincidence degree of quality detection of the elastomer and actual conditions of a production line in the prior art, finally realizes the technical aim of improving the accuracy of the quality detection result, and achieves the technical effect of improving the quality detection efficiency.
Description
Technical Field
The application relates to the technical field of quality evaluation, in particular to a quality evaluation method and a quality evaluation system for a blending type interpenetrating network thermoplastic elastomer.
Background
Quality assessment of the blended interpenetrating network thermoplastic elastomer is used to determine whether the quality of the product of the blended interpenetrating network thermoplastic elastomer meets established requirements or criteria. The quality performance, reliability, durability, safety and the like of the blended interpenetrating network thermoplastic elastomer are evaluated by collecting and analyzing the data of the blended interpenetrating network thermoplastic elastomer.
At present, the quality evaluation of the existing blending type interpenetrating network thermoplastic elastomer is usually carried out according to a conventional evaluation method, the production conditions of different production lines are ignored, the degree of coincidence of the evaluation result with the actual condition of the production line of the blending type interpenetrating network thermoplastic elastomer is poor, the quality detection result is inaccurate, the cost of secondary quality detection is increased, and the resource waste is caused. Accordingly, there is a need for a method to solve the above-mentioned problems.
In summary, in the prior art, the quality evaluation of the thermoplastic elastomer of the blend interpenetrating network and the actual condition of the production line of the thermoplastic elastomer of the blend interpenetrating network have poor conformity, which results in inaccurate quality detection results and causes the technical problems of increased cost of secondary quality detection and reduced efficiency of quality detection.
Disclosure of Invention
The application aims to provide a quality evaluation method and a quality evaluation system for a blending type interpenetrating network thermoplastic elastomer, which are used for solving the technical problems of increased cost and reduced efficiency of quality detection caused by inaccurate quality detection result due to poor conformity degree of the quality evaluation of the blending type interpenetrating network thermoplastic elastomer and the actual condition of a production line of the blending type interpenetrating network thermoplastic elastomer in the prior art.
In view of the above, the present application provides a method and system for quality assessment of a blended interpenetrating network thermoplastic elastomer.
In a first aspect, the present application provides a method for quality assessment of a blended interpenetrating network thermoplastic elastomer, the method being implemented by a quality assessment system of a blended interpenetrating network thermoplastic elastomer, wherein the method comprises: m production lines of the interactive target elastomer are used for obtaining M elastomer production data sets; traversing the production and processing data of the M production lines in a preset history window, and configuring a history quality spot check scheme library; fine tuning and optimizing the historical quality sampling inspection scheme library based on the quality feedback information to obtain a target quality sampling inspection scheme; sampling quality detection is carried out on the production products of the current production task by utilizing the target quality sampling detection scheme, and a sampling quality detection result is obtained; and carrying out bias analysis on the sampling quality detection result to obtain a quality evaluation result of the target elastomer.
In a second aspect, the present application also provides a quality assessment system of a blended interpenetrating network thermoplastic elastomer for performing a quality assessment method of a blended interpenetrating network thermoplastic elastomer according to the first aspect, wherein the system comprises: the system comprises M elastomer production data set acquisition modules, a control module and a control module, wherein the M elastomer production data set acquisition modules are used for interacting M production lines of a target elastomer to acquire M elastomer production data sets; the historical quality sampling inspection scheme library configuration module is used for traversing the production and processing data of the M production lines in a preset historical window and configuring a historical quality sampling inspection scheme library; the target quality sampling inspection scheme obtaining module is used for carrying out fine adjustment and optimization on the historical quality sampling inspection scheme base based on quality feedback information to obtain a target quality sampling inspection scheme; the sampling quality detection result obtaining module is used for carrying out sampling quality detection on the production product of the current production task by utilizing the target quality sampling detection scheme to obtain a sampling quality detection result; and the quality evaluation result obtaining module is used for carrying out bias analysis on the sampling quality detection result to obtain the quality evaluation result of the target elastomer.
One or more technical schemes provided by the application have at least the following technical effects or advantages:
Obtaining M elastomer production data sets through M production lines of the interactive target elastomer; traversing the production and processing data of the M production lines in a preset history window, and configuring a history quality spot check scheme library; fine tuning and optimizing the historical quality sampling inspection scheme library based on the quality feedback information to obtain a target quality sampling inspection scheme; sampling quality detection is carried out on the production products of the current production task by utilizing the target quality sampling detection scheme, and a sampling quality detection result is obtained; and carrying out bias analysis on the sampling quality detection result to obtain a quality evaluation result of the target elastomer, namely, improving the coincidence degree of a sampling detection quality sampling detection scheme and the actual condition of a production line, finally realizing the technical aim of improving the accuracy of the sampling detection obtained quality detection result and achieving the technical effect of improving the quality detection efficiency.
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. It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the application or to delineate the scope of the application. Other features of the present application will become apparent from the description that follows.
Drawings
In order to more clearly illustrate the application or the technical solutions of the prior art, the following brief description will be given of the drawings used in the description of the embodiments or the prior art, it being obvious that the drawings in the description below are only exemplary and that other drawings can be obtained from the drawings provided without the inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a method for evaluating the quality of a thermoplastic elastomer of a blended interpenetrating network of the present application;
FIG. 2 is a schematic diagram of a quality assessment system for a blended interpenetrating network thermoplastic elastomer of the application.
Reference numerals illustrate:
the system comprises M elastomer production data set obtaining modules 11, a historical quality sampling inspection scheme library configuration module 12, a target quality sampling inspection scheme obtaining module 13, a sampling quality detection result obtaining module 14 and a quality evaluation result obtaining module 15.
Detailed Description
The quality evaluation method and the system for the thermoplastic elastomer of the blending type interpenetrating network solve the technical problems of inaccurate quality detection result, increased cost of secondary quality detection and reduced efficiency of quality detection caused by poor conformity degree of the quality evaluation of the thermoplastic elastomer of the blending type interpenetrating network and the actual condition of a production line of the thermoplastic elastomer of the blending type interpenetrating network in the prior art. The technical aim of improving the accuracy of quality detection results obtained by sampling detection is finally realized by improving the coincidence degree of the quality sampling detection scheme of the sampling detection and the actual conditions of the production line, and the technical effect of improving the efficiency of the quality detection is achieved.
In the following, the technical solutions of the present application will be clearly and completely described with reference to the accompanying drawings, and it should be understood that the described embodiments are only some embodiments of the present application, but not all embodiments of the present application, and that the present application is not limited by the exemplary embodiments described herein. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application. It should be further noted that, for convenience of description, only some, but not all of the drawings related to the present application are shown.
Example 1
Referring to fig. 1, the application provides a quality evaluation method of a blending type interpenetrating network thermoplastic elastomer, wherein the method is applied to a quality evaluation system of the blending type interpenetrating network thermoplastic elastomer, and the method specifically comprises the following steps:
step one: m production lines of the interactive target elastomer are used for obtaining M elastomer production data sets;
Specifically, the target elastomer is a blended interpenetrating network thermoplastic elastomer to be subjected to quality evaluation. The production lines of the target elastomer are one complete production process, for example, each production line comprises processes of batching, mixing, extruding, cooling and the like. The production line for the target elastomer is configured as M production lines, where M is an integer greater than 1 since at least one production line is included. According to the M production lines, M production data corresponding to production in the M production lines, namely the production quantity, are obtained and used as M elastomer production data sets.
Step two: traversing the production and processing data of the M production lines in a preset history window, and configuring a history quality spot check scheme library;
Specifically, the preset history window is a time window in which a preset extraction is performed for the time of the history production, for example, the preset history window is the past one week time or the past one day time. Further, the production processing data is the production quantity of the elastomer. For example, the production process data within the preset history window is the number of elastomer production in the past day. And configuring a historical quality sampling inspection scheme library according to the ratio of the production processing data of each production line to the production processing data of M production lines in a preset historical window.
Step three: fine tuning and optimizing the historical quality sampling inspection scheme library based on the quality feedback information to obtain a target quality sampling inspection scheme;
specifically, the quality feedback information is the finished product quality feedback information obtained by producing the finished product of the obtained blend-type interpenetrating network thermoplastic elastomer. For example, the quality feedback information is feedback information of the buyer, or the like. Further, the quality feedback information is obtained to carry out fine adjustment optimization on the historical quality sampling inspection scheme library, wherein the greater the abnormality degree of the quality feedback information is, the greater the fine adjustment degree of fine adjustment optimization is, otherwise, the less the fine adjustment degree is, and then the target quality sampling inspection scheme is obtained.
Step four: sampling quality detection is carried out on the production products of the current production task by utilizing the target quality sampling detection scheme, and a sampling quality detection result is obtained;
specifically, the elastomer of the product of the current production task is subjected to sampling inspection according to the sampling inspection quantity of the target quality sampling inspection scheme, and then sampling quality detection is carried out, so that a sampling quality detection result is obtained. For example, the sampling quality detection is to detect defects of the elastic body, or the like.
Step five: and carrying out bias analysis on the sampling quality detection result to obtain a quality evaluation result of the target elastomer.
Specifically, a sampling quality detection result average value and a sampling quality detection result median value are obtained by calculating the sampling quality detection result, and the sampling quality detection result with higher deviation is used as a quality evaluation result of the target elastomer. Wherein, when the more other sampling quality detection results are near the sampling quality detection result, the higher the bias of the sampling quality detection result is, and conversely, the lower the bias is.
The quality evaluation method of the blending type interpenetrating network thermoplastic elastomer is applied to a quality evaluation system of the blending type interpenetrating network thermoplastic elastomer, and the technical aim of improving the accuracy of quality detection results obtained by sampling detection can be finally realized by improving the coincidence degree of a sampling detection quality sampling detection scheme and the actual condition of a production line, so that the technical effect of improving the efficiency of quality detection is achieved.
Further, the application also comprises the following steps:
Taking the historical quality sampling inspection scheme as an index, and searching the production and processing data to obtain a historical quality sampling inspection scheme set;
Performing uniformity evaluation on the historical quality sampling inspection scheme set to obtain Q historical sampling inspection uniformity factors;
Judging whether the Q historical sampling inspection uniformity factors meet preset sampling inspection uniformity factors, if so, storing the Q historical sampling inspection uniformity factors into the historical quality sampling inspection scheme library.
Specifically, the historical quality sampling inspection scheme of the historical time is used as an index, namely the historical quality sampling inspection scheme is used as a search target, the production and processing data of the historical time is searched, and the historical quality sampling inspection scheme obtained through searching is used as a historical quality sampling inspection scheme set. For example, historical quality spot check schemes include spot check line and corresponding spot check number schemes.
And then, judging whether the sampling inspection coefficient meets the production coefficient by calculating the sampling inspection coefficient of the production line, if the sampling inspection coefficient meets the corresponding production coefficient, calculating the ratio of the number of the production lines with the sampling inspection coefficient meeting the production coefficient to the number M of M production lines, and taking the ratio result as Q historical sampling inspection uniformity factors, wherein Q is an integer larger than 1.
And then, presetting a sampling inspection uniformity factor to obtain a preset sampling inspection uniformity factor. The preset sampling inspection uniformity factor is obtained by the user-defined setting of the person skilled in the art according to the actual situation, wherein the higher the preset sampling inspection uniformity factor is, the closer the sampling inspection coefficient is to the production coefficient, and the better the obtained sampling inspection scheme is, for example, the preset sampling inspection uniformity factor is 1/3 or 1/2. Further, judging whether the Q historical sampling inspection uniformity factors meet the preset sampling inspection uniformity factors, if the Q historical sampling inspection uniformity factors meet the preset sampling inspection uniformity factors, extracting the historical sampling inspection uniformity factors meeting the preset sampling inspection uniformity factors from the Q historical sampling inspection uniformity factors, and storing the obtained P historical quality sampling inspection schemes into a historical quality sampling inspection scheme library. Wherein P is an integer greater than or equal to 1, since there is at least one historical quality sampling plan.
Q historical sampling inspection uniformity factors are obtained through uniformity evaluation on the historical quality sampling inspection scheme set and are stored in a historical quality sampling inspection scheme library, so that a basis is provided for quality sampling inspection through a historical quality sampling inspection scheme in the follow-up process.
Further, the application also comprises the following steps:
traversing the production processing data to acquire multiple batches of data, and obtaining Q processing data and Q historical quality sampling inspection schemes, wherein the processing data comprise the number of elastic bodies produced by each production line of M production lines;
calculating production coefficients of the production lines according to the Q processing data respectively to obtain Q production coefficient sets, wherein each production coefficient set comprises production coefficients corresponding to M production lines;
extracting Q sampling inspection coefficient sets based on the Q historical quality sampling inspection schemes, wherein each sampling inspection coefficient set comprises M sampling inspection coefficients corresponding to M production lines;
and matching the Q production coefficient sets with the Q sampling inspection coefficient sets, and obtaining Q historical sampling inspection uniformity factors according to a matching result.
Specifically, the production process data of the preset history window has a plurality of production lots. Further, the production process data of the preset history window has Q production lots. For example, production process data produced in the morning and production process data produced in the afternoon during the past day may be divided into two batches of production process data. Further, the production processing data of the preset history window are sequentially accessed to collect data of each batch, and Q processing data corresponding to Q production batches and Q historical quality sampling inspection schemes corresponding to Q processing data of the Q production batches are obtained. Wherein each process data for each production lot has a corresponding one of the historical quality sampling plan. Further, each process data includes M production lines. And calculating the product according to the number of the elastomer produced in each production line and the number M of the production lines, and obtaining the processing data of each production batch.
Then, in each production batch, calculating the ratio of the number of the elastomers produced in each production line to the total number of the elastomers produced in the M production lines to obtain production coefficients corresponding to each production line, and further, in each production batch, obtaining M production coefficients corresponding to the M production lines. Further, in each production lot, M production coefficients are combined to obtain one production coefficient set. Further, product calculation is performed on one production coefficient set in each production batch and the number Q of the production batches, so that Q production coefficient sets are obtained.
And then, extracting sampling inspection coefficients of Q historical quality sampling inspection schemes of Q production batches respectively to obtain Q sampling inspection coefficient sets. Each set of sampling inspection coefficients comprises M sampling inspection coefficients corresponding to M production lines of each production batch. The sampling inspection coefficient is the ratio of the number of the elastic bodies sampled in each production line to the number of the elastic bodies produced in each production line in each historical quality sampling inspection scheme, and the sampling inspection elastic bodies are used for carrying out production quality evaluation. Further, the sampling coefficient of each production line is obtained by calculating the ratio of the number of elastomers sampled for each production line to the number of elastomers produced for each production line. And extracting the sampling inspection coefficients according to the M production lines to obtain M sampling inspection coefficients, and combining the M sampling inspection coefficients to obtain a sampling inspection coefficient set. And extracting the sampling inspection coefficients according to the Q historical quality sampling inspection schemes to obtain Q sampling inspection coefficient sets, namely Q multiplied by M sampling inspection coefficients.
And then, matching the Q production coefficient sets with the Q sampling inspection coefficient sets corresponding to the production lines to obtain each production coefficient corresponding to each production line and a matched sampling inspection coefficient. Comparing the production coefficient corresponding to each production line with the matched sampling inspection coefficient, if the sampling inspection coefficient is smaller than the production coefficient, the sampling inspection sample is too small relative to the production quantity of the production lines, the sampling inspection sample is not representative, and the production line with the sampling inspection coefficient smaller than the production coefficient is added to the matched failure result. For example, one production line produces 10 elastomer quantities, and M production lines produce 100 elastomer quantities as a whole, so that the production coefficient of the production line is calculated to be 1/10. When 20 sampling samples are obtained for the overall sampling of the M production lines, if the sampling sample number of the production line is smaller than 2, the sampling sample number of the sampling samples of the production line is too small. Further, if the sampling inspection coefficient is greater than or equal to the production coefficient, the number of sampling inspection samples is indicated to meet the number of elastomer required for sampling inspection on the production line, and then the production line with the sampling inspection coefficient greater than or equal to the production coefficient is added to the successful result of matching. Further, the successful result of the matching is taken as the matching result. In each production batch, calculating the ratio of the number of production lines corresponding to the matching result to the number M of M production lines to obtain the matching result/M, and taking the matching result/M as a historical sampling inspection uniformity factor. And further calculating the historical spot check uniformity factors in the Q production batches to obtain the Q historical spot check uniformity factors.
By comparing the production coefficient with the sampling inspection coefficient, the historical sampling inspection uniformity factor is further obtained, the sampling inspection accuracy is further improved, and the technical effect of improving the sampling inspection scheme accuracy is achieved.
Further, the application also comprises the following steps:
the M production lines are used as indexes to search the quality feedback information, and M abnormal quality feedback data sets are obtained;
Clustering the M abnormal quality feedback data sets respectively to obtain M abnormal quality feedback clustering results;
Respectively carrying out weighted calculation on the M abnormal quality feedback clustering results to obtain M abnormal quality feedback factors;
And performing fine tuning optimization on the historical quality sampling inspection scheme library according to the M abnormal quality feedback factors to obtain the target quality sampling inspection scheme.
Specifically, M production lines are used as indexes, i.e. search targets, the quality feedback information is searched to obtain abnormal quality feedback data corresponding to each production line, and M abnormal quality feedback data sets are obtained by combination. For example, the abnormal quality feedback data of the water pipe made of the thermoplastic elastomer of the blending type interpenetrating network is water leakage or water pipe fracture caused by notch generation.
And then, clustering M abnormal quality feedback data sets according to the abnormal quality feedback data types to obtain a data set of each abnormal quality feedback data type as M abnormal quality feedback clustering results.
Then, the different abnormal quality feedback data types are different in influence degree due to the abnormality, so that the weights of the different abnormal quality feedback data types are different, wherein the more serious the abnormality causes the influence degree, the larger the corresponding weight is, and conversely, the smaller the corresponding weight is. Further, weighting calculation is carried out on M abnormal quality feedback clustering results according to preset weights, and M abnormal quality feedback factors are obtained. The preset weight is obtained by custom setting according to actual conditions by a person skilled in the art.
And then, carrying out fine tuning optimization on the historical quality sampling inspection schemes in the historical quality sampling inspection scheme library according to M abnormal quality feedback factors, wherein when the abnormal degree of the abnormal quality feedback factors is higher, the fine tuning degree of the fine tuning optimization on the historical quality sampling inspection scheme is higher, otherwise, the fine tuning degree is lower, and then the target quality sampling inspection scheme is obtained.
And fine tuning and optimizing the historical quality sampling inspection scheme library by acquiring an abnormal quality feedback data set, so as to obtain a target quality sampling inspection scheme for subsequent sampling inspection.
Further, the application also comprises the following steps:
multiplying the ratio of the M abnormal quality feedback factors to the sum of the M abnormal quality feedback factors with a preset trimming bandwidth to obtain M trimming bandwidths, wherein the M trimming bandwidths are used for increasing or reducing the number of the production elastomers extracted from the M production lines in the historical quality sampling inspection scheme library for a single time;
The M fine tuning bandwidths are utilized to carry out multiple adjustment on the historical quality sampling inspection scheme library according to a preset adjustment mode, and P fine tuning historical quality sampling inspection scheme sets are obtained, wherein the preset adjustment mode is to increase or decrease the quantity of production elastomers extracted from the M production lines at a time according to the M fine tuning bandwidths;
and traversing the P fine tuning historical quality sampling inspection scheme sets to perform adaptability analysis, and obtaining P fine tuning adaptability sets.
Specifically, the ratio of each abnormal quality feedback factor to the sum of the corresponding M abnormal quality feedback factors is calculated respectively, and M ratio results are obtained. Further, the preset trimming bandwidth is the preset number of single increase or decrease of the number of the production elastomers extracted from each production line, namely the number of the sampling inspection of increasing or decreasing the number of the sampling inspection of the production elastomers. The preset trimming bandwidth is determined by a person skilled in the art according to the overall quality abnormal degree of M production lines after spot inspection, and is obtained by setting. For example, if the degree of abnormality of the overall quality after the spot inspection of the M production lines is higher than or equal to the threshold value of the degree of abnormality, the number of spot inspection is increased, otherwise, the number is decreased. The threshold value of the degree of abnormality of the overall quality can be obtained by a person skilled in the art according to the actual situation custom setting. Further, product calculation is carried out on the M ratio results and the preset trimming bandwidths, and M trimming bandwidths are obtained. Wherein the trimming bandwidth is the number of single increases or decreases of the spot check of the elastomer quantity of the production line.
Then, the preset adjustment mode is a mode of increasing or decreasing the quantity of the production elastomer of the spot check of the production line for a single time according to the fine adjustment bandwidth. Further, P historical quality sampling inspection schemes are extracted from the historical quality sampling inspection scheme library, wherein P is an integer greater than or equal to 1 because at least one historical quality sampling inspection scheme exists in the historical quality sampling inspection scheme library. Further, the P historical quality sampling inspection schemes are respectively adjusted for multiple times by using the M fine tuning bandwidths according to a preset adjustment mode, and P fine tuning historical quality sampling inspection scheme sets after the multiple adjustments are obtained. The number of fine tuning historical quality sampling inspection schemes in each fine tuning historical quality sampling inspection scheme set is the number of times of multiple adjustments.
Next, each fine tuning historical quality sampling plan of each of the P fine tuning historical quality sampling plan sets has a corresponding first fitness. The first fitness of each fine tuning historical quality sampling inspection scheme is a numerical value, and the numerical value of the first fitness is irrelevant to the quality of the scheme. But the degree of aggregation of the first fitness is obtained as the second fitness. The higher the fitness of the second fitness, the higher the degree of aggregation representing the first fitness, i.e. the greater the number of aggregates of the first fitness, the higher the obtained second fitness, and vice versa, the less. Further, a fitness analysis model is built based on a convolutional neural network, and the convolutional neural network is composed of a plurality of convolutional layers, a pooling layer, a full-connection layer and the like. The convolution layer is a core of an adaptability analysis model constructed based on a convolution neural network, and the feature extraction is carried out on input data through convolution operation. The pooling layer is then used to reduce the dimensionality and computational complexity of the data while preserving important features. The full connection layer is used for classifying or regressing the extracted features. Further, each fine tuning historical quality sampling inspection scheme of each fine tuning historical quality sampling inspection scheme set in the P fine tuning historical quality sampling inspection scheme sets and the corresponding first fitness input fitness analysis model are sequentially extracted, and a plurality of input data are obtained and used for training the fitness analysis model. Further, the plurality of input data is divided into a plurality of training data and a corresponding plurality of verification data. The dividing ratio of the plurality of training data and the corresponding plurality of verification data is obtained by a person skilled in the art through user-defined setting according to actual conditions, for example, the dividing ratio of the training data and the verification data is 6:4. further, the training data is input into an fitness analysis model, and the mapping relation between the fine tuning historical quality sampling inspection scheme set and the first fitness is learned by utilizing the training data. The characteristic of the convolutional neural network is that the characteristic of the input data can be automatically extracted, so that the complicated process of manually designing the characteristic is avoided. Meanwhile, the convolutional neural network has robustness and generalization capability, and can process data of various shapes and sizes. When the output data of the fitness analysis model tend to be stable, a plurality of fine tuning historical quality sampling inspection scheme sets in a plurality of verification data are input into the fitness analysis model, a plurality of verification first fitness is output through the calculation of the fitness analysis model, the plurality of verification first fitness corresponds to the plurality of fine tuning historical quality sampling inspection scheme sets one by one, cosine similarity between the plurality of verification first fitness and the plurality of first fitness in the plurality of verification data is calculated respectively, a plurality of verification calculation results are obtained, and whether the proportion of the plurality of verification calculation results exceeding a preset similarity threshold meets a preset output result threshold is judged. When the output result of the fitness analysis model meets a preset output result threshold, training of the fitness analysis model is completed, and the output result of the fitness analysis model is obtained, namely P fine adjustment fitness sets are obtained. The preset output result threshold is obtained by custom setting by a person skilled in the art according to practical situations, for example, the preset output result threshold is that the aggregation degree of the first fitness is 80%.
And the historical quality sampling inspection scheme library is adjusted by fine adjustment of the bandwidth, so that the sampling inspection adaptability of the historical quality sampling inspection scheme is further improved, and a basis is provided for subsequently improving the product quality.
Further, the application also comprises the following steps:
Selecting a fine tuning historical quality sampling inspection scheme corresponding to the maximum value in the P fine tuning adaptation degree sets as a leading direction, and adjusting the rest fine tuning historical quality sampling inspection schemes in the P fine tuning historical quality sampling inspection scheme sets according to M fine tuning bandwidths to obtain P stage fine tuning historical quality sampling inspection scheme sets;
and taking the stage history quality sampling inspection scheme corresponding to the maximum fine adjustment adaptability as the target quality sampling inspection scheme after multiple times of adjustment.
Specifically, the P fine tuning fitness sets are subjected to serialization processing according to the fitness from large to small, namely, are ranked according to the second fitness, a serialization processing result is obtained, and a fine tuning historical quality sampling inspection scheme corresponding to the first fine tuning fitness in the serialization processing result is extracted to serve as a leading direction. Further, the rest fine tuning historical quality sampling inspection schemes in the P fine tuning historical quality sampling inspection scheme sets are adjusted according to M fine tuning bandwidths, namely the fine tuning bandwidths are used as fine tuning step sizes, the leading direction is used as fine tuning direction, fine tuning optimization is carried out once, and P stage fine tuning historical quality sampling inspection scheme sets corresponding to the P fine tuning historical quality sampling inspection scheme sets are obtained.
And then, performing multiple fine tuning optimization on the P-stage fine tuning historical quality sampling inspection scheme sets according to the fine tuning bandwidth as a fine tuning step length and the leading direction as a fine tuning direction to obtain P multiple fine tuning stage fine tuning historical quality sampling inspection scheme sets. Further, first trimming fitness of P sets of multi-trimming-stage trimming historical quality sampling inspection schemes is obtained, serialization processing is carried out on the first trimming fitness of the P sets from large to small according to the fitness, and the trimming historical quality sampling inspection scheme of the first trimming stage in the sorting result is obtained and used as a target quality sampling inspection scheme.
And the fine adjustment historical quality sampling inspection schemes in the P fine adjustment historical quality sampling inspection scheme sets are adjusted for a plurality of times, and the maximum fine adjustment adaptability is obtained as a target quality sampling inspection scheme, so that quality sampling inspection is carried out, and the quality of the sampling inspection scheme is further improved.
Further, the application also comprises the following steps:
Traversing the sampling quality detection result to perform average value calculation to obtain a sampling quality detection result average value;
The first sampling quality detection result with the average value of the sampling quality detection results being a preset deviation step length is matched in the sampling quality detection results;
Judging whether the deviation factor of the first sampling quality detection result is larger than the deviation factor of the sampling quality detection result mean value or not;
If yes, moving and updating the first sampling quality detection result according to the preset deviation step length until the preset moving times are reached;
And taking a sampling quality detection result corresponding to the maximum value of the deviation factor in the moving process as a quality evaluation result of the target elastomer.
Specifically, the sampling quality detection results are sequentially accessed, and average value calculation is carried out on all the sampling quality results to obtain sampling quality detection result average value which is used for judging the adaptation degree of the target quality sampling detection scheme.
And then, matching the average value of the sampling quality detection results in the sampling quality detection results to obtain matched sampling quality detection results. Further, setting a preset deflection step length, wherein the preset deflection step length is the amplitude of single movement when carrying out deflection analysis on other sampling quality detection results except the average value of sampling quality detection results, and the preset deflection step length is obtained by carrying out custom setting according to actual conditions by a person skilled in the art. Further, performing single movement of the deviation analysis on other sampling quality detection results according to a preset deviation step length to obtain a first sampling quality detection result.
Next, a bias factor of the first sample quality detection result is obtained. The deviation factor of the first sampling quality detection result is the ratio of the number of detection results in the region constructed by taking the first sampling quality detection result as a circle center and taking a preset deviation step length as a radius to the area of the region. The bias factor of the first sample quality detection result reflects how many sample quality detection results are aggregated around the first sample quality detection result, wherein the more the number of aggregated sample quality detection results indicates the more representative the first sample quality detection result, and vice versa, the less representative the first sample quality detection result. Further, a deviation factor of the average value of the sampling quality detection results is obtained, wherein the deviation factor of the average value of the sampling quality detection results is a ratio of the number of detection results in an area constructed by taking the average value of the sampling quality detection results as a circle center and taking a preset deviation step length as a radius to the area of the area. The bias factor of the sample quality detection result mean reflects how many sample quality detection results are gathered around the sample quality detection result mean, wherein the more the number of gathered sample quality detection results, the more representative the sample quality detection result mean, and conversely, the less representative the sample quality detection result mean. Further, whether the deviation factor of the first sampling quality detection result is larger than the deviation factor of the average value of the sampling quality detection result is judged, and a judgment result is obtained.
And then, if the judgment result is that the deviation factor of the first sampling quality detection result is larger than the deviation factor of the sampling quality detection result mean value, indicating that the first sampling quality detection result is more representative than the sampling quality detection result mean value, moving and updating the first sampling quality detection result according to a preset deviation step length until the preset moving times are reached, and meanwhile discarding the sampling quality detection result mean value. For example, the first sample quality detection result is a median sample quality detection result, and the median sample quality detection result has a bias factor greater than the bias factor of the mean sample quality detection result. Further, the preset moving times are times of transforming the first sampling quality detection result. The preset number of movements is obtained by a person skilled in the art performing a custom setting according to the actual situation. For example, the preset number of movements is 5.
And secondly, when the preset moving times are reached, acquiring the deviation factor of the first sampling quality detection result of each movement, and further acquiring the deviation factors of the first sampling quality detection results in a plurality of movements. And sequencing the plurality of bias factors in the moving process according to the bias factors from large to small to obtain a sequencing result of the bias factors. And extracting a first biasing factor in the sequencing result of the biasing factors, namely extracting a maximum value of the biasing factors. And extracting a first sampling quality detection result corresponding to the maximum value of the biasing factor, namely extracting a sampling quality detection result corresponding to the maximum value of the biasing factor. And taking the sampling quality detection result corresponding to the maximum value of the deviation factor as the quality evaluation result of the target elastomer.
The sampling quality detection result obtained by carrying out the bias analysis on the sampling quality detection result is used as the quality evaluation result of the target elastomer, so that the accuracy of obtaining the quality evaluation result of the target elastomer is improved.
In summary, the quality evaluation method of the blend type interpenetrating network thermoplastic elastomer provided by the application has the following technical effects:
Obtaining M elastomer production data sets through M production lines of the interactive target elastomer; traversing the production and processing data of the M production lines in a preset history window, and configuring a history quality spot check scheme library; fine tuning and optimizing the historical quality sampling inspection scheme library based on the quality feedback information to obtain a target quality sampling inspection scheme; sampling quality detection is carried out on the production products of the current production task by utilizing the target quality sampling detection scheme, and a sampling quality detection result is obtained; and carrying out bias analysis on the sampling quality detection result to obtain a quality evaluation result of the target elastomer, namely, improving the coincidence degree of a sampling detection quality sampling detection scheme and the actual condition of a production line, finally realizing the technical aim of improving the accuracy of the sampling detection obtained quality detection result and achieving the technical effect of improving the quality detection efficiency.
Example two
Based on the method for evaluating the quality of the thermoplastic elastomer of the blend-type interpenetrating network in the foregoing embodiment, the application also provides a system for evaluating the quality of the thermoplastic elastomer of the blend-type interpenetrating network, please refer to fig. 2, the system comprises:
the device comprises M elastomer production data set obtaining modules 11, wherein the M elastomer production data set obtaining modules 11 are used for interacting M production lines of a target elastomer to obtain M elastomer production data sets;
The historical quality sampling inspection scheme library configuration module 12 is used for traversing the production and processing data of the M production lines in a preset historical window, and configuring a historical quality sampling inspection scheme library;
The target quality sampling plan obtaining module 13 is used for carrying out fine adjustment and optimization on the historical quality sampling plan library based on quality feedback information to obtain a target quality sampling plan;
The sampling quality detection result obtaining module 14, where the sampling quality detection result obtaining module 14 is configured to perform sampling quality detection on a product of a current production task by using the target quality sampling detection scheme to obtain a sampling quality detection result;
And a quality evaluation result obtaining module 15, where the quality evaluation result obtaining module 15 is configured to perform a bias analysis on the sampling quality detection result, and obtain a quality evaluation result of the target elastomer.
Further, the historical quality spot check scheme library configuration module 12 in the system is also configured to:
Taking the historical quality sampling inspection scheme as an index, and searching the production and processing data to obtain a historical quality sampling inspection scheme set;
Performing uniformity evaluation on the historical quality sampling inspection scheme set to obtain Q historical sampling inspection uniformity factors;
Judging whether the Q historical sampling inspection uniformity factors meet preset sampling inspection uniformity factors, if so, storing the Q historical sampling inspection uniformity factors into the historical quality sampling inspection scheme library.
Further, the historical quality spot check scheme library configuration module 12 in the system is also configured to:
traversing the production processing data to acquire multiple batches of data, and obtaining Q processing data and Q historical quality sampling inspection schemes, wherein the processing data comprise the number of elastic bodies produced by each production line of M production lines;
calculating production coefficients of the production lines according to the Q processing data respectively to obtain Q production coefficient sets, wherein each production coefficient set comprises production coefficients corresponding to M production lines;
extracting Q sampling inspection coefficient sets based on the Q historical quality sampling inspection schemes, wherein each sampling inspection coefficient set comprises M sampling inspection coefficients corresponding to M production lines;
and matching the Q production coefficient sets with the Q sampling inspection coefficient sets, and obtaining Q historical sampling inspection uniformity factors according to a matching result.
Further, the target quality spot check scheme obtaining module 13 in the system is further configured to:
the M production lines are used as indexes to search the quality feedback information, and M abnormal quality feedback data sets are obtained;
Clustering the M abnormal quality feedback data sets respectively to obtain M abnormal quality feedback clustering results;
Respectively carrying out weighted calculation on the M abnormal quality feedback clustering results to obtain M abnormal quality feedback factors;
And performing fine tuning optimization on the historical quality sampling inspection scheme library according to the M abnormal quality feedback factors to obtain the target quality sampling inspection scheme.
Further, the target quality spot check scheme obtaining module 13 in the system is further configured to:
multiplying the ratio of the M abnormal quality feedback factors to the sum of the M abnormal quality feedback factors with a preset trimming bandwidth to obtain M trimming bandwidths, wherein the M trimming bandwidths are used for increasing or reducing the number of the production elastomers extracted from the M production lines in the historical quality sampling inspection scheme library for a single time;
The M fine tuning bandwidths are utilized to carry out multiple adjustment on the historical quality sampling inspection scheme library according to a preset adjustment mode, and P fine tuning historical quality sampling inspection scheme sets are obtained, wherein the preset adjustment mode is to increase or decrease the quantity of production elastomers extracted from the M production lines at a time according to the M fine tuning bandwidths;
and traversing the P fine tuning historical quality sampling inspection scheme sets to perform adaptability analysis, and obtaining P fine tuning adaptability sets.
Further, the target quality spot check scheme obtaining module 13 in the system is further configured to:
Selecting a fine tuning historical quality sampling inspection scheme corresponding to the maximum value in the P fine tuning adaptation degree sets as a leading direction, and adjusting the rest fine tuning historical quality sampling inspection schemes in the P fine tuning historical quality sampling inspection scheme sets according to M fine tuning bandwidths to obtain P stage fine tuning historical quality sampling inspection scheme sets;
and taking the stage history quality sampling inspection scheme corresponding to the maximum fine adjustment adaptability as the target quality sampling inspection scheme after multiple times of adjustment.
Further, the quality evaluation result obtaining module 15 in the system is further configured to:
Traversing the sampling quality detection result to perform average value calculation to obtain a sampling quality detection result average value;
The first sampling quality detection result with the average value of the sampling quality detection results being a preset deviation step length is matched in the sampling quality detection results;
Judging whether the deviation factor of the first sampling quality detection result is larger than the deviation factor of the sampling quality detection result mean value or not;
If yes, moving and updating the first sampling quality detection result according to the preset deviation step length until the preset moving times are reached;
And taking a sampling quality detection result corresponding to the maximum value of the deviation factor in the moving process as a quality evaluation result of the target elastomer.
The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the difference from the other embodiments, and the method and specific example for evaluating the quality of the thermoplastic elastomer of the blended interpenetrating network in the first embodiment are equally applicable to the system for evaluating the quality of the thermoplastic elastomer of the blended interpenetrating network in this embodiment, and by the foregoing detailed description of the method for evaluating the quality of the thermoplastic elastomer of the blended interpenetrating network, those skilled in the art can clearly understand the system for evaluating the quality of the thermoplastic elastomer of the blended interpenetrating network in this embodiment, so that the details of the system for evaluating the quality of the thermoplastic elastomer of the blended interpenetrating network in this embodiment are not described herein for brevity. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant points refer to the description of the method section.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present application without departing from the spirit or scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the present application and the equivalent techniques thereof, the present application is also intended to include such modifications and variations.
Claims (4)
1. A method for quality assessment of a blended interpenetrating network thermoplastic elastomer, the method comprising:
M production lines of the interactive target elastomer are used for obtaining M elastomer production data sets;
traversing the production and processing data of the M production lines in a preset history window, and configuring a history quality spot check scheme library;
fine tuning and optimizing the historical quality sampling inspection scheme library based on the quality feedback information to obtain a target quality sampling inspection scheme;
sampling quality detection is carried out on the production products of the current production task by utilizing the target quality sampling detection scheme, and a sampling quality detection result is obtained;
Performing bias analysis on the sampling quality detection result to obtain a quality evaluation result of the target elastomer;
Fine tuning and optimizing the historical quality sampling inspection scheme library based on quality feedback information to obtain a target quality sampling inspection scheme, wherein the method comprises the following steps:
the M production lines are used as indexes to search the quality feedback information, and M abnormal quality feedback data sets are obtained;
Clustering the M abnormal quality feedback data sets respectively to obtain M abnormal quality feedback clustering results;
Respectively carrying out weighted calculation on the M abnormal quality feedback clustering results to obtain M abnormal quality feedback factors;
performing fine tuning optimization on the historical quality sampling inspection scheme library according to the M abnormal quality feedback factors to obtain the target quality sampling inspection scheme;
Fine tuning and optimizing the historical quality sampling inspection scheme library according to the M abnormal quality feedback factors to obtain the target quality sampling inspection scheme, wherein the method comprises the following steps:
multiplying the ratio of the M abnormal quality feedback factors to the sum of the M abnormal quality feedback factors with a preset trimming bandwidth to obtain M trimming bandwidths, wherein the M trimming bandwidths are used for increasing or reducing the number of the production elastomers extracted from the M production lines in the historical quality sampling inspection scheme library for a single time;
The M fine tuning bandwidths are utilized to carry out multiple adjustment on the historical quality sampling inspection scheme library according to a preset adjustment mode, and P fine tuning historical quality sampling inspection scheme sets are obtained, wherein the preset adjustment mode is to increase or decrease the quantity of production elastomers extracted from the M production lines at a time according to the M fine tuning bandwidths;
Traversing the P fine tuning historical quality sampling inspection scheme sets to perform adaptability analysis to obtain P fine tuning adaptability sets;
obtaining P fine-tuning fitness sets, after which the method further comprises:
Selecting a fine tuning historical quality sampling inspection scheme corresponding to the maximum value in the P fine tuning adaptation degree sets as a leading direction, and adjusting the rest fine tuning historical quality sampling inspection schemes in the P fine tuning historical quality sampling inspection scheme sets according to M fine tuning bandwidths to obtain P stage fine tuning historical quality sampling inspection scheme sets;
The stage history quality sampling inspection scheme corresponding to the maximum value of the fine adjustment fitness is used as the target quality sampling inspection scheme after multiple times of adjustment;
performing bias analysis on the sampling quality detection result to obtain a quality evaluation result of the target elastomer, wherein the method comprises the following steps:
Traversing the sampling quality detection result to perform average value calculation to obtain a sampling quality detection result average value;
The first sampling quality detection result with the average value of the sampling quality detection results being a preset deviation step length is matched in the sampling quality detection results;
Judging whether the deviation factor of the first sampling quality detection result is larger than the deviation factor of the sampling quality detection result mean value or not;
If yes, moving and updating the first sampling quality detection result according to the preset deviation step length until the preset moving times are reached;
And taking a sampling quality detection result corresponding to the maximum value of the deviation factor in the moving process as a quality evaluation result of the target elastomer.
2. The method of claim 1, wherein the historical quality spot check scheme library is configured by traversing production process data of the M production lines within a preset historical window, the method comprising:
Taking the historical quality sampling inspection scheme as an index, and searching the production and processing data to obtain a historical quality sampling inspection scheme set;
Performing uniformity evaluation on the historical quality sampling inspection scheme set to obtain Q historical sampling inspection uniformity factors;
Judging whether the Q historical sampling inspection uniformity factors meet preset sampling inspection uniformity factors, if so, storing the Q historical sampling inspection uniformity factors into the historical quality sampling inspection scheme library.
3. The method of claim 2, wherein the set of historical quality sampling plans are evaluated for uniformity to obtain Q historical sampling uniformity factors, the method comprising:
traversing the production processing data to acquire multiple batches of data, and obtaining Q processing data and Q historical quality sampling inspection schemes, wherein the processing data comprise the number of elastic bodies produced by each production line of M production lines;
calculating production coefficients of the production lines according to the Q processing data respectively to obtain Q production coefficient sets, wherein each production coefficient set comprises production coefficients corresponding to M production lines;
extracting Q sampling inspection coefficient sets based on the Q historical quality sampling inspection schemes, wherein each sampling inspection coefficient set comprises M sampling inspection coefficients corresponding to M production lines;
and matching the Q production coefficient sets with the Q sampling inspection coefficient sets, and obtaining Q historical sampling inspection uniformity factors according to a matching result.
4. A quality assessment system for a blended interpenetrating network thermoplastic elastomer, characterized by the steps for carrying out the method of any of claims 1 to 3, said system comprising:
the system comprises M elastomer production data set acquisition modules, a control module and a control module, wherein the M elastomer production data set acquisition modules are used for interacting M production lines of a target elastomer to acquire M elastomer production data sets;
the historical quality sampling inspection scheme library configuration module is used for traversing the production and processing data of the M production lines in a preset historical window and configuring a historical quality sampling inspection scheme library;
The target quality sampling inspection scheme obtaining module is used for carrying out fine adjustment and optimization on the historical quality sampling inspection scheme base based on quality feedback information to obtain a target quality sampling inspection scheme;
the sampling quality detection result obtaining module is used for carrying out sampling quality detection on the production product of the current production task by utilizing the target quality sampling detection scheme to obtain a sampling quality detection result;
and the quality evaluation result obtaining module is used for carrying out bias analysis on the sampling quality detection result to obtain the quality evaluation result of the target elastomer.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410416225.9A CN118014442B (en) | 2024-04-08 | 2024-04-08 | Quality evaluation method and system for blending type interpenetrating network thermoplastic elastomer |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410416225.9A CN118014442B (en) | 2024-04-08 | 2024-04-08 | Quality evaluation method and system for blending type interpenetrating network thermoplastic elastomer |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118014442A CN118014442A (en) | 2024-05-10 |
| CN118014442B true CN118014442B (en) | 2024-06-21 |
Family
ID=90956707
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410416225.9A Active CN118014442B (en) | 2024-04-08 | 2024-04-08 | Quality evaluation method and system for blending type interpenetrating network thermoplastic elastomer |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118014442B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115685946A (en) * | 2022-11-28 | 2023-02-03 | 浙江万胜智能科技股份有限公司 | Intelligent power consumption acquisition terminal production quality control method and system |
| CN116865851A (en) * | 2023-06-19 | 2023-10-10 | 国网内蒙古东部电力有限公司 | Multi-dimensional optical fiber operation quality monitoring method and system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116882847B (en) * | 2023-09-07 | 2023-12-01 | 山东盛日电力集团有限公司 | Installation quality detection method and system for photovoltaic module |
-
2024
- 2024-04-08 CN CN202410416225.9A patent/CN118014442B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115685946A (en) * | 2022-11-28 | 2023-02-03 | 浙江万胜智能科技股份有限公司 | Intelligent power consumption acquisition terminal production quality control method and system |
| CN116865851A (en) * | 2023-06-19 | 2023-10-10 | 国网内蒙古东部电力有限公司 | Multi-dimensional optical fiber operation quality monitoring method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118014442A (en) | 2024-05-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109597968B (en) | SMT big data-based solder paste printing performance influence factor analysis method | |
| CN111784093B (en) | Enterprise reworking auxiliary judging method based on power big data analysis | |
| CN109829497B (en) | Supervised learning-based station area user identification and discrimination method | |
| CN111476435B (en) | Charging pile load prediction method based on density peak value | |
| CN111008726B (en) | Class picture conversion method in power load prediction | |
| CN117313016B (en) | New energy power transaction spot electricity price difference data processing method | |
| CN108460486A (en) | A kind of voltage deviation prediction technique based on improvement clustering algorithm and neural network | |
| CN113515512A (en) | Quality control and improvement method for industrial internet platform data | |
| CN112287980B (en) | Power battery screening method based on typical feature vector | |
| CN109255029A (en) | A method of automatic Bug report distribution is enhanced using weighted optimization training set | |
| CN116049705A (en) | Clustering analysis-based power system user load characteristic clustering method and system | |
| CN116432867A (en) | Diode preparation control optimization method and system | |
| CN111062539A (en) | Total electric quantity prediction method based on secondary electric quantity characteristic clustering analysis | |
| CN118014442B (en) | Quality evaluation method and system for blending type interpenetrating network thermoplastic elastomer | |
| CN113076692B (en) | Method for inverting nitrogen content of leaf | |
| CN113592538A (en) | Method and system for calculating approximate construction cost | |
| CN114718861A (en) | Intelligent diagnosis method for working condition of screw pump well based on deep learning | |
| CN113919610A (en) | ARIMA model construction method and evaluation method for low-voltage transformer area line loss prediction | |
| CN116933194A (en) | Abnormality screening, repairing and active complement method for power report data of wind power plant | |
| CN116883184A (en) | Financial tax intelligent analysis method based on big data | |
| CN109547248A (en) | Based on artificial intelligence in orbit aerocraft ad hoc network method for diagnosing faults and device | |
| CN115239201A (en) | Power index evaluation method and system | |
| CN110175705B (en) | Load prediction method and memory and system comprising same | |
| CN118365173B (en) | Intelligent climate effect assessment method for large-scale wind power plant | |
| CN117789907B (en) | Intelligent medical data intelligent management method based on multi-source data fusion |
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 |