CN116882822A - PVB product quality association rule analysis method and system - Google Patents
PVB product quality association rule analysis method and system Download PDFInfo
- Publication number
- CN116882822A CN116882822A CN202310842896.7A CN202310842896A CN116882822A CN 116882822 A CN116882822 A CN 116882822A CN 202310842896 A CN202310842896 A CN 202310842896A CN 116882822 A CN116882822 A CN 116882822A
- Authority
- CN
- China
- Prior art keywords
- quality
- data
- rule
- pvb
- association
- 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
- 238000004458 analytical method Methods 0.000 title claims abstract description 31
- 238000000034 method Methods 0.000 claims abstract description 113
- 230000008569 process Effects 0.000 claims abstract description 88
- 238000004519 manufacturing process Methods 0.000 claims abstract description 74
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 67
- 238000012545 processing Methods 0.000 claims abstract description 28
- 239000002245 particle Substances 0.000 claims description 24
- 238000004364 calculation method Methods 0.000 claims description 14
- 238000005457 optimization Methods 0.000 claims description 14
- 239000011159 matrix material Substances 0.000 claims description 10
- 230000006872 improvement Effects 0.000 claims description 8
- 238000007781 pre-processing Methods 0.000 claims description 8
- 238000009411 base construction Methods 0.000 claims description 6
- 238000013138 pruning Methods 0.000 claims description 4
- 238000003491 array Methods 0.000 claims description 2
- 238000007621 cluster analysis Methods 0.000 claims description 2
- 230000005484 gravity Effects 0.000 claims description 2
- 238000012544 monitoring process Methods 0.000 abstract description 4
- 239000000047 product Substances 0.000 description 76
- 229920002037 poly(vinyl butyral) polymer Polymers 0.000 description 67
- 238000005406 washing Methods 0.000 description 15
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 14
- 150000001299 aldehydes Chemical class 0.000 description 10
- ZTQSAGDEMFDKMZ-UHFFFAOYSA-N Butyraldehyde Chemical compound CCCC=O ZTQSAGDEMFDKMZ-UHFFFAOYSA-N 0.000 description 8
- 238000004590 computer program Methods 0.000 description 8
- 238000003908 quality control method Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 238000004321 preservation Methods 0.000 description 5
- 239000002994 raw material Substances 0.000 description 5
- 230000007704 transition Effects 0.000 description 5
- 238000003064 k means clustering Methods 0.000 description 4
- 238000005065 mining Methods 0.000 description 4
- 238000013441 quality evaluation Methods 0.000 description 4
- HGBOYTHUEUWSSQ-UHFFFAOYSA-N valeric aldehyde Natural products CCCCC=O HGBOYTHUEUWSSQ-UHFFFAOYSA-N 0.000 description 4
- 230000001276 controlling effect Effects 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
- 238000007405 data analysis Methods 0.000 description 3
- 238000007418 data mining Methods 0.000 description 3
- 230000000630 rising effect Effects 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- VEXZGXHMUGYJMC-UHFFFAOYSA-N Hydrochloric acid Chemical compound Cl VEXZGXHMUGYJMC-UHFFFAOYSA-N 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000009833 condensation Methods 0.000 description 2
- 230000005494 condensation Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000004090 dissolution Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000010438 heat treatment Methods 0.000 description 2
- 229910000041 hydrogen chloride Inorganic materials 0.000 description 2
- IXCSERBJSXMMFS-UHFFFAOYSA-N hydrogen chloride Substances Cl.Cl IXCSERBJSXMMFS-UHFFFAOYSA-N 0.000 description 2
- 125000002887 hydroxy group Chemical group [H]O* 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000006641 stabilisation Effects 0.000 description 2
- 238000011105 stabilization Methods 0.000 description 2
- 230000000087 stabilizing effect Effects 0.000 description 2
- 239000003039 volatile agent Substances 0.000 description 2
- -1 yellow index Substances 0.000 description 2
- VESYUZDGKDLLCI-UHFFFAOYSA-N 2,3-diethylhex-2-enal Chemical compound C(C)C(=C(C=O)CC)CCC VESYUZDGKDLLCI-UHFFFAOYSA-N 0.000 description 1
- 238000003556 assay Methods 0.000 description 1
- 230000002860 competitive effect Effects 0.000 description 1
- 238000004132 cross linking Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 239000012535 impurity Substances 0.000 description 1
- 239000013067 intermediate product Substances 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 229920005989 resin Polymers 0.000 description 1
- 239000011347 resin Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000000007 visual effect Effects 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
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
- G06N5/022—Knowledge engineering; Knowledge acquisition
- G06N5/025—Extracting rules from data
-
- 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
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- 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)
- Strategic Management (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Marketing (AREA)
- Artificial Intelligence (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Quality & Reliability (AREA)
- Computational Linguistics (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Probability & Statistics with Applications (AREA)
- Manufacturing & Machinery (AREA)
- Primary Health Care (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- General Factory Administration (AREA)
Abstract
The application is suitable for the field of industrial big data and intelligent manufacturing, and provides a PVB product quality association rule analysis method and a PVB product quality association rule analysis system, wherein the method comprises the following steps: acquiring process data and quality data of the whole process of PVB product production; performing data processing on the acquired process data and quality data to prepare a sample set; an Apriori algorithm is applied to dig out frequent item sets among all data in the sample set, association rules of the frequent item sets are generated, and the support degree and the confidence degree of each association rule are calculated at the same time; based on a preset minimum support threshold and a preset minimum confidence threshold, clustering and optimizing association rules of the frequent item set by using a specified algorithm to obtain an optimal rule set; the application realizes searching PVB product quality optimal rule, and according to the production process monitoring, the corresponding technological parameters are adjusted by taking the rule as a guide so as to ensure the quality controllability of the whole production process.
Description
Technical Field
The application belongs to the field of industrial big data and intelligent manufacturing, particularly relates to the technical field of PVB product production, and particularly provides a PVB product quality association rule analysis method and system.
Background
The PVB (also called as polyvinyl butyral resin) industry has the characteristics of high profit, large additional value improving space and the like, and has huge market prospect. However, the overall competitive advantage of domestic PVB is not high, especially in the middle-to-high market.
The PVB product production process comprises a series of process flows, and the random fluctuation in the production process is large and the real-time requirement is high. The main characteristics of the PVB production process are as follows:
(1) Correlation and correlation
The multi-process production process depends on process production, the quality state of the product is influenced by various factors in the production process, the processes are mutually buckled layer by layer, and are mutually connected, if the quality control of a certain process is to be completed, the factors influencing the quality of the process in this section are analyzed, and meanwhile, the processes before and after linkage are also needed. Therefore, the whole process of product manufacture is understood completely to grasp the links between the process interiors in the face of the product quality problem of multiple process production stages.
(2) Mass error transmissibility
The process has a correlation and a transfer characteristic, and mainly mass error is transferred along with the process. When the product starts to be produced, when a fluctuation trace of the quality error of the product is captured on a certain process at a certain moment, the error produced in the process will continue to appear in the next process, and the probability of the error being amplified is extremely high.
(3) Complexity of quality fluctuation source
In the multi-process production process, the actual factors affecting the product quality are difficult to capture because of the complex connections of the process. When tracing product quality factors, it has been found that quality problems tend to be buried among the many strong coupling factors in the manufacturing process. Therefore, the source of the real quality fluctuation tends to be more complex in the face of the strong crosslinking highly coupling characteristic possessed by the process in the complex production process.
The PVB product quality evaluation index mainly comprises: melt index, bulk density, hydroxyl content, residual butyraldehyde, residual ET2H (residual diethylhexenal), residual hydrogen chloride, yellow index, volatiles, etc., while the production process affects significant process parameters as much as tens of. Therefore, there is a need to design a quality data analysis tool with less data processing and higher accuracy.
Disclosure of Invention
The embodiment of the application aims to provide a PVB product quality association rule analysis method, which aims to overcome the defects that quality control is influenced by complicated quality control data and uncontrollable key processes due to correlation, quality error transmissibility and quality fluctuation source complexity of PVB product production in the prior art; the incidence relation between the extraction influence factors and the quality evaluation indexes is realized, so that the purpose of gradually stabilizing and controlling the product quality is achieved.
The embodiment of the application is realized in such a way that a PVB product quality association rule analysis method comprises the following steps:
acquiring process data and quality data of the whole process of PVB product production;
performing data processing on the acquired process data and quality data to prepare a sample set;
an Apriori algorithm is applied to dig out frequent item sets among all data in the sample set, association rules of the frequent item sets are generated, and the support degree and the confidence degree of each association rule are calculated at the same time;
based on a preset minimum support threshold and a preset minimum confidence threshold, clustering and optimizing association rules of the frequent item set by using a specified algorithm to obtain an optimal rule set;
establishing a correlation coefficient matrix by using the optimal rule set to form a knowledge base;
and according to process data monitored in the PVB product production process, extracting rules from the knowledge base to adjust quality process parameters of PVB product production so as to realize controllable quality of PVB product production.
Another object of an embodiment of the present application is to provide a PVB product quality data analysis system for a PVB product quality association rule analysis method as described above, the PVB product quality data analysis system comprising: the system comprises a data acquisition module, a data preprocessing module, a first rule calculation module, a second rule calculation module, a knowledge base construction module and a quality improvement module;
the data acquisition module is used for acquiring process data and quality data of the whole PVB product production process;
the data preprocessing module can perform data processing on the acquired process data and quality data to prepare a sample set;
the first rule calculation module can apply an Apriori algorithm to dig out frequent item sets among all data in the sample set, generate association rules of the frequent item sets, and calculate the support and confidence of each association rule;
the second rule calculation module is used for carrying out clustering and optimizing processing on the association rules of the frequent item set by using a specified algorithm based on a preset minimum support threshold and a preset minimum confidence threshold so as to obtain an optimal rule set;
the knowledge base construction module is used for constructing a correlation coefficient matrix by using the optimal rule set so as to form a knowledge base;
the quality improvement module is used for adjusting quality technological parameters of PVB product production according to process data monitored in PVB product production process and extracting rules from the knowledge base so as to realize controllable quality of PVB product production.
According to the PVB product quality association rule analysis method provided by the embodiment of the application, process data and quality data of a PVB product production whole process are obtained, raw materials, key processes, whole samples of the quality data and multi-characteristic characteristics are mainly considered, each classification category is established or mined according to quality data classification results, specifically, apriori is selected as a mining tool of the association rule, a PSO-Kmeans-Apriori-based algorithm model is established by combining a K-Means clustering algorithm and a particle swarm optimization algorithm, the PVB product quality optimal rule is searched according to the PVB product quality optimal rule, and corresponding process parameters are adjusted according to production process monitoring by taking the optimal rule as a guide, so that quality dynamic analysis, diagnosis, prediction and adjustment of a production system are realized, and the quality of the whole production process is controllable.
Drawings
Fig. 1 is a quality association rule mining flow chart for PVB product production provided by an embodiment of the present application;
FIG. 2 is a flow diagram of an Apriori algorithm in one embodiment;
FIG. 3 is a flowchart of a PSO association rule based algorithm in one embodiment;
fig. 4 is a flowchart of a method for analyzing quality association rules of a PVB product according to an embodiment of the present application;
fig. 5 is a block diagram of a PVB product quality association rule analysis system according to an embodiment of the present application;
fig. 6 is a block diagram of a PVB product quality association rule analysis system according to an embodiment of the present application;
FIG. 7 is a correlation matrix plot of process data and viscosity(s) for one embodiment;
FIG. 8 is a graph of the results of the importance of a production index analyzed by one embodiment;
FIG. 9 is a schematic diagram of the internal structure of a computer device in one embodiment.
Detailed Description
The present application will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present application more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.
It will be understood that the terms "first," "second," and the like, as used herein, may be used to describe various elements, but these elements are not limited by these terms unless otherwise specified. These terms are only used to distinguish one element from another element. For example, a first xx script may be referred to as a second xx script, and similarly, a second xx script may be referred to as a first xx script, without departing from the scope of this disclosure.
The management of the production quality of modern factories is generally carried out from five aspects (specifically, operator literacy, production equipment, processing technology, raw materials and production environment) of 'people', 'machines', 'methods', 'materials', 'rings', and quality detection and control measures can be provided for each aspect so as to achieve the predictable and controllable quality improvement; for the person skilled in the art, in order to realize the management of the product quality, it is also easy to know that the data acquisition can be performed from aspects of "people", "machines", "methods", "materials", "rings"; and then data processing is carried out on the acquired data so as to facilitate data mining, and the method can be seen in fig. 1. Take PVB product production as an example: the processing technology (processing procedure) involved in the production comprises the following steps: feeding, dissolving, condensing, heating, preserving heat, washing, stabilizing and the like; correspondingly, the management of the product quality can be realized by detecting and controlling the following process data: PVA feeding amount, temperature rising start temperature/end temperature, jacket temperature, temperature rising rate plate washing level, phase transition temperature, butyraldehyde feeding amount, aldehyde feeding temperature, frequency setting before/during/after aldehyde feeding, temperature rising maximum temperature, heat preservation 2 maximum temperature, primary/secondary/tertiary reuse water washing times, primary/secondary/tertiary reuse water starting time temperature, ice pure water washing times, quality test indexes and the like. In this way, the quality association rules of PVA product production can be cleared by analyzing the internal relations between the process data and the quality states corresponding to the process data, so that guidance and support are provided for quality improvement of PVB products.
In one embodiment, as shown in fig. 4, a flow chart of a method of quality association rule analysis for PVB product production; the following steps S401 to S411 may be included:
s401, acquiring process data and quality data of a PVB product production whole procedure;
in this step, the process data of the whole process of PVB product production includes, but is not limited to, the PVA dosage, the temperature of the beginning/ending of the temperature increase, the jacket temperature, the washing level of the heating rate plate, the phase transition temperature, the dosage of butyraldehyde, the aldehyde adding temperature, the frequency setting before/during/after the aldehyde adding, the highest temperature of the temperature increase, the highest temperature of the heat preservation 2, the water washing times of primary/secondary/tertiary reuse, the water beginning time temperature of primary/secondary/tertiary reuse, the water washing times of ice pure water, the quality assay index, etc., and the quality data is the quality state of the raw materials, the intermediate products and the finished products related to the process data, such as: quality evaluation indexes related to dissolution, condensation, water washing, stabilization and the like: melt index, bulk density, hydroxyl content, residual butyraldehyde, residual ET2H, residual hydrogen chloride, yellow index, volatiles, and the like; the process data related to any one of the steps of dissolution, condensation, washing, stabilization, and the like may affect not only the quality evaluation index of the current step but also the steps subsequent to the current step.
Therefore, in order to analyze the possible effects of the process parameters of each process on the subsequent process, it is necessary to perform data collection and data mining on the overall process of PVB product production.
S403, performing data processing on the acquired process data and quality data to prepare a sample set;
after process data and quality data of the whole process of PVB product production are obtained, generally, discretization treatment, impurity removal treatment and the like are required to be carried out on related data; to facilitate subsequent data mining.
In one example, the step of performing data processing on the acquired process data and quality data to form a sample set specifically includes:
discretizing the acquired process data to obtain an m-dimension item set X, which can be expressed as:wherein X is i (i=1.,), n) is a randomly sampled sample in m-dimensional space.
Clustering the obtained quality data to obtain a process quality state table for representing various quality states in the PVB product generation process, and obtaining a term set Y;
the sample set (or object data set N) is composed of the item set X and the item set Y.
Specifically, an Apriori algorithm is applied to capture the relation rule of the former item set X-the latter item set Y, and the rule is certain to be credible. Wherein the support, confidence and promotion are defined as:
the support S defines the probability of simultaneous occurrence of the term sets X, Y in the sample set N. Confidence C measures the confidence level of the rule. When S and C meet the rule of the minimum threshold value at the same time, the rule is a strong association rule. The correlation between the item set X and the item set Y is characterized by L, the value of L is bounded by 1, when l=1, it indicates that there is no correlation between the two, when L >1, it indicates that the two have positive correlation, the higher the value, the higher the correlation, when L <1, it indicates that the two have negative correlation, the lower the value, the higher the correlation.
S405, applying an Apriori algorithm to dig out frequent item sets among all data in the sample set, generating association rules of the frequent item sets, and simultaneously calculating the support and the confidence of each association rule;
in the step, a total knowledge base can be directly constructed through the generated association rule of the frequent item set;
s407, based on a preset minimum support threshold and a preset minimum confidence threshold, clustering and optimizing association rules of the frequent item set by using a specified algorithm to obtain an optimal rule set;
the specified algorithm comprises but is not limited to a K-Means clustering algorithm and a particle swarm optimization algorithm (PSO optimization algorithm for short);
s409, establishing a correlation coefficient matrix by using the optimal rule set to form a knowledge base;
in this step, as shown in fig. 7, a correlation coefficient matrix is used in the example of PVB product production; FIG. 8 is a graph showing the results of the importance of the production index analyzed in this example; as can be seen from fig. 7 and 8: parameters with strong positive correlation with quality index data (correlation coefficient is close to 1): the temperature of the starting time of primary reuse water washing, the temperature of the starting time of tertiary reuse water washing, the highest temperature of heat preservation, the frequency setting before aldehyde feeding, the aldehyde feeding temperature, the phase transition temperature, the feeding end temperature and the like.
Therefore, when the technological parameters are regulated, the correlation coefficient matrix can be mainly referenced, and the important detection and control can be carried out on the temperature of the primary reuse water washing starting moment, the temperature of the tertiary reuse water washing starting moment, the heat preservation maximum temperature, the frequency setting before aldehyde addition, the aldehyde addition temperature, the phase transition temperature and the feeding end temperature, so that the control of higher production quality can be realized through less data processing.
S411, according to the process data of PVB product production process monitoring, extracting rules from the knowledge base to adjust the quality process parameters of PVB product production so as to realize the quality control of PVB product production.
As shown in fig. 2, in one embodiment, the step of applying Apriori algorithm to mine frequent item sets between data in the sample set and generate association rules of the frequent item sets specifically includes:
defining the item set X and the item set Y as input and output of a preset quality association rule analysis model:
constructing a thing data set N, and representing all relation rules of a previous item set X-a next item set Y; defining a minimum support threshold S min The method comprises the steps of carrying out a first treatment on the surface of the Frequent K term set initial value k=1;
calculating the support degree of all item sets in the object data set N;
selecting a support degree greater than a minimum support degree threshold S min Adding a K item set;
judging whether the K item set is an empty set or not, and if the K item set is the empty set, acquiring a frequent K-1 item set L k-1 And the termination algorithm, if not empty set, connects L k Self, derive k+1 term set C k+1 As a candidate and the algorithm ends;
pruning and iteration are carried out to obtain frequent K item sets;
wherein pruning is to remove non-frequent item sets and remove remaining candidate sets with a support less than S min The item set carries out empty set judgment on the k+1 item set;
let k=k+1, repeat the above process from calculating the support of all item sets in object data set N to pruning, to remove not infrequent item sets, remove the support of the remaining candidate sets less than S min A step of carrying out empty set judgment on the k+1 item set, and ending the algorithm when the K item set is empty;
and generating association rules of the frequent item sets according to the obtained frequent K item sets.
The quality association rule analysis model is constructed by coupling an apriori algorithm with a K-Means clustering algorithm and a particle swarm optimization algorithm, wherein the apriori algorithm is used for mining quality association rules, the K-Means clustering algorithm is used for clustering optimal rules, the particle swarm optimization algorithm is used for extracting quality association rules, and process parameters are generated according to the extracted quality association rules; to improve the production quality of PVB products.
As shown in fig. 3, in one embodiment, the step of clustering and optimizing the association rules of the frequent item set by using a specified algorithm based on the preset minimum support threshold and minimum confidence threshold to obtain an optimal rule set specifically includes:
setting a minimum support threshold and a minimum confidence threshold;
performing discrete coding processing on the object data set N by using a K-means algorithm;
all relation rules of the former item set X-the latter item set Y are subjected to rule optimization on each type of quality state by using a particle swarm algorithm based on classification of the item set Y; each minimum time period relation rule searched represents a particle, and the fitness F (r) value of the particle is calculated;
updating the speed, the position, the individual optimal influence pbest (i) and the global optimal influence gbest (i) of the particles;
and performing rule optimization through an iterative loop to obtain a final optimal rule set.
In one embodiment, the extraction of the quality association rule by the particle swarm optimization algorithm comprises the following steps:
classification: the rule corresponding to the process quality state extracted by the Apriori method is explained using the IF (condition) -THEN (result) mode method:
the first item set IF < conditions > -the last item set THEN < result >;
using logical connector OR, AND connects preconditions AND conclusions of rules, namely:
IF(V 1min ≤x 1 ＜＜V 1max )Λ...Λ(V mmin ≤x m ≤V mmax )THEN(y＝b) (1)；
(x 1 ,x 2 ,...,x m ) Is the input characteristic vector, Y is the item set Y, b is the specific value of Y, V mmin 、V mmax Representing the boundary value.
Data coding processing based on K-means algorithm: the transaction data set N is subjected to discrete encoding processing using a K-means algorithm.
In one embodiment, the step of performing discrete encoding processing on the object data set N by using a K-means algorithm specifically includes:
performing cluster analysis on m+1 arrays formed by the m-dimension item set X and the m-dimension item set Y by using a K-means algorithm;
determining a clustering K value, and setting model parameters to obtain a final clustering result;
and marking a designated label for each corresponding clustering category according to the final clustering result, and carrying out coding processing on the object data set N according to the designated labels.
As shown in fig. 3, in one embodiment, in the step of performing rule optimization on each class of quality states by using a particle swarm algorithm based on classification of the item set Y in all relation rules of the previous item set X-the next item set Y; the fitness F (r) of the particle swarm algorithm is also adjusted;
the fitness equation is:
F(r)＝αsupport(r)+βconfidence(r) (2)；
the support degree threshold and the confidence degree threshold are support (r) and confidence (r) respectively, the weight factors meet alpha, beta epsilon (0, 1), alpha+beta=1, and the relative proportion of the support degree and the confidence degree is controlled by adjusting the specific gravity of alpha and beta.
In one example of this embodiment, the weight factors α, β may be taken as 0.5, respectively, then: f (r) =0.5 support (r) +0.5confidence (r).
In one embodiment, before the step of mining out frequent item sets between data in the sample set by applying Apriori algorithm, the method further comprises:
classifying the quality state of the PVB product production process according to the obtained quality data;
interpreting association rules of each class of process quality states and corresponding classes using a conditional result schema;
and connecting preconditions of various quality states and association rules according to the association rules of each class of quality states and the corresponding class.
As shown in fig. 3, in one example, a process of PVB product quality association rule analysis can include:
the method comprises the steps of carrying out input and output adjustment on an initial model based on PSO-Kmeans-Apriori to form a quality association rule analysis model, wherein the initial model can be built by adopting a PSO-Kmeans algorithm and an Apriori algorithm in the prior art; the PSO-Kmeans algorithm and the apriori algorithm are all prior art and are not described in detail herein.
Setting a minimum support threshold and a minimum confidence threshold;
performing discrete coding processing on the object data set N by using a K-means algorithm;
all relation rules of the former item set X-the latter item set Y are subjected to rule optimization on each type of quality state by using a particle swarm algorithm based on classification of the item set Y; each minimum time period relation rule searched represents a particle, and the fitness F (r) value of the particle is calculated;
updating the speed, the position, the individual optimal influence pbest (i) and the global optimal influence gbest (i) of the particles;
and performing rule optimization through an iterative loop to obtain a final optimal rule set.
And in the iterative loop process, if the iterative loop is terminated, placing the optimal particles in a corresponding optimal rule set, and if the loop is more than one, continuing searching. And the support degree S, the confidence degree C and the lifting degree L corresponding to the quality rule of each previous item set X-next item set Y can be calculated.
Therefore, in this embodiment, based on the characteristics of multi-process flexible production of PVB products, taking into consideration the characteristics of raw materials, key processes, full samples of quality data and multiple characteristics, an improved PSO-Kmeans-Apriori algorithm model, namely a quality association rule analysis model, is utilized to avoid useless data information from related data of a large number of multiple sources, extract effective information implicit between key raw material characteristics, process parameters and product quality, such as a primary reuse water washing start time temperature, a tertiary reuse water washing start time temperature, a heat preservation maximum temperature, an aldehyde feeding pre-frequency setting, an aldehyde feeding temperature, a phase transition temperature, a feeding end temperature and the like, and establish a rule guiding production process so as to ensure the controllability of a quality control process.
In another embodiment, as shown in fig. 5, a PVB product quality association rule analysis system comprises: the system comprises a data acquisition module 100, a data preprocessing module 200, a first rule calculation module 300, a second rule calculation module 400, a knowledge base construction module 500 and a quality improvement module 600;
the data acquisition module 100 is used for acquiring process data and quality data of the whole PVB product production process;
the data preprocessing module 200 may perform data processing on the acquired process data and quality data to make a sample set;
the first rule calculation module 300 is capable of applying Apriori algorithm to mine out frequent item sets among data in the sample set, generating association rules of the frequent item sets, and calculating support and confidence of each association rule;
the second rule calculation module 400 performs clustering and optimizing processing on the association rules of the frequent item set by using a specified algorithm based on a preset minimum support threshold and a preset minimum confidence threshold so as to obtain an optimal rule set;
the knowledge base construction module 500 establishes a correlation coefficient matrix with the optimal rule set to form a knowledge base;
the quality improvement module 600 is configured to adjust quality process parameters of PVB product production according to process data monitored in a PVB product production process, and extract rules from the knowledge base, so as to realize quality control of PVB product production.
It will be appreciated that the specific implementation of the PVB product quality association rule analysis system can be found in the PVB product quality association rule analysis method described above, and will not be described in detail herein.
As shown in fig. 6, in one embodiment, the system further comprises a parameter self-tuning module 700; and the parameter self-adjusting module is used for carrying out parameter adjustment on the particle swarm algorithm in the specified algorithm.
For example: the parameter self-adjusting module 700 selects the Support degree (Support) and the Confidence degree (Confidence) as comprehensive weighted evaluation criteria, so that certain special association rules (such as high reliability when the Support degree is low, low reliability when the Support degree is high, etc.; wherein the fitness equation is:
F(r)＝αsupport(r)+βconfidence(r) (3)；
the support degree threshold and the confidence degree threshold are support (r) and confidence (r) respectively, the weight factors meet alpha, beta epsilon (0, 1), and alpha+beta=1.
As shown in fig. 6, in one embodiment, the system further comprises a data output module 800; the data output module 800 is configured to output quality process parameters for adjusting the production of the PVB product before and after.
In one example of this embodiment, the data output module 800 is a graphical transmission interface characterized by a computer program; the graphic transmission interface is connected with a visual interface, such as an industrial personal computer interface for controlling each process production link; and the display and output of quality process parameters of the front PVB product and the rear PVB product are realized.
As shown in fig. 9, in one embodiment, a computer device is provided, the computer device including a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the following steps S401 to S411 when executing the computer program:
s401, acquiring process data and quality data of a PVB product production whole procedure;
s403, performing data processing on the acquired process data and quality data to prepare a sample set;
s405, excavating a frequent item set among data in the sample set by applying an Apriori algorithm, generating association rules of the frequent item set, and simultaneously calculating the support and the confidence of each association rule;
s407, based on a preset minimum support threshold and a preset minimum confidence threshold, clustering and optimizing association rules of the frequent item set by using a specified algorithm to obtain an optimal rule set;
s409, establishing a correlation coefficient matrix by using the optimal rule set to form a knowledge base;
s411, according to process data of PVB product production process monitoring, extracting rules from the knowledge base to adjust quality process parameters of PVB product production so as to realize quality control of PVB product production.
In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, which when executed by a processor causes the processor to perform steps S401 to S411 in fig. 4.
FIG. 9 illustrates an internal block diagram of a computer device in one embodiment. The computer device includes a processor, a memory, a network interface, an input device, and a display (or an industrial personal computer) connected by a system bus. The memory includes a nonvolatile storage medium and an internal memory. The non-volatile storage medium of the computer device stores an operating system and may also store a computer program that, when executed by a processor, causes the processor to implement a PVB product quality association rule analysis method. The internal memory can also have stored therein a computer program that, when executed by a processor, can cause the processor to perform a PVB product quality association rule analysis method. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, the input device of the computer equipment can be a touch layer covered on the display screen, can also be keys, a track ball or a touch pad arranged on the shell of the computer equipment, and can also be an external keyboard, a touch pad or a mouse and the like.
It will be appreciated by persons skilled in the art that the architecture shown in fig. 9 is merely a block diagram of some of the architecture relevant to the present inventive arrangements and is not limiting as to the computer device to which the present inventive arrangements are applicable, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.
In one embodiment, the PVB product quality association rule analysis system provided by the present application can be implemented in the form of a computer program that can be run on a computer device as shown in FIG. 9. The memory of the computer device can store the various program modules that make up the PVB product quality association rules analysis system, such as the data acquisition module, the data preprocessing module, the first rule calculation module, and the like, as shown in fig. 5. The computer program of each program module is configured to cause a processor to perform the steps of the PVB product quality association rule analysis method of each of the embodiments of the present application described in the present specification.
For example, the computer device of fig. 9 can execute step S401 by a data acquisition module in a PVB product quality association rules analysis system as shown in fig. 5. The computer device may perform step S403 through the data preprocessing module. The computer device may perform step S405 and so on through the first rule calculation module.
It should be understood that, although the steps in the flowcharts of the embodiments of the present application are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in various embodiments may include multiple sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, nor do the order in which the sub-steps or stages are performed necessarily performed in sequence, but may be performed alternately or alternately with at least a portion of the sub-steps or stages of other steps or other steps.
The foregoing examples illustrate only a few embodiments of the application and are described in detail herein without thereby limiting the scope of the application. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application.
Claims (10)
1. A method for analyzing a PVB product quality association rule, comprising the steps of:
acquiring process data and quality data of the whole process of PVB product production;
performing data processing on the acquired process data and quality data to prepare a sample set;
an Apriori algorithm is applied to dig out frequent item sets among all data in the sample set, association rules of the frequent item sets are generated, and the support degree and the confidence degree of each association rule are calculated at the same time;
based on a preset minimum support threshold and a preset minimum confidence threshold, clustering and optimizing association rules of the frequent item set by using a specified algorithm to obtain an optimal rule set;
establishing a correlation coefficient matrix by using the optimal rule set to form a knowledge base;
and according to process data monitored in the PVB product production process, extracting rules from the knowledge base to adjust quality process parameters of PVB product production so as to realize controllable quality of PVB product production.
2. The method of claim 1, wherein the step of data processing the obtained process data and quality data to form a sample set comprises:
discretizing the acquired process data to obtain a term set X in m-n dimensions;
clustering the obtained quality data to obtain a process quality state table for representing various quality states in the PVB product generation process, and obtaining a term set Y;
the sample set is composed of the item set X and the item set Y.
3. The method for analyzing quality association rules of PVB products according to claim 2, wherein the step of applying Apriori algorithm to mine out frequent item sets among data in the sample set and generating association rules of the frequent item sets specifically comprises:
defining the item set X and the item set Y as input and output of a preset quality association rule analysis model:
constructing a thing data set N, and representing all relation rules of a previous item set X-a next item set Y; defining a minimum support threshold S min ；
Calculating the support degree of all item sets in the object data set N;
selecting a support degree greater than a minimum support degree threshold S min Adding a K item set; pruning and iteration are carried out to obtain frequent K item sets;
and generating association rules of the frequent item sets according to the obtained frequent K item sets.
4. The method for analyzing PVB product quality association rules according to claim 3, wherein the step of clustering and optimizing association rules of the frequent item set by using a specified algorithm based on a preset minimum support threshold and a minimum confidence threshold to obtain an optimal rule set specifically comprises the steps of:
setting a minimum support threshold and a minimum confidence threshold;
performing discrete coding processing on the object data set N by using a K-means algorithm;
all relation rules of the former item set X-the latter item set Y are subjected to rule optimization on each type of quality state by using a particle swarm algorithm based on classification of the item set Y; each minimum time period relation rule searched represents a particle, and the fitness F (r) value of the particle is calculated;
updating the speed, the position, the individual optimal influence pbest (i) and the global optimal influence gbest (i) of the particles;
and performing rule optimization through an iterative loop to obtain a final optimal rule set.
5. The method of claim 4, wherein the step of using K-means algorithm to perform discrete encoding processing on the transaction data set N, comprises:
performing cluster analysis on m+1 arrays formed by the m-dimension item set X and the m-dimension item set Y by using a K-means algorithm;
determining a clustering K value to obtain a final clustering result;
and marking a designated label for each corresponding clustering category according to the final clustering result, and carrying out coding processing on the object data set N according to the designated labels.
6. The method of claim 4, wherein in the step of optimizing all the relationship rules of the previous item set X to the next item set Y by using a particle swarm algorithm to perform rule optimization on each type of quality state based on classification of the item set Y; the fitness F (r) of the particle swarm algorithm is also adjusted;
the fitness equation is:
F(r)＝αsupport(r)+βconfidence(r)；
the support degree threshold and the confidence degree threshold are support (r) and confidence (r) respectively, the weight factors meet alpha, beta epsilon (0, 1), alpha+beta=1, and the relative proportion of the support degree and the confidence degree is controlled by adjusting the specific gravity of alpha and beta.
7. The method of claim 1, wherein prior to the step of applying Apriori algorithm to mine out frequent item sets between data in the sample set, the method further comprises:
classifying the quality state of the PVB product production process according to the obtained quality data;
interpreting association rules of each class of process quality states and corresponding classes using a conditional result schema;
and connecting preconditions of various quality states and association rules according to the association rules of each class of quality states and the corresponding class.
8. A PVB product quality association rule analysis system, comprising: the system comprises a data acquisition module, a data preprocessing module, a first rule calculation module, a second rule calculation module, a knowledge base construction module and a quality improvement module;
the data acquisition module is used for acquiring process data and quality data of the whole PVB product production process;
the data preprocessing module can perform data processing on the acquired process data and quality data to prepare a sample set;
the first rule calculation module can apply an Apriori algorithm to dig out frequent item sets among all data in the sample set, generate association rules of the frequent item sets, and calculate the support and confidence of each association rule;
the second rule calculation module is used for carrying out clustering and optimizing processing on the association rules of the frequent item set by using a specified algorithm based on a preset minimum support threshold and a preset minimum confidence threshold so as to obtain an optimal rule set;
the knowledge base construction module is used for constructing a correlation coefficient matrix by using the optimal rule set so as to form a knowledge base;
the quality improvement module is used for adjusting quality technological parameters of PVB product production according to process data monitored in PVB product production process and extracting rules from the knowledge base so as to realize controllable quality of PVB product production.
9. The PVB product quality association rule analysis system of claim 8, wherein the system further comprises a parameter self-adjustment module; and the parameter self-adjusting module is used for carrying out parameter adjustment on the particle swarm algorithm in the specified algorithm.
10. The PVB product quality association rule analysis system of claim 8, wherein the system further comprises a data output module; and the data output module is used for outputting and adjusting the quality technological parameters of PVB product production before and after.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310842896.7A CN116882822B (en) | 2023-07-11 | 2023-07-11 | PVB product quality association rule analysis method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310842896.7A CN116882822B (en) | 2023-07-11 | 2023-07-11 | PVB product quality association rule analysis method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116882822A true CN116882822A (en) | 2023-10-13 |
| CN116882822B CN116882822B (en) | 2024-05-07 |
Family
ID=88263805
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310842896.7A Active CN116882822B (en) | 2023-07-11 | 2023-07-11 | PVB product quality association rule analysis method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116882822B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102069094A (en) * | 2010-11-16 | 2011-05-25 | 北京首钢自动化信息技术有限公司 | Data mining-based plate shape control key process parameter optimization system |
| US20190213893A1 (en) * | 2018-01-05 | 2019-07-11 | Syracuse University | Smart products lifecycle management platform |
| CN110287382A (en) * | 2019-05-30 | 2019-09-27 | 武汉理工大学 | A kind of method for digging of the correlation rule towards battery production data |
| US20200150137A1 (en) * | 2018-11-09 | 2020-05-14 | Wyatt Technology Corporation | Indicating a status of an analytical instrument on a screen of the analytical instrument |
| CN114281811A (en) * | 2021-12-25 | 2022-04-05 | 盐城工学院 | Association rule mining method and system based on adaptive genetic algorithm |
| CN115562200A (en) * | 2022-09-29 | 2023-01-03 | 华能煤炭技术研究有限公司 | Coal face process control parameter feedback adjusting method and system based on Apriori |
| CN116263849A (en) * | 2022-11-30 | 2023-06-16 | 中移(苏州)软件技术有限公司 | Injection molding process parameter processing method and device and computing equipment |
-
2023
- 2023-07-11 CN CN202310842896.7A patent/CN116882822B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102069094A (en) * | 2010-11-16 | 2011-05-25 | 北京首钢自动化信息技术有限公司 | Data mining-based plate shape control key process parameter optimization system |
| US20190213893A1 (en) * | 2018-01-05 | 2019-07-11 | Syracuse University | Smart products lifecycle management platform |
| US20200150137A1 (en) * | 2018-11-09 | 2020-05-14 | Wyatt Technology Corporation | Indicating a status of an analytical instrument on a screen of the analytical instrument |
| CN110287382A (en) * | 2019-05-30 | 2019-09-27 | 武汉理工大学 | A kind of method for digging of the correlation rule towards battery production data |
| CN114281811A (en) * | 2021-12-25 | 2022-04-05 | 盐城工学院 | Association rule mining method and system based on adaptive genetic algorithm |
| CN115562200A (en) * | 2022-09-29 | 2023-01-03 | 华能煤炭技术研究有限公司 | Coal face process control parameter feedback adjusting method and system based on Apriori |
| CN116263849A (en) * | 2022-11-30 | 2023-06-16 | 中移(苏州)软件技术有限公司 | Injection molding process parameter processing method and device and computing equipment |
Non-Patent Citations (4)
| Title |
|---|
| CARLOS ARAUZ MORENO等: "Extended time-temperature rheology of polyvinyl butyral(PVB)", 《RHEOLOGICA ACTA》, 27 June 2022 (2022-06-27) * |
| 刘晓敏: "聚乙烯醇缩丁醛的半连续生产装置及工艺研究", 《中国优秀硕士论文 工程科技Ⅰ辑》, pages 37 - 52 * |
| 杨岚: "基于大数据的多工序制造过程产品质量控制研究", 《中国优秀硕士论文 工程科技Ⅱ辑》, pages 47 - 52 * |
| 林斌銮;刘栋;汪惠芬;刘庭煜;: "基于关联规则的产品工艺优化研究", 机械设计与制造工程, no. 04, 15 April 2019 (2019-04-15) * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116882822B (en) | 2024-05-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109271876B (en) | Video motion detection method based on time evolution modeling and multi-example learning | |
| CN111950191B (en) | Rotary kiln sintering temperature prediction method based on hybrid deep neural network | |
| WO2021139279A1 (en) | Data processing method and apparatus based on classification model, and electronic device and medium | |
| CN106709509B (en) | Satellite telemetry data clustering method based on time series special points | |
| CN108197647B (en) | Rapid clustering method for automobile starter endurance test data | |
| CN105955214B (en) | Batch process fault detection method based on sample time-series and neighbour's affinity information | |
| CN113591879A (en) | Deep multi-view clustering method, network, device and storage medium based on self-supervision learning | |
| CN113222149A (en) | Model training method, device, equipment and storage medium | |
| CN114328106A (en) | Log data processing method, device, equipment and storage medium | |
| CN116113942A (en) | Predicting equipment failure modes based on process traces | |
| Chu et al. | Co-training based on semi-supervised ensemble classification approach for multi-label data stream | |
| CN114676778A (en) | Abnormal data detection method and device for cooperative and mutual feedback of shield equipment data | |
| CN116258978A (en) | Target detection method for weak annotation of remote sensing image in natural protection area | |
| CN114328663A (en) | High-dimensional theater data dimension reduction visualization processing method based on data mining | |
| CN116882822B (en) | PVB product quality association rule analysis method and system | |
| CN116738551B (en) | Intelligent processing method for acquired data of BIM model | |
| CN111832426B (en) | Cross-library micro-expression recognition method and device based on double-sparse transfer learning | |
| CN111507374A (en) | Power grid mass data anomaly detection method based on random matrix theory | |
| CN116226693A (en) | Gaussian mixture model nuclear power operation condition division method based on density peak clustering | |
| CN111108516B (en) | Evaluating input data using a deep learning algorithm | |
| CN112052453A (en) | Webshell detection method and device based on Relief algorithm | |
| Wang et al. | Classification features of feather and hemp in cotton foreign fibers | |
| CN115460097B (en) | Fusion model-based mobile application sustainable trust evaluation method and device | |
| Zhong et al. | Handwritten digit recognition based on corner detection and convolutional neural network | |
| CN117076573B (en) | Data processing analysis system based on big data technology |
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 |