CN109669030A - A kind of industrial injecting products defect diagnostic method based on decision tree - Google Patents

A kind of industrial injecting products defect diagnostic method based on decision tree Download PDF

Info

Publication number
CN109669030A
CN109669030A CN201811624044.6A CN201811624044A CN109669030A CN 109669030 A CN109669030 A CN 109669030A CN 201811624044 A CN201811624044 A CN 201811624044A CN 109669030 A CN109669030 A CN 109669030A
Authority
CN
China
Prior art keywords
characteristic parameter
injecting products
decision tree
attribute type
sample data
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201811624044.6A
Other languages
Chinese (zh)
Inventor
张彩霞
王向东
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Foshan University
Original Assignee
Foshan University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Foshan University filed Critical Foshan University
Priority to CN201811624044.6A priority Critical patent/CN109669030A/en
Publication of CN109669030A publication Critical patent/CN109669030A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
    • G01N33/44—Resins; Plastics; Rubber; Leather
    • G01N33/442—Resins; Plastics
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
    • G01N33/44—Resins; Plastics; Rubber; Leather
    • G01N33/445—Rubber
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/243—Classification techniques relating to the number of classes
    • G06F18/24323—Tree-organised classifiers

Landscapes

  • Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Chemical & Material Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Food Science & Technology (AREA)
  • Evolutionary Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • Medicinal Chemistry (AREA)
  • Analytical Chemistry (AREA)
  • Biochemistry (AREA)
  • General Health & Medical Sciences (AREA)
  • Immunology (AREA)
  • Pathology (AREA)
  • Injection Moulding Of Plastics Or The Like (AREA)

Abstract

The invention discloses a kind of industrial injecting products defect diagnostic method based on decision tree, comprising: acquisition injecting products creation data, as sample data set, the data of characteristic parameter when obtaining injecting products attribute type and producing the injecting products of the attribute type；The data building decision tree for choosing the product attribute type and the characteristic parameter, obtains defect dipoles classifying rules；The product attribute type of injecting products to be measured is acquired, defect dipoles classifying rules is matched, obtains the characteristic parameter for influencing injecting products attribute type to be measured；The present invention carries out analytical calculation by the data to characteristic parameter when acquiring resulting product attribute type and producing the injecting products of the attribute type, it generates the branch node of decision tree and establishes decision tree, obtain defect classifying rules, positioning leads to the characterisitic parameter of product defects, be conducive to find out product and the reason of defect occurs, instead of Artificial Diagnosis, defect diagonsis efficiency is improved.

Description

A kind of industrial injecting products defect diagnostic method based on decision tree
Technical field
The present invention relates to industrial products defect diagonsis fields, are molded more specifically to a kind of industry based on decision tree Product defects diagnostic method.
Background technique
Traditional injection industry process of producing product can be because there are many defects in misoperation, and the type of defect also has very It is more, such as: deformation lacks and expects, has bubble etc., and product is caused many because being known as of defect occur, such as: when melt temperature, injection Between, injection speed, dwell pressure and pressure maintaining duration etc. because there are many factor influenced, occur faulty goods when It waits, the principal element for leading to defect occur cannot be positioned well.
Summary of the invention
Aiming at the problems existing in the prior art, the present invention provides a kind of industrial injecting products defect based on decision tree and examines Disconnected method improves defect diagonsis efficiency instead of Artificial Diagnosis.
The solution that the present invention solves its technical problem is: a kind of industrial injecting products defect diagonsis based on decision tree Method, comprising:
Step 1: acquisition injecting products creation data obtains injecting products attribute type and life as sample data set The data of characteristic parameter when producing the injecting products of the attribute type；
Step 2: the data building decision tree of the product attribute type and the characteristic parameter is chosen, defect is obtained and sentences Disconnected classifying rules；
Step 3: acquiring the product attribute type of injecting products to be measured, matches defect dipoles classifying rules, obtain influencing to Survey the characteristic parameter of injecting products attribute type.
Further, the building decision tree constructs decision tree using ID3 algorithm.
Further, the selection product attribute type in the step 2 and characteristic parameter include:
The characteristic parameter includes: melt temperature, injection speed, injection temperature, dwell pressure and pressure maintaining duration, and this 5 kinds Characteristic parameter forms defect dipoles parameter set A (A1,A2,A3,A4,A5) wherein A1Represent melt temperature, A2Represent injection speed, A3 Represent injection temperature, A4Represent dwell pressure, A5Represent pressure maintaining duration；
The product product attribute type includes: deformation, has bubble and lack material.
Further, the building decision tree in the step 2 includes:
Calculate characteristic parameter entropy and corresponding information gain, choose the maximum characteristic parameter of information gain as decision The root node of tree.
Further, the entropy for calculating characteristic parameter and corresponding information gain include:
The product attribute Type C that the sample data is concentrated has m seed type, product attribute Type Ci(i=1,2 ..., M) concentrating the frequency occurred in sample data is Pi(i=1,2,3 ..., m), then the entropy of sample data set are as follows:
Wherein S is sample data set；
Characteristic parameter has k different values in sample data set, and sample data set S is divided into k by characteristic parameter Sample data subset { S1,S2,...,Sk, then the entropy of characteristic parameter are as follows:
Wherein | Si| (i=1,2 ..., k) it is sample data subset SiIn include sample size, | S | for sample data son The sample size for including in collection S, Entropy (Si) it is sample data subset SiEntropy, Ai(i=1,2 ..., k) it is characterized ginseng Number；
Then press characteristic parameter AiInformation gain Gain (Si, Ai) it is that the entropy of sample data set subtracts the entropy of characteristic parameter Ai:
The beneficial effects of the present invention are: the present invention is by acquisition resulting product attribute type and producing the Attribute class The data of characteristic parameter when the injecting products of type carry out analytical calculation, generate the branch node of decision tree and establish decision tree, Obtaining defect classifying rules, positioning leads to the characterisitic parameter of product defects, and be conducive to find out product and the reason of defect occurs, instead of Artificial Diagnosis improves defect diagonsis efficiency.
Detailed description of the invention
To describe the technical solutions in the embodiments of the present invention more clearly, make required in being described below to embodiment Attached drawing is briefly described.Obviously, described attached drawing is a part of the embodiments of the present invention, rather than is all implemented Example, those skilled in the art without creative efforts, can also be obtained according to these attached drawings other designs Scheme and attached drawing.
Fig. 1 is flow chart of the invention；
Fig. 2 is the schematic diagram for the decision tree that the present invention establishes.
Specific embodiment
It is carried out below with reference to technical effect of the embodiment and attached drawing to design of the invention, specific structure and generation clear Chu, complete description, to be completely understood by the purpose of the present invention, feature and effect.Obviously, described embodiment is this hair Bright a part of the embodiment, rather than whole embodiments, based on the embodiment of the present invention, those skilled in the art are not being paid Other embodiments obtained, belong to the scope of protection of the invention under the premise of creative work.In addition, be previously mentioned in text All connection relationships not singly refer to that component directly connects, and referring to can be according to specific implementation situation, by adding or reducing connection Auxiliary, Lai Zucheng more preferably connection structure.Each technical characteristic in the invention, under the premise of not conflicting conflict It can be with combination of interactions.
Embodiment 1, referring to Fig.1, a kind of industrial injecting products defect diagnostic method based on decision tree, comprising:
Step 1: acquisition injecting products creation data obtains injecting products attribute type and life as sample data set The data of characteristic parameter when producing the injecting products of the attribute type；
Step 2: the data building decision tree of the product attribute type and the characteristic parameter is chosen, defect is obtained and sentences Disconnected classifying rules；
Step 3: acquiring the product attribute type of injecting products to be measured, matches defect dipoles classifying rules, obtain influencing to Survey the characteristic parameter of injecting products attribute type.
By acquiring injecting products creation data, the change curve of characteristic parameter in available process of producing product.
As optimization, the building decision tree constructs decision tree using ID3 algorithm.
As optimization, selection product attribute type and characteristic parameter in the step 2 include:
The characteristic parameter includes: melt temperature, injection speed, injection temperature, dwell pressure and pressure maintaining duration, and this 5 kinds Characteristic parameter forms defect dipoles parameter set A (A1,A2,A3,A4,A5) wherein A1Represent melt temperature, A2Represent injection speed, A3 Represent injection temperature, A4Represent dwell pressure, A5Represent pressure maintaining duration；
The product product attribute type includes: deformation, has bubble and lack material.
As optimization, the building decision tree in the step 2 includes:
Calculate characteristic parameter entropy and corresponding information gain, choose the maximum characteristic parameter of information gain as decision The root node of tree.
As optimization, the entropy for calculating characteristic parameter and corresponding information gain include:
The product attribute Type C that the sample data is concentrated has m seed type, product attribute Type Ci(i=1,2 ..., M) concentrating the frequency occurred in sample data is Pi(i=1,2,3 ..., m), then the entropy of sample data set are as follows:
Wherein S is sample data set；
Characteristic parameter has k different values in sample data set, and sample data set S is divided into k by characteristic parameter Sample data subset { S1,S2,...,Sk, then the entropy of characteristic parameter are as follows:
Wherein | Si| (i=1,2 ..., k) it is sample data subset SiIn include sample size, | S | for sample data son The sample size for including in collection S, Entropy (Si) it is sample data subset SiEntropy, Ai(i=1,2 ..., k) it is characterized ginseng Number；
Then press characteristic parameter AiInformation gain Gain (Si, Ai) it is that the entropy of sample data set subtracts the entropy of characteristic parameter Ai:
The course of work of the invention:
Acquisition injecting products creation data obtains product attribute type and produces the attribute as sample data set The characteristic parameter when product out of type, in the present embodiment, the product attribute type include: deformation, have bubble and lack material, The characteristic parameter includes: melt temperature, injection speed, injection temperature, dwell pressure and pressure maintaining duration, and the present embodiment chooses 30 For group as sample data set expansion explanation, the value that the characteristic parameter is chosen is the corresponding change curve of reaction this feature parameter Trend, as shown in table 1:
The sample data set of table 1 characteristic parameter and product attribute type
Product attribute type includes deformation, has bubble and lack material, and corresponding sample size is 10,12,8.It counts first The entropy for the 30 groups of sample data sets chosen is calculated, the comentropy of as each characterisitic parameter:
The conditional entropy and information gain of each characterisitic parameter are calculated referring next to formula (1-2) and (1-3).With dwell pressure A4Illustrate, obtain:
The comentropy of the characterisitic parameter calculated, conditional entropy and information gain are as shown in table 2:
Comentropy, conditional entropy and the information gain value of 2 characterisitic parameter of table
Characterisitic parameter Comentropy Conditional entropy Information gain
Dwell pressure 1.56559623 1.262471263 0.3008836
Injection speed 1.56559623 0.8 0.76559623
Injection pressure 1.56559623 0.819325461 0.746270769
Melt temperature 1.56559623 0.728955488 0.836640742
Pressure maintaining duration 1.56559623 0.965148445 0.600447785
Reference table 2, it can be deduced that the information gain of characterisitic parameter melt temperature is maximum.Melt temperature is then chosen as decision The root node of tree, and sample data concentrates the variation tendency of melt temperature to be divided into two parts, is divided into raising and lowering, the decision tree Two Bifurcation Set D will be generated1And D2, further division is carried out in Liang Ge branch, calculates Bifurcation Set D respectively1And D2In include it is each The information gain of a characterisitic parameter, and using the maximum characterisitic parameter of information gain as the next node of decision tree, and so on, Until the entropy of characterisitic parameter all in Bifurcation Set is 0, then decision tree is completed.
Node is selected according to resulting information gain is calculated, the decision tree for judging defect cause is obtained, such as Fig. 2 institute Show.
Referring to Fig. 2, defect dipoles classifying rules below is obtained, and obtains influencing the feature ginseng of injecting products attribute type Number:
1. product occurs lacking material when melt temperature decline；
2. when the dwell time declines, product is deformed when melt temperature rises；
3. the dwell time rises when melt temperature rises, when injection pressure declines, there is bubble in product；
4. the dwell time rises when melt temperature rises, injection pressure rises, and when injection speed level, product becomes Shape；
5. the dwell time rises when melt temperature rises, injection pressure rises, and when injection speed rises, gas occurs in product Bubble.
The attribute type of injecting products is to lack material, then matches defect dipoles classifying rules, it can be deduced that melt temperature is shadow Ring the characteristic parameter for lacking material attribute type.
Then when product occurs lacking material, this characterisitic parameter of melt temperature is navigated to according to the classifying rules of decision tree, is Defect classification provides decision-making foundation, navigates to and provides the device of melt temperature, checks whether the device breaks down, find out The reason of now lacking material defect.
Industrial injecting products can use the method for the present invention, and great amount of samples data set is calculated and analyzed, is sentenced There is the reason of defect in disconnected classifying rules, positioning.
The present invention passes through to spy when acquiring resulting product attribute type and producing the injecting products of the attribute type The data for levying parameter carry out analytical calculation, generate the branch node of decision tree and establish decision tree, obtain defect classifying rules, fixed Position leads to the characterisitic parameters of product defects, is conducive to find out product and the reason of defect occurs, instead of Artificial Diagnosis, improves defect and examines Disconnected efficiency.
Better embodiment of the invention is illustrated above, but the invention is not limited to the implementation Example, those skilled in the art can also make various equivalent modifications on the premise of without prejudice to spirit of the invention or replace It changes, these equivalent variation or replacement are all included in the scope defined by the claims of the present application.

Claims (5)

1. a kind of industrial injecting products defect diagnostic method based on decision tree, it is characterised in that: include:
Step 1: acquisition injecting products creation data, as sample data set, obtain injecting products product attribute type and The data of characteristic parameter when producing the injecting products of the product attribute type；
Step 2: the data building decision tree of the product attribute type and the characteristic parameter is chosen, defect dipoles point are obtained Rule-like；
Step 3: acquiring the product attribute type of injecting products to be measured, matches defect dipoles classifying rules, obtains influencing note to be measured The characteristic parameter of the product attribute type of molding product.
2. a kind of industrial injecting products defect diagnostic method based on decision tree according to claim 1, it is characterised in that: The building decision tree constructs decision tree using ID3 algorithm.
3. a kind of industrial injecting products defect diagnostic method based on decision tree according to claim 1, it is characterised in that: Selection product attribute type and characteristic parameter in the step 2 include:
The characteristic parameter includes: melt temperature, injection speed, injection temperature, dwell pressure and pressure maintaining duration, this 5 kinds of features Parameter forms defect dipoles parameter set A (A1,A2,A3,A4,A5) wherein A1Represent melt temperature, A2Represent injection speed, A3It represents Injection temperature, A4Represent dwell pressure, A5Represent pressure maintaining duration；
The product attribute type includes: deformation, has bubble and lack material.
4. a kind of industrial injecting products defect diagnostic method based on decision tree according to claim 1, it is characterised in that: Building decision tree in the step 2 includes:
Calculate characteristic parameter entropy and corresponding information gain, choose the maximum characteristic parameter of information gain as decision tree Root node.
5. a kind of industrial injecting products defect diagnostic method based on decision tree according to claim 4, it is characterised in that: The entropy for calculating characteristic parameter and corresponding information gain include:
The product attribute Type C that the sample data is concentrated has m seed type, product attribute Type Ci(i=1,2 ..., m) It is P that sample data, which concentrates the frequency occurred,i(i=1,2,3 ..., m), then the entropy of sample data set are as follows:
Wherein S is sample data set；
Characteristic parameter has k different values in sample data set, and sample data set S is divided into k sample by characteristic parameter Data subset { S1,S2,...,Sk, then the entropy of characteristic parameter are as follows:
Wherein | Si| (i=1,2 ..., k) it is sample data subset SiIn include sample size, | S | be sample data subset S In include sample size, Entropy (Si) it is sample data subset SiEntropy, Ai(i=1,2 ..., k) it is characterized parameter；
Then press characteristic parameter AiInformation gain Gain (Si, Ai) it is that the entropy of sample data set subtracts the entropy of characteristic parameter Ai:
CN201811624044.6A 2018-12-28 2018-12-28 A kind of industrial injecting products defect diagnostic method based on decision tree Pending CN109669030A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201811624044.6A CN109669030A (en) 2018-12-28 2018-12-28 A kind of industrial injecting products defect diagnostic method based on decision tree

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201811624044.6A CN109669030A (en) 2018-12-28 2018-12-28 A kind of industrial injecting products defect diagnostic method based on decision tree

Publications (1)

Publication Number Publication Date
CN109669030A true CN109669030A (en) 2019-04-23

Family

ID=66146460

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201811624044.6A Pending CN109669030A (en) 2018-12-28 2018-12-28 A kind of industrial injecting products defect diagnostic method based on decision tree

Country Status (1)

Country Link
CN (1) CN109669030A (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111125078A (en) * 2019-12-19 2020-05-08 华北电力大学 Defect data correction method for relay protection device
CN112308120A (en) * 2020-10-15 2021-02-02 国家电网公司华北分部 Method and device for grading defects of relay protection device and storage medium
CN117786543A (en) * 2024-02-28 2024-03-29 沂水友邦养殖服务有限公司 Digital broiler raising information storage management method and system
CN118456807A (en) * 2024-07-10 2024-08-09 汕头市高德斯精密科技有限公司 Self-adaptive control system of injection molding equipment

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20030163437A1 (en) * 2002-02-22 2003-08-28 Lee Shih-Jong J. Information integration method for decision regulation in hierarchic decision systems
CN103153576A (en) * 2010-06-07 2013-06-12 乌尔里克·佐伊特 Method and device for monitoring and optimizing injection molding processes
CN103714348A (en) * 2014-01-09 2014-04-09 北京泰乐德信息技术有限公司 Rail transit fault diagnosis method and system based on decision-making tree
CN103760231A (en) * 2014-01-07 2014-04-30 天津大学 Detection method and device for welding defect giant magneto-resistance eddy current based on decision-making tree
CN104111920A (en) * 2013-04-16 2014-10-22 华为技术有限公司 Decision-making tree based prediction method and device
CN104228012A (en) * 2014-07-02 2014-12-24 郑州轻工业学院 High-accuracy estimation method for relation between machining parameters and deformation of injection molding part
CN104850858A (en) * 2015-05-15 2015-08-19 华中科技大学 Injection-molded product defect detection and recognition method
CN108215052A (en) * 2017-12-30 2018-06-29 大连銮艺精密模塑制造有限公司 Prevent the method for liquid crystal polymer resin injection moulding process surface product defect

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20030163437A1 (en) * 2002-02-22 2003-08-28 Lee Shih-Jong J. Information integration method for decision regulation in hierarchic decision systems
CN103153576A (en) * 2010-06-07 2013-06-12 乌尔里克·佐伊特 Method and device for monitoring and optimizing injection molding processes
CN104111920A (en) * 2013-04-16 2014-10-22 华为技术有限公司 Decision-making tree based prediction method and device
CN103760231A (en) * 2014-01-07 2014-04-30 天津大学 Detection method and device for welding defect giant magneto-resistance eddy current based on decision-making tree
CN103714348A (en) * 2014-01-09 2014-04-09 北京泰乐德信息技术有限公司 Rail transit fault diagnosis method and system based on decision-making tree
CN104228012A (en) * 2014-07-02 2014-12-24 郑州轻工业学院 High-accuracy estimation method for relation between machining parameters and deformation of injection molding part
CN104850858A (en) * 2015-05-15 2015-08-19 华中科技大学 Injection-molded product defect detection and recognition method
CN108215052A (en) * 2017-12-30 2018-06-29 大连銮艺精密模塑制造有限公司 Prevent the method for liquid crystal polymer resin injection moulding process surface product defect

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
张彩霞 等: "基于信息物理融合系统的智能制造架构研究", 《计算机科学》 *
杨锦荣 等: "基于数据挖掘的表面贴装技术品质诊断系统", 《制造业自动化》 *
殷复莲: "《数据分析与数据挖掘实用教程》", 30 September 2017, 中国传媒大学出版社 *
瞿金平 等: "《聚合物成型原理及成型技术》", 30 June 2001, 化学工业出版社 *

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111125078A (en) * 2019-12-19 2020-05-08 华北电力大学 Defect data correction method for relay protection device
CN112308120A (en) * 2020-10-15 2021-02-02 国家电网公司华北分部 Method and device for grading defects of relay protection device and storage medium
CN112308120B (en) * 2020-10-15 2023-09-29 国家电网公司华北分部 Method, device and storage medium for grading defects of relay protection device
CN117786543A (en) * 2024-02-28 2024-03-29 沂水友邦养殖服务有限公司 Digital broiler raising information storage management method and system
CN117786543B (en) * 2024-02-28 2024-05-10 沂水友邦养殖服务有限公司 Digital broiler raising information storage management method and system
CN118456807A (en) * 2024-07-10 2024-08-09 汕头市高德斯精密科技有限公司 Self-adaptive control system of injection molding equipment

Similar Documents

Publication Publication Date Title
CN109669030A (en) A kind of industrial injecting products defect diagnostic method based on decision tree
CN102867115A (en) Farmland division method based on fuzzy c-means clustering
CN108241925A (en) A kind of discrete manufacture mechanical product quality source tracing method based on outlier detection
CN108280236A (en) A kind of random forest visualization data analysing method based on LargeVis
CN109272040B (en) Radar working mode generation method
Matuszny Building decision trees based on production knowledge as support in decision-making process
CN105574265B (en) Entire assembly model quantitative description towards model index
CN105631465A (en) Density peak-based high-efficiency hierarchical clustering method
CN112931919B (en) Method and device for controlling moisture content of cut tobacco
CN113641733B (en) Real-time intelligent estimation method for river cross section flow
CN107861965A (en) Data intelligence recognition methods and system
CN108537249B (en) Industrial process data clustering method for density peak clustering
CN105701672A (en) A traditional Chinese medicine quality tracing method based on big data technology
CN110033024A (en) Turbine optimal sliding pressure curve acquisition method for air Cooling and heat supply unit variable working condition
CN105590167A (en) Method and device for analyzing electric field multivariate operating data
CN116108115A (en) Automatic feature generation featureols data processing method for bank transaction flow data
CN110969111A (en) Automatic identification and classification method for mechanical part digital drawing
CN116090331A (en) Shale gas horizontal well fracturing parameter optimization method
CN114154433A (en) Fluid simulation method based on data comparison analysis
CN103901819B (en) The process operation fast searching method of feature based mark
CN113946621A (en) Mining method of filamentation workshop data fluctuation relation based on association rule
CN112685468B (en) Ecological system attribute component composition structure long-term evolution graph expression method
CN110008221A (en) A kind of injection molding creation data and MES system data interactive method
CN113741263B (en) Multi-mode process modal partitioning method based on global-local information clustering
CN113762609B (en) Product quality prediction method and device

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
CB02 Change of applicant information
CB02 Change of applicant information

Country or region after: China

Address after: 528000 Foshan Institute of science and technology, Xianxi reservoir West Road, Shishan town, Nanhai District, Foshan City, Guangdong Province

Applicant after: Foshan University

Address before: 528000 Foshan Institute of science and technology, Xianxi reservoir West Road, Shishan town, Nanhai District, Foshan City, Guangdong Province

Applicant before: FOSHAN University

Country or region before: China