CN108428067A - A kind of printing quality analysis of Influential Factors method based on historical data - Google Patents
A kind of printing quality analysis of Influential Factors method based on historical data Download PDFInfo
- Publication number
- CN108428067A CN108428067A CN201810311639.XA CN201810311639A CN108428067A CN 108428067 A CN108428067 A CN 108428067A CN 201810311639 A CN201810311639 A CN 201810311639A CN 108428067 A CN108428067 A CN 108428067A
- Authority
- CN
- China
- Prior art keywords
- data
- printing quality
- stamp
- analysis
- quality
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 56
- 238000007639 printing Methods 0.000 title claims abstract description 45
- 238000004458 analytical method Methods 0.000 title claims abstract description 38
- 238000012545 processing Methods 0.000 claims abstract description 27
- 238000007418 data mining Methods 0.000 claims abstract description 12
- 238000003066 decision tree Methods 0.000 claims description 23
- 230000008569 process Effects 0.000 claims description 22
- 230000002159 abnormal effect Effects 0.000 claims description 7
- 238000013138 pruning Methods 0.000 claims description 6
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000007405 data analysis Methods 0.000 claims description 3
- 238000001514 detection method Methods 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 230000017105 transposition Effects 0.000 claims description 3
- 238000004519 manufacturing process Methods 0.000 abstract description 12
- 238000004043 dyeing Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 4
- 230000007547 defect Effects 0.000 description 3
- 239000004744 fabric Substances 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 239000004753 textile Substances 0.000 description 2
- 239000003513 alkali Substances 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000009412 basement excavation Methods 0.000 description 1
- 239000000969 carrier Substances 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000002203 pretreatment Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000003908 quality control method Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000006641 stabilisation Effects 0.000 description 1
- 238000011105 stabilization Methods 0.000 description 1
- 238000010025 steaming Methods 0.000 description 1
- 238000011144 upstream manufacturing Methods 0.000 description 1
- 238000005406 washing Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—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
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- 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)
- Strategic Management (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Data Mining & Analysis (AREA)
- Entrepreneurship & Innovation (AREA)
- Educational Administration (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Operations Research (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Computational Biology (AREA)
- Game Theory and Decision Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Quality & Reliability (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Manufacturing & Machinery (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The printing quality analysis of Influential Factors method based on historical data that the present invention relates to a kind of, includes the following steps:Stamp initial data is stored by unified standard;Stamp data to being integrated into big data platform carry out quality of data processing;Data mining analysis is carried out to the data after data quality treatment, finds out the influence factor of printing quality;Analysis result is visualized and is fed back.The present invention can improve stamp quality of production instability problem, improve printing quality.
Description
Technical field
The present invention relates to dyeing and finishing technique fields, more particularly to a kind of printing quality influence factor based on historical data point
Analysis method.
Background technology
Dyeing and finishing is to enrich pattern fabric in textile industry, improve the most important link of added value of product.Textile printing quality
With kinds of fibers, fabric structure, patterns of fabric, printing method, equipment performance and pre-treatment, plate-making, colour combination, printing, steaming
All various aspects such as change, washing are related, are that dyeing and finishing converted products quality problems are most, maximum one of quality control difficulty is processed
Journey.Due to dyeing and finishing industry technological process is complicated, internal process relevance is strong and external influence factors are more, changes in process parameters is big,
Production is more with management controlling element, industrial automatization is low, and can be used for specification there is presently no quantitative, qualitative knowledge gives birth to
Production, causes printing quality in process of producing product to cannot keep stabilization.In recent years, the stamp quality of production is unstable annoyings always
Dyeing and finishing industry has brought tremendous economic losses to the enterprise in the field.
Dyeing and finishing industry is single to the solution of printing quality instability problem now, is all by not reached to printing quality
After carrying out little sample testing at mark, the process condition range of stable quality is provided.There are following 4 point defects for this method:
1, in actual production, lead to many because being known as of same mass defect.So printing quality influence factor be difficult to it is bright
Determine position, can not position defect can not just be improved.
2, process modification is similar to technology establishment process, all relies on the experience of technical staff, the improvement result tool obtained
There is unstability.
3, it tests, does not account for mutual between the upstream and downstream technique of production process for the sample of extra fine quality problem
It influences, often will appear new problem again after modified technique.
4, time-consuming, accuracy rate is low, durability is poor for current methods.
Based on disadvantages described above, dyeing and finishing industry to stamp quality of production instability problem urgently one it is unified, effective
Solution.
Invention content
The printing quality analysis of Influential Factors based on historical data that technical problem to be solved by the invention is to provide a kind of
Method can improve stamp quality of production instability problem, improve printing quality.
The technical solution adopted by the present invention to solve the technical problems is:A kind of printing quality based on historical data is provided
Analysis of Influential Factors method, which is characterized in that include the following steps:
(1) stamp initial data is stored by unified standard;
(2) quality of data processing is carried out to the stamp data for being integrated into big data platform;
(3) data mining analysis is carried out to the data after data quality treatment, finds out the influence factor of printing quality;
(4) analysis result is visualized and is fed back.
Stamp initial data is stored in distributed file system or data warehouse in the step (1), and is used
Hadoop+Spark big data analysis platforms, using Spark as computing engines.
The step (2) includes following sub-step:
(21) original stamp data, detection missing values, exceptional value, the abnormal conditions of characteristic value are read;
(22) processing of the missing values based on case scalping method is carried out to initial data;
(23) outlier processing based on box figure is carried out to the data by missing values processing;
(24) selection of the characteristic value based on Pearson correlation coefficient is carried out to the data by outlier processing;
(25) storage is by the quality of data treated data.
Case scalping method in the step (22) refers to:Judge whether missing values are more than 2 to a record, if then deleting
The data, if not the average value of the data set attribute is then used to fill.
The outlier processing based on box figure refers in the step (23):By calculating the boundary of data set box figure,
Outlier is rejected to new data set, obtains non-Outlier Data group, later, average value is carried out to abnormal data group and replaces to obtain target
Data.
The characteristic value based on Pearson correlation coefficient in the step (24) selects:Calculate each attribute of data set with
Pearson correlation coefficient between printing quality attribute chooses attribute of the coefficient more than 0.65 as new data set.
The step (3) includes following sub-step:
(31) the stamp data that the quality of data is handled well are read, libsvm format conversions are carried out to it;
(32) data after format transformation are trained using the decision Tree algorithms based on pre- paper-cut and rear Pruning strategy;
(33) the minimum decision-tree model of accuracy rate highest, the depth of tree is chosen to be preserved;
(34) decision-tree model of storage is analyzed, analytic process is divided into two parts:First, selection classification results are
The path of high quality stamp is analyzed, and the stamp of high quality can be produced by finding out technological parameter under what conditions;Second is that seeing
Decision tree Attribute transposition priority is examined, finds out which technique influences maximum to printing quality;
(35) result after data mining analysis is preserved by unified standard.
The decision Tree algorithms based on pre- paper-cut and rear Pruning strategy refer in the step (32):By the way that decision tree is arranged most
The threshold value of big depth and information delta, stopping the growth of tree early in training process prevents decision-tree model overfitting;Later,
The accuracy rate of the decision-tree model of each depth is calculated, chooses the minimum model of accuracy rate highest, depth as final defeated
Go out model.
The step (4) is specially:Printing quality influence factor is ranked up by importance with bar graph form, with item
Shape diagram form shows the relationship between printing quality and influence factor;Analysis result is fed back into enterprise with report form.
Advantageous effect
Due to the adoption of the above technical solution, compared with prior art, the present invention having the following advantages that and actively imitating
Fruit:Experience of the present invention independent of skilled worker, analysis result are stablized;Process cycle of the present invention is short and has reusable
Property;Processing cost of the present invention is low, and accuracy rate is high.
Description of the drawings
Fig. 1 is the printing quality analysis of Influential Factors method flow schematic diagram based on historical data;
Fig. 2 is the schematic diagram of quality of data processing;
Fig. 3 is the work flow diagram of data mining analysis.
Specific implementation mode
Present invention will be further explained below with reference to specific examples.It should be understood that these embodiments are merely to illustrate the present invention
Rather than it limits the scope of the invention.In addition, it should also be understood that, after reading the content taught by the present invention, people in the art
Member can make various changes or modifications the present invention, and such equivalent forms equally fall within the application the appended claims and limited
Range.
Embodiments of the present invention are related to a kind of printing quality analysis of Influential Factors method based on historical data, using big
Data technique is handled and is analyzed to stamp creation data, find out be hidden in the printing quality of data behind and influence factor it
Between relationship.
Present embodiment completes the processing to stamp data and analysis in terms of two:
The processing of the one, qualities of data.Data are the carriers of information, quality is to process management, decision branch as a kind of resource
It holds, the activity such as cooperation demand analysis has important guiding function.In order to enable data effectively to support daily operation and determine
Plan, data allow for accurately reflecting reality the situation in the world.Stamp production data recording each ring in stamp production process
The technological parameter of section.The under cover relationship between printing quality and influence factor inside stamp creation data.When the quality of data not
Height, such as data are incomplete, data are inconsistent, data redundancy when, can cause data that cannot effectively be handled.In recent years,
Many on-line detecting systems apply in the production of dyeing and finishing stamp, such as alkali concentration, pH value, humidity, temperature on-line checking.But
The production of dyeing and finishing stamp is a semi-automatic process, some process procedures need the intervention operation of skilled worker, and part stamp
Processing parameter still needs to manually estimate control.So stamp creation data acquires in data or during data integration, all without
Method avoids data quality problem.In conjunction with the characteristics of stamp data, the present invention is from the angle of instance layer, to stamp creation data
Data cleansing is carried out, the quality of data is promoted.Quality of data processing is divided into the processing of the missing values based on case scalping method, is based on box
The outlier processing of figure and three parts of feature selecting based on Pearson correlation coefficient.
Two, data mining analysis.Stamp data have good performance after the quality of data is handled, to hiding information
Power.But it still can not only be found out between printing quality and technological parameter from a large amount of stamp data with the mode of statistics
Relationship.It is therefore desirable to which data are analyzed and are handled using the means of data mining.Data mining is also known as knowing in database
Know and find, refers to and disclose the non-flat of information that is implicit, not previously known and having potential value from the mass data of database
All processes are the hot spots of current database field and artificial intelligence field research.In the data mining analysis stage, decision tree is used
Algorithm carries out knowledge excavation to stamp creation data, finds out the relationship between printing quality and influence factor.
As shown in Figure 1, being as follows:
Step 1 defines standard set, expansible uniform data exchange agreement, realizes stamp data from company information
System is to the Seamless integration- between big data platform.
Stamp initial data is pressed unified standard storage in distributed file system or data warehouse by step 2.This reality
It applies in mode, the big data analysis platform used is Hadoop+Spark, using HDFS as distributed file system, is used
Hive is as data warehouse, using Spark as computing engines.
Step 3 carries out quality of data processing to the stamp data for being integrated into big data platform.As shown in Fig. 2, detailed process
It is as follows:
1) original stamp data are read, detection missing values, exceptional value, the abnormal conditions of characteristic value targetedly select
Processing method.
2) processing of the missing values based on case scalping method is carried out to initial data;Specially:Judge whether a record lacks
Mistake value is more than 2, and the data are deleted if missing values are more than 2;If not the average value of the data set attribute is then used to fill.
3) outlier processing based on box figure is carried out to the data by missing values processing.Babinet contains most
Normal data, and except babinet coboundary and lower boundary be exactly abnormal data.By calculating the boundary of data set box figure,
Outlier is rejected to new data set, non-Outlier Data group [Q1-3IQR, Q3+3IQR] is obtained, later to abnormal data group [Q1-
3IQR, Q1-1.5IQR] and [Q3+1.5IQR, Q3+3IQR] carry out average value replace to obtain target data.
4) selection of the characteristic value based on Pearson correlation coefficient is carried out to the data by outlier processing;Specially:Meter
The Pearson correlation coefficient between each attribute of data set and printing quality attribute is calculated, chooses attribute of the coefficient more than 0.65 as new
Data set.
5) storage is by the quality of data treated data.
Step 4 carries out data mining analysis to the data after data quality treatment, finds out the influence factor of printing quality.
As shown in figure 3, detailed process is as follows:
1) the stamp data that the quality of data is handled well are read, libsvm format conversions are carried out to it.
2) data after format transformation are trained using the decision Tree algorithms based on pre- paper-cut and rear Pruning strategy;Its
In, it is the threshold value by the way that decision tree depth capacity and information delta is arranged based on pre- paper-cut and rear Pruning strategy, in training process
Stop the growth of tree early, prevent decision-tree model overfitting.Later, the accuracy rate of the decision-tree model of each depth is carried out
It calculates, chooses the minimum model of accuracy rate highest, depth as final output model.
3) the minimum decision-tree model of accuracy rate highest, the depth of tree is chosen to be preserved.
4) decision-tree model of storage is analyzed.Analytic process is also classified into two parts:First, selection classification results are
The path of high quality stamp is analyzed, and the stamp of high quality can be produced by finding out technological parameter under what conditions;Second is that seeing
Decision tree Attribute transposition priority is examined, finds out which technique influences maximum to printing quality.
5) result after data mining analysis is preserved by unified standard.
Step 5 visualizes analysis result and feeds back.Detailed process is as follows:
1) printing quality influence factor is ranked up with bar graph form by importance, stamp is shown with bar graph form
Relationship between quality and influence factor.
2) analysis result is fed back into enterprise with report form.
It is not difficult to find that experience of the present invention independent of skilled worker, analysis result is stablized;Process cycle of the present invention is short simultaneously
And there is reusability;Processing cost of the present invention is low, and accuracy rate is high.
Claims (9)
1. a kind of printing quality analysis of Influential Factors method based on historical data, which is characterized in that include the following steps:
(1) stamp initial data is stored by unified standard;
(2) quality of data processing is carried out to the stamp data for being integrated into big data platform;
(3) data mining analysis is carried out to the data after data quality treatment, finds out the influence factor of printing quality;
(4) analysis result is visualized and is fed back.
2. the printing quality analysis of Influential Factors method according to claim 1 based on historical data, which is characterized in that institute
It states stamp initial data in step (1) to be stored in distributed file system or data warehouse, and big using Hadoop+Spark
Data Analysis Platform, using Spark as computing engines.
3. the printing quality analysis of Influential Factors method according to claim 1 based on historical data, which is characterized in that institute
It includes following sub-step to state step (2):
(21) original stamp data, detection missing values, exceptional value, the abnormal conditions of characteristic value are read;
(22) processing of the missing values based on case scalping method is carried out to initial data;
(23) outlier processing based on box figure is carried out to the data by missing values processing;
(24) selection of the characteristic value based on Pearson correlation coefficient is carried out to the data by outlier processing;
(25) storage is by the quality of data treated data.
4. the printing quality analysis of Influential Factors method according to claim 3 based on historical data, which is characterized in that institute
The case scalping method stated in step (22) refers to:Judge whether missing values are more than 2 to a record, if so, the data are deleted, if
It is not that the average value of the data set attribute is then used to fill.
5. the printing quality analysis of Influential Factors method according to claim 3 based on historical data, which is characterized in that institute
Stating the outlier processing based on box figure in step (23) refers to:By calculating the boundary of data set box figure, to new data set
Outlier is rejected, non-Outlier Data group is obtained, later, average value is carried out to abnormal data group and replaces to obtain target data.
6. the printing quality analysis of Influential Factors method according to claim 3 based on historical data, which is characterized in that institute
State in step (24) based on Pearson correlation coefficient characteristic value selection refer to:Calculate each attribute of data set and printing quality category
Property between Pearson correlation coefficient, choose coefficient more than 0.65 attribute as new data set.
7. the printing quality analysis of Influential Factors method according to claim 1 based on historical data, which is characterized in that institute
It includes following sub-step to state step (3):
(31) the stamp data that the quality of data is handled well are read, libsvm format conversions are carried out to it;
(32) data after format transformation are trained using the decision Tree algorithms based on pre- paper-cut and rear Pruning strategy;
(33) the minimum decision-tree model of accuracy rate highest, the depth of tree is chosen to be preserved;
(34) decision-tree model of storage is analyzed, analytic process is divided into two parts:First, it is high-quality to choose classification results
The path of amount stamp is analyzed, and the stamp of high quality can be produced by finding out technological parameter under what conditions;Second is that observation is determined
Plan tree Attribute transposition priority finds out which technique influences maximum to printing quality;
(35) result after data mining analysis is preserved by unified standard.
8. the printing quality analysis of Influential Factors method according to claim 7 based on historical data, which is characterized in that institute
Stating the decision Tree algorithms based on pre- paper-cut and rear Pruning strategy in step (32) refers to:By the way that decision tree depth capacity and letter is arranged
The threshold value for ceasing increment, stopping the growth of tree early in training process prevents decision-tree model overfitting;Later, to each depth
The accuracy rate of decision-tree model is calculated, and chooses the minimum model of accuracy rate highest, depth as final output model.
9. the printing quality analysis of Influential Factors method according to claim 1 based on historical data, which is characterized in that institute
Stating step (4) is specially:Printing quality influence factor is ranked up by importance with bar graph form, it is aobvious with bar graph form
Show the relationship between printing quality and influence factor;Analysis result is fed back into enterprise with report form.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810311639.XA CN108428067A (en) | 2018-04-09 | 2018-04-09 | A kind of printing quality analysis of Influential Factors method based on historical data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810311639.XA CN108428067A (en) | 2018-04-09 | 2018-04-09 | A kind of printing quality analysis of Influential Factors method based on historical data |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108428067A true CN108428067A (en) | 2018-08-21 |
Family
ID=63160668
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810311639.XA Pending CN108428067A (en) | 2018-04-09 | 2018-04-09 | A kind of printing quality analysis of Influential Factors method based on historical data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108428067A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110009268A (en) * | 2018-10-31 | 2019-07-12 | 上海船舶工艺研究所(中国船舶工业集团公司第十一研究所) | One kind being used for body section logistics link analysis method |
CN110188085A (en) * | 2019-04-18 | 2019-08-30 | 红云红河烟草(集团)有限责任公司 | Quality data model method for building up between a kind of tobacco volume hired car |
CN110347721A (en) * | 2019-07-08 | 2019-10-18 | 紫光云技术有限公司 | A kind of floristic analysing method of flag flower |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106611283A (en) * | 2016-06-16 | 2017-05-03 | 四川用联信息技术有限公司 | Manufacturing material purchasing analysis method based on decision tree algorithm |
CN107330892A (en) * | 2017-07-24 | 2017-11-07 | 内蒙古工业大学 | A kind of sunflower disease recognition method based on random forest method |
CN107610469A (en) * | 2017-10-13 | 2018-01-19 | 北京工业大学 | A kind of day dimension regional traffic index forecasting method for considering multifactor impact |
-
2018
- 2018-04-09 CN CN201810311639.XA patent/CN108428067A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106611283A (en) * | 2016-06-16 | 2017-05-03 | 四川用联信息技术有限公司 | Manufacturing material purchasing analysis method based on decision tree algorithm |
CN107330892A (en) * | 2017-07-24 | 2017-11-07 | 内蒙古工业大学 | A kind of sunflower disease recognition method based on random forest method |
CN107610469A (en) * | 2017-10-13 | 2018-01-19 | 北京工业大学 | A kind of day dimension regional traffic index forecasting method for considering multifactor impact |
Non-Patent Citations (1)
Title |
---|
杨枝雨: "基于大数据的印花质量影响因素分析方法研究", 《中国优秀硕士学位论文全文数据 工程科技Ⅰ辑》 * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110009268A (en) * | 2018-10-31 | 2019-07-12 | 上海船舶工艺研究所(中国船舶工业集团公司第十一研究所) | One kind being used for body section logistics link analysis method |
CN110188085A (en) * | 2019-04-18 | 2019-08-30 | 红云红河烟草(集团)有限责任公司 | Quality data model method for building up between a kind of tobacco volume hired car |
CN110347721A (en) * | 2019-07-08 | 2019-10-18 | 紫光云技术有限公司 | A kind of floristic analysing method of flag flower |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US20220413455A1 (en) | Adaptive-learning intelligent scheduling unified computing frame and system for industrial personalized customized production | |
CN108428067A (en) | A kind of printing quality analysis of Influential Factors method based on historical data | |
JP4681426B2 (en) | Apparatus and method for analyzing relation between operation and quality in manufacturing process, computer program, and computer-readable recording medium | |
CN112418130A (en) | Banana maturity detection method and device based on BP neural network | |
CN107133628A (en) | A kind of method and device for setting up data identification model | |
CN113572625B (en) | Fault early warning method, early warning device, equipment and computer medium | |
CN110991495B (en) | Method, system, medium, and apparatus for predicting product quality in manufacturing process | |
CN110363355A (en) | A kind of cloud-Bian Xietong the forecast system and method for alumina producing index | |
WO2021219515A1 (en) | Method, device and computer program for generating quality information concerning a coating profile, method, device and computer program for generating a database, and monitoring device | |
CN111077876B (en) | Power station equipment state intelligent evaluation and early warning method, device and system | |
CN111340269B (en) | Real-time optimization method for process industrial process | |
CN109656808A (en) | A kind of Software Defects Predict Methods based on hybrid active learning strategies | |
EP4388496A1 (en) | Methods and systems for generating segmentation masks | |
CN109669030A (en) | A kind of industrial injecting products defect diagnostic method based on decision tree | |
CN109711665A (en) | A kind of prediction model construction method and relevant device based on financial air control data | |
CN116026487B (en) | Liquid level temperature measuring method, liquid level temperature measuring device, computer equipment and storage medium | |
JP2003141215A (en) | Operation analyzing device, method, computer program and computer readable storage medium, in manufacturing process | |
JP2010231524A (en) | Data analysis method and data analysis program | |
Ullah | Blockchain Technology in Smart Agriculture Environment: A PLS-SEM | |
CN114842178A (en) | Online visual interaction system and method based on electronic product | |
US7877238B2 (en) | Data classification supporting method, computer readable storage medium, and data classification supporting apparatus | |
WO2021076609A1 (en) | Collaborative learning model for semiconductor applications | |
Wang et al. | Patterned Fabric Defect Detection Based on Double-branch Parallel Improved Faster-RCNN | |
US20240127449A1 (en) | Computer vision based monoclonal quality control | |
Gilabert et al. | Welding process quality improvement with machine learning techniques |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180821 |