CN107808241A - A kind of stainless steel surfaces testing result overall analysis system - Google Patents
A kind of stainless steel surfaces testing result overall analysis system Download PDFInfo
- Publication number
- CN107808241A CN107808241A CN201710962040.8A CN201710962040A CN107808241A CN 107808241 A CN107808241 A CN 107808241A CN 201710962040 A CN201710962040 A CN 201710962040A CN 107808241 A CN107808241 A CN 107808241A
- Authority
- CN
- China
- Prior art keywords
- weight
- defect
- points
- meter
- 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.)
- Granted
Links
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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/06—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons
- G06N3/061—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons using biological neurons, e.g. biological neurons connected to an integrated circuit
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Neurology (AREA)
- Molecular Biology (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Microelectronics & Electronic Packaging (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Operations Research (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
- Investigating And Analyzing Materials By Characteristic Methods (AREA)
Abstract
A kind of stainless steel surfaces testing result overall analysis system, including：Data back system, data statistic analysis system, data-base recording system, remote access interface system；The data statistic analysis system includes neutral net evaluation system, defect marking evaluation system.Onsite surface quality testing log file is back to data statistic analysis system by data back system automatically；After data statistic analysis system receives file, the evaluation of two sets of methods is performed, and statistic analysis result is transferred to data-base recording system according to neutral net evaluation system, defect marking evaluation system；After data-base recording system receives statistic analysis result, deposited.The present invention improves scientific research personnel with quality inspection personnel to the live rapid integrated evaluation of coil of strip surface quality.
Description
Technical field
The invention belongs to stainless steel field, data analysis, Surface testing field.
Background technology
Surface testing is the direct measurement to stainless steel surfaces quality judging, but due to the continuous lifting of industrialization, coil of strip
Cross linear velocity to be also substantially improved, therefore only judge with Quality Inspector's bore hole, can not meet the needs of stainless steel surfaces inspection.Examine on surface
The application of instrument is surveyed, alleviates the work of Quality Inspector, but is only capable of recording the information of defect, coil of strip can not be carried out according to these information
Synthetic determination.
The content of the invention
The present invention seeks to by stainless steel surfaces testing result overall analysis system, to scientific research personnel and quality inspection personnel pair
Coil of strip defect makes evaluation.
A kind of stainless steel surfaces testing result overall analysis system enters on the basis of being built upon data analysis identification
Capable.Instrument is examined by Maintenance Table to record, steps up the accuracy of table inspection record, and is combined big data and analyzed, can be to every volume
Ratio of defects, defect number, defective locations, distribution characteristics are counted, and realize defect by the grading automatical judgement of light and heavy degree.
Technical solution of the present invention：A kind of stainless steel surfaces testing result overall analysis system, it is taken based on linux system
Build, using Spring does WEB frameworks, MySQL does data persistence, Shiro does rights management for Mybatis access, uses
RESTful styles WebService services, Lucene makees search engine, Quartz does timer-triggered scheduler, BootStrap+HTML5 is done
Front end page, supports the access at PC, Android, IOS end, on this system portable to HADOOP big data cluster servers, tool
There is scalability.
A kind of stainless steel surfaces testing result overall analysis system, including：Data back system, data statistic analysis system
System, data-base recording system, remote access interface system；The data statistic analysis system include neutral net evaluation system,
Defect marking evaluation system；
The neutral net evaluation system, every meter of defect number is counted by coil of strip point upper surface, point 1 to 9 places, at 9 more than, totally 10
Individual parameter, lower surface count every meter of defect number, point 1 to 9 places, at 9 more than, totally 10 parameters.With this 20 parameter conducts
Nerve network input parameter, totally 26 layers of intermediate layer, output level judge 0-100 1 parameter of level,（Export adding for input component
Quan He, i.e. intermediate layer are equal to the weighting of the preceding layer neuron output adjacent with it with the input of any neuron in output layer
With）；I.e.
In formula, netjFor the input of any neuron j in a certain layer, export as Oj, OiFor with it is any in this layer of adjacent preceding layer
The output of neuron；wjiFor the connection weight between neuron j and neuron i；
Wherein： f(netj) be neuron output function, desired output Dpk, reality output Ypk, then the variance exported is：
Wherein N is input sample（Vector）Total number, p are input vector dimension（This programme is 20）, k is output vector dimension
（This programme is 1）.
The defect marking evaluation system, according to defect（Such as：It is mingled with, scratches）It is the average length of attribute, average area, every
Rice number by stages is scored, then gets such defect score value by the weighted average of these attributes, last all kinds of defects
The weighted average of score value gets the comprehensive grading of this coil of strip, and score range is at 0-100 points.Detailed assessment is as follows：
Average length comments 95 points, weight 0.1 in 0-5mm, and 80 points, weight 0.1 are commented in 5-10mm, and 60 points, weight are commented in 10-15mm
0.1,10 points, weight 0.1 are commented in more than 15mm, weighted score can choose the score value of length attribute；
Average area is in 0-7mm295 points, weight 0.2 are commented, in 7-15mm280 points, weight 0.2 are commented, in 15-25mm2Comment 60 points, power
0.2 is weighed, in 25mm210 points, weight 0.2 are commented above, and weighted score can choose the score value of area attribute；
Every meter of number comments 95 points, weight 0.03 at 0-2, and 80 points, weight 0.07 are commented at 3-4, and 60 points, weight are commented at 5-6
0.1,40 points, weight 0.2 are commented at 7-9,10 points, weight 0.3 are commented more than 10, weighted score can choose every meter of number category
The score value of property；
The score value of defect is the score value of average length of defect, the score value three of the score value of average area and every meter of number and.It is comprehensive
Weighted average point of the scoring for all kinds of defects is closed, the score value that the score value of inclusion defect is multiplied by 0.6 weight and scuffing defect is multiplied by
The sum of 0.4 weight, comprehensive scores are divided in 0-100, comprehensive grading of this score value as current coil of strip surface quality.
The above three levels of appraisement system point, first layer is the score value of each generic attribute of defect, and the second layer is various defects
Score value, last layer is comprehensive grading.Wherein, average length value can only fall in a score value section, therefore average length
Weight be 0.1；Average area value can only fall in a score value section, therefore the weight of average area is 0.2；Every meter of number
There is value in each section, therefore the weight of every meter of number is 0.03+0.07+0.1+0.2+0.3=0.7.Three groups of category more than
The weight for such defect that property read group total goes out is 0.1+0.2+0.7=1.The weight that comprehensive grading is calculated by all kinds of defects is
0.6+0.4=1.Above appraisement system, calculating process weight and be 1, each weight are optimization gained；According to actual conditions, defect
The interval of each generic attribute can increase and adjust, weight also can adjust, but must ensure weight and for 1.
There are average length, average area and three attributes of every meter of number per a kind of defect, pass through the score value of this three attributes
With the score value that can calculate this defect, comprehensive grading can be calculated finally by the weighted sum of all kinds of defect score values, you can as
The Comprehensive Assessment of coil of strip surface quality.
The present invention improves scientific research personnel with quality inspection personnel to the live rapid integrated evaluation of coil of strip surface quality.
Embodiment
The root module of the embodiment of the present invention examines data analysis for table, and submodule is table inspection report（Data summarization
Diagram）, it is mingled with management, scratches management（Two sub- defect management modules）, appraisement system（Evaluation system is with new module）Log in system
After system, it can be seen that table examines data analysis module and corresponding submodule.I.e. table examines reporting modules, is mingled with management module, is mingled with
Management module, scratch management module, appraisement system module.
Onsite surface quality testing log file is back to data statistic analysis system by data back system automatically；Data
After statistical analysis system receives file, two sets of methods are performed according to neutral net evaluation system, defect marking evaluation system
Evaluation, and statistic analysis result is transferred to data-base recording system；After data-base recording system receives statistic analysis result, enter
Row deposit；Interface is remotely accessed, ensures that scientific research personnel remotely accesses the system by browser, reporting modules point production is examined by table
Line, steel grade, defect, date carry out statistical analysis, the statistic analysis result of Real Time Observation surface quality, pass through each defect management mould
Block can check flaw evaluation score value, defect distribution diagram, normal distribution, evaluating can be changed by appraisement system module,
Amendment evaluation system in real time.
Claims (5)
1. a kind of stainless steel surfaces testing result overall analysis system, including：Data back system, data statistic analysis system,
Data-base recording system, remote access interface system；The data statistic analysis system includes neutral net evaluation system, defect
Marking evaluation system；It is characterized in that the neutral net evaluation system counts every meter of defect number by coil of strip point upper surface, 1 is divided to arrive
At 9, at 9 more than, totally 10 parameters, lower surface count every meter of defect number, point 1 to 9 places, at 9 more than, totally 10 parameters；Fortune
By the use of this 20 parameters as nerve network input parameter, totally 26 layers of intermediate layer exports and is
In formula, netj is the input of any neuron j in a certain layer, and it is to appoint in the preceding layer adjacent with this layer to export as Oj, Oi
The output of one neuron；Connection weights of the wji between neuron j and neuron i；
Wherein：F (netj) is the output function of neuron, and desired output Dpk, reality output Ypk, then the variance exported is：
Wherein N is input sample vector total number, and p is input vector dimension, and k is output vector dimension.
A kind of 2. stainless steel surfaces testing result overall analysis system according to claim 1, it is characterized in that the defect is beaten
Divide evaluation system, scored according to the average length of defect attribute, average area, every meter of number by stages, then pass through defect
The weighted average of attribute gets such defect score value, and the synthesis that the weighted averages of last all kinds of defect score values gets coil of strip is commented
Point, score range is at 0-100 points.
A kind of 3. stainless steel surfaces testing result overall analysis system according to claim 1, it is characterized in that average length exists
0-5mm comments 95 points, weight 0.1, and average length comments 80 points, weight 0.1 in 5-10mm, and average length comments 60 points, power in 10-15mm
0.1 is weighed, average length comments 10 points, weight 0.1 in more than 15mm, and weighted score is the score value of length attribute；
Average area is in 0-7mm295 points, weight 0.2 are commented, average area is in 7-15mm280 points, weight 0.2 are commented, average area exists
15-25mm260 points, weight 0.2 are commented, average area is in 25mm210 points, weight 0.2 are commented above, and weighted score is to choose area category
The score value of property；Every meter of number comments 95 points, weight 0.03 at 0-2, and every meter of number comments 80 points, weight 0.07 at 3-4, and every meter individual
Number comments 60 points, weight 0.1 at 5-6, and every meter of number comments 40 points, weight 0.2 at 7-9, and every meter of number comments 10 more than 10
Divide, weight 0.3, weighted score is the score value of every meter number attribute.
4. a kind of stainless steel surfaces testing result overall analysis system according to claim 1, it is characterized in that the score value of defect=
The score value of the number of the score value of score value+average area of the average length of defect+every meter.
A kind of 5. stainless steel surfaces testing result overall analysis system according to claim 1, it is characterized in that comprehensive grading is
The weighted average of all kinds of defects point, the score value of inclusion defect are multiplied by the weight that 0.6 weight is multiplied by 0.4 with scratching the score value of defect
Sum.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710962040.8A CN107808241B (en) | 2017-10-16 | 2017-10-16 | Stainless steel surface detection result comprehensive analysis system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710962040.8A CN107808241B (en) | 2017-10-16 | 2017-10-16 | Stainless steel surface detection result comprehensive analysis system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107808241A true CN107808241A (en) | 2018-03-16 |
| CN107808241B CN107808241B (en) | 2021-08-06 |
Family
ID=61583515
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710962040.8A Active CN107808241B (en) | 2017-10-16 | 2017-10-16 | Stainless steel surface detection result comprehensive analysis system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107808241B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109002974A (en) * | 2018-06-29 | 2018-12-14 | 首钢京唐钢铁联合有限责任公司 | A kind of coil of strip surface quality grading determination method and device |
| CN109685761A (en) * | 2018-11-08 | 2019-04-26 | 宁波送变电建设有限公司甬城配电网建设分公司 | A kind of power cable defect inspection method and its detection system based on cloud platform |
| CN115049319A (en) * | 2022-08-15 | 2022-09-13 | 张家港广大特材股份有限公司 | Quality evaluation method and system for steel forging forming |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101097581A (en) * | 2006-06-27 | 2008-01-02 | 宝山钢铁股份有限公司 | Processing parameter setting method of tension straightening machine set correct roller |
| CN102880934A (en) * | 2012-09-07 | 2013-01-16 | 中国标准化研究院 | Integrity evaluation method for food enterprise |
| CN102968701A (en) * | 2012-12-17 | 2013-03-13 | 天津职业技术师范大学 | Method for assessing teacher practical skills based on neural network technology |
| CN104751288A (en) * | 2015-03-30 | 2015-07-01 | 北京首钢自动化信息技术有限公司 | Segment-based multi-dimensional online quality evaluation system and method for steel coils |
| CN105469423A (en) * | 2015-11-16 | 2016-04-06 | 北京师范大学 | Online target tracking method based on continuous attractor neural network |
| CN105741023A (en) * | 2016-01-26 | 2016-07-06 | 秦皇岛首秦金属材料有限公司 | Informationized steel plate quality testing system |
| CN105976098A (en) * | 2016-04-28 | 2016-09-28 | 大连理工大学 | BP neural network-based college and university teaching quality evaluation method |
| CN106096788A (en) * | 2016-06-21 | 2016-11-09 | 重庆科技学院 | Converter steelmaking process cost control method based on PSO_ELM neutral net and system |
| CN106447765A (en) * | 2016-09-26 | 2017-02-22 | 宁波舜宇智能科技有限公司 | Product data processing apparatus and method |
| CN106845825A (en) * | 2017-01-18 | 2017-06-13 | 西安交通大学 | It is a kind of to be traced to the source and control method based on the cold rolling of strip steel quality problems for improving PCA |
-
2017
- 2017-10-16 CN CN201710962040.8A patent/CN107808241B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101097581A (en) * | 2006-06-27 | 2008-01-02 | 宝山钢铁股份有限公司 | Processing parameter setting method of tension straightening machine set correct roller |
| CN102880934A (en) * | 2012-09-07 | 2013-01-16 | 中国标准化研究院 | Integrity evaluation method for food enterprise |
| CN102968701A (en) * | 2012-12-17 | 2013-03-13 | 天津职业技术师范大学 | Method for assessing teacher practical skills based on neural network technology |
| CN104751288A (en) * | 2015-03-30 | 2015-07-01 | 北京首钢自动化信息技术有限公司 | Segment-based multi-dimensional online quality evaluation system and method for steel coils |
| CN105469423A (en) * | 2015-11-16 | 2016-04-06 | 北京师范大学 | Online target tracking method based on continuous attractor neural network |
| CN105741023A (en) * | 2016-01-26 | 2016-07-06 | 秦皇岛首秦金属材料有限公司 | Informationized steel plate quality testing system |
| CN105976098A (en) * | 2016-04-28 | 2016-09-28 | 大连理工大学 | BP neural network-based college and university teaching quality evaluation method |
| CN106096788A (en) * | 2016-06-21 | 2016-11-09 | 重庆科技学院 | Converter steelmaking process cost control method based on PSO_ELM neutral net and system |
| CN106447765A (en) * | 2016-09-26 | 2017-02-22 | 宁波舜宇智能科技有限公司 | Product data processing apparatus and method |
| CN106845825A (en) * | 2017-01-18 | 2017-06-13 | 西安交通大学 | It is a kind of to be traced to the source and control method based on the cold rolling of strip steel quality problems for improving PCA |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109002974A (en) * | 2018-06-29 | 2018-12-14 | 首钢京唐钢铁联合有限责任公司 | A kind of coil of strip surface quality grading determination method and device |
| CN109685761A (en) * | 2018-11-08 | 2019-04-26 | 宁波送变电建设有限公司甬城配电网建设分公司 | A kind of power cable defect inspection method and its detection system based on cloud platform |
| CN109685761B (en) * | 2018-11-08 | 2020-09-22 | 宁波送变电建设有限公司甬城配电网建设分公司 | Power cable defect detection method and detection system based on cloud platform |
| CN115049319A (en) * | 2022-08-15 | 2022-09-13 | 张家港广大特材股份有限公司 | Quality evaluation method and system for steel forging forming |
| CN115049319B (en) * | 2022-08-15 | 2022-12-20 | 张家港广大特材股份有限公司 | Quality evaluation method and system for steel forging forming |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107808241B (en) | 2021-08-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105445421B (en) | A kind of method of aesthetic quality during predictive slice nicotinic alcohol by appearance index | |
| CN107808241A (en) | A kind of stainless steel surfaces testing result overall analysis system | |
| CN106549813A (en) | A kind of appraisal procedure and system of network performance | |
| CN107248030A (en) | A kind of bond Risk Forecast Method and system based on machine learning algorithm | |
| CN105843870B (en) | The analysis method and its application of repeatability and reproducibility | |
| CN109359770B (en) | Model and method for predicting heatstroke occurrence based on machine learning | |
| CN111861703A (en) | Data-driven wind control strategy rule generation method and system and risk control method and system | |
| CN113177729A (en) | Risk early warning method, system and equipment based on enterprise associated risk conduction | |
| PAPAIOANNOU | Use of social media for assessing sustainable urban mobility indicators | |
| CN102937575B (en) | Watermelon sugar degree rapid modeling method based on secondary spectrum recombination | |
| CN107632010A (en) | A kind of quantitative approach of combination LIBS to steel samples | |
| CN103902798B (en) | Data preprocessing method | |
| CN110288149A (en) | Multizone water resource supply and demand risk evaluating method and equipment | |
| CN109685321A (en) | Event risk method for early warning, electronic equipment and medium based on data mining | |
| CN107944761A (en) | Early warning and monitoring analysis method is complained based on artificial intelligence protection of consumers' rights index enterprise | |
| CN114943458A (en) | Enterprise ESG (electronic service guide) rating method based on weight distribution model | |
| CN104899424A (en) | Microscopic feature based method for objectively testing ripeness and leaf structure of flue-cured tobacco leaves | |
| Kona et al. | AMMI and GGE biplot analysis of genotype by environment interaction for yield and yield contributing traits in confectionery groundnut | |
| CN116881530B (en) | Device surface defect detection system based on deep learning | |
| CN107895235A (en) | Financial modeling system based on decision tree | |
| CN114722295B (en) | Internet-based technology promotion system and method | |
| Uygun et al. | Overview of methodological trends of the last decade in strategic management research | |
| CN103593561B (en) | A kind of method using characteristic index to characterize tobacco style feature | |
| Nagaraj et al. | IPL Players Cost Pay Prediction using Machine Learning Techniques | |
| Saparamadu et al. | What Leads to Intra-Industry Trade between Sri Lanka and South Asia? |
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 |