CN108241925A - A kind of discrete manufacture mechanical product quality source tracing method based on outlier detection - Google Patents
A kind of discrete manufacture mechanical product quality source tracing method based on outlier detection Download PDFInfo
- Publication number
- CN108241925A CN108241925A CN201611243368.6A CN201611243368A CN108241925A CN 108241925 A CN108241925 A CN 108241925A CN 201611243368 A CN201611243368 A CN 201611243368A CN 108241925 A CN108241925 A CN 108241925A
- Authority
- CN
- China
- Prior art keywords
- quality
- data
- product
- cluster
- product 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
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 35
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000013450 outlier detection Methods 0.000 title claims abstract description 13
- 230000002159 abnormal effect Effects 0.000 claims abstract description 21
- 241001269238 Data Species 0.000 claims abstract description 4
- 238000004364 calculation method Methods 0.000 claims description 10
- 230000007547 defect Effects 0.000 claims description 9
- 239000000463 material Substances 0.000 claims description 4
- 238000012935 Averaging Methods 0.000 claims description 3
- 238000013138 pruning Methods 0.000 claims description 3
- 238000013480 data collection Methods 0.000 claims 1
- 238000000605 extraction Methods 0.000 claims 1
- 238000011835 investigation Methods 0.000 claims 1
- 238000012545 processing Methods 0.000 claims 1
- 239000002699 waste material Substances 0.000 claims 1
- 238000007619 statistical method Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012797 qualification 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
- 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
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Theoretical Computer Science (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Educational Administration (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Manufacturing & Machinery (AREA)
- Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- General Factory Administration (AREA)
Abstract
The present invention discloses a kind of discrete manufacture mechanical product quality source tracing method based on outlier detection, and fields are manufacturing informatization technical field.For the problem of currently quality tracing method cannot accurately analyze the reason of causing mechanical product quality problem very much in Discrete Manufacturing Process, it is proposed a kind of discrete manufacture mechanical product quality source tracing method based on outlier detection, the m kind reasons of quality problems may be caused by extracting first under the various conditions of production, then the tracking data in production process counts the n kind quality index datas of the product produced under these potential causes respectively, the quality problems that a m*n is constructed using these data are traced to the source data set, then the factor that peels off of the quality index data under various potential causes is calculated, and calculate abnormal quality index, the possibility size for the reason of causing quality problems is analyzed finally by the size for comparing abnormal quality index, so as to which the quality tracing for product provides important information.
Description
Technical field
The invention belongs to manufacturing informatization technical fields, are related to a kind of discrete manufacture machinery production based on outlier detection
Quality source tracing method.
Background technology
With manufacturing fast development, manufacturing enterprise increasingly pays close attention to the quality tracing of product.How product is solved
Quality tracing problem proposes the informatization of manufacturing enterprise new requirement.And realize that the core of quality tracing is matter
Amount is traced to the source.
In recent years, with the raising that enterprise-quality is realized, some simple quality tracing methods are gradually general in enterprise
And it promotes, but mostly based on the statistical method of the single quality index data of utilization.These methods are generated in quality problems of tracing to the source
The reason of when generally by the use of the mean value of this kind of index of such as product qualification rate as data come analyze contrast quality problems generate
The reason of.But in discrete mechanical manufacture course of products, due to production process complexity, process of producing product is also different, makes
The reason of causing product quality problem can not quickly and be correctly traceable to the statistical method of single quality index data.
Invention content
The purpose of the present invention is mainly for currently quality tracing method cannot be analyzed accurately very much in Discrete Manufacturing Process
The problem of the reason of going out to cause mechanical product quality problem, proposes a kind of discrete manufacture engineering goods matter based on outlier detection
Source tracing method is measured, quality problems may be caused by being extracted first, in accordance with people, machine, material, method, ring etc. under the various conditions of production
M kind reasons, then the tracking data in production process count the n kinds of the product produced under these potential causes respectively
Quality index data, the quality problems that a m*n is constructed using these data are traced to the source data set, then calculated various potential
The factor that peels off of quality index data under reason, and calculate abnormal quality index, finally by comparing abnormal quality index
Size analyze the possibility size for the reason of causing quality problems, so as to which the quality tracing for product provides important letter
Breath.
The present invention is to reach above-mentioned purpose by the following technical programs：A kind of discrete manufacture machinery based on outlier detection
Product quality source tracing method, this method comprises the following steps：
1) product quality problem data set is built：
1.1) quality problems potential cause is extracted：It is extracted under the various conditions of production according to people, machine, material, method, ring etc.
It may cause the m kind reasons of quality problems；
1.2) statistical product quality index data：Tracking data in production process counts potential at these respectively
The n kind quality index datas of the product produced under reason；
1.3) data set is built：A m*n is constructed using the n kind product quality indicator data under potential m kinds reason
Quality problems trace to the source data set, the product quality indicator includes two major class：One kind is to reflect the index of product inherent quality,
Mainly product averaging parameter；It is another kind of be reflect process of producing product in work quality index, as mass loss rate,
Rejection rate, finished product repair rate etc.；
2) data are pre-processed, calculates product quality indicator：For eliminate different product quality index data dimension and
The different influence of value range, and retain the relationship between each data, the present invention is using " min-max laws for criterion " as quality
Problem is traced to the source the preprocess method of data set, and formula is as follows：
Wherein x is the data before pretreatment, and x* is pretreated data, and max is the maximum value of sample data, and min is
The minimum value of sample data, max-min are very poor；
3) part for calculating product quality indicator peels off the factor：
3.1) the corresponding n kinds product quality indicator data of potential cause of quality problems will likely be caused to be divided into one group of number
According to D, each data object is expressed as p in D；
3.2) data set is clustered using Clustering, calculates cluster centre, cluster radius successively, to cluster centre
Distance, similar point is divided into a cluster, the data object beta pruning that will can be clustered, will be unable to the data of cluster according to
Decision condition selects outlier Candidate Set.The cluster centre calculation formula is as follows：
Wherein niTo cluster the data object number of i, xiFor the data object in cluster i, xoFor cluster centre；
The calculation formula of the cluster radius R is as follows：
Wherein R be cluster radius, niTo cluster the data object number of i；
The calculation formula of the data point to cluster centre is as follows：
Wherein diDistance for data point to cluster centre；
4) part for calculating product quality indicator peels off the factor：
4.1) the k distances of data object p in outlier Candidate Set are calculated, k-distance (p) are expressed as, when k meets item
Part：
A) at least there are k number according to object o ' ∈ D { p } so that d (p, o ')≤d (p, o)；
B) at least there are k-1 data object o ' ∈ D { p } so that d (p, o ') ＜ d (p, o)；
The calculation formula of k distances is as follows：
K-distance (p)=d (p, o)
Wherein, the kth distance of data object p is k-distance (p), Euclideans of the d (p, o) between object p and object o
Distance, Euclidean distances of the d (p, o ') between object p and object o '；The calculation formula of the Euclidean distance is as follows：
4.2) kth of computing object p is apart from neighborhood NK(p), formula is as follows：
NK(p)=q | d (p, o)≤k-distance (p) }
4.3) reach distance of two objects in D is calculated, formula is as follows：
Reach-disk (p, o)=max { k-distance (o), d (p, o) }
4.4) the local reachability density lrd of computing object pk(p), formula is as follows：
4.5) part of computing object p peels off factor LOF, and formula is as follows：
4.6) step 3.3) is repeated to step 3.7), and the part of dead band peels off the factor when calculating all；
5) abnormal quality index is calculated, formula is as follows：
L=LOFk*u
Wherein, L defines abnormal quality index, and u is product defects rate, and wherein product defects rate calculation formula is：
Wherein, for c to identify defects of number, N is Sample Size；
6) according to the abnormal quality index calculated in 5), to that may cause quality problems the reason of is ranked up, wherein
The the abnormal quality index of data object the big, more it is possible that for the reason of causing product quality problem；
7) according to sequence the reason of may causing quality problems in 6), output is traced to the source sort result；
8) according to tracing to the source in 7) as a result, one by one to quality problems may be caused the reason of according to abnormal quality exponential size into
Row is investigated one by one.
Description of the drawings
Fig. 1 shows a kind of discrete manufacture mechanical product quality source tracing method based on outlier detection provided by the invention
Flow chart；
Fig. 2 shows the flow charts of the method for cluster data beta pruning provided by the invention of tracing to the source quality problems；
Fig. 3 shows the flow chart of the method provided by the invention for calculating abnormal quality index；
Specific embodiment
To make the objectives, technical solutions, and advantages of the present invention clearer, the present invention is made below in conjunction with attached drawing into
The detailed description of one step：
The present invention proposes a kind of discrete manufacture mechanical product quality source tracing method based on outlier detection, as shown in Figure 1,
This method comprises the following steps：
1. the discrete manufacture product quality problem data set of structure：According to people, machine, material, method, ring, etc. mark off and cause
The m kind potential causes of product quality problem；Tracking data in production process is counted respectively under these potential causes
The n kind quality index datas of the product of production；One is constructed using the n kind product quality indicator data under potential m kinds reason
The quality problems of a m*n are traced to the source data set, and the product quality indicator includes two major class, and one kind is to reflect product inherent quality
Index, mainly product averaging parameter, another kind of is the index for reflecting work quality in process of producing product, as quality is damaged
Mistake rate, rejection rate, finished product repair rate etc..
2. a pair data pre-process：The influence different with value range to eliminate different product quality index data dimension
And retain the relationship between each data, it usesData set of tracing to the source quality problems pre-processes.Wherein x is
Data before pretreatment, x* are pretreated data, and max is the maximum value of sample data, and min is the minimum of sample data
Value, max-min are very poor.
3. being clustered using Clustering to data set, similar point is divided into a cluster, as shown in Fig. 2, according to
Secondary calculating cluster centre, cluster radius, the distance to cluster centre.It utilizesCalculate cluster centre, wherein niFor
Cluster the data object number of i, xiFor the data object in cluster i, xoFor cluster centre；It utilizesMeter
Calculate cluster radius R, wherein R be cluster radius, niTo cluster the data object number of i；It utilizesMeter
Data point is calculated to the distance of cluster centre；Outlier Candidate Set is selected according to decision condition.
4. calculate the local factor that peels off：As shown in figure 3, input outlier Candidate Set D and neighbour's number k first is calculated often
The distance matrix of a object, then calculate successively the k distances of each point q in data set, k apart from field, reach distance, up to close
Degree, the local factor that peels off.The k distances refer to that for the arbitrary point q in data set k-th nearest of distance is claimed with q points
For the k distances of point q, the distance refers to Euclidean distance.The k referred to apart from neighborhood for the arbitrary point q in data set,
The neighborhood that the data object point of k distance of all distances no more than q is formed is referred to as k apart from neighborhood.The reach distance,
Be calculated using reach-disk (p, o)=max { k-distance (o), d (p, o) }, wherein, the kth of data object p away from
From for k-distance (p), Euclidean distances of the d (p, o) between object p and object o.
The local reachability density lrdk(p), it usesIt is calculated.The office
Portion peels off factor LOF, usesIt calculates.
5. calculate abnormal quality index：As shown in figure 3, peeling off the factor according to the part calculated before, formula L=is used
LOFk* u calculates abnormal quality index, wherein, L defines abnormal quality index, and u is product defects rate, and the product defects rate makes
Use formulaIt calculates, wherein, for c to identify defects of number, N is Sample Size.
6. pair quality abnormal index sorts：According to the abnormal quality index calculated before, to quality problems may be caused
The reason of be ranked up, the abnormal quality index of wherein data object the big, more it is possible that original to cause product quality problem
Cause.
7. output is as a result, the sequence of the possibility size for the reason of result refers to causing product problem.
Claims (4)
1. a kind of discrete manufacture mechanical product quality source tracing method based on outlier detection, it is characterised in that：Including following step
Suddenly：
1) structure product quality problem data set D；
2) to quality problem data collection D standardization processings；
3) cluster extraction outlier Candidate Set；
4) part for calculating product quality indicator peels off factor LOF；
5) abnormal quality index L is calculated；
6) according to 5) to quality problems may be caused the reason of be ranked up, wherein the abnormal quality index of data object more it is big then
More it is possible that for the reason of causing product quality problem；
7) according to sequence the reason of may causing quality problems in 6), output is traced to the source sort result；
8) according to tracing to the source in 7) as a result, one by one to quality problems may be caused the reason of carried out according to abnormal quality exponential size
Investigation.
2. a kind of discrete manufacture mechanical product quality source tracing method based on outlier detection as described in claim 1, special
Sign is：Step 1) includes the following steps：
1.1) quality problems potential cause is extracted：Being extracted according to people, machine, material, method, ring etc. may under the various conditions of production
Cause the m kind reasons of quality problems；
1.2) statistical product quality index data：Tracking data in production process is counted respectively in these potential causes
The n kind quality index datas of the product of lower production；
1.3) data set is built：The matter of a m*n is constructed using the n kind product quality indicator data under potential m kinds reason
Amount problem is traced to the source data set, and the product quality indicator includes two major class：One kind is to reflect the index of product inherent quality, mainly
It is product averaging parameter；Another kind of is the index for reflecting work quality in process of producing product, such as mass loss rate, waste product
Rate, finished product repair rate etc..
3. a kind of discrete manufacture mechanical product quality source tracing method based on outlier detection as described in claim 1, special
Sign is：The step 3) includes the following steps：
3.1) the corresponding n kinds product quality indicator data of potential cause of quality problems will likely be caused to be divided into one group of data D,
Each data object is expressed as p in D；
3.2) data set is clustered using Clustering, successively calculate cluster centre, cluster radius, to cluster centre away from
From similar point being divided into a cluster, the data object beta pruning that will can be clustered will be unable to the data of cluster according to judgement
Condition selects outlier Candidate Set.The cluster centre calculation formula is as follows：
Wherein niTo cluster the data object number of i, xiFor the data object in cluster i, xoFor cluster centre；
The calculation formula of the cluster radius R is as follows：
Wherein R be cluster radius, niTo cluster the data object number of i；
The calculation formula of the data point to cluster centre is as follows：
Wherein diDistance for data point to cluster centre.
4. a kind of discrete manufacture mechanical product quality source tracing method based on outlier detection as described in claim 1, special
Sign is：The formula that abnormal quality index L is calculated in the step 5) is as follows；
L=LOFk*u
Wherein, L defines abnormal quality index, and u is product defects rate, and wherein product defects rate calculation formula is：
Wherein, for c to identify defects of number, N is Sample Size.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611243368.6A CN108241925A (en) | 2016-12-23 | 2016-12-23 | A kind of discrete manufacture mechanical product quality source tracing method based on outlier detection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611243368.6A CN108241925A (en) | 2016-12-23 | 2016-12-23 | A kind of discrete manufacture mechanical product quality source tracing method based on outlier detection |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108241925A true CN108241925A (en) | 2018-07-03 |
Family
ID=62701807
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611243368.6A Pending CN108241925A (en) | 2016-12-23 | 2016-12-23 | A kind of discrete manufacture mechanical product quality source tracing method based on outlier detection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108241925A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109446189A (en) * | 2018-10-31 | 2019-03-08 | 成都天衡智造科技有限公司 | A kind of technological parameter outlier detection system and method |
| CN110276410A (en) * | 2019-06-27 | 2019-09-24 | 京东方科技集团股份有限公司 | Determine method, apparatus, electronic equipment and the storage medium of poor prognostic cause |
| CN113095340A (en) * | 2019-12-23 | 2021-07-09 | 神讯电脑(昆山)有限公司 | Abnormity early warning method for production machine and mass production method for objects |
| CN115860579A (en) * | 2023-02-27 | 2023-03-28 | 山东金利康面粉有限公司 | Production quality monitoring system for flour processing |
| CN115983721A (en) * | 2023-03-20 | 2023-04-18 | 青岛豪迈电缆集团有限公司 | Cable production quality data management system based on Internet of things big data |
| CN116109209A (en) * | 2023-04-11 | 2023-05-12 | 广东广泽实业有限公司 | Electric power product quality tracing and tracking management method and system based on big data |
| CN116485418A (en) * | 2023-06-21 | 2023-07-25 | 福建基茶生物科技有限公司 | Tracing method and system for tea refining production |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103530808A (en) * | 2013-10-25 | 2014-01-22 | 西安凌科信息技术有限公司 | Whole-process tracing system for quality safety of fruit logistics |
| CN104462802A (en) * | 2014-11-26 | 2015-03-25 | 浪潮电子信息产业股份有限公司 | Method for analyzing outlier data in large-scale data |
| CN104573050A (en) * | 2015-01-20 | 2015-04-29 | 安徽科力信息产业有限责任公司 | Continuous attribute discretization method based on Canopy clustering and BIRCH hierarchical clustering |
| CN104714964A (en) * | 2013-12-13 | 2015-06-17 | 中国移动通信集团公司 | Physiological data outlier detection method and device |
| CN105512206A (en) * | 2015-11-27 | 2016-04-20 | 河海大学 | Outlier detection method based on clustering |
-
2016
- 2016-12-23 CN CN201611243368.6A patent/CN108241925A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103530808A (en) * | 2013-10-25 | 2014-01-22 | 西安凌科信息技术有限公司 | Whole-process tracing system for quality safety of fruit logistics |
| CN104714964A (en) * | 2013-12-13 | 2015-06-17 | 中国移动通信集团公司 | Physiological data outlier detection method and device |
| CN104462802A (en) * | 2014-11-26 | 2015-03-25 | 浪潮电子信息产业股份有限公司 | Method for analyzing outlier data in large-scale data |
| CN104573050A (en) * | 2015-01-20 | 2015-04-29 | 安徽科力信息产业有限责任公司 | Continuous attribute discretization method based on Canopy clustering and BIRCH hierarchical clustering |
| CN105512206A (en) * | 2015-11-27 | 2016-04-20 | 河海大学 | Outlier detection method based on clustering |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109446189A (en) * | 2018-10-31 | 2019-03-08 | 成都天衡智造科技有限公司 | A kind of technological parameter outlier detection system and method |
| CN110276410A (en) * | 2019-06-27 | 2019-09-24 | 京东方科技集团股份有限公司 | Determine method, apparatus, electronic equipment and the storage medium of poor prognostic cause |
| CN113095340A (en) * | 2019-12-23 | 2021-07-09 | 神讯电脑(昆山)有限公司 | Abnormity early warning method for production machine and mass production method for objects |
| CN113095340B (en) * | 2019-12-23 | 2024-04-16 | 神讯电脑(昆山)有限公司 | Abnormality early warning method of production machine and mass production method of objects |
| CN115860579A (en) * | 2023-02-27 | 2023-03-28 | 山东金利康面粉有限公司 | Production quality monitoring system for flour processing |
| CN115860579B (en) * | 2023-02-27 | 2023-05-09 | 山东金利康面粉有限公司 | Production quality monitoring system for flour processing |
| CN115983721A (en) * | 2023-03-20 | 2023-04-18 | 青岛豪迈电缆集团有限公司 | Cable production quality data management system based on Internet of things big data |
| CN116109209A (en) * | 2023-04-11 | 2023-05-12 | 广东广泽实业有限公司 | Electric power product quality tracing and tracking management method and system based on big data |
| CN116109209B (en) * | 2023-04-11 | 2023-06-30 | 广东广泽实业有限公司 | Electric power product quality tracing and tracking management method and system based on big data |
| CN116485418A (en) * | 2023-06-21 | 2023-07-25 | 福建基茶生物科技有限公司 | Tracing method and system for tea refining production |
| CN116485418B (en) * | 2023-06-21 | 2023-09-05 | 福建基茶生物科技有限公司 | Tracing method and system for tea refining production |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108241925A (en) | A kind of discrete manufacture mechanical product quality source tracing method based on outlier detection | |
| CN109145097A (en) | A kind of judgement document's classification method based on information extraction | |
| CN108985380B (en) | Point switch fault identification method based on cluster integration | |
| CN112766334B (en) | Cross-domain image classification method based on pseudo label domain adaptation | |
| CN108470022A (en) | A kind of intelligent work order quality detecting method based on operation management | |
| CN111367777B (en) | Alarm processing method, device, equipment and computer readable storage medium | |
| CN116309577B (en) | Intelligent detection method and system for high-strength conveyor belt materials | |
| CN109033322A (en) | A kind of test method and device of multidimensional data | |
| CN109783633A (en) | Data analysis service procedural model recommended method | |
| CN113591948A (en) | Defect pattern recognition method and device, electronic equipment and storage medium | |
| CN113407644A (en) | Enterprise industry secondary industry multi-label classifier based on deep learning algorithm | |
| CN108280561A (en) | A kind of discrete manufacture mechanical product quality source tracing method based on comentropy and Weighted distance | |
| CN105488599A (en) | Method and device of prediction of article popularity | |
| CN108537249B (en) | Industrial process data clustering method for density peak clustering | |
| CN108090635B (en) | Road performance prediction method based on cluster classification | |
| CN115841491B (en) | Quality detection method for porous metal material | |
| CN110287114B (en) | Method and device for testing performance of database script | |
| CN116629709A (en) | Intelligent analysis alarm system of power supply index | |
| CN116307761A (en) | Business invitation data management system based on cloud platform | |
| CN115345846A (en) | Intelligent grading method and system for grain size of medium and low carbon steel | |
| CN108460119A (en) | A kind of system for supporting efficiency using machine learning lift technique | |
| CN115017238A (en) | Data flow detection classification method capable of dynamically predicting | |
| CN111833297B (en) | Disease association method of marrow cell morphology automatic detection system | |
| CN113705920A (en) | Generation method of water data sample set for thermal power plant and terminal equipment | |
| CN111813442A (en) | Software taste detection method based on machine learning |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20180703 |