CN112732541B - Intelligent criterion mining system for fault diagnosis of complex equipment - Google Patents
Intelligent criterion mining system for fault diagnosis of complex equipment Download PDFInfo
- Publication number
- CN112732541B CN112732541B CN202011585556.3A CN202011585556A CN112732541B CN 112732541 B CN112732541 B CN 112732541B CN 202011585556 A CN202011585556 A CN 202011585556A CN 112732541 B CN112732541 B CN 112732541B
- Authority
- CN
- China
- Prior art keywords
- module
- data
- mining
- criteria
- criterion
- 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.)
- Active
Links
- 238000005065 mining Methods 0.000 title claims abstract description 77
- 238000003745 diagnosis Methods 0.000 title claims abstract description 25
- 238000012360 testing method Methods 0.000 claims abstract description 77
- 238000000034 method Methods 0.000 claims abstract description 39
- 238000012216 screening Methods 0.000 claims abstract description 30
- 238000007726 management method Methods 0.000 claims abstract description 26
- 230000008569 process Effects 0.000 claims abstract description 18
- 238000004140 cleaning Methods 0.000 claims abstract description 16
- 238000013523 data management Methods 0.000 claims abstract description 15
- 230000003993 interaction Effects 0.000 claims abstract description 13
- 230000036541 health Effects 0.000 claims abstract description 10
- 230000009467 reduction Effects 0.000 claims abstract description 6
- 230000006870 function Effects 0.000 claims description 18
- 238000000605 extraction Methods 0.000 claims description 15
- 238000009499 grossing Methods 0.000 claims description 13
- 230000003862 health status Effects 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 8
- 238000004422 calculation algorithm Methods 0.000 claims description 4
- 230000000007 visual effect Effects 0.000 claims description 4
- 238000001914 filtration Methods 0.000 claims description 3
- 230000008676 import Effects 0.000 claims description 3
- 238000002864 sequence alignment Methods 0.000 claims description 3
- 238000003860 storage Methods 0.000 claims description 3
- 238000013075 data extraction Methods 0.000 claims description 2
- 238000012800 visualization Methods 0.000 abstract 1
- 230000002159 abnormal effect Effects 0.000 description 9
- 238000004458 analytical method Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 5
- 238000004088 simulation Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000009412 basement excavation Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000007621 cluster analysis Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000002405 diagnostic procedure Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000008054 signal transmission Effects 0.000 description 1
- 238000011524 similarity measure Methods 0.000 description 1
- 208000024891 symptom Diseases 0.000 description 1
- 238000010998 test method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/34—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment
- G06F11/3452—Performance evaluation by statistical analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
- G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- 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
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Probability & Statistics with Applications (AREA)
- Data Mining & Analysis (AREA)
- Quality & Reliability (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Computer Hardware Design (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an intelligent criterion mining system for fault diagnosis of complex equipment, which comprises a test data management module, a data health state screening module, a data cleaning module, a criterion mining module, a criterion management module and a man-machine interaction module; the test data management module is used for uniformly managing the test data; the data health state screening module screens the data according to the test data state label so as to extract the data of the later-stage module; the data cleaning module preprocesses the test data; the criterion mining module is used for mining target criteria; the criterion management module tests and mines the criterion and uniformly manages the known criterion; the man-machine interaction module controls the whole criterion mining process; the invention can mine parameter envelope or threshold time sequence criteria for fault diagnosis, support time dimension error calibration of multiple test data sequences, support smooth noise reduction treatment of mining criteria, support validity test of mining criteria, and have controllable visualization and friendly man-machine interaction in the process of mining criteria.
Description
Technical Field
The invention relates to the technical field of fault diagnosis of complex equipment, in particular to an intelligent criterion mining system for fault diagnosis of complex equipment.
Background
In the modern industry, the role of complex equipment is becoming increasingly important. In order to reduce the influence on production efficiency and working efficiency caused by equipment faults and reduce maintenance cost, a state-based equipment maintenance mode which benefits from the development of equipment fault diagnosis technology is started to be applied.
Current equipment failure diagnosis techniques can be divided into two broad categories, model-based diagnosis and data-based diagnosis. The data-based equipment fault diagnosis technology has a plurality of branches, wherein the direct extraction of abnormal symptoms of a data sequence from a time dimension is the most important and widely applied technology.
In the technology, when judging whether test data are normal or not or extracting abnormal characteristic points of certain test parameters, in engineering practice, common characteristic extraction methods comprise envelope analysis and threshold analysis, which are classical and practical methods in data abnormal characteristic extraction, and other characteristic extraction methods are improved on the basis.
It is noted that the implementation of the above diagnostic method is closely linked to diagnostic criteria, and in current engineering practice, the criteria for envelope and threshold analysis are mainly obtained by expert experience or system simulation. However, human errors exist in expert experience, modeling errors exist in system simulation, and therefore, the expert experience and the envelope obtained by the system simulation cannot reflect the real characteristics of the system test data. How to overcome human errors and modeling errors brought by criteria in diagnosis, a set of parameter envelope or threshold criterion system which can extract the characteristics of real reaction equipment by analyzing a large amount of test data is designed, and the technical problem to be solved in the prior art.
Disclosure of Invention
The invention solves the technical problems: aiming at the requirements of data-based fault diagnosis implementation of complex equipment, the intelligent criterion mining system is designed and solves the problem of intelligent criterion mining, and the intelligent criterion mining system for fault diagnosis of the complex equipment is provided. The system mainly solves the problems that: based on a large amount of measurement data of equipment, parameter envelopes or threshold criteria capable of truly reflecting the characteristics of the equipment or the parts are mined and extracted.
The invention adopts the technical scheme that: an intelligent criterion mining system for fault diagnosis of complex equipment comprises a test data management module, a data health state screening module, a data cleaning module, a criterion mining module, a criterion management module and a man-machine interaction module; wherein,,
the test data management module consists of a database storing test data, supports batch import and unified management of the test data, and transmits the data to the data health status screening module;
the data health state screening module screens the test data state labels sent by the test data management module, the function call of screening inquiry is packaged by the interface, the inquiry screening function engine of the MySQL database is relied on to realize, and the screened data is sent to the data cleaning module;
the data cleaning module is used for carrying out pretreatment including burr removal, default value filling and the like on the test data sent by the data health status screening module according to the pretreatment requirement selected by control, and sending clean data to the criterion mining module after the pretreatment;
the criterion mining module is used for completing the function of mining target criteria from the clean data sent by the data cleaning module and sending the mined target criteria to the criterion management module;
the criterion management module consists of a database storing the criteria and a result feedback submodule, and is used for carrying out validity test on the mined target criteria sent by the criterion mining module, storing the criteria passing the validity test into a criterion library and uniformly managing the existing criteria;
and the man-machine interaction module is used for carrying out visual test data and criteria, displaying the task process of the system in real time, and simultaneously controlling the process of mining the system criteria in real time by a user.
The criterion mining module comprises a sequence calibration sub-module, a mining core sub-module and a data smoothing sub-module, and is used for completing the function of mining target criteria from clean data;
the sequence calibration sub-module is used for completing the calibration alignment of the data sequence in the time dimension by adopting a time sequence alignment method for the test data sent to the criterion mining module, the method comprises the steps of taking one of the multiple test data sequences to be calculated as a reference, sliding the rest sequence, determining the time alignment state of the data sequences under the reference by adopting a distance minimization algorithm, and sending the aligned multiple data sequences to the mining core sub-module;
the kernel mining sub-module is used for mining possible criteria by adopting an extremum feature extraction calculation strategy based on statistics or an envelope extraction calculation strategy based on clustering and extremum learning for the aligned multiple data sequences from the sequence calibration sub-module and sending the data smoothing sub-module;
and the data smoothing sub-module adopts a sequence smoothing noise reduction method, including but not limited to a box division method, a moving average method or a filtering method, for mining possible criteria sent by the core sub-module, so as to smooth the mined possible sequence type criteria, improve the usability of the criteria, reduce noise errors and finally send the criteria to the criteria management module by the criteria mining module.
The criterion management module comprises: a database storing known criteria and a result feedback sub-module are used for completing the function of criterion management;
the result feedback sub-module selects other sample data from the data extracted from the test data management module through the data health status screening module for possible criteria from the criteria mining module to complete the function of validity check, and stores the criteria which pass the validity check into the known criteria database only.
The human-computer interaction module visualizes the test data and the criteria, displays the task process of the system in real time, and the interface buttons and windows are connected with the back-end program to control the whole criteria mining process, wherein the whole criteria mining process comprises the steps of importing operation, exporting operation, data health state screening operation, data extraction operation, data cleaning method selection, result feedback sub-module test data selection operation and criteria storage and warehousing operation.
Compared with the prior art, the invention has the advantages that:
(1) The invention supports unified management of test data and provides a basis for data management;
(2) The invention supports unified management of known criteria and can better serve a fault diagnosis system;
(3) The invention can mine parameter envelope or threshold time sequence criterion for the data driving fault diagnosis method from the historical data, thereby avoiding the human error of the criterion given by expert experience and the modeling error of the criterion given by system simulation;
(4) The sequence calibration submodule supports time dimension error calibration of multiple test data sequences, so that the system has robustness on the requirement of time sequence alignment on multiple data sequence objects to be mined;
(5) The data smoothing sub-module supports a smooth mined criterion sequence, reduces noise errors and improves the usability of the mined criterion;
(6) The result feedback submodule supports the validity test of the mining criteria, and ensures the usability of the mining criteria;
(7) The human-computer interaction module can control the whole intelligent criterion mining process, the test data analysis result and the mining criterion in the visual mining process can display the task progress of the system in real time, so that a user can conveniently know the current state of the task, the intermediate result of the task can be intuitively displayed, and the system can be conveniently operated and controlled.
Drawings
FIG. 1 is a block diagram of an intelligent criterion mining system for fault diagnosis of complex equipment according to the present invention;
FIG. 2 is a schematic diagram of an extremum feature extraction method based on statistics in the present invention;
fig. 3 is a schematic diagram of an envelope extraction method based on clustering and extremum learning.
Detailed Description
The invention is further described below with reference to the drawings and detailed description.
Referring to fig. 1, the intelligent criterion mining system for fault diagnosis of complex equipment comprises a test data management module, a data health status screening module, a data cleaning module, a criterion mining module, a criterion management module and a man-machine interaction module. The test data management module consists of a database, supports batch importing of test data and performs unified management; the data health state screening module can screen data according to the test data state label so as to enable the later-stage module to extract the data; the data cleaning module preprocesses the test data; the criterion mining module comprises a sequence calibration sub-module, a mining core sub-module and a data smoothing sub-module, and the time dimension error calibration, the criterion mining core calculation and the mining result noise reduction of the test data sequence are completed in each sub-module in sequence, and finally possible target criteria are mined; the criterion management module comprises a database storing known criteria and a result feedback sub-module, and the obtained criteria obtained through excavation and checked by the result feedback sub-module are stored in the known criterion database; the man-machine interaction module visualizes the test data and the criteria, displays the task progress of the system in real time, and controls the whole criteria mining process.
The test data management module adopts a MySQL relational database management system. The MySQL database has the characteristics of small volume, high speed, low total possession cost and open source code, and is therefore one of the most popular relational database management systems. The database stores the original test data obtained by monitoring, including normal data, abnormal data and gray data (data between normal and abnormal), and establishes the most fundamental data base for the criterion mining. The test data management module supports batch import and batch export of historical test data, supports gradual editing of library data, simultaneously serves as a function extension type system of the complex equipment state monitoring and fault diagnosis type system, provides a real-time data transmission interface connected with the function extension type system, and supports real-time state test data storage of equipment or components.
The data health status screening module screens the data according to the test data status tag. The module encapsulates test data to generate a combination screening sub-function which is accurate and reasonable in setting of screening query conditions in a service logic layer. The screening query condition includes, from the perspective of the data object, the complete machine of the equipment to which the test data belongs, the system of the equipment to which the test data belongs (e.g., a mechanical system, an electrical system, etc.), the parts to which the test data belongs, the type of the test data signal (e.g., signals of current, voltage, vibration, temperature, etc.), the type of the test data value (e.g., continuous value, discrete value, label value, etc.); the screening query conditions include a test data generation date, a test data generation time, a production lot to which the test data is generated, and the like from the viewpoint of data production time. And finally, carrying out state screening on the data according to the test data state label. The bottom layer of the screening function of the data health status screening module is realized by the query screening function of the MySQL database.
The data cleaning module is used for preprocessing test data and mainly solving the problems of high-frequency burr noise and value missing generated by sensor signal acquisition and signal transmission. The module detects outliers through an outlier analysis technology, and burrs are removed; the module fills in the missing values by filling in the missing values as a special string or sequence data point average or sequence data point median.
The criterion mining module comprises a sequence calibration sub-module, a mining core sub-module and a data smoothing sub-module, and error calibration, criterion mining core calculation and mining result noise reduction of the time dimension of the test data sequence are completed in each sub-module in sequence, and finally possible target criteria are mined. The sequence calibration submodule takes one of the multiple test data sequences to be calculated as a reference, slides the rest sequences, and adopts an algorithm of minimizing the distance (namely maximizing the similarity measure) to determine the time alignment state of the data sequences under the reference; among other things, algorithms have a particularly accurate sequence time dimension error calibration effect when the distance metric employs a Dynamic Time Warping (DTW) distance. The core mining sub-module is provided with two calculation strategies of extremum feature extraction based on statistics and envelope extraction based on clustering and extremum learning; referring to fig. 2, a statistical extremum feature extraction calculation strategy adopts a statistical maximum value and minimum value extraction method, wherein the maximum value, the median value and the minimum value represent a group of states of maximum and minimum data, the change range of the data is represented, a variable high-dimensional time sequence matrix formed by absolute normal data is subjected to extremum extraction according to time dimension to obtain a change range of a normal value in time dimension, and then variable dimension combination is carried out to obtain two groups of time sequences with the same dimension and aligned time sequence; referring to fig. 3, firstly, on the time dimension, carrying out cluster analysis on data points of different sequences which belong to each moment, such as data points obtained by intersecting a t moment axis with each data sequence shown in fig. 3, to obtain three class clusters with marked cluster center points 1, 2 and 3 as centers and the distribution situation of the t moment data, extracting the data class cluster with the largest density through the clusters, such as the data class cluster with the cluster center point 2 as the center shown in fig. 3, as the data with better distribution, forming a cluster center sequence on the time dimension from the time interval of the last scanned data sequence to the cluster center point 2 obtained at each position, if a plurality of center sequences are obtained through multiple scanning, then adopting the method of extracting the maximum value and the minimum value in statistics shown in fig. 2, and extracting the data points of the data center sequences extracted through the clusters at each moment, so as to form a normal criterion on the time dimension. The data smoothing submodule adopts a box division method, a moving average method or a filtering method to finish the smoothing noise reduction function of the criterion sequence.
The criterion management module comprises a database which adopts a MySQL relational database management system and stores known criteria and a result feedback sub-module, and the obtained criteria which is checked by the result feedback sub-module are stored in the known criterion database. Whether the obtained criteria can meet the requirements of equipment state monitoring and fault diagnosis or not is mined, and validity check is needed for the criteria. The result feedback submodule completes the function of validity test, namely the test method selects sample data from the extracted data, wherein the sample data comprises normal values, abnormal values and gray values, envelope or threshold analysis is carried out on envelope and threshold criteria, similarity measurement is carried out on criteria obtained based on clustering and extremum learning, whether the abnormal data can be detected by the sample data or not is tested, and normal data is detected to be normal. If the requirements are met, the extracted features can be used as criteria to be stored in a criterion library; if the abnormal data is judged to be normal or the normal data is judged to be abnormal, the envelope or threshold criterion does not pass the validity test, and the criterion management module controls discarding of the mining criterion.
The human-computer interaction module is a visual interface designed for C# and is used for visualizing test data and criteria, displaying the task process of the system in real time, and connecting interface buttons and windows with a back-end program to control the whole criterion mining process, wherein the whole criterion mining process comprises the steps of test data importing operation, test data exporting operation, data health state screening operation, data extracting operation, data cleaning method selection, result feedback sub-module test data selection operation and criterion storage and warehousing operation.
Claims (4)
1. An intelligent criterion mining system for fault diagnosis of complex equipment is characterized in that: the system comprises a test data management module, a data health state screening module, a data cleaning module, a criterion mining module, a criterion management module and a man-machine interaction module; wherein,,
the test data management module consists of a database storing test data, supports batch import and unified management of the test data, and transmits the data to the data health status screening module;
the data health state screening module screens the test data state labels sent by the test data management module, the function call of screening inquiry is packaged by the interface, the inquiry screening function engine of the MySQL database is relied on to realize, and the screened data is sent to the data cleaning module;
the data cleaning module is used for carrying out pretreatment including burr removal, default value filling and the like on the test data sent by the data health status screening module according to the pretreatment requirement selected by control, and sending clean data to the criterion mining module after the pretreatment;
the criterion mining module is used for completing the function of mining target criteria from the clean data sent by the data cleaning module and sending the mined target criteria to the criterion management module;
the criterion management module consists of a database storing the criteria and a result feedback submodule, and is used for carrying out validity test on the mined target criteria sent by the criterion mining module, storing the criteria passing the validity test into a criterion library and uniformly managing the existing criteria;
and the man-machine interaction module is used for carrying out visual test data and criteria, displaying the task process of the system in real time, and simultaneously controlling the process of mining the system criteria in real time by a user.
2. An intelligent criterion mining system for complex equipment fault diagnosis as claimed in claim 1, wherein: the criterion mining module comprises a sequence calibration sub-module, a mining core sub-module and a data smoothing sub-module, and is used for completing the function of mining target criteria from clean data;
the sequence calibration sub-module is used for completing the calibration and alignment of the data sequences in the time dimension by adopting a time sequence alignment method for the test data sent to the criterion mining module, determining the time alignment state of the data sequences under the reference by adopting a distance minimization algorithm, and sending the aligned data sequences to the mining core sub-module;
the kernel mining sub-module is used for mining possible criteria by adopting an extremum feature extraction calculation strategy based on statistics or an envelope extraction calculation strategy based on clustering and extremum learning for the aligned multiple data sequences from the sequence calibration sub-module and sending the data smoothing sub-module;
and the data smoothing sub-module adopts a sequence smoothing noise reduction method, including a box division method, a moving average method or a filtering method, for mining possible criteria sent by the core sub-module, so as to smooth the mined possible sequence type criteria, improve the usability of the criteria, reduce noise errors and finally send the criteria to the criteria management module by the criteria mining module.
3. An intelligent criterion mining system for complex equipment fault diagnosis as claimed in claim 1, wherein: the criterion management module comprises: a database storing known criteria and a result feedback sub-module are used for completing the function of criterion management;
the result feedback sub-module selects other sample data from the data extracted from the test data management module through the data health status screening module for possible criteria from the criteria mining module to complete the function of validity check, and stores the criteria which pass the validity check into the known criteria database only.
4. An intelligent criterion mining system for complex equipment fault diagnosis as claimed in claim 1, wherein: the human-computer interaction module visualizes the test data and the criteria, displays the task process of the system in real time, and the interface buttons and windows are connected with the back-end program to control the whole criteria mining process, wherein the whole criteria mining process comprises the steps of importing operation, exporting operation, data health state screening operation, data extraction operation, data cleaning method selection, result feedback sub-module test data selection operation and criteria storage and warehousing operation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011585556.3A CN112732541B (en) | 2020-12-28 | 2020-12-28 | Intelligent criterion mining system for fault diagnosis of complex equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011585556.3A CN112732541B (en) | 2020-12-28 | 2020-12-28 | Intelligent criterion mining system for fault diagnosis of complex equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112732541A CN112732541A (en) | 2021-04-30 |
| CN112732541B true CN112732541B (en) | 2023-05-09 |
Family
ID=75606953
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011585556.3A Active CN112732541B (en) | 2020-12-28 | 2020-12-28 | Intelligent criterion mining system for fault diagnosis of complex equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112732541B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113505862B (en) * | 2021-09-07 | 2022-02-15 | 深圳市信润富联数字科技有限公司 | Hybrid fault detection method and device |
| CN115186735B (en) * | 2022-06-20 | 2024-02-23 | 成都飞机工业（集团）有限责任公司 | Data threshold mining method, device, equipment and medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105205113A (en) * | 2015-09-01 | 2015-12-30 | 西安交通大学 | System and method for excavating abnormal change process of time series data |
| CN105372557A (en) * | 2015-12-03 | 2016-03-02 | 国家电网公司 | Power grid resource fault diagnosis method based on association rules |
| CN107133632A (en) * | 2017-02-27 | 2017-09-05 | 国网冀北电力有限公司 | A kind of wind power equipment fault diagnosis method and system |
| CN107909096A (en) * | 2017-11-08 | 2018-04-13 | 南京因泰莱电器股份有限公司 | A kind of fault of converter early warning criterion implementation method based on two points of K mean clusters |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8406912B2 (en) * | 2010-06-25 | 2013-03-26 | Taiwan Semiconductor Manufacturing Company, Ltd. | System and method for data mining and feature tracking for fab-wide prediction and control |
-
2020
- 2020-12-28 CN CN202011585556.3A patent/CN112732541B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105205113A (en) * | 2015-09-01 | 2015-12-30 | 西安交通大学 | System and method for excavating abnormal change process of time series data |
| CN105372557A (en) * | 2015-12-03 | 2016-03-02 | 国家电网公司 | Power grid resource fault diagnosis method based on association rules |
| CN107133632A (en) * | 2017-02-27 | 2017-09-05 | 国网冀北电力有限公司 | A kind of wind power equipment fault diagnosis method and system |
| CN107909096A (en) * | 2017-11-08 | 2018-04-13 | 南京因泰莱电器股份有限公司 | A kind of fault of converter early warning criterion implementation method based on two points of K mean clusters |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112732541A (en) | 2021-04-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111230887B (en) | Industrial gluing robot running state monitoring method based on digital twin technology | |
| CN112034789B (en) | Health assessment method, system and assessment terminal for key parts and complete machine of numerical control machine tool | |
| CN112732541B (en) | Intelligent criterion mining system for fault diagnosis of complex equipment | |
| CN112085261B (en) | Enterprise production status diagnosis method based on cloud fusion and digital twin technology | |
| CN108873830A (en) | A kind of production scene online data collection analysis and failure prediction system | |
| CN111459700A (en) | Method and apparatus for diagnosing device failure, diagnostic device, and storage medium | |
| CN110515781B (en) | Complex system state monitoring and fault diagnosis method | |
| CN115062478A (en) | Dynamic workshop production scheduling method, system and medium based on digital twin | |
| CN114118673A (en) | Workshop intelligent fault diagnosis early warning method based on digital twin technology | |
| CN114330026A (en) | Digital twin system simulation method and device | |
| WO2022030041A1 (en) | Prediction system, information processing device, and information processing program | |
| CN111160393B (en) | Modularized modeling method of carrier rocket health evaluation model based on data driving | |
| CN107122907B (en) | Method for analyzing symbolized quality characteristics of mechanical and electrical products and tracing fault reasons | |
| CN115062674A (en) | Tool arrangement and tool changing method and device based on deep learning and storage medium | |
| CN116861503A (en) | Method for constructing digital twin model of power transformer based on big data | |
| CN106054832B (en) | Multivariable-based dynamic online monitoring method and device for intermittent chemical production process | |
| CN117172509A (en) | Construction project distribution system based on decoration construction progress analysis | |
| CN116859838B (en) | Early warning system for monitoring equipment operation condition | |
| CN117382129A (en) | Injection molding machine data analysis system and electronic equipment | |
| CN110320802B (en) | Complex system signal time sequence identification method based on data visualization | |
| CN109556861A (en) | A kind of bearing real-time fault diagnosis system of case-based reasioning | |
| CN111950133B (en) | Engine reliable life prediction method based on digital twinning | |
| KR102469610B1 (en) | Data preprocessing system | |
| WO2021111936A1 (en) | Prediction system, information processing device, and information processing program | |
| CN118092362B (en) | Method, device and equipment for analyzing abnormal reasons in sintering process |
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 |