CN109271407A - A kind of equipment routing inspection method based on machine learning - Google Patents
A kind of equipment routing inspection method based on machine learning Download PDFInfo
- Publication number
- CN109271407A CN109271407A CN201811131729.7A CN201811131729A CN109271407A CN 109271407 A CN109271407 A CN 109271407A CN 201811131729 A CN201811131729 A CN 201811131729A CN 109271407 A CN109271407 A CN 109271407A
- Authority
- CN
- China
- Prior art keywords
- target device
- equipment
- data
- operating status
- operating
- 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
- 238000007689 inspection Methods 0.000 title claims abstract description 23
- 238000010801 machine learning Methods 0.000 title claims abstract description 21
- 238000000034 method Methods 0.000 title claims abstract description 21
- 239000013598 vector Substances 0.000 claims description 28
- 238000012545 processing Methods 0.000 claims description 7
- 230000002159 abnormal effect Effects 0.000 claims description 5
- 238000012549 training Methods 0.000 claims description 5
- 238000012423 maintenance Methods 0.000 abstract description 11
- 238000010586 diagram Methods 0.000 description 7
- 238000012512 characterization method Methods 0.000 description 3
- 241000208340 Araliaceae Species 0.000 description 2
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 2
- 235000003140 Panax quinquefolius Nutrition 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 235000008434 ginseng Nutrition 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000008439 repair process Effects 0.000 description 2
- 241001269238 Data Species 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000009415 formwork Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
- G06F18/24155—Bayesian classification
-
- 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
- G06Q10/20—Administration of product repair or maintenance
-
- 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
- G06Q50/40—Business processes related to the transportation industry
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Data Mining & Analysis (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Economics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Operations Research (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Quality & Reliability (AREA)
- Probability & Statistics with Applications (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention belongs to industrial circles, specifically disclose a kind of equipment routing inspection method and inspection device based on machine learning, operating parameter including obtaining target device, data in the target device database are examined and verified, equipment operating mode library is established according to the target device database, obtain the current operating status of the target device, judge whether target device operation is normal according to the equipment operating mode library, pass through the mass data that is mutually related under acquisition equipment different conditions, establish the operational mode library under equipment difference operating status, pass through the comparison of the operational mode in the operational mode and equipment operating mode library under the operating status current to target device, judge the operating status of equipment, can accurate science judgement equipment operating status, improve the reliability and accuracy of equipment routing inspection maintenance.
Description
[technical field]
The invention belongs to train overhaul fields, and in particular to a kind of equipment routing inspection method based on machine learning.
[background technique]
The maintenance of railroad train is a most important ring in train operation maintenance work, in the maintenance and maintenance of railroad train
In the process, under normal circumstances that train groups are hanging, the bottom of train groups is entered by staff, since one end of train,
Each component part of detailed inspection train groups.Structure is complicated for train set, components are various, so that repair and maintenance environmental abnormality
It is complicated.And train composition is complicated, involves great expense, and the parameter complicated pluralism of each spare parts logistics is characterized in train operation, letter
Single artificial maintenance can not the detailed state for judging each components of train.And for the train groups of high-speed cruising, one zero
The failure of component can lead to serious accident, cause great loss.
Manual inspection safeguards the capability problems due to staff, is difficult according to a large amount of, no of characterization equipment running status
Together, and the data that are mutually related are made and accurately and reliably being judged.The existing monitoring of tools based on data acquisition cannot be to component
State do effective analytical judgment, the crucial intelligence of repair and maintenance is completed by artificial experience.
[summary of the invention]
The disclosure provides a kind of equipment routing inspection method based on machine learning, can do accurate science to the operating status of equipment
Judgement.
To achieve the above object, the disclosure provides a kind of equipment routing inspection method based on machine learning, which comprises
The operating parameter under target device difference operating status is obtained, and the operating parameter is stored in target device number
According in library；
Data in the target device database are examined and verified, check the consistency of data, it is invalid to delete
Data and repeated data, according to the different data type of the type definition of the target device；
Equipment operating mode library is established according to the target device database；
The current operating status of the target device is obtained, judges that target device is run according to the equipment operating mode library
It is whether normal.
It is optionally, described that equipment operating mode library is established according to the target device database, comprising:
Feature vector is extracted from the target device database, and is classified to described eigenvector, and feature is established
Vector data library；
According to the type of the target device, recognition threshold is set, and uses fixed characteristic vector data as instruction
Practice data, the operating status of the target device is divided into normal condition and abnormal condition using Naive Bayes Classifier.
Optionally, described to obtain the current operating status of the target device, judged according to the equipment operating mode library
Whether target device operation is normal, comprising:
The current operating parameter of target device is extracted in the operating status current from the target device；
The current operational mode of the target device is determined according to the current operating parameter of the target device.
The second aspect of the disclosure provides a kind of equipment patrolling device based on machine learning, and described device includes:
Operating parameter obtains module, for obtaining the operating parameter under target device difference operating status, and the ginseng
Number is stored in target device database；
Data processing module checks data for the data in the target device database to be examined and verified
Consistency, invalid data and repeated data are deleted, according to the different data type of the type definition of the target device；
Pattern base establishes module, for establishing equipment operating mode library according to the target device database；
Operating status obtains module, for obtaining the current operating status of the target device, is run according to the equipment
Pattern base judges whether target device operation is normal.
Optionally, the pattern base establishes module, comprising: characteristic vector data library setting up submodule is used for from the mesh
Feature vector is extracted in marking device database, and is classified to described eigenvector, and characteristic vector data library is established；
State classification submodule sets recognition threshold for the type according to the target device, and using fixed
The operating status of the target device is divided into normally by characteristic vector data as training data, using Naive Bayes Classifier
State and abnormal condition.
Optionally, the operating status obtains module, comprising: operating parameter acquisition submodule, for being set from the target
The current operating parameter of target device is extracted in standby current operating status；
Operational mode determines submodule, for determining the target device according to the current operating parameter of the target device
Operational mode.
Compared with prior art, technical solution provided by the present disclosure can realize following technical effect: be set by obtaining target
Operating parameter under standby different operating statuses, and the parameter is stored in target device database, to the target device
Data in database are examined and are verified, and check the consistency of data, invalid data and repeated data are deleted, according to described
The different data type of the type definition of target device is established equipment operating mode library according to the target device database, is obtained
The operating status for taking the target device current judges whether target device operation is normal according to the equipment operating mode library.
By the mass data that is mutually related under acquisition equipment different conditions, the operational mode library under equipment difference operating status is established,
By the comparison of the operational mode in the operational mode and equipment operating mode library under the operating status current to target device, sentence
The operating status of disconnected equipment, can accurate science judgement equipment operating status, improve reliability and standard that equipment routing inspection is safeguarded
True property.
[Detailed description of the invention]
Fig. 1 is a kind of stream of the equipment routing inspection method based on machine learning according to disclosed in one exemplary embodiment of the disclosure
Cheng Tu；
A kind of Fig. 2 equipment routing inspection method flow diagram based on machine learning disclosed in embodiment according to Fig. 1；
A kind of Fig. 3 equipment routing inspection method flow diagram based on machine learning disclosed in embodiment according to Fig. 1；
Fig. 4 is a kind of equipment patrolling device based on machine learning according to disclosed in disclosure another exemplary embodiment
Block diagram；
Pattern base is built in a kind of equipment patrolling device based on machine learning disclosed in embodiment according to Fig.4, when Fig. 5
The block diagram of formwork erection block 403；
Fig. 6 is operating status in a kind of equipment patrolling device based on machine learning disclosed in embodiment according to Fig.4,
Obtain the block diagram of module 404.
[specific embodiment]
Clear and complete description is carried out to technical solution of the present invention below in conjunction with attached drawing.Obviously, described implementation
Example is a part of the embodiments of the present invention, instead of all the embodiments.Based on the embodiment of the present invention, the common skill of this field
Art personnel other embodiments obtained without making creative work, belong to protection scope of the present invention.
Fig. 1 is a kind of equipment routing inspection method flow based on machine learning shown according to one exemplary embodiment of the disclosure
Figure, referring to Fig. 1, the equipment routing inspection method the following steps are included:
Step 101, the operating parameter under target device difference operating status is obtained, and the operating parameter is stored in target
In device databases.
It is exemplary, the target device can in train overhaul in debugging mode some high temperature, high-tension apparatus or
Some critical component after high-speed rotation equipment or train high-speed cruising.Database can be built upon network-side
Server, the server can configure the memory of certain capacity.
For different target devices, the operating parameter of target device is obtained by different modes.Such as in debugging
High temperature, high-tension apparatus, can by temperature sensor and pressure sensor temperature collection and pressure, rotating machinery by tachymeter,
The speed and operation image of video acquisition terminal acquisition.Some static components can be adopted using two dimension or 3-D image
Acquisition means acquire the image information of target device, and the operating parameter of target device is extracted from image information.
Operating parameter can be by the database established in server, such as SQL database is by the corresponding storage of data.
Step 102, the data in the target device database are examined and is verified, checked the consistency of data, delete
Except invalid data and repeated data, according to the different data type of the type definition of the target device.
Illustratively, in the storage and processing to the operating parameter of target device, not according to the type definition of target device
Same data type, such as high temperature, high-tension apparatus, define the numerical data for being directed to temperature and pressure in equipment operation, turn
The revolving speed and the equipment state under different rotating speeds that dynamic equipment division defines equipment.For the image class data of part class, definition
Different 3 d image datas and two-dimensional image data.The data of the target device of acquisition are examined and verified, nothing is deleted
Data and repeated data are imitated, and obtains the consistency feature of data from data.
Step 103, equipment operating mode library is established according to the target device database.
Illustratively, by the processing to target equipment data, consistent data is extracted from a large amount of data, passes through data
Establish the operational mode library of equipment.Such as in the operation of high temperature, high-tension apparatus, under different operating statuses, temperature and pressure
In different numberical ranges, by the analysis to different temperatures and pressure value, the operational mode library of equipment is established.Such as it is lower than
The low pressure operation mode of normal operating temperature and pressure, normal operation mode and higher than the high pressure of normal operating temperature and pressure transport
Row mode.
Step 104, the current operating status of the target device is obtained, judges that target device is transported according to equipment operating mode library
Whether row is normal.
Illustratively, the current operating status of target device is acquired by acquisition device, such as equipment is acquired by sensor
Temperature and pressure information in debugging judges the current operational mode of target device by the current operating parameter of target device,
And the operational mode in equipment operating mode library is compared, judge whether equipment operation is normal.
In the above-mentioned technical solutions, by establishing data to parameter acquisition different under target device difference operating status
Equipment operating mode library is established by the processing to database in library.During the inspection of equipment, acquisition target device is currently transported
Different parameters under row state, judge the operational mode of equipment, and the equipment operating mode library in comparison data library judges that target is set
Whether standby operating status is normal, by the acquisition to different data in target device difference operating status, by multiple numbers
According to processing integration establish the moving model of equipment, the operating status of equipment is judged by the moving model of equipment, can reduce people
The operating pressure of work inspection maintenance, improves the quality of inspection maintenance.
Further, Fig. 2 is another equipment routing inspection method based on machine learning for implementing to exemplify according to Fig. 1
Flow chart equipment operating mode library is established according to the target device database described in step 103 referring to fig. 2, comprising:
Step 1031, feature vector is extracted from the target device database, and classification foundation is carried out to this feature vector
Characteristic vector data library.
Illustratively, the operating status of equipment passes through multiple and different data characterizations, and between multiple data each other
Association.From the data in target device database, extract characterization target device operating status, and to different feature vectors into
Row classification, establishes characteristic vector data library.
Step 1032, according to the type of the target device, recognition threshold is set, and uses fixed characteristic vector data
As training data, the operating status of the target device is divided into normal condition and improper shape using Naive Bayes Classifier
State.
Illustratively, according to the type of different target devices, to the feature vector given threshold of target device.Specifically,
In high temperature, high-tension apparatus, temperature and pressure is low-temp low-pressure operation lower than certain value, and the high certain value of temperature and pressure is high temperature
High-voltage operation, it is normal operating condition that temperature and pressure, which is in a certain range section,.
According to different operating statuses, the threshold value of feature vector is set, and using Naive Bayes Classifier to different
Threshold value is classified, and the connection relationship of data is established, and establishes the operational mode of equipment, distinguishes the operating status under different mode.
Further, Fig. 3 is another the equipment routing inspection method based on machine learning for implementing to exemplify according to Fig. 1
Flow chart the current operating status of the target device is obtained described in step 104, according to the equipment operating mode referring to Fig. 3
Library judges whether target device operation is normal, comprising:
Step 1041, the current operating parameter of target device is extracted from the current operating status of the target device.
Illustratively, in the Image Acquisition to components, zero can be obtained by the analysis to two dimension or three-dimensional image information
The operating parameter of component.Displacement, dislocation and the height change information of such as components.
Step 1042, the current operational mode of the target device is determined according to the current operating parameter of the target device.
In conclusion in the inspection maintenance process of equipment, by multiple interrelated under equipment difference operating status
Data acquisition, arrangement and storage, and establish device running model by the data in database, pass through acquisition current device
The data of operation judge that equipment is presently in by the equipment operating mode in the current operating status comparison data library of equipment
Operational mode accurately and reliably the operating status of equipment can be judged to judge the operating status of equipment.
Fig. 4 is a kind of frame for equipment patrolling device based on machine learning that disclosure another exemplary embodiment provides
Figure, referring to fig. 4, which includes:
Operating parameter obtains module 401, for obtaining the operating parameter under target device difference operating status, and the ginseng
Number is stored in target device database.
Data processing module 402 checks data for the data in the target device database to be examined and verified
Consistency, invalid data and repeated data are deleted, according to the different data type of the type definition of the target device.
Pattern base establishes module 403, for establishing equipment operating mode library according to the target device database.
Operating status obtains module 404, for obtaining the current operating status of the target device, runs mould according to the equipment
Formula library judges whether target device operation is normal.
Further, Fig. 5 is that pattern base is established in a kind of equipment patrolling device based on machine learning according to Fig.4,
The block diagram of module 403, comprising:
Characteristic vector data library setting up submodule 4031, for extracting feature vector from the target device database, and
Classify to this feature vector, establishes characteristic vector data library；
State classification submodule 4032 sets recognition threshold for the type according to the target device, and use has determined that
Characteristic vector data as training data, the operating status of the target device is divided into normally using Naive Bayes Classifier
State and abnormal condition.
Further, Fig. 6 is that operating status obtains in a kind of equipment patrolling device based on machine learning according to Fig.4,
The block diagram of modulus block 404, comprising:
Operating parameter acquisition submodule 4041 is worked as extracting target device from the current operating status of the target device
Preceding operating parameter；
Operational mode determines submodule 4042, for determining the target device according to the current operating parameter of the target device
Current operational mode.
It should be noted that device provided by the above embodiment is when realizing its function, only with above-mentioned each functional module
Division be illustrated.In actual use, it can according to need and distribute above-mentioned functional module by different functional modules
It completes, i.e., the content structure of equipment is divided into different functional modules, to complete above description all or part function.
About the device in above-described embodiment, the concrete operations mode that wherein modules execute is in related this method
Embodiment in be described in detail, explanation is not set forth in detail herein.
Above-described embodiment is only used to illustrate the technical scheme of the present invention, rather than its limitations.The invention is not limited to upper
Face has been described and the accurate structural illustrated in the accompanying drawings is, and it cannot be said that specific implementation of the invention is only limited to these instructions.
For those of ordinary skill in the art to which the present invention belongs, without departing from the inventive concept of the premise, that makes is each
Kind change and modification, all shall be regarded as belonging to protection scope of the present invention.
Claims (6)
1. a kind of equipment routing inspection method based on machine learning, which is characterized in that the described method includes:
The operating parameter under target device difference operating status is obtained, and the operating parameter is stored in target device database
In；
Data in the target device database are examined and verified, check the consistency of data, delete invalid data
And repeated data, according to the different data type of the type definition of the target device；
Equipment operating mode library is established according to the target device database；
The current operating status of the target device is obtained, whether target device operation is judged according to the equipment operating mode library
Normally.
2. the method as described in claim 1, it is characterised in that: described to establish equipment operation according to the target device database
Pattern base, comprising:
Feature vector is extracted from the target device database, and is classified to described eigenvector, and feature vector is established
Database；
According to the type of the target device, recognition threshold is set, and uses fixed characteristic vector data as training number
According to the operating status of the target device is divided into normal condition and abnormal condition using Naive Bayes Classifier.
3. the method as described in claim 1, which is characterized in that described to obtain the current operating status of the target device, root
Judge whether target device operation is normal according to the equipment operating mode library, comprising:
The current operating parameter of target device is extracted in the operating status current from the target device；
The current operational mode of the target device is determined according to the current operating parameter of the target device.
4. a kind of equipment patrolling device based on machine learning, which is characterized in that described device includes:
Operating parameter obtains module, joins for obtaining the operating parameter under target device difference operating status, and the operation
Number is stored in target device database；
Data processing module checks the one of data for the data in the target device database to be examined and verified
Cause property deletes invalid data and repeated data, according to the different data type of the type definition of the target device；
Pattern base establishes module, for establishing equipment operating mode library according to the target device database；
Operating status obtains module, for obtaining the current operating status of the target device, according to the equipment operating mode
Library judges whether target device operation is normal.
5. device according to claim 4, which is characterized in that the pattern base establishes module, comprising:
Characteristic vector data library setting up submodule, for extracting feature vector from the target device database, and to described
Feature vector is classified, and characteristic vector data library is established；
State classification submodule sets recognition threshold for the type according to the target device, and uses fixed feature
The operating status of the target device is divided into normal condition as training data, using Naive Bayes Classifier by vector data
And abnormal condition.
6. device according to claim 4, which is characterized in that the operating status obtains module, comprising:
Operating parameter acquisition submodule, for extracting the current fortune of target device from the current operating status of the target device
Row parameter；
Operational mode determines submodule, for determining that the target device is current according to the current operating parameter of the target device
Operational mode.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811131729.7A CN109271407A (en) | 2018-09-27 | 2018-09-27 | A kind of equipment routing inspection method based on machine learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811131729.7A CN109271407A (en) | 2018-09-27 | 2018-09-27 | A kind of equipment routing inspection method based on machine learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109271407A true CN109271407A (en) | 2019-01-25 |
Family
ID=65198565
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811131729.7A Pending CN109271407A (en) | 2018-09-27 | 2018-09-27 | A kind of equipment routing inspection method based on machine learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109271407A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110525486A (en) * | 2019-08-14 | 2019-12-03 | 朔黄铁路发展有限责任公司 | Train operation state recognition methods, device, system and storage medium |
| CN112882442A (en) * | 2019-11-29 | 2021-06-01 | 内蒙古伊利实业集团股份有限公司 | Production monitoring device and method based on OMAC standard |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002359268A (en) * | 2001-03-30 | 2002-12-13 | Toshiba Corp | Method for inspecting manufacturing process of semiconductor device, and method of manufacturing the semiconductor device |
| CN102722166A (en) * | 2012-06-29 | 2012-10-10 | 山东电力集团公司电力科学研究院 | Intelligent vision detection system and state detection method of transformer substation device |
| CN107167497A (en) * | 2017-06-27 | 2017-09-15 | 北京必可测科技股份有限公司 | A kind of equipment fault detection method and system |
| CN107784310A (en) * | 2017-11-08 | 2018-03-09 | 浙江国自机器人技术有限公司 | Status information of equipment acquisition methods, device, system, storage medium and robot |
-
2018
- 2018-09-27 CN CN201811131729.7A patent/CN109271407A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002359268A (en) * | 2001-03-30 | 2002-12-13 | Toshiba Corp | Method for inspecting manufacturing process of semiconductor device, and method of manufacturing the semiconductor device |
| CN102722166A (en) * | 2012-06-29 | 2012-10-10 | 山东电力集团公司电力科学研究院 | Intelligent vision detection system and state detection method of transformer substation device |
| CN107167497A (en) * | 2017-06-27 | 2017-09-15 | 北京必可测科技股份有限公司 | A kind of equipment fault detection method and system |
| CN107784310A (en) * | 2017-11-08 | 2018-03-09 | 浙江国自机器人技术有限公司 | Status information of equipment acquisition methods, device, system, storage medium and robot |
Non-Patent Citations (1)
| Title |
|---|
| 苗彦英 等: "《2003·大连城市轨道交通发展研讨会论文集》", 30 September 2003, 中国铁道出版社 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110525486A (en) * | 2019-08-14 | 2019-12-03 | 朔黄铁路发展有限责任公司 | Train operation state recognition methods, device, system and storage medium |
| CN112882442A (en) * | 2019-11-29 | 2021-06-01 | 内蒙古伊利实业集团股份有限公司 | Production monitoring device and method based on OMAC standard |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107941537B (en) | A kind of mechanical equipment health state evaluation method | |
| CN108444708B (en) | Method for establishing rolling bearing intelligent diagnosis model based on convolutional neural network | |
| CN104390657B (en) | A kind of Generator Unit Operating Parameters measurement sensor fault diagnosis method and system | |
| CN103529051B (en) | A kind of Woven textiles flaw automatic on-line detection method | |
| CN109324604A (en) | A kind of intelligent train resultant fault analysis method based on source signal | |
| CN110261394A (en) | Online fan blade damages real-time diagnosis system and method | |
| CN109613428A (en) | It is a kind of can be as system and its application in motor device fault detection method | |
| CN102662390B (en) | Fault diagnosis method of random fuzzy fault characteristic fusion rotating mechanical device | |
| CN103699698A (en) | Method and system for track traffic failure recognition based on improved Bayesian algorithm | |
| CN109271407A (en) | A kind of equipment routing inspection method based on machine learning | |
| CN109781411A (en) | A kind of combination improves the Method for Bearing Fault Diagnosis of sparse filter and KELM | |
| CN111768417B (en) | Railway wagon overrun detection method based on monocular vision 3D reconstruction technology | |
| CN112017204A (en) | Tool state image classification method based on edge marker graph neural network | |
| CN112613454A (en) | Electric power infrastructure construction site violation identification method and system | |
| CN111289256A (en) | Data-driven marine diesel engine fault detection method | |
| CN111898686A (en) | Bearing fault identification method based on gated cyclic unit network | |
| CN116107280B (en) | Digital twin plant control system for multidimensional visual management | |
| CN115614292B (en) | Vibration monitoring device and method for vertical water pump unit | |
| CN115993096A (en) | High-rise building deformation measuring method | |
| CN115144399B (en) | Assembly quality detection method and device based on machine vision | |
| CN113720605B (en) | Cement production rotating equipment fault diagnosis method based on machine learning | |
| CN117114420B (en) | Image recognition-based industrial and trade safety accident risk management and control system and method | |
| Song et al. | An improved bearing defect detection algorithm based on Yolo | |
| CN113128555A (en) | Method for detecting abnormality of train brake pad part | |
| CN110057588A (en) | The bearing incipient fault detection and diagnostic method and system merged based on singular value with characteristics of graph theory |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190125 |