CN105759784A - Fault diagnosis method based on data envelopment analysis - Google Patents
Fault diagnosis method based on data envelopment analysis Download PDFInfo
- Publication number
- CN105759784A CN105759784A CN201610080503.3A CN201610080503A CN105759784A CN 105759784 A CN105759784 A CN 105759784A CN 201610080503 A CN201610080503 A CN 201610080503A CN 105759784 A CN105759784 A CN 105759784A
- Authority
- CN
- China
- Prior art keywords
- test data
- envelope
- original test
- data
- many
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
- G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
- G05B23/0218—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults
- G05B23/0224—Process history based detection method, e.g. whereby history implies the availability of large amounts of data
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/20—Pc systems
- G05B2219/24—Pc safety
- G05B2219/24048—Remote test, monitoring, diagnostic
Abstract
The invention relates to a fault diagnosis method based on data envelopment analysis. The fault diagnosis method is characterized by comprising the following steps that multiple sets of original test data are inputted; time alignment processing is performed on the multiple sets of original test data so that envelope upper and lower lines of the multiple sets of original test data are generated; test data required to be diagnosed are inputted; and whether the test data are in the envelope area of the envelope upper and lower lines is judged, the test data are judged to be qualified if the test data are in the envelope area, and the test data are judged to be failure if there are data outside the envelope area. Systemic historical data envelope analysis is performed according to the accumulated large number of historical data of a carrier rocket so that the modeling bottleneck of the conventional fault diagnosis method can be effectively solved, and the problems that modeling of the conventional fault tree is complex and workload is high can be solved.
Description
Technical field
The present invention relates to a kind of method for diagnosing faults based on DEA, belong to fault diagnosis field.
Background technology
Carrier rocket is in test and emission process, it is necessary to it is carried out status monitoring by operational failure diagnostic system, and traditional method for diagnosing faults is adopt the diagnostic method based on fault tree mostly.Setting up on the basis of object outages tree-model, when object actual motion, adopting fault method for searching to search fault tree, and complete fault diagnosis.
Conventional fault method for searching has logic method (to adopt method for searching from top to down, from fault tree top event, first test initial intermediate event, test result further according to intermediate event removes test next stage intermediate event, until test bottom event, complete fault diagnosis) with Minimal Cut Set (minimal cut set corresponding with fault mode in test failure tree one by one, complete fault diagnosis) two kinds.
Fault tree method of diagnosis has diagnostic mode intuitively simple advantage, but build core and key that correct comprehensively fault tree is fault tree method of diagnosis, and fault tree models the bottleneck of fault diagnosis exactly, typically require very comprehensively fault tree analysis and could set up the fault tree of system perfecting, and workload is huge, need to consume substantial amounts of manpower and materials, and once Construction of Fault Tree is incorrect or not comprehensively, then fault tree method of diagnosis will lose efficacy to a great extent.
Summary of the invention
It is an object of the invention to overcome the deficiencies in the prior art, a kind of method for diagnosing faults based on DEA is provided, breach the modeling bottleneck of conventional fault diagnosis method, can automatically generated data envelope by DATA ENVELOPMENT ANALYSIS METHOD, carry out the real-time comparison of test data, complete fault parameter detection and fault location function.
The object of the invention is achieved by following technical solution:
There is provided a kind of method for diagnosing faults based on DEA, it is characterised in that comprise the steps:
(1) typing many groups original test data;
(2) many group original test data are carried out time unifying process, generate the upper and lower line of envelope organizing original test data more;
(3) input needs the test data of diagnosis;
(4) judging that test data are whether in the envelope region of the upper and lower line of envelope, if in envelope region, then it is qualified to be judged to, is positioned at the extra-regional data of envelope if existed, is then judged to fault.
Preferably, generate the upper and lower line method of envelope organizing original test data in described step (2) is more: for any time t, takes maximum in many group original test data, forms envelope and reach the standard grade;Take minima in many group original test data, form envelope and roll off the production line;
Preferably, typing many groups original test data in step (1), and set up the database instance of MySQL database;Data in MySQL database example are imported in Hive instrument;Realized many group original test data by Hive instrument carry out time unifying process and generate the upper and lower line of envelope organizing original test data more.
Preferably, the assembly sqoop that increases income in Hive is utilized to perform importing task.
Preferably, many group original test data are carried out time unifying process by described step (2), generate the upper and lower line of envelope organizing original test data method particularly includes: the sampling time is divided into equal interval of N number of time more, take the maximum of many groups original test data in each interval, carry out fitting a straight line formation envelope and reach the standard grade;Take the minima in many groups original test data in each interval, carry out fitting a straight line formation envelope and roll off the production line.
Preferably, many group original test data are carried out time unifying process by described step (2), generates the upper and lower line of envelope organizing original test data more method particularly includes: be fitted respectively obtaining a plurality of matched curve to many group original test data;Select one group of sampled data as benchmark, calculate the maximum of each point in the corresponding a plurality of matched curve of this each sampling instant of group sampled data, be fitted, form envelope and reach the standard grade;Calculate the minima of each point in the corresponding a plurality of matched curve of this each sampling instant of group sampled data, be fitted, form envelope and roll off the production line.
Preferably, in step (1), many groups original test data of typing selects the original test data in a year.
Preferably, if it is decided that for qualified, then step (5) is also included, it would be desirable in the test data input MySQL database of diagnosis.
Preferably, many group original test data are more than 5 groups.
The present invention compared with prior art has the advantage that
(1) a large amount of historical datas that the present invention accumulates according to carrier rocket based on the method for diagnosing faults of DEA, carry out the historical data Envelope Analysis of system, efficiently solve the modeling bottleneck of conventional failure method for diagnosing faults, solve the difficult problem that the modeling of conventional failure tree is complicated and workload is big;Conventional failure method for diagnosing faults depends on expertise, it is necessary to ensures the integrity of fault tree, the method for diagnosing faults of the present invention, based on the historical test data of conformity testing, it is not necessary to set up fault tree, reduces the difficulty of fault diagnosis;
(2) present invention is analyzed based on many group historical test data, and probability of miscarriage of justice is low.
(3) present invention carries out alignment of data process, can reflect the undulatory property of initial data truly, improve the precision of the upper and lower line of envelope.
(4) present invention adopts Hive instrument realization many groups original test data carry out time unifying process and generate the upper and lower line of envelope, analyzes speed soon, and processing capability in real time is strong.
(5) present invention adopts beyond envelope region intelligent alarm, it is achieved that the intellectuality of fault diagnosis.
Accompanying drawing explanation
Fig. 1 is Fig. 1 overall procedure of the present invention planning schematic diagram;
Fig. 2 is Fig. 2 data prediction of the present invention alignment schematic diagram;
Fig. 3 is the present invention fault diagnosis schematic diagram based on envelope;
Fig. 4 is that the present invention sends out time A, B data schematic diagram;
Fig. 5 is embodiment of the present invention Envelope Analysis schematic diagram.
Detailed description of the invention
1, flow of task planning
Overall workflow is as shown in Figure 1, initial data stores with the form of DAT file, first resolve in text the MySQL database that imports, transfer to Hive data base, through data prediction and data analysis, excavate information in historical data, be stored in HBase data base, web server inquiry HBase, returns the data needed.
2, typing initial data
Initial data according to model, send out time, the hierarchical structure of parameter is organized, each DAT file generally has 2-3 arrange, and several thousand row not etc., are not imported in MySQL in batches by Python program between hundreds of thousands row.
3, transfer data are to Hive
Hive is based on a kind of Tool for Data Warehouse of Hadoop, it is possible to structurized data file is mapped as a database table, and provides SQL query function.For the ease of big data mining program work, MySQL data are imported in Hive, utilize assembly sqoop executed in parallel of increasing income to import task.
4, data prediction and Envelope Analysis
Same model difference is sent out secondary data sampling time and is not mated completely, for follow-up Envelope Analysis, it is necessary to data are processed as according to time close alignment, ensureing the verity of data simultaneously, is illustrated in figure 2 interval alignment algorithm.
DATA ENVELOPMENT ANALYSIS METHOD is a kind of anomaly parameter diagnostic method based on historical data, by relative time in multiple rocket historical test data is calculated in the historical data of synchronization, obtain the envelope upper limit and envelope lower limit, finally, all of envelope upper limit moment point is linked to be curve, generate the envelope upper limit, all of envelope lower limit moment point is linked to be curve, generate envelope lower limit, ultimately generate envelope territory, when carrying out the fault diagnosis based on DEA, compare with envelope territory by testing data measured value, whether interpretation test parameter is abnormal.Envelope Analysis chooses the historical parameter data that multiple task is close, this parameter history envelope under this task is determined by the maximum and minima finding out each moment, utilize big data platform, can comprehensively analyze a large amount of historical data, reliably reflected the parameters history envelope of truth, it is simple to the abnormal conditions of timely monitoring parameter in the future.
But, owing to each subtask is likely to otherwise varied, same parameter may present different characteristic under difference is sent out time, if arbitrarily selecting to send out time generation envelope, can cause that envelope is degenerated, relatively wide between bound, it is difficult to the feature of reflection design parameter, as shown in Figure 3.
Therefore, close send out time should be selected when generating envelope, for instance the data in adopting 1 year, make every effort to accomplish that envelope can be accomplished to reflect true common scenario, again will not as the feature of degeneration self.By calculating envelope contribution degree and abnormal envelope, reject incoherent time.
The mode of the first alignment is: the sampling time is divided into equal interval of N number of time, takes the maximum of many groups original test data in each interval, carries out fitting a straight line and forms envelope and reach the standard grade;Take the minima in many groups original test data in each interval, carry out fitting a straight line formation envelope and roll off the production line.
The mode of the second alignment is: be fitted respectively obtaining a plurality of matched curve to many group original test data;Select one group of sampled data as benchmark, calculate the maximum of each point in the corresponding a plurality of matched curve of this each sampling instant of group sampled data, be fitted, form envelope and reach the standard grade;Calculate the minima of each point in the corresponding a plurality of matched curve of this each sampling instant of group sampled data, be fitted, form envelope and roll off the production line.
5, front end is shown
Upper, envelope are rolled off the production line and diagnostic message displays, in order to facilitate data results to check, adopt B/S mode to show result.Adopting uWSGI as web server, the request of browser is forwarded in the Python webService write, utilizes Happybase module accesses HBase data base, Query Result returns to browser via uWSGI.
DATA ENVELOPMENT ANALYSIS METHOD program is realized, generates plug-in unit, be integrated in big data platform, ultimately generate the fault diagnosis system based on DEA.
6, embodiment
By big data platform, flying quality is entered into big data platform, Envelope Analysis program is joined big data platform, form stronger analysis ability, be verified by certain model data, referring to known of Fig. 4 the abnormal situation of A, with this A for checking data, using other several secondary data as historical basis data, comparing verification platform analytic function with conventional analysis, test parameter chooses certain temperature (XX) in existing analysis report.
The Envelope Analysis of parameter XX is as shown in Figure 5.It can be seen that send out secondary comparing at about 1240s, parameter XX and B and occur extremely in conventional analysis figure.It can be seen that at about 580s, send out time A parameter and occur in that slight more zone phenomenon, occur in that serious more zone phenomenon at about 1240s in Envelope Analysis figure.
By the relative analysis of parameter XX it can be seen that conventional method of analysis could not judge the fault of about 500s, breakdown judge can only be provided after 1240s occurs in that severely subnormal.Envelope Analysis Method can interpolate that out the fault of about 500s.
The present invention realizes carrier rocket test and launches the effective means of real-time online fault detect and location, has greatly promoted fault diagnosis system application in carrier rocket industry simultaneously, has had broad application prospects and huge market potential.
The above; being only the detailed description of the invention that the present invention is best, but protection scope of the present invention is not limited thereto, any those familiar with the art is in the technical scope that the invention discloses; the change that can readily occur in or replacement, all should be encompassed within protection scope of the present invention.
The content not being described in detail in description of the present invention belongs to the known technology of professional and technical personnel in the field.
Claims (9)
1. the method for diagnosing faults based on DEA, it is characterised in that comprise the steps:
(1) typing many groups original test data;
(2) many group original test data are carried out time unifying process, generate the upper and lower line of envelope organizing original test data more;
(3) input needs the test data of diagnosis;
(4) judging that test data are whether in the envelope region of the upper and lower line of envelope, if in envelope region, then it is qualified to be judged to, is positioned at the extra-regional data of envelope if existed, is then judged to fault.
2. method according to claim 1, it is characterised in that: generate the upper and lower line method of envelope organizing original test data in described step (2) is more: for any time t, takes maximum in many group original test data, forms envelope and reach the standard grade;Take minima in many group original test data, form envelope and roll off the production line.
3. method according to claim 1, it is characterised in that: typing many groups original test data in step (1), and set up the database instance of MySQL database;Data in MySQL database example are imported in Hive instrument;Hive instrument realizes many group original test data carry out time unifying process and generate the upper and lower line of envelope organizing original test data more.
4. method according to claim 3, it is characterised in that: utilize the assembly sqoop that increases income in Hive to perform importing task.
5. method according to claim 1, it is characterized in that: many group original test data are carried out time unifying process by described step (2), generate the upper and lower line of envelope organizing original test data method particularly includes: the sampling time is divided into equal interval of N number of time more, take the maximum of many groups original test data in each interval, be fitted forming envelope and reach the standard grade;Take the minima in many groups original test data in each interval, be fitted forming envelope and roll off the production line.
6. method according to claim 1, it is characterized in that: many group original test data are carried out time unifying process by described step (2), generates the upper and lower line of envelope organizing original test data more method particularly includes: be fitted respectively obtaining a plurality of matched curve to the often group initial data in many group original test data;Select one group of sampled data as benchmark, calculate the maximum of each point in the corresponding a plurality of matched curve of this each sampling instant of group sampled data, be fitted, form envelope and reach the standard grade;Calculate the minima of each point in the corresponding a plurality of matched curve of this each sampling instant of group sampled data, be fitted, form envelope and roll off the production line.
7. method according to claim 1, it is characterised in that: many groups original test data of typing in step (1) select 1 year in original test data.
8. method according to claim 3, it is characterised in that: if it is determined that qualified, then also include step (5), it would be desirable in the test data input MySQL database of diagnosis.
9. method according to claim 1, it is characterised in that: many group original test data are more than 5 groups.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610080503.3A CN105759784B (en) | 2016-02-04 | 2016-02-04 | A kind of method for diagnosing faults based on DEA |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610080503.3A CN105759784B (en) | 2016-02-04 | 2016-02-04 | A kind of method for diagnosing faults based on DEA |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105759784A true CN105759784A (en) | 2016-07-13 |
CN105759784B CN105759784B (en) | 2019-04-09 |
Family
ID=56330599
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610080503.3A Active CN105759784B (en) | 2016-02-04 | 2016-02-04 | A kind of method for diagnosing faults based on DEA |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105759784B (en) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107229234A (en) * | 2017-05-23 | 2017-10-03 | 深圳大学 | The distributed libray system and method for Aviation electronic data |
CN107545145A (en) * | 2017-09-08 | 2018-01-05 | 国网湖南省电力公司 | Power network mountain fire calamity danger degree super efficiency envelope Analysis Method and system |
CN107957926A (en) * | 2016-10-18 | 2018-04-24 | 美光科技公司 | Method for detecting error event |
CN109597399A (en) * | 2018-11-28 | 2019-04-09 | 北京宇航系统工程研究所 | Information control platform for information-based rocket launching |
CN110187631A (en) * | 2019-06-25 | 2019-08-30 | 北京临近空间飞行器系统工程研究所 | A kind of time unifying method and system of control system |
CN110646212A (en) * | 2019-10-23 | 2020-01-03 | 成都飞机工业(集团)有限责任公司 | Novel method for calibrating aircraft engine |
CN110851497A (en) * | 2019-11-01 | 2020-02-28 | 唐山钢铁集团有限责任公司 | Method for detecting whether converter oxygen blowing is not ignited |
CN111486920A (en) * | 2020-04-15 | 2020-08-04 | 上海航天精密机械研究所 | Method, system and medium for judging and analyzing volume measurement data of carrier rocket storage tank |
CN111770002A (en) * | 2020-06-12 | 2020-10-13 | 南京领行科技股份有限公司 | Test data forwarding control method and device, readable storage medium and electronic equipment |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP3103193B2 (en) * | 1992-04-15 | 2000-10-23 | 東京電力株式会社 | Diagnostic equipment for rotating machinery |
CN1834607A (en) * | 2005-03-16 | 2006-09-20 | 欧姆龙株式会社 | Inspection method and inspection apparatus |
CN102477916A (en) * | 2010-11-30 | 2012-05-30 | 丰田自动车株式会社 | Vehicle, abnormality determination method for internal combustion engine, and abnormality determination device for internal combustion engine |
CN103269345A (en) * | 2013-05-30 | 2013-08-28 | 沈阳师范大学 | Intelligent display device and method based on Modbus protocol |
CN203350691U (en) * | 2013-05-30 | 2013-12-18 | 沈阳师范大学 | Intelligent display device based on Modbus protocol |
CN103698637A (en) * | 2013-12-25 | 2014-04-02 | 云南电力调度控制中心 | Electric power key indicator abnormity rapid detecting method and device |
CN103868694A (en) * | 2014-03-26 | 2014-06-18 | 东南大学 | Embedded variable-rotation-speed bearing fault diagnosis device |
CN105092239A (en) * | 2014-05-09 | 2015-11-25 | 潍坊学院 | Method for detecting early stage fault of gear |
-
2016
- 2016-02-04 CN CN201610080503.3A patent/CN105759784B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP3103193B2 (en) * | 1992-04-15 | 2000-10-23 | 東京電力株式会社 | Diagnostic equipment for rotating machinery |
CN1834607A (en) * | 2005-03-16 | 2006-09-20 | 欧姆龙株式会社 | Inspection method and inspection apparatus |
CN102477916A (en) * | 2010-11-30 | 2012-05-30 | 丰田自动车株式会社 | Vehicle, abnormality determination method for internal combustion engine, and abnormality determination device for internal combustion engine |
CN103269345A (en) * | 2013-05-30 | 2013-08-28 | 沈阳师范大学 | Intelligent display device and method based on Modbus protocol |
CN203350691U (en) * | 2013-05-30 | 2013-12-18 | 沈阳师范大学 | Intelligent display device based on Modbus protocol |
CN103698637A (en) * | 2013-12-25 | 2014-04-02 | 云南电力调度控制中心 | Electric power key indicator abnormity rapid detecting method and device |
CN103868694A (en) * | 2014-03-26 | 2014-06-18 | 东南大学 | Embedded variable-rotation-speed bearing fault diagnosis device |
CN105092239A (en) * | 2014-05-09 | 2015-11-25 | 潍坊学院 | Method for detecting early stage fault of gear |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107957926A (en) * | 2016-10-18 | 2018-04-24 | 美光科技公司 | Method for detecting error event |
CN107229234A (en) * | 2017-05-23 | 2017-10-03 | 深圳大学 | The distributed libray system and method for Aviation electronic data |
CN107545145B (en) * | 2017-09-08 | 2020-04-07 | 国网湖南省电力有限公司 | Power grid forest fire disaster danger degree super-efficiency envelope analysis method and system |
CN107545145A (en) * | 2017-09-08 | 2018-01-05 | 国网湖南省电力公司 | Power network mountain fire calamity danger degree super efficiency envelope Analysis Method and system |
CN109597399B (en) * | 2018-11-28 | 2020-09-18 | 北京宇航系统工程研究所 | Information control platform for informatization rocket launching |
CN109597399A (en) * | 2018-11-28 | 2019-04-09 | 北京宇航系统工程研究所 | Information control platform for information-based rocket launching |
CN110187631A (en) * | 2019-06-25 | 2019-08-30 | 北京临近空间飞行器系统工程研究所 | A kind of time unifying method and system of control system |
CN110646212A (en) * | 2019-10-23 | 2020-01-03 | 成都飞机工业(集团)有限责任公司 | Novel method for calibrating aircraft engine |
CN110646212B (en) * | 2019-10-23 | 2022-01-25 | 成都飞机工业(集团)有限责任公司 | Novel method for calibrating aircraft engine |
CN110851497A (en) * | 2019-11-01 | 2020-02-28 | 唐山钢铁集团有限责任公司 | Method for detecting whether converter oxygen blowing is not ignited |
CN111486920A (en) * | 2020-04-15 | 2020-08-04 | 上海航天精密机械研究所 | Method, system and medium for judging and analyzing volume measurement data of carrier rocket storage tank |
CN111486920B (en) * | 2020-04-15 | 2022-06-14 | 上海航天精密机械研究所 | Method, system and medium for judging and analyzing volume measurement data of carrier rocket storage tank |
CN111770002A (en) * | 2020-06-12 | 2020-10-13 | 南京领行科技股份有限公司 | Test data forwarding control method and device, readable storage medium and electronic equipment |
Also Published As
Publication number | Publication date |
---|---|
CN105759784B (en) | 2019-04-09 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105759784A (en) | Fault diagnosis method based on data envelopment analysis | |
CN111985561B (en) | Fault diagnosis method and system for intelligent electric meter and electronic device | |
CN110232056A (en) | A kind of the blood relationship analytic method and its tool of structured query language | |
CN101989087B (en) | On-line real-time failure monitoring and diagnosing system device for industrial processing of residual oil | |
US20100179951A1 (en) | Systems and methods for mapping enterprise data | |
CN101536002A (en) | System and method for process monitoring | |
CN114118224B (en) | Neural network-based full-system telemetry parameter anomaly detection system | |
US10360238B1 (en) | Database systems and user interfaces for interactive data association, analysis, and presentation | |
CN109858886B (en) | Integrated learning-based cost control success rate promotion analysis method | |
CN106776208B (en) | Fault Locating Method when a kind of running software | |
CN106874483A (en) | A kind of device and method of the patterned quality of data evaluation and test based on big data technology | |
CN113360722B (en) | Fault root cause positioning method and system based on multidimensional data map | |
US20210117051A1 (en) | Object-centric user system and graphical user interface | |
CN106446091A (en) | Preprocessing method and device for multi-source time series data | |
CN111027615A (en) | Middleware fault early warning method and system based on machine learning | |
CN103631788A (en) | Vehicle manufacturing quality problem diagnosis system based on shared data base | |
Zhang et al. | A survey on quality assurance techniques for big data applications | |
CN114398442A (en) | Data-driven information processing system | |
CN116467674A (en) | Intelligent fault processing fusion updating system and method for power distribution network | |
CN113965389A (en) | Network security management method, equipment and medium based on firewall log | |
Nguyen | Using control charts for detecting and understanding performance regressions in large software | |
Lin et al. | Design and implementation of a CPS‐based predictive maintenance and automated management platform | |
Grambau et al. | Reference Architecture framework for enhanced social media data analytics for Predictive Maintenance models | |
US11175648B2 (en) | Method and apparatus for providing an instantiated industrial semantic model for an industrial infrastructure | |
CN113887932A (en) | Operation and maintenance management and control method and device based on artificial intelligence and computer equipment |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |