CN102765643B - Elevator fault diagnosis and early-warning method based on data drive - Google Patents
Elevator fault diagnosis and early-warning method based on data drive Download PDFInfo
- Publication number
- CN102765643B CN102765643B CN201210176351.9A CN201210176351A CN102765643B CN 102765643 B CN102765643 B CN 102765643B CN 201210176351 A CN201210176351 A CN 201210176351A CN 102765643 B CN102765643 B CN 102765643B
- Authority
- CN
- China
- Prior art keywords
- case
- elevator
- fault
- elevator faults
- faults
- 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.)
- Expired - Fee Related
Links
Landscapes
- Indicating And Signalling Devices For Elevators (AREA)
- Maintenance And Inspection Apparatuses For Elevators (AREA)
Abstract
The invention relates to the field of elevators. In order to early discover and diagnose A elevator fault, the invention adopts the technical scheme that an elevator fault diagnosis and early-warning method based on data drive is achieved by means of a remote service center, a fault diagnosis and prediction terminal and an elevator controller, and the method comprises the steps as follows: firstly, elevator fault data are mined to obtain characteristic information in an elevator fault data stream, and the mined result is stored in an elevator fault case base of the fault diagnosis and prediction terminal; secondly, an elevator fault knowledge base on the fault diagnosis and prediction terminal is updated by the elevator fault case base; thirdly, the case retrieval is carried out on the characteristic of a new elevator fault problem, and the fault diagnosis is carried out on the elevator system by adopting the fault diagnosis method based on the case-base reasoning; and finally information with the characteristic that is most similar with that of the new elevator fault problem is acquired through retrieval of the knowledge or the case in the elevator fault knowledge base to solve the diagnosis problem. The method is mainly suitable for manufacturing and designing image sensors.
Description
Technical field
The present invention relates to elevators field, specifically, relate to the Elevator Fault Diagnosis based on data-driven and method for early warning.
Background technology
The elevator quantity that there is potential safety hazard due to recent year increases rapidly, carries out maintenance and has that efficiency is low, poor accuracy and the problem such as post-event diagnosis often by means of only maintenance personal's experience or servicing manual to elevator, can not meet the needs of elevator safety.Elevator needs a kind of intelligent trouble diagnosis and early warning system to ensure system safety operation.
Domestic solution elevator safety problem is mainly through two approach: one is the fault diagnosis after fault occurs, and two is the regular maintainings of maintenance personal.And the fault diagnosis technology of widespread use at present mainly contains expert system, fuzzy reasoning, neural network etc.But these technology depend critically upon expertise, acquirement of expert knowledge difficulty becomes the bottleneck that fault diagnosis is implemented.In addition, most of method for diagnosing faults all can not provide failure prediction function, and passive-type diagnosis cannot stop the generation of fault, can only be fixed against elevator periodic maintenance maintenance.Not only cost is high for the indefinite periodic maintenance of object, efficiency is low, and relies on hand inspection to be also difficult to find the potential safety hazard of elevator.
Summary of the invention
The present invention is intended to overcome the deficiencies in the prior art, realize early detection and the diagnosis of elevator faults, for achieving the above object, the technical scheme that the present invention takes is, based on Elevator Fault Diagnosis and the method for early warning of data-driven, realize by means of remote service center, fault diagnosis and fault prediction terminal and electric life controller, comprise the steps:
First carry out excavating the characteristic information obtained in elevator faults data stream to real-time elevator faults data, and Result is kept in the elevator faults case library of fault diagnosis and fault prediction terminal, as the source of elevator faults knowledge base; Then elevator faults case library is utilized to upgrade the elevator faults knowledge base in fault diagnosis and fault prediction terminal, calculated by similarity mode, realize upgrading in time of elevator faults knowledge base, feature again for new elevator faults problem carries out Case Retrieval, the method for diagnosing faults of case-based reasioning is adopted to carry out fault diagnosis to elevator device: by retrieval elevator faults knowledge base knowledge or case, obtain the information with new elevator faults problem with most similar features, solve diagnosis problem;
In addition, utilize the elevator faults recognition classifier on remote service center, cluster analysis is carried out to the elevator faults data stream obtained, corresponding elevator faults data stream and elevator faults type association are got up, and with this elevator faults data stream and corresponding failure type training classifier, sorter is tested, to verify the correctness of the sorter after training by another group elevator faults data stream and corresponding fault type again; Remote service center constantly updates sorter, and up-to-date sorter is downloaded in local fault diagnosis and fault prediction terminal, local fault diagnosis and fault prediction terminal Real-time Collection elevator data stream is also inputted sorter, carry out similarity degree by sorter output real-time stream with existing elevator faults data stream to compare, similarity degree is larger, occur that the possibility of fault of the same race is larger, carry out elevator faults prediction according to this.
Adopting the method for diagnosing faults of case-based reasioning to carry out fault diagnosis to elevator device is carry out in fault diagnosis and fault prediction terminal, and is further refined as following steps:
(1) elevator faults knowledge base: the set being Elevator Fault Diagnosis knowledge, experience, there is provided primarily of expert, comprise elevator essential information, the classified information of elevator faults and the various key feature attribute of variety classes fault needs and weights thereof, and build elevator faults case library and sign variable storehouse according to this;
(2) set up elevator faults case library: maintenance personal fills in the various information about elevator faults according to the historical data comprising elevator faults daily record and maintenance daily record, and store case on this basis and produce new case;
(3) sign variable storehouse is set up: the fault type traffic flow information collected when storing Lift out of order, the parameters that when namely fault occurs, elevator runs;
(4) rule base is set up: store the interrelated information between various elevator faults type, to fault case storehouse association rule-based algorithm, carry out data mining, from numerous elevator faults case informations, extract profound, tacit knowledge, for Elevator Fault Diagnosis, guide maintenance personnel make the maintenance measure of response;
(5) inference system: be made up of Case Retrieval, case coupling, case adjustment, be specially: find one or more case the most similar to current failure by carrying out Case Retrieval to elevator faults case library, the searching algorithm used has template to check, concludes retrieval, nearest neighbor search; Then generate solution according to the case retrieved and adjusted the solution generated by Case-based adaptation, the method for adjustment has transformation approach, Shift Method, specific objective to drive method;
(6) case study: according to the feedback information of maintenance personal, case carried out to elevator faults case library multiplexing, if namely the program can solve the fault run into, preserve the maintenance suggestion in elevator faults case library, otherwise be saved in fault case storehouse after the program is modified, so continuous acquisition new knowledge and the old knowledge of improvement, form new maintenance program, and add in case library, case library is constantly expanded and perfect.
Case Retrieval specific implementation step:
(1) elevator faults data stream is gathered, characteristic information extraction according to taxonomic structure index, preliminary search goes out to meet the case kind of characteristic information.
(2) according to the kind of fault case, failure message eigenwert is mated with elevator faults knowledge base.
(3) calculate according to the European algorithm improved, calculate the matching degree of all cases in this target case and initial matching casebook, and sort according to the size of matching degree, export former the cases of mating most with target case, complete case matching process; Finally, display case coupling details, and prepare for Case-based adaptation.
The generative process of sorter comprises data preprocessing module, characteristic extracting module and sorter generation module, wherein data preprocessing module adopts and comprises standardization, variance reduction step, is responsible for rejecting the noise data such as abnormal data, redundant data in data; Characteristic extracting module adopts principal component analysis (PCA), partial least square method, is responsible for reduced data stream, improves training effectiveness; Sorter generation module also comprises neural network, support vector machine submodule.
Technical characterstic of the present invention and effect:
Data mining identifies type that is effective, novel, potentially useful and that finally can be understood from data.The key of fault diagnosis and matter of utmost importance are exactly Fault Identification, to the process of diagnosing malfunction i.e. the process of fault type acquisition and Fault Identification.Consider the unique advantage of data mining technology in knowledge acquisition, it is practicable for introducing this technology in fault diagnosis field.Historical data can be utilized to excavate wherein potential rule, for fault diagnosis provides decision-making foundation, there is actual reference.
Have the following advantages based on the fault diagnosis of data mining and early warning system:
(1) breach elevator diagnostic knowledge and obtain the bottleneck difficult, knowledge quantity is few.Can automatically obtain diagnostic experiences and without the need to manually summing up and inputting, substantially increase diagnosis efficiency and accuracy, reduce diagnosis cost.
(2) for fault that is larger, that relate to multiple variable, use and cannot solve the diagnostic method of single part, utilizing data mining technology to carry out holistic approach to car movement data can effectively diagnose.
(3) failure cause and position can not only be found for maintenance personal, corresponding fault solution can also be provided.
(4) Real-Time Monitoring can be carried out to car movement data, be obtained the similarity degree of real-time stream and fault type by sorter, thus realize early detection and the early warning of elevator faults.
(5) this system has self-learning capability, and the fault data that unceasing study is new forms new diagnostic knowledge, and along with the continuous increase of fault data, the trouble diagnosibility of system can constantly strengthen.
(6) for preventative maintenance provides basis.Preventative maintenance based on failure prediction decreases blindness, and make elevator keeping in repair to effective in the best breakdown maintenance time, not only reduce maintenance frequency and cost, the efficiency of maintenance also improves greatly.
Accompanying drawing explanation
Fig. 1 is based on the Elevator Fault Diagnosis of data-driven and early warning system one-piece construction figure.
The Elevator Fault Diagnosis frame diagram of Fig. 2 case-based reasioning.
Fig. 3 case information represents schematic diagram.
Fig. 4 elevator faults case retrieval strategy process flow diagram.
Fig. 5 is based on the elevator faults prediction process flow diagram of sorter.
Fig. 6 elevator long distance service centre sorter generates schematic diagram.
Fig. 7 is based on the classifier design schematic diagram of BP neural network.
Embodiment
The object of the invention is to propose a kind of Elevator Fault Diagnosis based on data-driven and early warning system, realize efficient fault diagnosis and failure prediction accurately.
There is acquirement of expert knowledge difficulty in existing Elevator Fault Diagnosis technology, diagnosis efficiency is low, high in cost of production problem, for these problems, the method for diagnosing faults of the present invention's application case-based reasioning carries out fault diagnosis to elevator device, in elevator faults case library, optimum matching case is retrieved after breaking down, and according to the failure cause in case information, abort situation and fault solution are safeguarded, simultaneous faults case library can carry out the maintenance of case library automatically, comprise increase case, merge case, delete redundancy case etc., thus possess very strong learning ability.
Current most of fault diagnosis system lacks failure prediction function, the present invention analyzes elevator historical data by data mining technology, induction and conclusion goes out the data stream of corresponding specific fault, consider expertise and data stream, data stream during by being run by elevator contrasts with known fault data stream in real time, and quantum chemical method is carried out to both similarity degrees, fault pre-alarming can be proposed to elevator device after similarity acquires a certain degree, thus complete failure prediction function.This system obtains the general parameters of elevator operation and automatically analyzes service data, breaches the bottleneck that expert system obtains difficulty, has the advantage that diagnosis efficiency is high, cost is low and can realize failure prediction function.The present invention does not need to install additional sensors additional, is applicable to the elevator of various different brands, has good application prospect and economic worth, and this System and method for also has very high reference value to the fault diagnosis of other field.
The present invention utilizes elevator faults data mining technology, devise a kind of Elevator Fault Diagnosis system, this system constantly collects data analysis to from elevator device, the ability in knowledge acquisition of data mining technology is relied on to form the fault diagnosis knowledge of elevator device automatically and efficiently, solve the problem of acquirement of expert knowledge difficulty, overcome the technical bottleneck of current Elevator Fault Diagnosis.Then, on the basis of this system architecture, propose a kind of Elevator Fault Diagnosis method of case-based reasioning, the knowledge utilizing said method to be formed is diagnosed.
In addition, the basis of this system architecture adds the failure prediction function based on sorter, can Real-Time Monitoring elevator data stream, and utilize sorter analyzed these data stream and identify, calculate similarity size and the trend of current data stream and fault data stream, and then realize early detection and the diagnosis of elevator faults.
The present invention, by data mining technology, designs a kind of Elevator Fault Diagnosis based on data-driven and early warning system, has the Fault diagnosis and forecast function of enhancing.
First the present invention carries out excavating the characteristic information obtained in elevator faults data stream to real-time elevator faults data by data mining algorithm, and is kept at by Result in elevator faults case library, as the source of elevator faults knowledge base.Then utilize elevator faults case library to upgrade elevator faults knowledge base, calculated by similarity mode, realize upgrading in time of elevator faults knowledge base.Feature again for new problem carries out Case Retrieval, by knowledge or the case of retrieval elevator faults knowledge base, obtains the information with new elevator faults problem with most similar features, for solving diagnosis problem.
In addition, be designed for elevator faults recognition classifier, cluster analysis is carried out to the group data stream obtained, corresponding data stream is associated with fault type, and with this data stream and corresponding failure type training classifier, by another group data stream and corresponding fault type, sorter is tested again, to verify the correctness of the sorter after training.Remote service center constantly updates sorter, and up-to-date sorter is downloaded in local diagnosis terminal, data stream is also inputted sorter by local diagnosis terminal Real-time Collection elevator data stream, the similarity degree of real-time stream and existing fault data stream is exported by sorter, similarity is larger, occur that the possibility of fault of the same race is larger, elevator faults prediction can be carried out successively.
Below in conjunction with accompanying drawing, the invention will be further described.
Core of the present invention is by analyzing car movement data stream, excavate the characteristic information of data stream during fault, find the data stream corresponding with elevator faults type, and be translated into expertise, stored in Elevator Fault Diagnosis case library, then the method for diagnosing faults of case-based reasioning is adopted to carry out fault diagnosis to elevator device.In addition, design error failure data flow classification device, real-time grading can be carried out in real time to elevator current data stream, and calculate current data stream and elevator faults data stream similarity size by the similarity algorithm based on distance, more major break down possibility is larger for similarity, carries out failure prediction according to this similarity trend or by the method arranging threshold value.
See Fig. 1, comprise three parts based on the Elevator Fault Diagnosis of data-driven and early warning system: remote service center, fault diagnosis and fault prediction terminal and electric life controller.
When fault occurs, parameters in diagnostic trouble code in electric life controller register system and current elevator device, as: traction machine rotating speed, car acceleration, frequency converter voltage, inverter current, flat bed signal, signal of rushing to summit, hit end signal, door machine signal etc.And import diagnostic trouble code and parameter current into local diagnostic platform in the lump.During normal operation, only need current system parameter to be sent to local diagnosis terminal in real time for failure prediction.
Elevator Fault Diagnosis and forecasting software and SQLServer2005 database software are set in local diagnosis terminal, the eigenwert of this fault type will be extracted after receiving elevator faults code and parameter current, then in case library, find optimum matching case according to this, then send this failure message to far-end maintenance personal with the failure cause of mating and solution by the mobile terminal such as Internet or mobile phone; If find that the matching degree of current and best case is less than threshold value when mating best case, then this fault is regarded as new fault type, and current failure message is sent to remote service center.On the other hand, the classifier modules that in Elevator Fault Diagnosis and forecasting software, integrated utilization com component is write, completes the forecast function of elevator faults.
Remote service center is responsible for data stream when collecting all elevator device faults, and the sorter and case library that are stored in service centre is trained by the data stream under these malfunctions, continuous renewal sorter and case library make fault type recognition further accurate with diagnosis; What remote service center was regular downloads to local diagnosis terminal up-to-date sorter and case library, and makes response to elevator faults early warning information.
See Fig. 2, the Elevator Fault Diagnosis framework of case-based reasioning mainly comprises four databases, an inference system and a case study module.Each several part specifically describes as follows:
(1) knowledge base: the set of Elevator Fault Diagnosis knowledge, experience, it provides primarily of expert, comprise elevator essential information, the classified information of elevator faults and the various key feature attribute of variety classes fault needs and weights thereof, and build elevator faults case library and sign variable storehouse according to this.
(2) fault case storehouse: maintenance personal fills in the various information about elevator faults according to historical datas such as elevator faults daily record and maintenance daily records, and stores case on this basis and produce new case.
(3) sign variable storehouse: the fault type traffic flow information collected during Lift out of order, the parameters that when namely fault occurs, elevator runs.
(4) rule base: the interrelated information between various elevator faults type.Be to fault case storehouse association rule-based algorithm, carry out data mining, from numerous elevator faults case informations, extract profound, tacit knowledge, for Elevator Fault Diagnosis, guide maintenance personnel make the maintenance measure of response.
(5) inference system: the core of diagnostic system, is made up of Case Retrieval, case coupling, case adjustment.Find one or more case the most similar to current failure by carrying out Case Retrieval to elevator faults case library, the searching algorithm that may use has template to check, concludes retrieval, nearest neighbor search etc.Then generate solution according to the case retrieved and transformation approach, Shift Method, specific objective may be had by Case-based adaptation to drive method to the method that the solution generated carries out adjustment, most case adjustment is all completed by man-machine interaction mode.Inference system determines the height of diagnosis efficiency, realizes from existing casebook, find the case the most similar to current problem, and provides corresponding fault solution.
(6) case study: according to the feedback information of maintenance personal, case carried out to elevator faults case library multiplexing, if namely the program can solve the fault run into, preserve the maintenance suggestion in elevator faults case library, otherwise be saved in fault case storehouse after the program is modified.So continuous acquisition new knowledge and improve old knowledge, forming new maintenance program, and add in case library, is that case library is constantly expanded and perfect.
See Fig. 3, each case in case library is made up of case essential information, failure cause and location and fault solution, in diagnostic procedure, electric life controller provides the essential informations such as fault data stream elevator signal, diagnostic system is then analyzed according to these information, returns failure cause and the information such as location and fault solution.
See Fig. 4, Case Retrieval is the key of the Elevator Fault Diagnosis flow process of whole case-based reasioning, is below specific implementation step:
(1) the fault data stream of fault elevator is gathered, characteristic information extraction according to taxonomic structure index, preliminary search goes out to meet the case kind of characteristic information.
(2) according to the kind of fault case, failure message eigenwert is mated with casebook.
(3) calculate according to the European algorithm improved, calculate the matching degree of all cases in this target case and initial matching casebook, and sort according to the size of matching degree, export former the cases of mating most with target case, complete case matching process.Finally, display case coupling details, and prepare for Case-based adaptation.
As follows according to case structure attribute Jacobian matrix each in elevator faults case library:
Wherein A
ijrepresent a jth attribute of i-th case.A note jth attribute mean value be B
j, then:
Note intermediate variable M
ij
Make again:
Improvement Euclidean distance between target case and source case is:
W in formula
ifor the weighted value that expertise provides.D
tivalue larger, show that the distance between target case and source case is less, similarity is higher, calculates and diagnose apart from minimum source case in retrieving.
The European algorithm improved introduces intermediate variable M on the basis of the European algorithm of tradition
ij, namely add a normalized process of property value, can effectively prevent some attribute value in same case excessive, cause result for retrieval to depart from actual situation and occur.
See Fig. 5, by the calculating of sorter to the identification of elevator faults data stream and similarity, finally can obtain the development trend of fault similarity or the comparative result with threshold value, in order to ensure it is other accuracy, sorter has remote service center to carry out regular update, finally completes the failure prediction function of elevator.
See Fig. 6, the generation of sorter comprises two stages (training stage and testing stage).The fault data stream generated for sorter is divided into two parts, and wherein the data of 2/3rds are with the training stage, and the data of 1/3rd are used for testing stage.Training stage tentatively generates sorter, verifies to ensure its accuracy to the sorter generated at testing stage.
The generative process of sorter comprises data preprocessing module, characteristic extracting module and sorter generation module, wherein data preprocessing module is responsible for rejecting the noise data such as abnormal data, redundant data in data, characteristic extracting module is responsible for reduced data stream, improves training effectiveness.Sorter generation module is in fact the module that support vector machine, neural network etc. have nonlinear function models function.Statistics used by data preprocessing module needs and mathematical tool comprises standardization, variance reduction etc., and feature processing block may use the mathematical method such as principal component analysis (PCA), offset minimum binary.
See Fig. 7, adopt BP neural network in sorter generation module, the nodes of definition input layer is 2, and output layer nodes is 1, and node in hidden layer is 6, uses Logsig type transport function, is expressed as follows:
Weights amendment formula is:
W
sq(t+1)＝W
sq(t)+η(t)δ
qy
s+αΔW
sq(t)
Wherein, η is gain term to weights, δ
qfor error term, y
sfor the output of node s node, α is the weights of setting.W
sq(t) be the t time iteration weights.This sorter realizes under Visual C++ environment.Input amendment collection and corresponding training objective collection are directly stored in SQL database, to ensure the versatility of data.Classifier modules is designed to com component, when needing, this assembly is called.
Claims (3)
1. based on Elevator Fault Diagnosis and the method for early warning of data-driven, it is characterized in that, realize by means of remote service center, fault diagnosis and fault prediction terminal and electric life controller, comprise the steps:
First carry out excavating the characteristic information obtained in elevator faults data stream to real-time elevator faults data, and Result is kept in the elevator faults case library of fault diagnosis and fault prediction terminal, as the source of elevator faults knowledge base; Then elevator faults case library is utilized to upgrade the elevator faults knowledge base in fault diagnosis and fault prediction terminal, calculated by similarity mode, realize upgrading in time of elevator faults knowledge base, feature again for new elevator faults problem carries out Case Retrieval, the method for diagnosing faults of case-based reasioning is adopted to carry out fault diagnosis to elevator device: by the knowledge in retrieval elevator faults knowledge base or temporary elevator fault case storehouse or case, obtain the information with new elevator faults problem with most similar features, solve diagnosis problem;
In addition, utilize the elevator faults recognition classifier on remote service center, cluster analysis is carried out to the elevator faults data stream obtained, corresponding elevator faults data stream and elevator faults type association are got up, and with this elevator faults data stream and corresponding failure type training classifier, sorter is tested, to verify the correctness of the sorter after training by another group elevator faults data stream and corresponding fault type again; Remote service center constantly updates sorter, and up-to-date sorter is downloaded in local fault diagnosis and fault prediction terminal, local fault diagnosis and fault prediction terminal Real-time Collection elevator data stream is also inputted sorter, carry out similarity degree by sorter output real-time stream with existing elevator faults data stream to compare, similarity degree is larger, occur that the possibility of fault of the same race is larger, carry out elevator faults prediction according to this;
Case Retrieval specific implementation step:
(1) elevator faults data stream is gathered, characteristic information extraction according to taxonomic structure index, preliminary search goes out to meet the case kind of characteristic information;
(2) according to the kind of fault case, failure message eigenwert is mated with elevator faults knowledge base;
(3) calculate according to the European algorithm improved, calculate the matching degree of all cases in target case and initial matching casebook, and sort according to the size of matching degree, export former the cases of mating most with target case, complete case matching process; Finally, display case coupling details, and prepare for Case-based adaptation; Wherein:
As follows according to case structure attribute Jacobian matrix each in elevator faults case library:
Wherein A
ijrepresent a jth attribute of i-th case, a note jth attribute mean value be B
j, then:
Note intermediate variable M
ij
Make again:
Improvement Euclidean distance between target case and source case is:
The basis of the European algorithm of tradition is introduced intermediate variable M
ij, namely increase a normalized process of property value.
2. as claimed in claim 1 based on Elevator Fault Diagnosis and the method for early warning of data-driven, it is characterized in that, adopting the method for diagnosing faults of case-based reasioning to carry out fault diagnosis to elevator device is carry out in fault diagnosis and fault prediction terminal, and is further refined as following steps:
(1) elevator faults knowledge base: the set being Elevator Fault Diagnosis knowledge, experience, there is provided primarily of expert, comprise elevator essential information, the classified information of elevator faults and the various key feature attribute of variety classes fault needs and weights thereof, and build elevator faults case library and sign variable storehouse according to this;
(2) set up elevator faults case library: maintenance personal fills in the various information about elevator faults according to the historical data comprising elevator faults daily record and maintenance daily record, and store case on this basis and produce new case;
(3) sign variable storehouse is set up: the fault type traffic flow information collected when storing Lift out of order, the parameters that when namely fault occurs, elevator runs;
(4) rule base is set up: store the interrelated information between various elevator faults type, to fault case storehouse association rule-based algorithm, carry out data mining, from numerous elevator faults case informations, extract profound, tacit knowledge, for Elevator Fault Diagnosis, guide maintenance personnel make the maintenance measure of response;
(5) inference system: be made up of Case Retrieval, case coupling, case adjustment, be specially: find one or more case the most similar to current failure by carrying out Case Retrieval to elevator faults case library, the searching algorithm used has template to check, concludes retrieval, nearest neighbor search; Then generate solution according to the case retrieved and adjusted the solution generated by Case-based adaptation, the method for adjustment has transformation approach, Shift Method, specific objective to drive method;
(6) case study: according to the feedback information of maintenance personal, case carried out to elevator faults case library multiplexing, if namely the program can solve the fault run into, preserve the maintenance suggestion in elevator faults case library, otherwise be saved in fault case storehouse after the program is modified, so continuous acquisition new knowledge and the old knowledge of improvement, form new maintenance program, and add in case library, case library is constantly expanded and perfect.
3. as claimed in claim 1 based on Elevator Fault Diagnosis and the method for early warning of data-driven, it is characterized in that, the generative process of sorter comprises data preprocessing module, characteristic extracting module and sorter generation module, wherein data preprocessing module adopts and comprises standardization, variance reduction step, is responsible for rejecting the noise data such as abnormal data, redundant data in data; Characteristic extracting module adopts principal component analysis (PCA), partial least square method, is responsible for reduced data stream, improves training effectiveness; Sorter generation module also comprises neural network, support vector machine submodule.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210176351.9A CN102765643B (en) | 2012-05-31 | 2012-05-31 | Elevator fault diagnosis and early-warning method based on data drive |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210176351.9A CN102765643B (en) | 2012-05-31 | 2012-05-31 | Elevator fault diagnosis and early-warning method based on data drive |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102765643A CN102765643A (en) | 2012-11-07 |
| CN102765643B true CN102765643B (en) | 2015-06-17 |
Family
ID=47093264
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210176351.9A Expired - Fee Related CN102765643B (en) | 2012-05-31 | 2012-05-31 | Elevator fault diagnosis and early-warning method based on data drive |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102765643B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3367558A1 (en) * | 2017-02-24 | 2018-08-29 | Siemens Aktiengesellschaft | Method for operating a linear motor based transport system and control unit |
Families Citing this family (89)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103135014A (en) * | 2012-12-14 | 2013-06-05 | 西安电子科技大学 | Transformer fault diagnosis method based on case-based reasoning |
| CN103159106A (en) * | 2013-03-27 | 2013-06-19 | 中山市卓梅尼控制技术有限公司 | Elevator maintenance system |
| CN103278728B (en) * | 2013-04-27 | 2015-09-16 | 广东电网公司电力科学研究院 | Short Circuit Between Generator Rotor Windings method for diagnosing faults and system |
| CN103231962A (en) * | 2013-05-15 | 2013-08-07 | 北京晶科华盛科技有限公司 | Diagnosis and early-warning system for elevator faults |
| CN103359572A (en) * | 2013-05-23 | 2013-10-23 | 中国矿业大学 | Elevator fault diagnosis method and device |
| CN104236933B (en) * | 2013-06-13 | 2017-12-26 | 同济大学 | A kind of potential faults method for early warning for train traction system |
| JP6190882B2 (en) * | 2013-07-05 | 2017-08-30 | 富士機械製造株式会社 | An automatic system that can estimate where maintenance is needed |
| CN103523625B (en) * | 2013-07-27 | 2015-12-02 | 安徽理工大学 | Based on the coal mine shaft lining cage runaway anti-drop method of algorithm of support vector machine |
| CN103466397A (en) * | 2013-09-11 | 2013-12-25 | 昆山新金福精密电子有限公司 | Method for identifying elevator group control traffic mode based on support vector machine |
| CN104579737A (en) * | 2013-10-29 | 2015-04-29 | 北大方正集团有限公司 | Method and system for operating maintenance of distributed web system |
| CN103592919B (en) * | 2013-11-13 | 2016-03-09 | 青岛海尔软件有限公司 | A kind of home appliance failure risk Prediction System and method |
| CN103617105B (en) * | 2013-12-17 | 2016-08-17 | 中国科学院合肥物质科学研究院 | A kind of adaptive multi-layer flow model facility diagnosis method based on data-driven |
| CN103646104A (en) * | 2013-12-23 | 2014-03-19 | 北京华力创通科技股份有限公司 | Hard real-time fault diagnosis method and system |
| CN103744919B (en) * | 2013-12-26 | 2017-02-08 | 广州供电局有限公司 | Power grid knowledge base self learning method and system |
| CN103903408B (en) * | 2014-04-04 | 2017-07-21 | 内蒙古大唐国际新能源有限公司 | Method for early warning and system are investigated in equipment fault |
| CN104361500A (en) * | 2014-11-25 | 2015-02-18 | 珠海格力电器股份有限公司 | Air conditioner after-sale fault data processing method and system |
| CN105712140A (en) * | 2014-12-05 | 2016-06-29 | 华夏视清数字技术(北京)有限公司 | Monitoring and early-warning device and method |
| CN104599193A (en) * | 2015-01-16 | 2015-05-06 | 国家电网公司 | Rule base based single-phase ground fault positioning method of distribution network |
| JP6520539B2 (en) * | 2015-08-05 | 2019-05-29 | 三菱電機ビルテクノサービス株式会社 | Search system |
| CN105731209A (en) * | 2016-03-17 | 2016-07-06 | 天津大学 | Intelligent prediction, diagnosis and maintenance method for elevator faults on basis of Internet of Things |
| CN105775943A (en) * | 2016-04-12 | 2016-07-20 | 广州深度数据科技有限公司 | Data driven elevator part early warning system and method |
| CN105955241B (en) * | 2016-06-03 | 2018-09-14 | 北京科技大学 | A kind of quality fault localization method based on joint data-driven production process |
| JP6607830B2 (en) * | 2016-07-05 | 2019-11-20 | 株式会社日立ビルシステム | Maintenance work management device and maintenance work management system |
| CN106516923A (en) * | 2016-08-31 | 2017-03-22 | 江苏鸿信系统集成有限公司 | Elevator running failure prediction method based on technology of Internet of Things |
| CN107991100A (en) * | 2016-10-27 | 2018-05-04 | 福建宁德核电有限公司 | A kind of diesel engine method for detecting operation state and system |
| CN106526425A (en) * | 2016-11-23 | 2017-03-22 | 衢州学院 | Low-voltage diagnosis method based on real collected data of intelligent electric meter |
| CN106779066A (en) * | 2016-12-02 | 2017-05-31 | 上海无线电设备研究所 | A kind of radar circuit plate method for diagnosing faults |
| CN106672733A (en) * | 2016-12-02 | 2017-05-17 | 常州大学 | Elevator failure analysis and early warning system based on micro-cloud intelligent terminal and method thereof |
| JP6693576B2 (en) * | 2016-12-26 | 2020-05-13 | 三菱電機株式会社 | Recovery system |
| CN108466884A (en) * | 2017-02-23 | 2018-08-31 | 无锡鸿廷科技有限公司 | A kind of elevator operation action management and analysis |
| CN106959662B (en) * | 2017-05-10 | 2019-03-08 | 东北大学 | A kind of identification of electric melting magnesium furnace unusual service condition and control method |
| CN107194053B (en) * | 2017-05-16 | 2020-10-20 | 歌拉瑞电梯股份有限公司 | Intelligent elevator control system operation fault prediction method |
| CN107153876A (en) * | 2017-05-25 | 2017-09-12 | 南通大学 | Machine vision shutter Self-tuning System intelligent control method based on Expert Rules |
| CN107966942A (en) * | 2017-06-18 | 2018-04-27 | 广东金宝力化工科技装备股份有限公司 | A kind of equipment fault forecasting system in knowledge based storehouse |
| CN107381269A (en) * | 2017-07-10 | 2017-11-24 | 安徽奥里奥克科技股份有限公司 | Elevator safety management system based on elevator safety information interaction screen |
| CN107294788A (en) * | 2017-07-17 | 2017-10-24 | 郑州云海信息技术有限公司 | A kind of method and device of troubleshooting |
| CN109388661B (en) * | 2017-08-02 | 2020-04-21 | 创新先进技术有限公司 | Model training method and device based on shared data |
| CN107862324B (en) * | 2017-10-19 | 2021-11-02 | 北京化工大学 | MWSPCA-based CBR prediction model intelligent early warning method |
| CN108100794B (en) * | 2017-12-18 | 2019-06-04 | 快创科技（大连）有限公司 | A kind of elevator reparing management system based on AR and intelligent push |
| CN108304350B (en) * | 2017-12-25 | 2021-04-30 | 明阳智慧能源集团股份公司 | Fan index prediction and fault early warning method based on big data set neighbor strategy |
| JP6837427B2 (en) * | 2017-12-27 | 2021-03-03 | 株式会社日立ビルシステム | Elevator failure diagnosis system |
| CN108357999B (en) * | 2018-01-05 | 2019-12-31 | 揭阳市聆讯软件有限公司 | Monitoring rescue method, device, intelligent equipment and storage medium |
| US10939477B2 (en) | 2018-01-29 | 2021-03-02 | Otis Elevator Company | Service tool wireless access management |
| CN108416520A (en) * | 2018-03-01 | 2018-08-17 | 南京理工大学 | Elevator system level of integrity appraisal procedure based on Hopfield neural networks |
| CN108584598B (en) * | 2018-03-16 | 2020-09-15 | 广州市金度信息科技有限公司 | Elevator fault automatic analysis and early warning method, storage medium and intelligent terminal |
| CN108529380B (en) * | 2018-03-27 | 2021-01-19 | 深圳市永达电子信息股份有限公司 | Elevator safety prediction method and system |
| US20200002125A1 (en) * | 2018-06-29 | 2020-01-02 | Otis Elevator Company | Maintenance scheduling based on remote monitoring data and service data analytics |
| CN108946370B (en) * | 2018-07-24 | 2021-05-07 | 日立楼宇技术（广州）有限公司 | Elevator fault information processing method, system, equipment and readable storage medium |
| CN110817628A (en) * | 2018-08-08 | 2020-02-21 | 北京感瞰科技有限公司 | Intelligent fault diagnosis method, device and system for elevator |
| CN109032872B (en) * | 2018-08-13 | 2021-08-10 | 广东电网有限责任公司广州供电局 | Bayesian network-based equipment fault diagnosis method and system |
| CN108750854B (en) * | 2018-08-20 | 2020-06-16 | 山东润一智能科技有限公司 | Hospital elevator safety three-dimensional monitoring cloud platform, system and method thereof, and elevator system |
| US20200065691A1 (en) * | 2018-08-21 | 2020-02-27 | Otis Elevator Company | Model development framework for remote monitoring condition-based maintenance |
| US11472663B2 (en) | 2018-10-01 | 2022-10-18 | Otis Elevator Company | Automatic software upgrade assistant for remote elevator monitoring experts using machine learning |
| CN109240244B (en) * | 2018-10-26 | 2020-11-20 | 云达世纪（北京）科技有限公司 | Data-driven equipment running state health degree analysis method and system |
| CN109436980B (en) * | 2018-11-01 | 2020-06-26 | 日立楼宇技术（广州）有限公司 | Method and system for detecting state of elevator component |
| CN109693983B (en) * | 2019-01-02 | 2021-09-10 | 日立楼宇技术（广州）有限公司 | Elevator fault processing method, device, server, storage medium and system |
| US11993480B2 (en) | 2019-04-30 | 2024-05-28 | Otis Elevator Company | Elevator shaft distributed health level with mechanic feed back condition based monitoring |
| CN110436289A (en) * | 2019-05-22 | 2019-11-12 | 安徽奥里奥克科技股份有限公司 | A kind of Elevator Fault Diagnosis and early warning system based on data-driven |
| CN110155840B (en) * | 2019-05-22 | 2021-05-14 | 安徽奥里奥克科技股份有限公司 | Elevator data acquisition management system |
| CN110377618B (en) * | 2019-06-17 | 2024-01-05 | 平安科技（深圳）有限公司 | Method, device, computer equipment and storage medium for analyzing decision result |
| CN110275481B (en) * | 2019-07-03 | 2020-10-30 | 北京北特圣迪科技发展有限公司 | Stage self-adaptive maintenance correction method and system |
| CN110489475B (en) * | 2019-08-14 | 2021-01-26 | 广东电网有限责任公司 | Multi-source heterogeneous data processing method, system and related device |
| WO2021072687A1 (en) * | 2019-10-16 | 2021-04-22 | 西门子（中国）有限公司 | Fault processing method and system, and computer readable medium |
| CN110837566B (en) * | 2019-11-15 | 2022-05-13 | 北京邮电大学 | Dynamic construction method of knowledge graph for CNC (computerized numerical control) machine tool fault diagnosis |
| CN111026008B (en) * | 2019-12-16 | 2021-12-24 | 上海宏力达信息技术股份有限公司 | Intelligent switch first-aid repair method and system based on ant colony algorithm |
| CN111556111A (en) * | 2020-04-21 | 2020-08-18 | 天津市市政工程设计研究院 | Pipe gallery equipment fault remote diagnosis system based on Internet of things |
| WO2021224539A1 (en) * | 2020-05-04 | 2021-11-11 | Kone Corporation | A solution for generating dynamic information content of a people transport system |
| CN111650918A (en) * | 2020-05-14 | 2020-09-11 | 中铁第四勘察设计院集团有限公司 | Vertical elevator full-life cycle operation safety monitoring system |
| CN111648992B (en) * | 2020-06-02 | 2022-06-10 | 上海工业自动化仪表研究院有限公司 | Gas turbine compressor fault identification early warning method |
| CN111784064A (en) * | 2020-07-09 | 2020-10-16 | 河南中电投华新电力工程有限公司 | Power plant equipment intelligent prediction maintenance method and system based on big data |
| CN111994745A (en) * | 2020-08-31 | 2020-11-27 | 郑州大学 | Elevator equipment portrait drawing system and method |
| CN112596495B (en) * | 2020-12-07 | 2022-03-25 | 中科蓝智(武汉)科技有限公司 | Industrial equipment fault diagnosis method and system based on knowledge graph |
| CN112631204A (en) * | 2020-12-14 | 2021-04-09 | 成都航天科工大数据研究院有限公司 | Health management platform, terminal, system and method for numerical control machine tool |
| CN112520528B (en) * | 2020-12-23 | 2021-06-22 | 江苏梯卫士网络科技有限公司 | Automatic monitoring elevator fault detection system and detection method thereof |
| CN112926632B (en) * | 2021-02-01 | 2023-04-18 | 广州赛特智能科技有限公司 | Method for detecting height difference between elevator and floor |
| CN112860348A (en) * | 2021-03-10 | 2021-05-28 | 博创智能装备股份有限公司 | Intelligent diagnosis and analysis system of injection molding machine |
| CN113091817A (en) * | 2021-04-06 | 2021-07-09 | 重庆大学 | Triethylene glycol dewatering device state monitoring and fault diagnosis system |
| CN113204212A (en) * | 2021-04-26 | 2021-08-03 | 江苏博尚工业装备有限公司 | Numerical control machine tool fault diagnosis method based on double-expert system |
| CN113296994A (en) * | 2021-05-18 | 2021-08-24 | 北京计算机技术及应用研究所 | Fault diagnosis system and method based on domestic computing platform |
| CN113486150B (en) * | 2021-07-13 | 2024-02-02 | 广西民族大学 | Machine fault diagnosis method and device based on event structure model |
| CN113511577A (en) * | 2021-08-09 | 2021-10-19 | 合肥市春华起重机械有限公司 | Gantry crane for rail type container |
| CN113682919B (en) * | 2021-09-22 | 2022-11-15 | 赵福杰 | Intelligent repair elevator based on Internet of things |
| CN113609299B (en) * | 2021-10-11 | 2021-12-28 | 浙江浙能技术研究院有限公司 | Fault diagnosis library establishment method based on ant colony algorithm and feature recombination |
| CN113809721B (en) * | 2021-11-01 | 2023-10-31 | 宁波申菱机电科技股份有限公司 | Permanent magnet door machine controller of elevator |
| CN114291675B (en) * | 2021-11-18 | 2024-05-03 | 杭州电子科技大学 | Elevator fault diagnosis method based on complex network and confidence rule reasoning |
| CN114611575B (en) * | 2022-01-29 | 2023-09-15 | 国网河北省电力有限公司邯郸供电分公司 | Fault case classification method and system |
| CN114780732B (en) * | 2022-06-22 | 2022-09-13 | 天津市天锻压力机有限公司 | Forging hydraulic press predictive maintenance method and system based on Bayes classification model |
| CN115956543A (en) * | 2022-07-15 | 2023-04-14 | 生态环境部南京环境科学研究所 | Fishing device and fishing method for wild giant salamander resource investigation |
| CN116588776B (en) * | 2023-07-19 | 2023-11-03 | 常熟理工学院 | Elevator passenger flow prediction and optimal scheduling method and system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1887674A (en) * | 2006-07-27 | 2007-01-03 | 隋舒杰 | Lift remote monitoring and warning system based on radio network |
| CN201592932U (en) * | 2010-01-14 | 2010-09-29 | 四川润智兴科技有限公司 | Elevator safety early warning system |
| CN201777739U (en) * | 2010-08-06 | 2011-03-30 | 北京诚信能环科技有限公司 | ES elevator monitoring management information system |
| CN102295206A (en) * | 2010-06-22 | 2011-12-28 | 深圳市新开元信息技术发展有限公司 | Elevator safety remote real-time monitoring system based on Internet of things |
-
2012
- 2012-05-31 CN CN201210176351.9A patent/CN102765643B/en not_active Expired - Fee Related
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1887674A (en) * | 2006-07-27 | 2007-01-03 | 隋舒杰 | Lift remote monitoring and warning system based on radio network |
| CN201592932U (en) * | 2010-01-14 | 2010-09-29 | 四川润智兴科技有限公司 | Elevator safety early warning system |
| CN102295206A (en) * | 2010-06-22 | 2011-12-28 | 深圳市新开元信息技术发展有限公司 | Elevator safety remote real-time monitoring system based on Internet of things |
| CN201777739U (en) * | 2010-08-06 | 2011-03-30 | 北京诚信能环科技有限公司 | ES elevator monitoring management information system |
Non-Patent Citations (1)
| Title |
|---|
| DEDS故障诊断方法在电梯中的应用;宗群等;《天津大学学报》;20060525;第39卷(第05期);553-558 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3367558A1 (en) * | 2017-02-24 | 2018-08-29 | Siemens Aktiengesellschaft | Method for operating a linear motor based transport system and control unit |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102765643A (en) | 2012-11-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102765643B (en) | Elevator fault diagnosis and early-warning method based on data drive | |
| CN113723632B (en) | Industrial equipment fault diagnosis method based on knowledge graph | |
| CN108614548B (en) | Intelligent fault diagnosis method based on multi-mode fusion deep learning | |
| CN112418451A (en) | Transformer fault diagnosis positioning system based on digital twinning | |
| JP2023042527A (en) | Data drive active power distribution network abnormal state sensing method and system | |
| Lv et al. | A predictive maintenance system for multi-granularity faults based on AdaBelief-BP neural network and fuzzy decision making | |
| CN109754110A (en) | A kind of method for early warning and system of traction converter failure | |
| CN106021545A (en) | Method for remote diagnoses of cars and retrieval of spare parts | |
| CN109947898B (en) | Equipment fault testing method based on intellectualization | |
| CN113339204B (en) | Wind driven generator fault identification method based on hybrid neural network | |
| CN111459144A (en) | Airplane flight control system fault prediction method based on deep cycle neural network | |
| CN114856941A (en) | Offshore wind power plant and unit fault diagnosis operation and maintenance system and diagnosis operation and maintenance method thereof | |
| CN115791174B (en) | Rolling bearing abnormality diagnosis method, system, electronic equipment and storage medium | |
| CN115524002B (en) | Operation state early warning method, system and storage medium of power plant rotating equipment | |
| CN117713221A (en) | Micro-inversion photovoltaic grid-connected optimization system | |
| KR102379957B1 (en) | Method for providing machinery malfunction diagnostic service for pneumatic-driven operating door on train | |
| CN115938124A (en) | Urban rail transit emergency influence prediction method, system and product | |
| CN117521498A (en) | Charging pile guide type fault diagnosis prediction method and system | |
| CN117852541A (en) | Entity relation triplet extraction method, system and computer equipment | |
| CN112988843A (en) | SMT chip mounter fault management and diagnosis system based on SQL Server database | |
| CN116523722A (en) | Environment monitoring analysis system with machine learning capability | |
| CN115623004A (en) | Block chain-based rail transit equipment management system and method | |
| CN114295981A (en) | Motor fault diagnosis method based on RN network current multi-feature form recognition | |
| Mbuli et al. | Root causes analysis and fault prediction in intelligent transportation systems: coupling unsupervised and supervised learning techniques | |
| CN114881154A (en) | Natural gas station fault detection method and system based on PCA and deep forest |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20150617 Termination date: 20200531 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |