CN108536945A - A kind of fault diagnosis method and system for large-scale phase modifier - Google Patents
A kind of fault diagnosis method and system for large-scale phase modifier Download PDFInfo
- Publication number
- CN108536945A CN108536945A CN201810282563.2A CN201810282563A CN108536945A CN 108536945 A CN108536945 A CN 108536945A CN 201810282563 A CN201810282563 A CN 201810282563A CN 108536945 A CN108536945 A CN 108536945A
- Authority
- CN
- China
- Prior art keywords
- phase modifier
- scale phase
- vector
- scale
- diagnosed
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Geometry (AREA)
- Probability & Statistics with Applications (AREA)
- Computer Hardware Design (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The invention discloses a kind of fault diagnosis method and system for large-scale phase modifier, the implementation steps of diagnostic method include:It obtains temperature, vibration, noise and the electric parameter information for being diagnosed large-scale phase modifier and constitutes input vector;Input vector is inputted into trained machine learning classification model, obtains the malfunction for being diagnosed large-scale phase modifier, the machine learning classification model be trained to after comprising the mapping relations between input vector and malfunction;System includes the corresponding system of method.The present invention is directed to large-scale phase modifier bulky dimensions, problem complicated, parts are numerous, can integrated temperature, vibration, noise, electric parameter etc. to the facility information diagnostic analysis of phase modifier, have the advantages that deagnostic structure is accurate comprehensive, large-scale phase modifier can be directed to and find failure in time to take corresponding measure.
Description
Technical field
The present invention relates to Diagnosing Faults of Electrical technologies, and in particular to a kind of method for diagnosing faults for large-scale phase modifier and
System.
Background technology
Phase modifier is the synchronous motor of no-load running, by changing the size of its exciting current, can control it be from
Absorbing reactive power or output reactive power in system.When system voltage is relatively low, its overexcited operation becomes idle electricity
Source can provide reactive power to system, system voltage is turned up;When system voltage is higher, its underexcited operation becomes idle
Load turns down system voltage from system absorbing reactive power.Phase modifier is generally installed in load-center substation.Using phase modifier
The advantages of carrying out reactive-load compensation is that adjustment load or burden without work is very convenient, and the size by changing exciting current can smoothly, even
Its idle output is adjusted continuously;Can bidirectional modulation, absorbing reactive power but also reactive power can be sent out;The phase modulation of full-load run
Machine has certain capability of overload, is drastically reduced when because of the electric system voltage that breaks down, and when stability being made to be on the hazard, adjusts
Camera can be made operations staff that can during this period of time be handled accordingly, avoided electricity with the running overload a bit of time
The generation of the major accidents such as pressure collapse, for keeping the effect specific capacitance device of power system stability to get well.
Phase modulation machine equipment of new generation will carry out being greatly improved in plant maintenance, technical characteristic etc. it is perfect, to adapt to electricity
Network operation demand.There is Shanghai in the manufacturer of the phase modifier of China's large capacity, breathes out electricity and Dong electricity San great hosts manufacturer, generally
It is to be produced by the demand of user, due to being the phase modifier of first production large capacity, the manufacture level of phase modifier needs
Every inspection is carried out in the process of running.Currently, the debugging of ultra-high voltage converter station phase modifier and O&M level are accumulated also in experience
The tired stage.It is unavoidable that various failures occur in operational process.There are the noise for miniature motor, vibration, electromagnetism both at home and abroad
The research of field distribution rule, it is mainly horizontal to improve product design, and the noise to the phase modifier of large capacity, vibration, electromagnetism
The research of field distribution rule is less, less to phase modifier progress state evaluation researcher in operation, passes through state evaluation and proposes to control
Phase modifier method of operation measure person processed almost without.But large-scale phase modifier bulky dimensions, complicated, parts are numerous, because
This only can not carry out diagnostic analysis for large-scale electric rotating machine by the facility information that some sensor acquires, this
The diagnosis that sample obtains is often unilateral, it is easy to the case where judging by accident and failing to judge occurs.If its vibration can will be monitored
The metrical information of multiple sensors of state considers, and the information fusion diagnosis of multisensor is carried out to equipment, then could
Obtain more comprehensive and accurate diagnosis.There is an urgent need for the fault diagnosis systems that one is suitable for large-scale phase modifier.
Invention content
The technical problem to be solved in the present invention:For the above problem of the prior art, provide a kind of for large-scale phase modifier
Fault diagnosis method and system, the present invention is directed to large-scale phase modifier bulky dimensions, problem complicated, parts are numerous,
Can integrated temperature, vibration, noise, electric parameter etc. to the facility information diagnostic analysis of phase modifier, have deagnostic structure accurate
Really comprehensive advantage can be directed to large-scale phase modifier and find failure in time to take corresponding measure.
In order to solve the above-mentioned technical problem, the technical solution adopted by the present invention is:
A kind of method for diagnosing faults for large-scale phase modifier, implementation steps include:
1)It obtains temperature, vibration, noise and the electric parameter information for being diagnosed large-scale phase modifier and constitutes input vector;
2)Input vector is inputted into trained machine learning classification model, obtains the malfunction for being diagnosed large-scale phase modifier,
The machine learning classification model be trained to after comprising mapping relations between input vector and malfunction.
Preferably, step 1)In temperature include the multiple measuring points being installed on around the Stator and Rotor Windings of large-scale phase modifier
Temperature, vibration include being installed on the vibration amplitude, frequency that multiple measuring points detect around the shaft and engine base of large-scale phase modifier
And orbit of shaft center, noise include the acoustic power level that noise is sent out when large-scale phase modifier operation, electric parameter includes large-scale phase modifier
Electric current, voltage and power.
Preferably, the machine learning classification model is RBF neural network model.
Preferably, the RBF neural network model includes input layer, hidden layer and output layer, wherein input layer include and
Collectively form input vectorxN input datax 1 ~x nOne-to-one input node, wherein n are the dimension of input vector;
Hidden layer includespA hidden node, theiThe input of a hidden node is | |x-h i | |,h i It isiData center's vector of a hidden node,
Activation primitive is radial basis function, and output layer includesmA output node, each output node correspond to the one of large-scale phase modifier
Kind malfunction, the routine weight value between each hidden node and output nodewThe training for being determined as RBF neural network model
Target.
Preferably, the radial basis function is the radial basis function of Gaussian.
Preferably, the historical device information library of large-scale phase modifier is diagnosed according to data center's vector of the hidden node
It is determined using K- means clustering algorithms, and use K- means clustering algorithms determine the step packet of data center's vector of hidden node
It includes:
S1)Arbitrarily select K object as K- means clustering algorithms from the historical device information library for being diagnosed large-scale phase modifier
Data center's vector, the historical device information library includes the temperature for being diagnosed large-scale phase modifier history run, vibrates, makes an uproar
Sound, electric parameter information data, each data are an object;
S2)Calculate be diagnosed each object and these data centers vector in the historical device information library of large-scale phase modifier away from
From, and division classification is carried out to corresponding object according to minimum range and is clustered;
S3)The mean value each clustered is calculated, as new data center's vector;
S4)When judging that data center's vector no longer changes or the variation difference of data center's vector is less than predetermined threshold value, then will
Obtained new data center's vector is contacted and is exited respectively as data center's vector of hidden node;Otherwise, it redirects and executes step
Rapid S2).
The present invention also provides a kind of fault diagnosis system for large-scale phase modifier, including computer equipment, the calculating
Machine equipment is programmed to perform the step of method for diagnosing faults of the present invention for large-scale phase modifier.
The present invention also provides a kind of method for diagnosing faults for large-scale phase modifier, including:
Program unit is inputted, for obtaining the temperature for being diagnosed large-scale phase modifier, vibration, noise and electric parameter information and constituting
Input vector;
Machine learning classification program unit obtains being examined for input vector to be inputted trained machine learning classification model
The malfunction of disconnected large size phase modifier, the machine learning classification model be trained to after comprising between input vector and malfunction
Mapping relations.
Present invention tool has the advantage that:The present invention by obtain be diagnosed the temperature of large-scale phase modifier, vibration, noise and
Electric parameter information simultaneously constitutes input vector, and input vector is inputted trained machine learning classification model, obtains being diagnosed big
The malfunction of type phase modifier, machine learning classification model close after being trained to comprising the mapping between input vector and malfunction
System, for large-scale phase modifier bulky dimensions, problem complicated, parts are numerous, the present invention can integrated temperature, vibration,
Noise, electric parameter etc. have the advantages that accurate comprehensive, the Neng Gouzhen of deagnostic structure to the facility information diagnostic analysis of phase modifier
Failure is found in time to large-scale phase modifier to take corresponding measure.
Description of the drawings
Fig. 1 is the basic procedure schematic diagram of present invention method.
Fig. 2 is the structural schematic diagram of RBF neural network model of the present invention.
Fig. 3 is the training structure schematic diagram of RBF neural network model of the present invention.
Fig. 4 is the basic structure schematic diagram of system of the embodiment of the present invention.
Specific implementation mode
As shown in Figure 1, the implementation steps that the present embodiment is used for the method for diagnosing faults of large-scale phase modifier include:
1)It obtains temperature, vibration, noise and the electric parameter information for being diagnosed large-scale phase modifier and constitutes input vector;
2)Input vector is inputted into trained machine learning classification model, obtains the malfunction for being diagnosed large-scale phase modifier,
Machine learning classification model be trained to after comprising mapping relations between input vector and malfunction.
In the present embodiment, step 1)In temperature include the multiple surveys being installed on around the Stator and Rotor Windings of large-scale phase modifier
The temperature of point, vibration include be installed on multiple measuring points detect around the shaft and engine base of large-scale phase modifier vibration amplitude,
Frequency and orbit of shaft center, noise include the acoustic power level that noise is sent out when large-scale phase modifier operation, and electric parameter includes large-scale adjusts
Electric current, voltage and the power of camera.
In the present embodiment, machine learning classification model is RBF neural network model(Radial basis function neural network model).
As shown in Fig. 2, the RBF neural network model in the present embodiment includes input layer, hidden layer and output layer, wherein input layer includes
With collectively form input vectorxN input datax 1 ~x nOne-to-one input node, wherein n are the dimension of input vector
Degree;Hidden layer includespA hidden node, theiThe input of a hidden node is | |x-h i | |,h i It isiThe data center of a hidden node to
Amount, activation primitive is radial basis function, and output layer includesmA output node, each output node correspond to large-scale phase modifier
A kind of malfunction, the routine weight value between each hidden node and output nodewThe instruction for being determined as RBF neural network model
Practice target.Wherein, | |x-h i | | it is expressed as input vectorxWith data center's vector of i-th of hidden nodeh i | 2- norms(I.e. away from
From).WhereinmThe output valve of a output nodey 1 ~y mConstitute the corresponding output vector of malfunction, each output node it is defeated
Go out valuey iNumber of the corresponding value between [0,1], occurrence is depending on the state of large-scale phase modifier;If large-scale phase modifier is normally transported
Row, the output valve of each output nodey iIt is 0.
In the present embodiment, radial basis function is the radial basis function of Gaussian, is denoted as Ф referring to Fig. 3, thepA hidden node
Output can be expressed as Фp(||x-h p| |), wherein ФpIt ispThe radial basis function of the Gaussian of a hidden node, | |x-h p|
| it is thepThe input of a hidden node,h pIt ispThe data center of a hidden node is vectorial, in the present embodiment, in the data of hidden node
The historical device information library that large-scale phase modifier is diagnosed according to Heart vector is determined using K- means clustering algorithms, and uses K- equal
Value clustering algorithm determines that the step of data center's vector of hidden node includes:
S1)Arbitrarily select K object as K- means clustering algorithms from the historical device information library for being diagnosed large-scale phase modifier
Data center's vector, historical device information library includes the temperature for being diagnosed large-scale phase modifier history run, vibration, noise, electricity
Parameter information data, each data are an object;
S2)Calculate be diagnosed each object and these data centers vector in the historical device information library of large-scale phase modifier away from
From, and division classification is carried out to corresponding object according to minimum range and is clustered;
S3)The mean value each clustered is calculated, as new data center's vector;
S4)When judging that data center's vector no longer changes or the variation difference of data center's vector is less than predetermined threshold value, then will
Obtained new data center's vector is contacted and is exited respectively as data center's vector of hidden node;Otherwise, it redirects and executes step
Rapid S2).
As shown in figure 3, when being trained to RBF neural network model, first has to basis and be diagnosed going through for large-scale phase modifier
History facility information library generates training set, and determines the structure and parameter of RBF neural network model(Input layer input node quantityn, hidden layer hidden node quantityp, output layer output node quantitymAnd hidden node relevant parameter), then utilize training set pair
RBF neural network model is trained, and obtains structure and weights(Routine weight value between each hidden node and output nodew)
Fixed RBF neural network model completes the training of RBF neural network model.After training, you can using being diagnosed
The real-time device information of large-scale phase modifier diagnoses the malfunction for being diagnosed large-scale phase modifier.
The present embodiment also provides a kind of fault diagnosis system for large-scale phase modifier, including computer equipment, the calculating
Machine equipment is programmed to perform the step of method for diagnosing faults of the present embodiment for large-scale phase modifier.Referring to Fig. 4, the system by
Temperature monitoring module, vibration monitoring module, noise module, electric parameter monitoring modular, computer equipment and mobile device
Composition.Temperature monitoring module is installed on around the Stator and Rotor Windings of phase modifier, can monitor the temperature of phase modifier in real time;Vibration monitoring
Module is installed on the positions such as the shaft of phase modifier, engine base;Noise module is arranged in outside phase modifier;Electric parameter monitoring modular
It is installed on phase modulation machine circuit;The signal transmission of modules monitoring is to server.Computer equipment is mounted near phase modifier,
Computer equipment handles the signal that modules are transmitted to, by the phase modifier historical Device for being stored in computer equipment
Information(Information including normal operation and when failure operation), real-time fault diagnosis is carried out to large-scale phase modifier.Mobile device can
To access to computer equipment by network, the facility information of phase modifier is understood in real time.
The present embodiment also provides a kind of method for diagnosing faults for large-scale phase modifier, including:
Program unit is inputted, for obtaining the temperature for being diagnosed large-scale phase modifier, vibration, noise and electric parameter information and constituting
Input vector;
Machine learning classification program unit obtains being examined for input vector to be inputted trained machine learning classification model
The malfunction of disconnected large size phase modifier, machine learning classification model be trained to after include reflecting between input vector and malfunction
Penetrate relationship.
The above is only a preferred embodiment of the present invention, protection scope of the present invention is not limited merely to above-mentioned implementation
Example, all technical solutions belonged under thinking of the present invention all belong to the scope of protection of the present invention.It should be pointed out that for the art
Those of ordinary skill for, several improvements and modifications without departing from the principles of the present invention, these improvements and modifications
It should be regarded as protection scope of the present invention.
Claims (8)
1. a kind of method for diagnosing faults for large-scale phase modifier, it is characterised in that implementation steps include:
1)It obtains temperature, vibration, noise and the electric parameter information for being diagnosed large-scale phase modifier and constitutes input vector;
2)Input vector is inputted into trained machine learning classification model, obtains the malfunction for being diagnosed large-scale phase modifier,
The machine learning classification model be trained to after comprising mapping relations between input vector and malfunction.
2. the method for diagnosing faults according to claim 1 for large-scale phase modifier, which is characterized in that step 1)In temperature
Degree includes the temperature for the multiple measuring points being installed on around the Stator and Rotor Windings of large-scale phase modifier, and vibration includes being installed on large-scale phase modulation
Vibration amplitude, frequency and the orbit of shaft center that multiple measuring points detect around the shaft and engine base of machine, noise include large-scale adjust
Camera sends out the acoustic power level of noise when running, electric parameter includes the electric current, voltage and power of large-scale phase modifier.
3. the method for diagnosing faults according to claim 1 for large-scale phase modifier, which is characterized in that the machine learning
Disaggregated model is RBF neural network model.
4. the method for diagnosing faults according to claim 3 for large-scale phase modifier, which is characterized in that the RBF nerves
Network model includes input layer, hidden layer and output layer, and wherein input layer includes and collectively forms input vectorxN input
Datax 1 ~x n One-to-one input node, wherein n are the dimension of input vector;Hidden layer includespA hidden node, theiIt is a hidden
The input of node is | |x-h i | |,h i It isiData center's vector of a hidden node, activation primitive is radial basis function, output
Layer includemA output node, each output node correspond to a kind of malfunction of large-scale phase modifier, each hidden node and defeated
Routine weight value between egresswThe training objective for being determined as RBF neural network model.
5. the method for diagnosing faults according to claim 4 for large-scale phase modifier, which is characterized in that the radial direction base letter
Number is the radial basis function of Gaussian.
6. the method for diagnosing faults according to claim 4 for large-scale phase modifier, which is characterized in that the hidden node
The historical device information library that large-scale phase modifier is diagnosed according to data center's vector is determined using K- means clustering algorithms, and is adopted
Determine that the step of data center's vector of hidden node includes with K- means clustering algorithms:
S1)Arbitrarily select K object as K- means clustering algorithms from the historical device information library for being diagnosed large-scale phase modifier
Data center's vector, the historical device information library includes the temperature for being diagnosed large-scale phase modifier history run, vibrates, makes an uproar
Sound, electric parameter information data, each data are an object;
S2)Calculate be diagnosed each object and these data centers vector in the historical device information library of large-scale phase modifier away from
From, and division classification is carried out to corresponding object according to minimum range and is clustered;
S3)The mean value each clustered is calculated, as new data center's vector;
S4)When judging that data center's vector no longer changes or the variation difference of data center's vector is less than predetermined threshold value, then will
Obtained new data center's vector is contacted and is exited respectively as data center's vector of hidden node;Otherwise, it redirects and executes step
Rapid S2).
7. a kind of fault diagnosis system for large-scale phase modifier, including computer equipment, which is characterized in that the computer is set
Standby the step of being programmed to perform the method for diagnosing faults that large-scale phase modifier is used for described in any one of claim 1~6.
8. a kind of method for diagnosing faults for large-scale phase modifier, it is characterised in that including:
Program unit is inputted, for obtaining the temperature for being diagnosed large-scale phase modifier, vibration, noise and electric parameter information and constituting
Input vector;
Machine learning classification program unit obtains being examined for input vector to be inputted trained machine learning classification model
The malfunction of disconnected large size phase modifier, the machine learning classification model be trained to after comprising between input vector and malfunction
Mapping relations.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810282563.2A CN108536945A (en) | 2018-04-02 | 2018-04-02 | A kind of fault diagnosis method and system for large-scale phase modifier |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810282563.2A CN108536945A (en) | 2018-04-02 | 2018-04-02 | A kind of fault diagnosis method and system for large-scale phase modifier |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108536945A true CN108536945A (en) | 2018-09-14 |
Family
ID=63482248
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810282563.2A Pending CN108536945A (en) | 2018-04-02 | 2018-04-02 | A kind of fault diagnosis method and system for large-scale phase modifier |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108536945A (en) |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109387724A (en) * | 2018-09-30 | 2019-02-26 | 南京理工大学 | Based on the lateral modified synchronous capacitor method for diagnosing faults of vertical analysis |
CN109410718A (en) * | 2018-11-27 | 2019-03-01 | 国网湖南省电力有限公司 | Phase modifier simulation training system and its method |
CN110398375A (en) * | 2019-07-16 | 2019-11-01 | 广州亚美信息科技有限公司 | Monitoring method, device, equipment and the medium of cooling system of vehicle working condition |
CN110617981A (en) * | 2019-09-16 | 2019-12-27 | 江苏方天电力技术有限公司 | Fault diagnosis method for phase modulator |
CN110749810A (en) * | 2019-12-05 | 2020-02-04 | 国网山东省电力公司电力科学研究院 | Insulation fault prediction method and system for phase modulator |
CN110836696A (en) * | 2019-12-04 | 2020-02-25 | 江苏方天电力技术有限公司 | Remote fault prediction method and system suitable for phase modulator system |
CN110941725A (en) * | 2019-11-29 | 2020-03-31 | 国网湖南省电力有限公司 | Knowledge graph-based hydroelectric generating set fault diagnosis method and system |
CN110988547A (en) * | 2019-12-17 | 2020-04-10 | 国网江苏省电力有限公司检修分公司 | Power grid phase modulator state monitoring system |
CN111007429A (en) * | 2019-11-26 | 2020-04-14 | 国网江苏省电力有限公司检修分公司 | ANFIS-based synchronous phase modulator short-circuit fault identification method and system |
CN111351527A (en) * | 2020-04-01 | 2020-06-30 | 国网湖南省电力有限公司 | Intelligent cable explosion-proof box with pressure and gas monitoring function, system and application method thereof |
CN113128832A (en) * | 2021-03-16 | 2021-07-16 | 国网湖南省电力有限公司 | Operation state online diagnosis method and system for auxiliary system of large phase modulator |
CN113159717A (en) * | 2021-04-19 | 2021-07-23 | 国网江苏省电力有限公司检修分公司 | Phase modulator state analysis early warning method and system based on weight evaluation mechanism |
CN114237197A (en) * | 2021-11-22 | 2022-03-25 | 上海电气电站设备有限公司 | Phase modulator multi-factor coupling online diagnosis method |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101275900A (en) * | 2008-05-08 | 2008-10-01 | 江汉大学 | Method for recognizing road surface types based on vehicle wheel vibration |
CN103745229A (en) * | 2013-12-31 | 2014-04-23 | 北京泰乐德信息技术有限公司 | Method and system of fault diagnosis of rail transit based on SVM (Support Vector Machine) |
US20160335548A1 (en) * | 2015-05-12 | 2016-11-17 | Rolls-Royce Plc | Methods and apparatus for predicting fault occurrence in mechanical systems and electrical systems |
CN107248408A (en) * | 2017-06-30 | 2017-10-13 | 邢优胜 | A kind of active noise controlling method based on fuzzy neural network, system and helicopter pilot's helmet |
CN107755451A (en) * | 2017-09-30 | 2018-03-06 | 重庆鸽牌电线电缆有限公司 | The preparation method of Large Copacity phase modifier argentiferous copper bar |
-
2018
- 2018-04-02 CN CN201810282563.2A patent/CN108536945A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101275900A (en) * | 2008-05-08 | 2008-10-01 | 江汉大学 | Method for recognizing road surface types based on vehicle wheel vibration |
CN103745229A (en) * | 2013-12-31 | 2014-04-23 | 北京泰乐德信息技术有限公司 | Method and system of fault diagnosis of rail transit based on SVM (Support Vector Machine) |
US20160335548A1 (en) * | 2015-05-12 | 2016-11-17 | Rolls-Royce Plc | Methods and apparatus for predicting fault occurrence in mechanical systems and electrical systems |
CN107248408A (en) * | 2017-06-30 | 2017-10-13 | 邢优胜 | A kind of active noise controlling method based on fuzzy neural network, system and helicopter pilot's helmet |
CN107755451A (en) * | 2017-09-30 | 2018-03-06 | 重庆鸽牌电线电缆有限公司 | The preparation method of Large Copacity phase modifier argentiferous copper bar |
Non-Patent Citations (1)
Title |
---|
刘亚军: "基于小波分析和神经网络的电机故障诊断研究", 《中国优秀硕士学位论文全文数据库》 * |
Cited By (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109387724B (en) * | 2018-09-30 | 2020-10-27 | 南京理工大学 | Fault diagnosis method for synchronous phase modulator based on longitudinal analysis and transverse correction |
CN109387724A (en) * | 2018-09-30 | 2019-02-26 | 南京理工大学 | Based on the lateral modified synchronous capacitor method for diagnosing faults of vertical analysis |
CN109410718A (en) * | 2018-11-27 | 2019-03-01 | 国网湖南省电力有限公司 | Phase modifier simulation training system and its method |
CN110398375A (en) * | 2019-07-16 | 2019-11-01 | 广州亚美信息科技有限公司 | Monitoring method, device, equipment and the medium of cooling system of vehicle working condition |
CN110617981A (en) * | 2019-09-16 | 2019-12-27 | 江苏方天电力技术有限公司 | Fault diagnosis method for phase modulator |
CN110617981B (en) * | 2019-09-16 | 2021-06-15 | 江苏方天电力技术有限公司 | Fault diagnosis method for phase modulator |
CN111007429A (en) * | 2019-11-26 | 2020-04-14 | 国网江苏省电力有限公司检修分公司 | ANFIS-based synchronous phase modulator short-circuit fault identification method and system |
CN110941725A (en) * | 2019-11-29 | 2020-03-31 | 国网湖南省电力有限公司 | Knowledge graph-based hydroelectric generating set fault diagnosis method and system |
CN110836696A (en) * | 2019-12-04 | 2020-02-25 | 江苏方天电力技术有限公司 | Remote fault prediction method and system suitable for phase modulator system |
CN110749810A (en) * | 2019-12-05 | 2020-02-04 | 国网山东省电力公司电力科学研究院 | Insulation fault prediction method and system for phase modulator |
CN110988547A (en) * | 2019-12-17 | 2020-04-10 | 国网江苏省电力有限公司检修分公司 | Power grid phase modulator state monitoring system |
CN111351527A (en) * | 2020-04-01 | 2020-06-30 | 国网湖南省电力有限公司 | Intelligent cable explosion-proof box with pressure and gas monitoring function, system and application method thereof |
CN113128832A (en) * | 2021-03-16 | 2021-07-16 | 国网湖南省电力有限公司 | Operation state online diagnosis method and system for auxiliary system of large phase modulator |
CN113159717A (en) * | 2021-04-19 | 2021-07-23 | 国网江苏省电力有限公司检修分公司 | Phase modulator state analysis early warning method and system based on weight evaluation mechanism |
CN113159717B (en) * | 2021-04-19 | 2024-05-28 | 国网江苏省电力有限公司检修分公司 | Camera state analysis and early warning method and system based on weight evaluation mechanism |
CN114237197A (en) * | 2021-11-22 | 2022-03-25 | 上海电气电站设备有限公司 | Phase modulator multi-factor coupling online diagnosis method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108536945A (en) | A kind of fault diagnosis method and system for large-scale phase modifier | |
CN108803552B (en) | Monitoring system and monitoring method for equipment fault | |
CN208076675U (en) | A kind of trouble-shooter for large-scale phase modifier | |
CN104503399B (en) | The regimental Wind turbines status monitoring of one kind collection and fault diagnosis platform | |
CN103138280B (en) | Method of controlling the power input to a HVDC transmission link | |
CN106525415B (en) | A kind of wind turbine transmission chain health status evaluation system and method | |
CN109765484A (en) | Motor on-line monitoring and fault diagonosing method based on " correct tree " model | |
CN112700032A (en) | Fault prediction system and method for low-voltage direct-current power distribution and utilization system | |
CN103852744A (en) | Distributed online monitoring system and method for electric energy metering device | |
CN104052051B (en) | Direct current transmission and delivery system and the method for operating the system | |
CN102033200A (en) | On-line monitoring and diagnosis method of AC (alternating current) motor based on statistical model | |
CN105515184A (en) | Wireless sensor network-based cooperative monitoring system of multi-sensor and multi-parameter distribution network | |
CN104380554A (en) | Fault detection in energy supply networks | |
CN112697267A (en) | Abnormal vibration detection device for industrial equipment | |
CN102930408B (en) | A kind of 750kV electric grid secondary equipment state appraisal procedure based on information fusion | |
CN104392591B (en) | Transmission pole malfunction monitoring expert system | |
CN115327990A (en) | AI-based electrical equipment state monitoring and early warning model and method thereof | |
CN110749810A (en) | Insulation fault prediction method and system for phase modulator | |
CN207408100U (en) | Bear vibration monitoring device based on wireless sensor network | |
CN105652120A (en) | Power transformer fault detection method and detection system | |
CN202091172U (en) | Device for monitoring state and analyzing reliability of gas compressor | |
CN113064075B (en) | Motor service life prediction method based on edge calculation and deep learning | |
CN109209781B (en) | The Fault Locating Method and device of wind power generating set | |
KR101896442B1 (en) | System, Server and Method for monitoring wind plant with ICT fusion | |
CN104700148A (en) | Motor fault diagnosis method based on behavior |
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 |
Application publication date: 20180914 |
|
RJ01 | Rejection of invention patent application after publication |