CN110646706A - Method, device and system for detecting differential protection fault of super capacitor charging device of energy storage tramcar - Google Patents
Method, device and system for detecting differential protection fault of super capacitor charging device of energy storage tramcar Download PDFInfo
- Publication number
- CN110646706A CN110646706A CN201910864474.3A CN201910864474A CN110646706A CN 110646706 A CN110646706 A CN 110646706A CN 201910864474 A CN201910864474 A CN 201910864474A CN 110646706 A CN110646706 A CN 110646706A
- Authority
- CN
- China
- Prior art keywords
- data
- neural network
- output
- current
- input
- 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
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/08—Locating faults in cables, transmission lines, or networks
- G01R31/088—Aspects of digital computing
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R19/00—Arrangements for measuring currents or voltages or for indicating presence or sign thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
Abstract
The invention discloses a method, a device and a system for detecting differential protection faults of a super capacitor charging device of an energy storage tramcar based on a BP neural network, wherein the method comprises the following steps: acquiring real-time voltage and current data of an input side of the charging device, real-time voltage and current data of an output side, voltage and current fault data of the input side and voltage and current fault data of the output side; calculating to obtain input-output current differential data based on the acquired real-time data; the collected real-time data and the current differential data are used as input layer neuron data of a pre-constructed BP neural network model, and output data of the BP neural network model are obtained; and judging the position of the fault point according to the output data of the BP neural network model. The invention has high detection accuracy, can shorten the maintenance time and improve the troubleshooting working efficiency of fault points.
Description
Technical Field
The invention relates to the technical field of urban rail transit charging, in particular to a method, a device and a system for detecting differential protection faults of a super capacitor charging device of an energy storage tramcar based on a BP neural network.
Background
With the great demand of urban construction on traffic, urban rail transit is rapidly developed, and particularly, an energy storage tramcar which is a main form of a modern tramcar is rapidly developed and has the advantages of attractive appearance, large transportation capacity, energy conservation, environmental protection, stable and quiet running and the like.
The energy storage tramcar is a novel rail vehicle, and mainly adopts a super capacitor as a power unit of the vehicle. The vehicle can convert more than 85% of braking energy into electric energy to be stored for reuse, the vehicle does not need an overhead contact network for power supply during running, and the electric energy is supplemented by the time of parking and getting on/off the bus at the station. The rail transit has no visual pollution, no power transmission loss and no electric corrosion to facilities such as underground pipelines along the line, and is a green, intelligent and environment-friendly rail transit.
Like the charging of a traditional electric automobile, in the charging process of the energy storage tramcar, faults in voltage and current of the charging device can occur due to various reasons, and at the moment, the charging device can act according to a preset protection value. However, the charging device of the energy storage tramcar is not an independent system in the charging process, the upper stage relates to a rectifying system, the lower stage relates to a vehicle-mounted capacitor system, and once the charging device fails, whether the charging device fails or not can not be judged. This causes great difficulty in on-site maintenance work and increases much workload.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: the method, the device and the system for detecting the differential protection fault of the super capacitor charging device of the energy storage tramcar by utilizing the BP neural network can distinguish the fault of the charging device from the faults of an upper system and a lower system, and the detection and judgment result is reliable.
The technical scheme adopted by the invention is as follows:
in one aspect, the invention provides a method for detecting a differential protection fault of a super capacitor charging device of an energy storage tramcar, which comprises the following steps:
acquiring real-time voltage and current data of an input side of the charging device, real-time voltage and current data of an output side, voltage and current fault data of the input side and voltage and current fault data of the output side;
calculating to obtain input-output current differential data based on the acquired real-time data;
the collected real-time data and the current differential data are used as input layer neuron data of a pre-constructed BP neural network model, and output data of the BP neural network model are obtained;
and judging the position of the fault point according to the output data of the BP neural network model.
The input side voltage and current fault data and the output side voltage and current fault data can be obtained through the control platform of the charging device in each station. The detection method can be operated in a control platform of the charging device, and the detection device can also be independently arranged.
Further, the method of the invention also comprises the following steps: and transmitting the input data and the corresponding output data of the BP neural network model corresponding to each detection period to a remote comprehensive control platform through a network, so that the remote comprehensive control platform trains the BP neural network model based on the received data, and then returning the newly trained BP neural network model at a set frequency. The return target is the detection device which operates the detection method, so that when the detection device detects a fault point, the current latest BP neural network is always utilized to judge the fault point, and the judgment accuracy of the fault position is higher and higher.
Optionally, the real-time data is acquired in a preset sampling period, and the determination of the current differential zone bit, the calculation of the BP neural network and the judgment of the fault point are performed in a preset detection period; the detection period is greater than the sampling period. Optionally, the detection period is 10 times the sampling period.
Furthermore, the invention also comprises the step of carrying out weighted average calculation on a plurality of sampling point data corresponding to the same data type in a single detection period, and taking the weighted average value of the real-time collected data as corresponding input layer neuron data of a preset neural network model. The accuracy of the detection result can be further ensured.
Optionally, the input-output current differential data is a current differential flag bit; based on the collected real-time data, firstly calculating an input-output differential current value, and then determining a current differential zone bit according to a preset determination rule. Optionally, when the differential current value is within the threshold range of [0.5,1] a, the current differential flag is 0, otherwise it is 1.
Optionally, the pre-constructed BP neural network model includes an input layer, a hidden layer, and an output layer; the input layer comprises 9 neurons, wherein the neurons respectively correspond to real-time voltage and current on the input side, real-time voltage and current on the output side, input-output differential current, input-side voltage and current fault data and output-side voltage and current fault data; the hidden layer comprises 3 neurons, and the output layer comprises 1 neuron; the output data form of the output layer neuron is a [1 x 3] matrix, different data arrangement forms in the matrix represent different fault position detection results, and the fault position detection results at least comprise input side faults, output side faults and device external faults.
Optionally, in the output data matrix of the output layer, each matrix element is a boolean value. The [1 × 3] matrix only has 3 different arrangement modes, namely [1,0,0], [0,1,0] and [0,0,1], and the three matrices respectively correspond to one fault position, the corresponding relation between the matrix element arrangement mode and the fault position is determined when the BP neural network model is constructed, and then the corresponding fault position can be judged according to the output of the output layer.
Optionally, the hidden layer and the output layer of the BP neural network model respectively use an S-type activation function, where the activation function of the hidden layer uses tansig, and the expression is:
the output layer activation function selects logsig, and the expression is as follows:
the training error target of the BP neural network model is 1 e-5;
the input signals of the hidden layer are:
in the above formula, xiFor input data of the ith neuron of the input layer,
is the input signal received by the jth neuron of the hidden layer from the input layer, wijThe weights for the input layer ith neuron to the hidden layer jth neuron.
Through the above construction, it is possible to construct,
by activating a function f1(x) So as to obtain the output signal of the jth neuron of the hidden layer
Comprises the following steps:
the output signal u of the output layer neurons is:
wherein, wjFor weights of the jth neuron of the hidden layer to the neurons of the output layer, f1 and f2 represent the transfer functions of the hidden layer and the output layer, respectively.
In a second aspect, the present invention provides a differential protection fault detection device for a super capacitor charging device of an energy storage tramcar, comprising:
the data acquisition module is used for acquiring real-time voltage and current data of an input side of the charging device, real-time voltage and current data of an output side, voltage and current fault data of the input side and voltage and current fault data of the output side;
the differential calculation module is used for calculating to obtain input-output current differential data based on the acquired real-time data and further determining a current differential zone bit according to a calculation result;
the neural network computing module is used for acquiring output data of the BP neural network model by taking the acquired real-time data and the current differential zone bits as input layer neuron data of the pre-constructed BP neural network model;
and the fault position judging module is used for judging the position of the fault point according to the output data of the BP neural network model.
In a third aspect, the invention further provides a differential protection fault detection system for the super capacitor charging device of the energy storage tramcar, which comprises a detection device and a comprehensive control platform, wherein the detection device is connected and communicated with the comprehensive control platform through a network; the detection device executes the differential protection fault detection method for the energy storage tramcar super capacitor charging device in the first aspect, so that the position information of a fault point is obtained by judging according to a set detection period by using a BP neural network model;
the detection device transmits the input data and the corresponding output data of the BP neural network model corresponding to each detection period to the remote comprehensive control platform;
and the remote comprehensive control platform trains the BP neural network model based on the received data, and then returns the newly trained BP neural network model to the detection device at a set frequency, so that the detection device judges fault points by respectively utilizing the currently newly trained BP neural network model in each detection period.
Optionally, the number of the detection devices is multiple, and the detection devices are respectively arranged on the tramcar platforms with the charging devices.
Advantageous effects
(1) According to the detection method, through the BP neural network and the input and output differential calculation of the charging device, the self fault of the charging device can be distinguished from the faults of the upper and lower systems, the fault position point can be quickly positioned, and the fault point troubleshooting time is shortened;
(2) due to the adoption of the BP neural network, the detection method is not limited by the working condition of the charging device, and meanwhile, the influence of the external environment and an external loop is less, so that the reliability of the detection result can be ensured;
(3) according to the invention, offline training and learning of the BP neural network are carried out through the remote comprehensive control platform, and the detection data updated along with time and the corresponding detection result are used as training samples, so that the output of the BP neural network model is closer to the actual output, and the detection device always utilizes the BP neural network model obtained by the latest training to carry out fault detection, so that the detection accuracy is higher and higher.
Drawings
Fig. 1 is a schematic diagram of a charging system of a conventional energy storage tramcar;
FIG. 2 is a schematic view of the tramcar differential protection of the present invention;
FIG. 3 is a schematic diagram of the detection system architecture of the present invention;
FIG. 4 is a schematic diagram of a BP neural network fault identification model;
fig. 5 is a schematic diagram of an embodiment of the present invention.
Wherein: 1. a grid power supply; 2. a charging device; 3. a charging rail; 4. a ground rail; 5. energy storage tramcar.
Detailed Description
The following further description is made in conjunction with the accompanying drawings and the specific embodiments.
Referring to fig. 1, an energy storage tramcar charging system in the prior art includes a power grid power supply, a charging device, a charging rail, a ground rail, and a vehicle-mounted super capacitor, where the power is taken from the power grid power supply by the charging device and is output to the charging rail and the ground rail, respectively, and the charging rail and the ground rail are disconnected from each other. At the moment, the charging device charges the vehicle-mounted super capacitor, wherein the current flows into a charging rail and flows out of a ground rail.
The invention is based on the differential protection principle, realizes the differential analysis when the fault occurs by combining the BP neural network, thereby improving the efficiency of judging the fault point by the neural network calculation on the basis of ensuring the accuracy of the differential protection.
Example 1
The embodiment is a method for detecting a differential protection fault of a super capacitor charging device of an energy storage tramcar, which comprises the following steps:
acquiring real-time voltage and current data of an input side of the charging device, real-time voltage and current data of an output side, voltage and current fault data of the input side and voltage and current fault data of the output side;
calculating to obtain input-output current differential data based on the acquired real-time data;
the collected real-time data and the current differential data are used as input layer neuron data of a pre-constructed BP neural network model, and output data of the BP neural network model are obtained;
and judging the position of the fault point according to the output data of the BP neural network model.
The input side voltage and current fault data and the output side voltage and current fault data can be obtained through the control platform of the charging device in each station. The detection method can be operated in a control platform of the charging device, and the detection device can also be independently arranged.
Further, the method further comprises: and transmitting the input data and the corresponding output data of the BP neural network model corresponding to each detection period to a remote comprehensive control platform through a network, so that the remote comprehensive control platform trains the BP neural network model based on the received data, and then returning the newly trained BP neural network model at a set frequency. The return target is the detection device which operates the detection method, so that when the detection device detects a fault point, the current latest BP neural network is always utilized to judge the fault point, and the judgment accuracy of the fault position is higher and higher. Meanwhile, the strong data processing and computing capabilities of the comprehensive control platform are utilized to train and learn the fault point recognition BP neural network model deployed on the comprehensive control platform, and the data processing load of the platform detection device for executing neural network training is also reduced.
During data acquisition, the embodiment acquires the real-time data in a preset sampling period, and determines a current differential zone bit, calculates a BP neural network and judges a fault point in a preset detection period; the detection period is greater than the sampling period. The detection period may be selected to be 10 times the sampling period.
Furthermore, the embodiment further includes performing weighted average calculation on a plurality of sampling point data corresponding to the same data type in a single detection period, and using the weighted average value of the real-time acquired data as the corresponding input layer neuron data of the preset neural network model, so as to further ensure the accuracy of the detection result. The weighted average calculation process can set a weighting coefficient Kp, and the data in the detection period is subjected to addition average and then multiplied by the weighting coefficient Kp to be used as the input of the BP neural network model.
In this embodiment, to simplify the analysis process of the BP neural network and improve the analysis efficiency, the input-output current differential data is a current differential flag bit; based on the collected real-time data, firstly calculating an input-output differential current value, and then determining a current differential zone bit according to a preset determination rule. Optionally, when the differential current value is within the threshold range of [0.5,1] a, the current differential flag is 0, otherwise it is 1.
The pre-constructed BP neural network model comprises an input layer, a hidden layer and an output layer; the input layer comprises 9 neurons, wherein the neurons respectively correspond to real-time voltage and current on the input side, real-time voltage and current on the output side, input-output differential current, input-side voltage and current fault data and output-side voltage and current fault data; the hidden layer comprises 3 neurons, and the output layer comprises 1 neuron; the output data form of the output layer neuron is a [1 x 3] matrix, different data arrangement forms in the matrix represent different fault position detection results, and the fault position detection results at least comprise input side faults, output side faults and device external faults.
In the output data matrix of the output layer, each matrix element is respectively a Boolean value. The [1 × 3] matrix only has 3 different arrangement modes, namely [1,0,0], [0,1,0] and [0,0,1], and the three matrices respectively correspond to one fault position, the corresponding relation between the matrix element arrangement mode and the fault position is determined when the BP neural network model is constructed, and then the corresponding fault position can be judged according to the output of the output layer. If can be set as: [1,0,0] is an input-side fault, [0,1,0] is an output-side fault, and [0,0,1] is an apparatus external fault.
The hidden layer and the output layer of the BP neural network model respectively adopt S-shaped activation functions, wherein the activation function of the hidden layer adopts tansig, and the expression is as follows:
the output layer activation function selects logsig, and the expression is as follows:
the training error target of the BP neural network model is 1 e-5;
the input signals of the hidden layer are:
in the above formula, xiFor input data of the ith neuron of the input layer,
is the input signal received by the jth neuron of the hidden layer from the input layer, wijThe weights for the input layer ith neuron to the hidden layer jth neuron.
Through the above construction, it is possible to construct,
by activating a function f1(x) So as to obtain the output signal of the jth neuron of the hidden layer
Comprises the following steps:
the output signal u of the output layer neurons is:
wherein, wjFor weights of the jth neuron of the hidden layer to the neurons of the output layer, f1 and f2 represent the transfer functions of the hidden layer and the output layer, respectively.
Example 2
Based on the same inventive concept as embodiment 1, this embodiment is a differential protection fault detection device for a super capacitor charging device of an energy storage tram, including:
the data acquisition module is used for acquiring real-time voltage and current data of an input side of the charging device, real-time voltage and current data of an output side, voltage and current fault data of the input side and voltage and current fault data of the output side;
the differential calculation module is used for calculating to obtain input-output current differential data based on the acquired real-time data and further determining a current differential zone bit according to a calculation result;
the neural network computing module is used for acquiring output data of the BP neural network model by taking the acquired real-time data and the current differential zone bits as input layer neuron data of the pre-constructed BP neural network model;
and the fault position judging module is used for judging the position of the fault point according to the output data of the BP neural network model.
When a fault occurs, the BP neural network analyzes the state values corresponding to different elements of the neuron matrix of the output layer by carrying out differential analysis on the voltage and the current value of the input side and the voltage and the current value of the output side, and introduces the state values into a state matrix [1 × 3], which can define: [ A, B, C ] variables represent input side fault, output side fault, and device external fault in order, and when the variable values are 0, they represent normal, and when the variable values are 1, they represent fault
Example 3
The embodiment is a differential protection fault detection system for a super capacitor charging device of an energy storage tramcar, which comprises a detection device and a comprehensive control platform, wherein the detection device is connected and communicated through a network; the detection device executes the differential protection fault detection method of the energy storage tramcar super capacitor charging device in embodiment 1 to obtain fault point position information by utilizing a BP neural network model and judging in a set detection period;
the detection device transmits the input data and the corresponding output data of the BP neural network model corresponding to each detection period to the remote comprehensive control platform;
and the remote comprehensive control platform trains the BP neural network model based on the received data, and then returns the newly trained BP neural network model to the detection device at a set frequency, so that the detection device judges fault points by respectively utilizing the currently newly trained BP neural network model in each detection period.
The number of the detection devices is multiple, and the detection devices are respectively arranged on the tramcar platforms with the charging devices.
The training aims to adjust each weight coefficient in the network by training the constructed neural network, and finally, a mapping relation is established between the input and the target output of the neural network.
The training samples of the integrated control platform comprise input side voltage and current, output side voltage and current and various fault types of the charging device under different working conditions during charging, the data are 8 neuron data required by an input layer and are obtained from a charging device control platform in a platform, fault point data are also obtained from a control platform of the energy storage tramcar charging device, and the control platform operates the detection method of the embodiment 1 of the invention. The control platform of the existing charging device can also judge the input side current, voltage fault and output side current and voltage fault type data of the charging device.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above description is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, several modifications and variations can be made without departing from the technical principle of the present invention, and these modifications and variations should also be regarded as the protection scope of the present invention.
Claims (10)
1. A differential protection fault detection method for a super capacitor charging device of an energy storage tramcar is characterized by comprising the following steps:
acquiring real-time voltage and current data of an input side of the charging device, real-time voltage and current data of an output side, voltage and current fault data of the input side and voltage and current fault data of the output side;
calculating to obtain input-output current differential data based on the acquired real-time data;
the collected real-time data and the current differential data are used as input layer neuron data of a pre-constructed BP neural network model, and output data of the BP neural network model are obtained;
and judging the position of the fault point according to the output data of the BP neural network model.
2. The method of claim 1, further comprising: and transmitting the input data and the corresponding output data of the BP neural network model corresponding to each detection period to a remote comprehensive control platform through a network, so that the remote comprehensive control platform trains the BP neural network model based on the received data, and then returning the newly trained BP neural network model at a set frequency.
3. The method as claimed in claim 1, wherein the real-time data is collected in a preset sampling period, and the determination of the current differential zone bit, the calculation of the BP neural network and the judgment of the fault point are carried out in a preset detection period; the detection period is greater than the sampling period.
4. The method of claim 3, further comprising performing a weighted average calculation on a plurality of sample point data corresponding to the same data type in a single detection period, wherein the weighted average of the real-time collected data is used as the corresponding input layer neuron data of the preset neural network model.
5. The method of claim 1, wherein the input-output current differential data is a current differential flag; based on the collected real-time data, firstly calculating an input-output differential current value, and then determining a current differential zone bit according to a preset determination rule.
6. The method of claim 1, wherein the pre-constructed BP neural network model comprises an input layer, a hidden layer, and an output layer; the input layer comprises 9 neurons, wherein the neurons respectively correspond to real-time voltage and current on the input side, real-time voltage and current on the output side, input-output differential current, input-side voltage and current fault data and output-side voltage and current fault data; the hidden layer comprises 3 neurons, and the output layer comprises 1 neuron; the output data form of the output layer neuron is a [1 x 3] matrix, different data arrangement forms in the matrix represent different fault position detection results, and the fault position detection results at least comprise input side faults, output side faults and device external faults.
7. The method of claim 6, wherein the output layer outputs the data matrix with respective Boolean values for each matrix element. The 1 x 3 matrix will only have 3 different permutations, namely [1,0,0], [0,1,0] and [0,0,1], with each of the three matrices corresponding to a fault location.
8. The method of claim 6, wherein the hidden layer and the output layer of the BP neural network model are respectively selected from S-type activation functions, and the activation function of the hidden layer is selected from tansig, and the expression is:
the output layer activation function selects logsig, and the expression is as follows:
the training error target of the BP neural network model is 1 e-5;
the input signals of the hidden layer are:
in the above formula, xiFor input data of the ith neuron of the input layer,
is the input signal received by the jth neuron of the hidden layer from the input layer, wijThe weights for the input layer ith neuron to the hidden layer jth neuron.
9. The utility model provides an energy storage tram super capacitor charging device differential protection fault detection device, characterized by includes:
the data acquisition module is used for acquiring real-time voltage and current data of an input side of the charging device, real-time voltage and current data of an output side, voltage and current fault data of the input side and voltage and current fault data of the output side;
the differential calculation module is used for calculating to obtain input-output current differential data based on the acquired real-time data and further determining a current differential zone bit according to a calculation result;
the neural network computing module is used for acquiring output data of the BP neural network model by taking the acquired real-time data and the current differential zone bits as input layer neuron data of the pre-constructed BP neural network model;
and the fault position judging module is used for judging the position of the fault point according to the output data of the BP neural network model.
10. A differential protection fault detection system for a super capacitor charging device of an energy storage tramcar is characterized by comprising a detection device and a comprehensive control platform which are connected and communicated through a network; the detection device executes the differential protection fault detection method of the energy storage tram super capacitor charging device according to any one of claims 1 to 8, so as to judge and obtain fault point position information by using a BP neural network model in a set detection period;
the detection device transmits the input data and the corresponding output data of the BP neural network model corresponding to each detection period to the remote comprehensive control platform;
and the remote comprehensive control platform trains the BP neural network model based on the received data, and then returns the newly trained BP neural network model to the detection device at a set frequency, so that the detection device judges fault points by respectively utilizing the currently newly trained BP neural network model in each detection period.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910864474.3A CN110646706B (en) | 2019-09-12 | 2019-09-12 | Method, device and system for detecting differential protection fault of super capacitor charging device of energy storage tramcar |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910864474.3A CN110646706B (en) | 2019-09-12 | 2019-09-12 | Method, device and system for detecting differential protection fault of super capacitor charging device of energy storage tramcar |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110646706A true CN110646706A (en) | 2020-01-03 |
| CN110646706B CN110646706B (en) | 2022-06-07 |
Family
ID=68991750
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910864474.3A Active CN110646706B (en) | 2019-09-12 | 2019-09-12 | Method, device and system for detecting differential protection fault of super capacitor charging device of energy storage tramcar |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110646706B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115891741A (en) * | 2022-09-30 | 2023-04-04 | 南京邮电大学 | Remote fault early warning method and device suitable for electric vehicle charging process |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH06233403A (en) * | 1993-02-02 | 1994-08-19 | Mitsubishi Electric Corp | Trouble notifying device for electric railcar |
| CN102095953A (en) * | 2010-11-26 | 2011-06-15 | 广东电网公司中山供电局 | On-line detection method for performance of accumulator charger |
| CN102879680A (en) * | 2012-09-26 | 2013-01-16 | 中南大学 | Rail transit vehicle equipment universal detection and fault diagnosis method and system |
| CN106292631A (en) * | 2016-08-25 | 2017-01-04 | 哈尔滨理工大学 | A kind of PWM rectifier fault diagnosis system based on neutral net |
| CN108490370A (en) * | 2018-03-19 | 2018-09-04 | 万帮充电设备有限公司 | A kind of method and apparatus of fault diagnosis |
| CN109239485A (en) * | 2018-08-20 | 2019-01-18 | 国电南瑞科技股份有限公司 | Energy storage tramcar super capacitor fault recognition method and system based on BP neural network |
| CN110015081A (en) * | 2017-07-18 | 2019-07-16 | 本德尔有限两合公司 | To the charging station with difference current monitoring of the power storage component charging of electric vehicle |
-
2019
- 2019-09-12 CN CN201910864474.3A patent/CN110646706B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH06233403A (en) * | 1993-02-02 | 1994-08-19 | Mitsubishi Electric Corp | Trouble notifying device for electric railcar |
| CN102095953A (en) * | 2010-11-26 | 2011-06-15 | 广东电网公司中山供电局 | On-line detection method for performance of accumulator charger |
| CN102879680A (en) * | 2012-09-26 | 2013-01-16 | 中南大学 | Rail transit vehicle equipment universal detection and fault diagnosis method and system |
| CN106292631A (en) * | 2016-08-25 | 2017-01-04 | 哈尔滨理工大学 | A kind of PWM rectifier fault diagnosis system based on neutral net |
| CN110015081A (en) * | 2017-07-18 | 2019-07-16 | 本德尔有限两合公司 | To the charging station with difference current monitoring of the power storage component charging of electric vehicle |
| CN108490370A (en) * | 2018-03-19 | 2018-09-04 | 万帮充电设备有限公司 | A kind of method and apparatus of fault diagnosis |
| CN109239485A (en) * | 2018-08-20 | 2019-01-18 | 国电南瑞科技股份有限公司 | Energy storage tramcar super capacitor fault recognition method and system based on BP neural network |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115891741A (en) * | 2022-09-30 | 2023-04-04 | 南京邮电大学 | Remote fault early warning method and device suitable for electric vehicle charging process |
| CN115891741B (en) * | 2022-09-30 | 2023-09-22 | 南京邮电大学 | Remote fault early warning method and device suitable for electric automobile charging process |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110646706B (en) | 2022-06-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110262463B (en) | Rail transit platform door fault diagnosis system based on deep learning | |
| CN102063109B (en) | Neural network-based subway train fault diagnosis device and method | |
| CN100538761C (en) | Built-in intelligent fault diagnosing device and method based on the data fusion pattern-recognition | |
| CN103258427B (en) | Urban expressway traffic real-time monitoring system and method based on information physical network | |
| WO2015158198A1 (en) | Fault recognition method and system based on neural network self-learning | |
| CN106844949B (en) | Training method of bidirectional LSTM model for realizing energy-saving control of locomotive | |
| CN109835375A (en) | High Speed Railway Trains automated driving system based on artificial intelligence technology | |
| CN108647813B (en) | High-speed train dynamic interval energy-saving optimization method based on elastic force adjustment | |
| CN109239485B (en) | Energy storage tramcar super capacitor fault identification method and system based on BP neural network | |
| CN101592673A (en) | The method of forecasting wind speed along railway | |
| CN102072789B (en) | Method for continuously processing wheel-track force of track vehicle by means of ground test | |
| CN104318485A (en) | Power transmission line fault identification method based on nerve network and fuzzy logic | |
| CN109782124A (en) | A kind of main adapted integration Fault Locating Method and system based on gradient descent algorithm | |
| CN112686453A (en) | Intelligent prediction method and system for locomotive energy consumption | |
| CN104851280A (en) | Vehicle driving control method, device, system and related equipment | |
| CN105572492A (en) | City rail train auxiliary inverter fault diagnosis device | |
| CN103955135A (en) | Method for calculating locomotive optimized operation sequence based on double-layer mode curve | |
| CN110646706B (en) | Method, device and system for detecting differential protection fault of super capacitor charging device of energy storage tramcar | |
| CN109455178A (en) | A kind of road vehicles traveling active control system and method based on binocular vision | |
| Zhang et al. | An AI based high-speed railway automatic train operation system analysis and design | |
| CN114202316A (en) | Urban rail transit train schedule optimization method based on deep reinforcement learning | |
| CN110957774B (en) | Super capacitor state online monitoring method and device and charging system | |
| CN202063165U (en) | Subway train fault diagnostic equipment based on neural network | |
| CN113641486B (en) | Intelligent turnout fault diagnosis method based on edge computing network architecture | |
| CN110816531B (en) | Control system and control method for safe distance between unmanned automobile vehicles |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |