CN112327804A - Fault diagnosis method, device and system of traction control unit and train - Google Patents
Fault diagnosis method, device and system of traction control unit and train Download PDFInfo
- Publication number
- CN112327804A CN112327804A CN202011194475.0A CN202011194475A CN112327804A CN 112327804 A CN112327804 A CN 112327804A CN 202011194475 A CN202011194475 A CN 202011194475A CN 112327804 A CN112327804 A CN 112327804A
- Authority
- CN
- China
- Prior art keywords
- circuit
- diagnosed
- fault
- data
- control unit
- 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
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
- G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
- G05B23/0259—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterized by the response to fault detection
- G05B23/0262—Confirmation of fault detection, e.g. extra checks to confirm that a failure has indeed occurred
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/20—Pc systems
- G05B2219/24—Pc safety
- G05B2219/24065—Real time diagnostics
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Test And Diagnosis Of Digital Computers (AREA)
Abstract
The invention discloses a fault diagnosis method, a device and a system of a traction control unit and a train, wherein the method comprises the following steps: collecting monitoring data of each test point when a circuit to be diagnosed in a traction control unit works; processing the monitoring data to obtain actual circuit characteristic information of the circuit to be diagnosed; inputting the actual circuit characteristic information into a pre-constructed fault diagnosis model for fault analysis, and outputting the working state of the circuit to be diagnosed; if the working state of the circuit to be diagnosed represents that the circuit is in a fault state, the protection action corresponding to the fault type is executed according to the incidence relation between the fault type and the protection action in the working state of the circuit to be diagnosed, so that the fault diagnosis accuracy and the applicability among different circuits are ensured to the maximum extent under the condition of increasing a small amount of hardware resources.
Description
Technical Field
The invention belongs to the technical field of rail vehicle control, and particularly relates to a fault diagnosis method, device and system for a traction control unit and a train.
Background
The traction control unit is a core component of the railway vehicle traction converter, and mainly realizes functions of logic control, rectification control, motor control and the like of the converter, and the internal structure of the traction control unit can be divided into three functional modules, namely a signal processing module (comprising a digital signal acquisition unit 30, an analog signal acquisition unit 30, a digital signal output unit, a pulse signal output unit and the like), a control module (comprising a logic control unit, a network side control unit, a machine side control unit and the like), and a communication module (comprising a communication unit based on modes of Ethernet, MVB or optical fiber and the like) according to the functions. The reliability of various interface circuits for inputting and outputting signals in the signal processing module directly influences the correct execution of various control functions of the traction control unit. At present, there are two main fault diagnosis schemes for interface circuits in the traction control unit:
1. fault diagnosis based on hardware redundancy: two or more hardware circuits are used for parallel processing, the same excitation signal is given, and the output results of the hardware circuits are compared to detect whether the circuit has faults or not. The scheme has a simple principle, can remove the fault while finding the fault, and has good stability and real-time performance. However, because a plurality of hardware circuits are required to be parallel, the complexity of the system is increased, the cost is higher, and the occupied space is large, so that the application range of the method is greatly limited;
2. the fault diagnosis based on the model needs to deeply know and understand the operation mechanism of the circuit in advance, a more accurate model is constructed for the circuit to be diagnosed, a specific input signal is given to the circuit, and the fault diagnosis is carried out by comparing the actual output of the circuit with the model calculation output. The method has simple hardware structure, reduces the requirements on cost and space, and does not need to preset fault categories. However, for complex circuits, it is difficult to obtain an accurate model, which limits the diagnosis accuracy, and the models of different circuits have great differences, so that the modeling experience between different circuits is difficult to refer to, and the popularization is poor.
Therefore, how to ensure the accuracy of fault diagnosis and the applicability of different circuits at low cost is a technical problem to be solved urgently by those skilled in the art.
Disclosure of Invention
The invention mainly aims to provide a fault diagnosis method, a fault diagnosis device, a fault diagnosis system and a train of a traction control unit, so that the fault diagnosis accuracy and the applicability of different circuits can be ensured under the condition of low cost.
In view of the above problems, the present invention provides a method for diagnosing a failure of a traction control unit, including:
collecting monitoring data of a circuit to be diagnosed when the circuit to be diagnosed in the traction control unit works;
processing the monitoring data to obtain actual circuit characteristic information of the circuit to be diagnosed;
inputting the actual circuit characteristic information into a pre-constructed fault diagnosis model for fault analysis, and outputting the working state of the circuit to be diagnosed;
and if the working state of the circuit to be diagnosed represents that the circuit is in a fault state, executing a protection action corresponding to the fault type according to the incidence relation between the fault type and the protection action in the working state of the circuit to be diagnosed.
Further, in the method for diagnosing a fault of a traction control unit, a process of constructing the fault diagnosis model includes: performing k-fold cross training on the initial support vector machine model by using the acquired sample data to obtain k groups of model parameters corresponding to k groups of verification data;
calculating k groups of error data corresponding to the k groups of verification data according to the k groups of model parameters and the k groups of verification data;
and selecting the model parameter corresponding to the minimum error data to construct the fault diagnosis model.
Further, in the method for diagnosing a fault of a traction control unit, performing k-fold cross training on an initial support vector machine model by using the acquired sample data includes:
dividing the sample data into k groups to obtain k groups of sample data;
and traversing one group of data in the k groups of sample data as verification data, taking the k-1 groups of sample data as training data, and performing iterative training on the initial support vector machine model by using each group of training data to obtain model parameters corresponding to each group of verification data.
Further, in the method for diagnosing a fault of a traction control unit, before performing k-fold cross training on an initial support vector machine model by using the obtained sample data to obtain k sets of model parameters corresponding to k sets of verification data, the method further includes:
drawing a schematic diagram of a sample circuit based on simulation software, setting simulation parameters and test points, carrying out simulation analysis, and obtaining simulation data of the test points under different circuit working states of the same sample circuit; the working state of the circuit is a fault state or a non-fault state;
and processing the simulation data to obtain simulation circuit characteristic information of the sample circuit as the sample data.
Further, the method for diagnosing a failure of a traction control unit described above further includes:
if the working state of the circuit to be diagnosed represents that the circuit is in a fault state, selecting the same circuit of the circuit to be diagnosed from different circuits drawn by simulation software;
and outputting the same circuit of the circuit to be diagnosed.
Further, in the method for diagnosing a fault of a traction control unit, outputting a circuit of the same kind as the circuit to be diagnosed includes:
acquiring the identifier and the failure mode of the electrical element with the circuit fault to be diagnosed;
marking the same type of circuit with the circuit to be diagnosed based on the identification and the failure mode of the electrical element with the circuit to be diagnosed;
and outputting the same circuit of the circuit to be diagnosed with the mark.
Further, the method for diagnosing a failure of a traction control unit further includes:
and if the working state of the circuit to be diagnosed represents that the circuit is in a fault state, sending fault prompt information to a monitoring terminal.
The present invention also provides a failure diagnosis device of a traction control unit, including:
the signal acquisition unit is used for acquiring monitoring data of the circuit to be diagnosed when the circuit to be diagnosed in the traction control unit works;
the characteristic extraction unit is used for processing the monitoring data to obtain the actual circuit characteristic information of the circuit to be diagnosed;
the fault diagnosis unit is used for inputting the actual circuit characteristic information into a pre-constructed fault diagnosis model for fault analysis and outputting the working state of the circuit to be diagnosed;
and the fault processing unit is used for executing the protection action corresponding to the fault type according to the incidence relation between the fault type and the protection action in the working state of the circuit to be diagnosed if the working state of the circuit to be diagnosed represents that the circuit is in the fault state.
The invention also provides a fault diagnosis system of the traction control unit, which comprises a memory and a controller;
the memory has stored thereon a computer program which, when executed by the controller, implements the steps of the above-described method of fault diagnosis of a traction control unit.
The invention also provides a train which is provided with the fault diagnosis system of the traction control unit.
Compared with the prior art, one or more embodiments in the above scheme can have the following advantages or beneficial effects:
according to the fault diagnosis method, the fault diagnosis device and the fault diagnosis system for the traction control unit and the train, the monitoring data of the circuit to be diagnosed when the circuit to be diagnosed in the traction control unit works are collected and processed, so that the actual circuit characteristic information of the circuit to be diagnosed is obtained; the method comprises the steps of inputting actual circuit characteristic information into a pre-constructed fault diagnosis model for fault analysis, outputting the working state of a circuit to be diagnosed, and executing protection actions corresponding to fault categories according to the incidence relation between the fault categories and the protection actions in the working state of the circuit to be diagnosed when the working state of the circuit to be diagnosed shows that the circuit is in the fault state, so that the fault diagnosis accuracy and the applicability of different circuits are guaranteed to the maximum extent under the condition that a small amount of hardware resources are added.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by the practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
FIG. 1 is a flow chart of an embodiment of a method of fault diagnosis of a traction control unit of the present invention;
FIG. 2 is a flow chart of the training of the fault diagnosis model;
FIG. 3 is a schematic structural diagram of an embodiment of a fault diagnosis device of the traction control unit of the present invention;
fig. 4 is a schematic structural diagram of an embodiment of a fault diagnosis apparatus of a traction control unit of the present invention.
Detailed Description
The following detailed description of the embodiments of the present invention will be provided with reference to the drawings and examples, so that how to apply the technical means to solve the technical problems and achieve the technical effects can be fully understood and implemented. It should be noted that, as long as there is no conflict, the embodiments and the features of the embodiments of the present invention may be combined with each other, and the technical solutions formed are within the scope of the present invention.
Example one
In order to solve the technical problems in the prior art, an embodiment of the present invention provides a method for diagnosing a fault of a traction control unit.
Fig. 1 is a flowchart of an embodiment of a method for diagnosing a fault of a traction control unit according to the present invention, and as shown in fig. 1, the method for diagnosing a fault of a traction control unit according to the present embodiment may specifically include the following steps:
100. collecting monitoring data of a circuit to be diagnosed when the circuit to be diagnosed in the traction control unit works;
in a specific implementation process, the related devices may be used to monitor the designated test points in the circuit to be diagnosed, so as to collect the monitoring data of each test point when the circuit to be diagnosed in the traction control unit operates. For example, the circuit to be diagnosed may include interface circuits for medium voltage/current/digital signal acquisition, digital/pulse signal output, and the like. Correspondingly, the monitoring data may include voltage signals, current signals, and the like. This embodiment is preferably voltage.
101. Processing the monitoring data to obtain the actual circuit characteristic information of the circuit to be diagnosed;
in this embodiment, the obtained monitoring data of the test point may be transformed to obtain actual circuit characteristic information of the circuit to be diagnosed.
102. Inputting the actual circuit characteristic information into a pre-constructed fault diagnosis model for fault analysis, and outputting the working state of the circuit to be diagnosed;
in one specific implementation, the pre-constructed fault diagnosis model may be implemented by the steps shown in fig. 2. Fig. 2 is a training flowchart of the fault diagnosis model.
200. Performing k-fold cross training on the initial support vector machine model by using the acquired sample data to obtain k groups of model parameters corresponding to k groups of verification data;
in this embodiment, a schematic diagram of a circuit can be drawn based on simulation software to serve as a sample circuit, and simulation parameters and test points are set to perform simulation analysis, so as to obtain simulation data of the test points of the same circuit in different working states; and processing the simulation data to obtain simulation circuit characteristic information of the sample circuit, and taking the obtained simulation circuit characteristic information of the sample circuit as sample data. For example, the accuracy and range of the simulation data are made to coincide with data sampled by an actual a/D (analog-to-digital converter), and data conversion is performed to obtain simulation circuit characteristic information of the sample circuit. The working state of the circuit is a fault state or a non-fault state. Selecting the faults needing to be diagnosed to form a fault set, wherein each fault information in the fault set consists of two parts:
1) a fault component: numbering faulty components in the circuit;
2) the type of component failure: hard faults (open, short), soft faults (positive drift, negative drift).
The selection mode is as follows: analyzing the models of all components in the circuit, listing all failure modes and failure rates of the components, and then selecting by combining the following three aspects: 1. whether the fault occurred in the past; 2. the degree of influence on the circuit and upper systems after the fault occurs; 3. the possibility of failure.
In this embodiment, the number of test points and hardware required to be added for data acquisition are as small as possible, and the circuit feature vector needs to be able to distinguish all faults in the fault set as possible. In some cases, when some faults of the fault set cannot be distinguished by the circuit characteristic vector because the faults cannot be distinguished or the distinguishing cost is too large, the faults which cannot be distinguished from each other are combined to be treated as a type of fault.
In a specific implementation process, after sample data is obtained, the sample data can be divided into k groups to obtain k groups of sample data; and traversing one group of data in the k groups of sample data as verification data, taking the k-1 group of sample data as training data, and performing iterative training on the initial support vector machine model by using each group of training data to obtain model parameters corresponding to each group of verification data.
The support vector machine model of the embodiment may be a single support vector machine as a two-classifier, and the multiple classifiers may be constructed by One-to-One algorithm (One vertex One, OVO), One-to-many algorithm (One vertex Rest, OVR), decision-Directed Acyclic Graph support vector machine algorithm (Directed Acyclic Graph SVM, DAGSVM), and the like. Here, a one-to-one algorithm is selected to realize the multi-classification support vector machine, and the construction is commonly required
And N is the number of circuit states. Kernel function selection gaussian radial basis kernel function (RBF kernel function): k (x, y) { - γ | | | x-y | | | luminance2X-y is the distance between two data. Parameters needing to be set in the training process of the support vector machine comprise a penalty factor C and gamma in an RBF kernel function, and the penalty factor C and the gamma are selected through a grid search method and a cross verification method. And training the training data as the input of the multi-classification support vector machine to obtain the current optimized support vector machine model. For data in a test data set, inputting a circuit characteristic vector into a current optimized support vector machine model obtained through training, comparing a circuit state label of the data with a label output by the current optimized support vector machine model, and calculating the fault diagnosis accuracy of the model:
and judging whether the fault diagnosis accuracy of the current optimized support vector machine model meets the expected requirement, namely is more than or equal to a certain set threshold (such as 95%): if not, returning to the previous step, adjusting the model parameters, and retraining; if yes, obtaining the current secondary model parameters.
It should be noted that, in the present embodiment, the training data includes data of all circuit states (no fault state and fault state), and the number of data of each circuit state is equal. For test data, multiple sets of data under all circuit states need to be included for test completeness, and for soft faults, component parameter values need to be selected randomly for multiple times within a drift range.
201. Calculating k groups of error data corresponding to the k groups of verification data according to the k groups of model parameters and the k groups of verification data;
for each group of verification data, when calculating the corresponding error data, firstly, inputting the input data in the verification data into the trained support vector machine model corresponding to the group of verification data, so that the corresponding output data can be output by the network, and then, calculating the error standard deviation of the data in the verification data and the output data of the support vector machine model, thereby obtaining the error data corresponding to the group of verification data.
202. And selecting the model parameter corresponding to the minimum error data to construct the fault diagnosis model.
In a specific implementation process, the actual circuit characteristic information of the circuit to be diagnosed can be input into a pre-constructed fault diagnosis model for fault analysis, so that the working state of the circuit to be diagnosed can be output. If the working state of the circuit to be diagnosed indicates that the circuit is in a fault state, the working state of the circuit to be diagnosed may include an association relationship between a fault type and a protection action. If the working state of the circuit to be diagnosed indicates that the circuit is in a non-fault state, the working state of the circuit to be diagnosed may include monitoring information of normal operation, and the like.
In the embodiment, because the fault diagnosis model can be used for directly carrying out learning reasoning from the collected monitoring data, the internal mechanism of the system does not need to be deeply understood and a complex system model does not need to be established when fault diagnosis is carried out, so that the fault diagnosis accuracy can be ensured to the maximum extent under the condition of increasing a small amount of hardware resources, and the occupation of computing resources is small. Meanwhile, the method has high universality and high popularization performance on different circuits, and the applicability of different circuits is guaranteed.
103. And if the working state of the circuit to be diagnosed represents that the circuit is in a fault state, executing a protection action corresponding to the fault type according to the incidence relation between the fault type and the protection action in the working state of the circuit to be diagnosed.
In this embodiment, if the operating state of the circuit to be diagnosed indicates that the circuit is in a fault state, the protection action corresponding to the fault category is executed according to the association relationship between the fault category and the protection action in the operating state of the circuit to be diagnosed. For example, the signal processing module blocks the pulse signal, etc., so that the relevant circuits do not work any more, thereby protecting the traction control unit.
According to the fault diagnosis method of the traction control unit, monitoring data of a circuit to be diagnosed when the circuit to be diagnosed in the traction control unit works are collected, and the monitoring data are processed to obtain actual circuit characteristic information of the circuit to be diagnosed; the method comprises the steps of inputting actual circuit characteristic information into a pre-constructed fault diagnosis model for fault analysis, outputting the working state of a circuit to be diagnosed, and executing protection actions corresponding to fault categories according to the incidence relation between the fault categories and the protection actions in the working state of the circuit to be diagnosed when the working state of the circuit to be diagnosed shows that the circuit is in the fault state, so that the fault diagnosis accuracy and the applicability of different circuits are guaranteed to the maximum extent under the condition that a small amount of hardware resources are added.
Further, when the working state of the circuit to be diagnosed indicates that the circuit is in a fault state, in order to enable monitoring personnel to quickly solve the fault, fault prompt information can be sent to the monitoring terminal, and in addition, the same circuit of the circuit to be diagnosed can be selected from different circuits drawn by simulation software; and outputting the same circuit of the circuit to be diagnosed.
Specifically, acquiring the identifier and the failure mode of the electrical element with the circuit fault to be diagnosed; marking the same type of circuit with the circuit to be diagnosed based on the identification and the failure mode of the electrical element with the circuit to be diagnosed; and outputting the same circuit of the circuit to be diagnosed with the mark. Therefore, monitoring personnel can know the relevant fault position according to the same circuit as the circuit to be diagnosed, and therefore relevant faults can be processed quickly.
The fault diagnosis method of the traction control unit in the embodiment can judge whether the circuit has a fault and can further position the circuit to a specific fault device, thereby greatly improving the precision of circuit fault positioning, and simultaneously outputting the same circuit with the circuit to be diagnosed with a fault mark, so that a monitoring person can rapidly process the fault according to the working principle and the fault mark of the same circuit with the circuit to be diagnosed, and the fault processing efficiency is improved.
It should be noted that the method of the embodiment of the present invention may be executed by a single device, such as a computer or a server. The method of the embodiment can also be applied to a distributed scene and completed by the mutual cooperation of a plurality of devices. In the case of such a distributed scenario, one device of the multiple devices may only perform one or more steps of the method according to the embodiment of the present invention, and the multiple devices interact with each other to complete the method.
Example two
In order to solve the above technical problems in the prior art, an embodiment of the present invention provides a fault diagnosis apparatus for a traction control unit.
Fig. 3 is a schematic structural diagram of an embodiment of a fault diagnosis device of a traction control unit according to the present invention, and as shown in fig. 3, the fault diagnosis device of the traction control unit of the present embodiment includes: a signal acquisition unit 30, a feature extraction unit 31, a fault diagnosis unit 32, and a fault processing unit 33.
The signal acquisition unit 30 is used for acquiring monitoring data of the circuit to be diagnosed when the circuit to be diagnosed in the traction control unit works;
the feature extraction unit 31 is configured to process the monitoring data to obtain actual circuit feature information of the circuit to be diagnosed;
the fault diagnosis unit 32 is configured to input actual circuit characteristic information into a fault diagnosis model which is constructed in advance to perform fault analysis, and output a working state of the circuit to be diagnosed;
in this embodiment, a schematic diagram of a circuit may be drawn based on simulation software as a sample circuit, and simulation parameters and test points may be set to perform simulation analysis, so as to obtain simulation data of the sample circuit in different circuit operating states of the same circuit; the working state of the circuit is a fault state or a non-fault state; and processing the simulation data to obtain simulation circuit characteristic information of the circuit to be diagnosed as sample data. Performing k-fold cross training on the initial support vector machine model by using the acquired sample data to obtain k groups of model parameters corresponding to k groups of verification data; and selecting the model parameter corresponding to the minimum error data to construct the fault diagnosis model according to the k groups of model parameters and the k groups of verification data.
In a specific implementation process, sample data can be divided into k groups to obtain k groups of sample data; and traversing one group of data in the k groups of sample data as verification data, taking the k-1 group of sample data as training data, and performing iterative training on the initial support vector machine model by using each group of training data to obtain model parameters corresponding to each group of verification data.
Therefore, after the actual circuit characteristic information is obtained, the actual circuit characteristic information can be input into a pre-constructed fault diagnosis model for fault analysis, and the working state of the circuit to be diagnosed is output.
And the fault processing unit 33 is configured to execute a protection action corresponding to the fault type according to the association relationship between the fault type and the protection action in the working state of the circuit to be diagnosed, if the working state of the circuit to be diagnosed indicates that the circuit is in the fault state.
Further, in the above embodiment, the fault diagnosis unit 32 is further configured to send fault prompt information to the monitoring terminal if the working state of the circuit to be diagnosed indicates that the circuit is in a fault state, and may select a similar circuit to the circuit to be diagnosed from different circuits drawn by the simulation software; the same kind of circuit as the circuit to be diagnosed is output. Specifically, the identifier and failure mode of the electrical component with the circuit fault to be diagnosed can be obtained; marking the same type of circuit with the circuit to be diagnosed based on the identification and the failure mode of the electrical element with the circuit to be diagnosed; and outputting the same circuit of the circuit to be diagnosed with the mark.
The apparatus of the foregoing embodiment is used to implement the corresponding method in the foregoing embodiment, and specific implementation schemes thereof may refer to the method described in the foregoing embodiment and relevant descriptions in the method embodiment, and have beneficial effects of the corresponding method embodiment, which are not described herein again.
EXAMPLE III
In order to solve the technical problems in the prior art, an embodiment of the present invention provides a fault diagnosis system for a traction control unit.
Fig. 4 is a schematic structural diagram of an embodiment of a fault diagnosis system of a traction control unit according to the present invention, and as shown in fig. 4, the fault diagnosis system of the traction control unit according to the present embodiment includes a memory 40 and a controller 41; the memory 40 has stored thereon a computer program that, when executed by the controller 41, implements the steps of the fault diagnosis method of the traction control unit of the above-described embodiment.
Example four
In order to solve the technical problems in the prior art, an embodiment of the present invention provides a train, where the train is provided with the fault diagnosis system of the traction control unit of the above embodiment.
EXAMPLE five
In order to solve the above technical problems in the prior art, embodiments of the present invention provide a storage medium.
The storage medium of this embodiment stores thereon a computer program that, when executed by the controller, implements the steps of the method for diagnosing a failure of the traction control unit of the above-described embodiment.
It is understood that the same or similar parts in the above embodiments may be mutually referred to, and the same or similar parts in other embodiments may be referred to for the content which is not described in detail in some embodiments.
It should be noted that the terms "first," "second," and the like in the description of the present invention are used for descriptive purposes only and are not to be construed as indicating or implying relative importance. Further, in the description of the present invention, the meaning of "a plurality" means at least two unless otherwise specified.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and alternate implementations are included within the scope of the preferred embodiment of the present invention in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present invention.
It should be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
It will be understood by those skilled in the art that all or part of the steps carried by the method for implementing the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium, and when the program is executed, the program includes one or a combination of the steps of the method embodiments.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing module 32, or each unit may exist alone physically, or two or more units are integrated in one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a stand-alone product, may also be stored in a computer readable storage medium.
The storage medium mentioned above may be a read-only memory, a magnetic or optical disk, etc.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
Although the embodiments of the present invention have been described above, the above description is only for the convenience of understanding the present invention, and is not intended to limit the present invention. It will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (10)
1. A method of diagnosing a fault in a traction control unit, comprising:
collecting monitoring data of a circuit to be diagnosed when the circuit to be diagnosed in the traction control unit works;
processing the monitoring data to obtain actual circuit characteristic information of the circuit to be diagnosed;
inputting the actual circuit characteristic information into a pre-constructed fault diagnosis model for fault analysis, and outputting the working state of the circuit to be diagnosed;
and if the working state of the circuit to be diagnosed represents that the circuit is in a fault state, executing a protection action corresponding to the fault type according to the incidence relation between the fault type and the protection action in the working state of the circuit to be diagnosed.
2. The method of diagnosing a failure in a traction control unit according to claim 1, wherein the process of constructing the failure diagnosis model includes: performing k-fold cross training on the initial support vector machine model by using the acquired sample data to obtain k groups of model parameters corresponding to k groups of verification data;
calculating k groups of error data corresponding to the k groups of verification data according to the k groups of model parameters and the k groups of verification data;
and selecting the model parameter corresponding to the minimum error data to construct the fault diagnosis model.
3. The method of diagnosing a fault in a traction control unit according to claim 2, wherein performing k-fold cross training on the initial support vector machine model using the acquired sample data includes:
dividing the sample data into k groups to obtain k groups of sample data;
and traversing one group of data in the k groups of sample data as verification data, taking the k-1 groups of sample data as training data, and performing iterative training on the initial support vector machine model by using each group of training data to obtain model parameters corresponding to each group of verification data.
4. The method of diagnosing a failure in a traction control unit according to claim 2, wherein before k-fold cross training of the initial support vector machine model using the acquired sample data to obtain k sets of model parameters corresponding to k sets of verification data, the method further comprises:
drawing a schematic diagram of a sample circuit based on simulation software, setting simulation parameters and test points, carrying out simulation analysis, and obtaining simulation data of the test points under different circuit working states of the same sample circuit; the working state of the circuit is a fault state or a non-fault state;
and processing the simulation data to obtain simulation circuit characteristic information of the sample circuit as the sample data.
5. The method of diagnosing a failure of a traction control unit according to claim 4, characterized by further comprising:
if the working state of the circuit to be diagnosed represents that the circuit is in a fault state, selecting the same circuit of the circuit to be diagnosed from different circuits drawn by simulation software;
and outputting the same circuit of the circuit to be diagnosed.
6. The method of diagnosing a failure in a traction control unit according to claim 5, wherein outputting a circuit of the same kind as the circuit to be diagnosed includes:
acquiring the identifier and the failure mode of the electrical element with the circuit fault to be diagnosed;
marking the same type of circuit with the circuit to be diagnosed based on the identification and the failure mode of the electrical element with the circuit to be diagnosed;
and outputting the same circuit of the circuit to be diagnosed with the mark.
7. The method of diagnosing a failure of a traction control unit according to claim 1, characterized by further comprising:
and if the working state of the circuit to be diagnosed represents that the circuit is in a fault state, sending fault prompt information to a monitoring terminal.
8. A failure diagnosis device of a traction control unit, characterized by comprising:
the signal acquisition unit is used for acquiring monitoring data of the circuit to be diagnosed when the circuit to be diagnosed in the traction control unit works;
the characteristic extraction unit is used for processing the monitoring data to obtain the actual circuit characteristic information of the circuit to be diagnosed;
the fault diagnosis unit is used for inputting the actual circuit characteristic information into a pre-constructed fault diagnosis model for fault analysis and outputting the working state of the circuit to be diagnosed;
and the fault processing unit is used for executing the protection action corresponding to the fault type according to the incidence relation between the fault type and the protection action in the working state of the circuit to be diagnosed if the working state of the circuit to be diagnosed represents that the circuit is in the fault state.
9. A fault diagnosis system of a traction control unit, comprising a memory and a controller;
the memory has stored thereon a computer program which, when being executed by the controller, carries out the steps of the method of fault diagnosis of a traction control unit according to any one of claims 1 to 8.
10. A train provided with a fault diagnosis system of a traction control unit according to claim 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011194475.0A CN112327804A (en) | 2020-10-30 | 2020-10-30 | Fault diagnosis method, device and system of traction control unit and train |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011194475.0A CN112327804A (en) | 2020-10-30 | 2020-10-30 | Fault diagnosis method, device and system of traction control unit and train |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112327804A true CN112327804A (en) | 2021-02-05 |
Family
ID=74322804
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011194475.0A Pending CN112327804A (en) | 2020-10-30 | 2020-10-30 | Fault diagnosis method, device and system of traction control unit and train |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112327804A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113110387A (en) * | 2021-04-20 | 2021-07-13 | 上海市环境科学研究院 | Environment-friendly intelligent diagnosis system, method and storage medium |
| CN113159100A (en) * | 2021-02-19 | 2021-07-23 | 湖南第一师范学院 | Circuit fault diagnosis method, circuit fault diagnosis device, electronic equipment and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105095566A (en) * | 2015-06-29 | 2015-11-25 | 南京航空航天大学 | Inverter fault diagnosis method based on wavelet analysis and SVM |
| CN105137324A (en) * | 2015-08-18 | 2015-12-09 | 电子科技大学 | Multi-detecting-point fault component positioning method based on simulation classification model |
| CN109506963A (en) * | 2018-11-29 | 2019-03-22 | 中南大学 | A kind of intelligence train traction failure big data abnormality detection discrimination method |
| CN109858503A (en) * | 2017-11-30 | 2019-06-07 | 株洲中车时代电气股份有限公司 | The traction converter failure diagnostic method of decision tree is promoted based on gradient |
| CN109917200A (en) * | 2017-12-12 | 2019-06-21 | 株洲中车时代电气股份有限公司 | Train traction current transformer method for diagnosing faults, system, equipment and storage medium |
| CN110909444A (en) * | 2019-10-15 | 2020-03-24 | 北京交通大学 | High-speed rail traction power supply scheduling simulation training system |
| CN111204363A (en) * | 2020-04-23 | 2020-05-29 | 湖南中车时代通信信号有限公司 | Fault diagnosis early warning and state evaluation method, device and system for traction system |
| US20200200813A1 (en) * | 2018-12-21 | 2020-06-25 | Zhejiang University | Online diagnosis method for deformation position on trasnformation winding |
-
2020
- 2020-10-30 CN CN202011194475.0A patent/CN112327804A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105095566A (en) * | 2015-06-29 | 2015-11-25 | 南京航空航天大学 | Inverter fault diagnosis method based on wavelet analysis and SVM |
| CN105137324A (en) * | 2015-08-18 | 2015-12-09 | 电子科技大学 | Multi-detecting-point fault component positioning method based on simulation classification model |
| CN109858503A (en) * | 2017-11-30 | 2019-06-07 | 株洲中车时代电气股份有限公司 | The traction converter failure diagnostic method of decision tree is promoted based on gradient |
| CN109917200A (en) * | 2017-12-12 | 2019-06-21 | 株洲中车时代电气股份有限公司 | Train traction current transformer method for diagnosing faults, system, equipment and storage medium |
| CN109506963A (en) * | 2018-11-29 | 2019-03-22 | 中南大学 | A kind of intelligence train traction failure big data abnormality detection discrimination method |
| US20200200813A1 (en) * | 2018-12-21 | 2020-06-25 | Zhejiang University | Online diagnosis method for deformation position on trasnformation winding |
| CN110909444A (en) * | 2019-10-15 | 2020-03-24 | 北京交通大学 | High-speed rail traction power supply scheduling simulation training system |
| CN111204363A (en) * | 2020-04-23 | 2020-05-29 | 湖南中车时代通信信号有限公司 | Fault diagnosis early warning and state evaluation method, device and system for traction system |
Non-Patent Citations (1)
| Title |
|---|
| 刘一鸣: "《基于支持向量机的设备故障诊断研究》", 《电子设计工程》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113159100A (en) * | 2021-02-19 | 2021-07-23 | 湖南第一师范学院 | Circuit fault diagnosis method, circuit fault diagnosis device, electronic equipment and storage medium |
| CN113159100B (en) * | 2021-02-19 | 2023-03-31 | 湖南第一师范学院 | Circuit fault diagnosis method, circuit fault diagnosis device, electronic equipment and storage medium |
| CN113110387A (en) * | 2021-04-20 | 2021-07-13 | 上海市环境科学研究院 | Environment-friendly intelligent diagnosis system, method and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3584658B1 (en) | Method, system, device, and computer readable storage medium for diagnosing vehicle | |
| CN108414896B (en) | Power grid fault diagnosis method | |
| CN102096410B (en) | Dynamic function test method of high-speed train operation control system | |
| CN116610092A (en) | Method and system for vehicle analysis | |
| CN112327804A (en) | Fault diagnosis method, device and system of traction control unit and train | |
| CN102707712B (en) | Electronic equipment fault diagnosis method and system | |
| CN115062538B (en) | Method and system for diagnosing faults of converter based on attention mechanism and convolution NN | |
| CN104364664A (en) | An algorithm and structure for creation, definition, and execution of an SPC rule decision tree | |
| CN112729884B (en) | Equipment fault diagnosis method and device based on big data | |
| CN112285484B (en) | Power system fault diagnosis information fusion method and device based on deep neural network | |
| CN110888011B (en) | In-situ test method and test device based on testability modeling | |
| CN113093695A (en) | Data-driven SDN controller fault diagnosis system | |
| CN109889258B (en) | Optical network fault checking method and equipment | |
| CN115684835B (en) | Power distribution network fault diagnosis method, device, equipment and storage medium | |
| CN116820821A (en) | Disk failure detection method, apparatus, electronic device and computer readable storage medium | |
| Amati et al. | An incremental approach to functional diagnosis | |
| CN113392589B (en) | High-voltage direct-current converter station fault analysis method and system based on convolutional neural network | |
| CN114879647A (en) | ECU fault code test system, electronic controller and car | |
| DE102021101757A1 (en) | Big data for error detection in battery systems | |
| CN114928528B (en) | Fault diagnosis method, controller, protocol conversion system and storage medium | |
| CN110751745A (en) | Routing inspection method for power grid regulation and control integrated machine room | |
| CN117439899B (en) | Communication machine room inspection method and system based on big data | |
| CN118567321A (en) | Vehicle testing method and device, vehicle, electronic equipment and storage medium | |
| CN117110733A (en) | Automatic diagnosis method and device for battery management system | |
| CN116502096A (en) | Information processing system, information processing method, and computer-readable storage medium |
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: 20210205 |
|
| RJ01 | Rejection of invention patent application after publication |