Alternating current-direct current switching action time parameter selection method and system

Abstract

The present invention relates to the field of rail transit, and provides an alternating current-direct current switching action time parameter selection method and system. The method comprises the following steps: acquiring alternating current-direct current switching action time data of a train; performing feature extraction and optimization on the alternating current-direct current switching action time data; training a support vector machine model; constructing a probability support vector machine model; and outputting an optimal value of an action time parameter. On the basis of actual running data, the probability support vector machine model is used to select the action time parameter, so that an alternating current-direct current power supply switching operation is more efficient and more accurate.

Description

A method and system for selecting AC / DC switching action time parameters

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to Chinese patent application number 2023115634013, filed with the Chinese Patent Office on November 22, 2023, entitled “A method and system for selecting time parameters of AC / DC switching action”, the entire contents of which are incorporated by reference into this application. Technical Field

[0003] The present application relates to the field of rail transportation, and in particular to a method and system for selecting time parameters for AC / DC switching action. Background Art

[0004] With the development of urban economies, intra-city transportation is gradually becoming more subway-based, while inter-city transportation is becoming more inter-city. However, with the implementation of subway and inter-city rail transit, the challenges posed by the independence and complexity of rail transit projects are becoming increasingly prominent. Specifically, subway projects in different regions and inter-city projects between different cities often cannot be directly connected due to factors such as different project approval times and different technical foundations.

[0005] The most critical issue is power supply. Subway trains typically use 1500V DC power, while intercity lines typically use 25kV / 50Hz AC power. Therefore, trainsets must switch between AC and DC power during operation. However, switching between AC and DC power is not a simple operation; it involves multiple, continuous manipulations of the pantograph, AC / DC transfer switch, and main circuit breaker. Only when all these steps are successfully completed can the AC / DC switching be considered successful. If the AC / DC switching operation fails, the trainset control system must respond as quickly as possible.

[0006] Application Contents

[0007] In view of this, how the train control system can achieve the shortest response time without misjudgment has become a difficult problem. The purpose of this application is to provide a method and system for selecting time parameters for AC / DC switching actions, which fully utilizes train operation data and machine learning algorithms to truly achieve accurate monitoring and rapid response of AC / DC switching actions.

[0008] The present application provides a method for selecting AC / DC switching action time parameters, comprising the following steps: collecting AC / DC switching action time data of a train; performing feature extraction and optimization on the time data of the AC / DC switching action; training a support vector machine model; constructing a probabilistic support vector machine model; and outputting the optimal value of the action time parameter.

[0009] In some embodiments, the AC / DC switching action time data may be at least one of AC / DC pantograph raising action time data, AC / DC pantograph lowering action time data, AC / DC transfer switch action time data, main circuit breaker closing action time data, or main circuit breaker opening action time data.

[0010] In some embodiments, the method further includes: collecting AC / DC switching action device data of the train; performing feature extraction and optimization on the AC / DC switching action device data, and associating it with the AC / DC switching action time data.

[0011] In some embodiments, the training of the support vector machine model includes: using the optimized features of the AC / DC switching action time data and the AC / DC switching action device data as training data and constructing a probabilistic support vector machine model.

[0012] In some embodiments, the method further includes: setting an alarm threshold for determining that the AC / DC switching action is unsuccessful based on the optimal value of the action time parameter.

[0013] In some embodiments, the method further comprises: setting an extension value, wherein the alarm threshold is the optimal value of the action time parameter plus the extension value.

[0014] In some embodiments, the method further includes: setting update conditions, and when the update conditions are met, re-collecting the latest AC / DC switching action time data of the train; performing feature extraction and optimization on the time data of the latest AC / DC switching action; training the support vector machine model; constructing a probabilistic support vector machine model; and outputting the latest optimal value of the action time parameter.

[0015] In some embodiments, the update condition may be at least one of when the train starts running, when the train stops running, when the train travels in a special geographical environment, and when the train travels a specific number of kilometers.

[0016] In some embodiments, the optimal value of the output action time parameter can be at least one of the optimal value of the AC / DC pantograph raising action time parameter, the optimal value of the AC / DC pantograph lowering action time parameter, the optimal value of the AC / DC transfer switch action time parameter, the optimal value of the main circuit breaker closing action time parameter, or the optimal value of the main circuit breaker opening action time parameter.

[0017] At the same time, the present application also provides a system for selecting AC / DC switching action time parameters, the system comprising:

[0018] A data acquisition module is configured to collect AC / DC switching action time data and / or AC / DC switching action device data of the train;

[0019] a data processing module configured to perform standardization processing on the time data of the AC / DC switching action and extract characteristic values, and / or perform feature extraction and optimization on the AC / DC switching action device data and associate it with the AC / DC switching action time data;

[0020] a model training module configured to use the time data of the AC / DC switching action and / or the optimized features of the AC / DC switching action device data as training data and construct a probabilistic support vector machine model;

[0021] The result output module is configured to calculate the optimal value of the action time parameter.

[0022] The beneficial effects that this application can achieve are:

[0023] 1. Compared to the existing techniques of randomly selecting parameters or selecting parameters based solely on technical experience, which excessively redundantly set the action time parameters to ensure successful AC / DC power supply switching, this application cleverly uses a probabilistic support vector machine model based on actual operation data to select the optimal value of the action time parameter, making the monitoring of AC / DC power supply switching operations more efficient and accurate.

[0024] 2. The method for selecting the action time parameters proposed in this application is based on data that includes not only the AC / DC switching action time data of the train, but also the data of the AC / DC switching action devices of the train, making the optimal value of the action time parameter ultimately output more reliable;

[0025] 3. The action time parameter selection method proposed in this application has a data basis and analysis model that is not only based on train operation data, but also updated in real time based on update conditions, so that the final output action time parameters are more optimized.

[0026] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without creative work.

[0028] FIG1 shows a flow chart of a method for selecting time parameters for AC / DC switching operation according to the present invention;

[0029] FIG2 shows a schematic structural diagram of a system for selecting time parameters for AC / DC switching action according to the present application. DETAILED DESCRIPTION

[0030] In order to more clearly understand the above-mentioned objects, features and advantages of the present invention, the present invention is described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that, in the absence of conflict, the embodiments of the present application and the features therein may be combined with each other.

[0031] The following description sets forth numerous specific details to facilitate a thorough understanding of the present invention. The embodiments described are merely some, not all, of the present invention. All other embodiments derived by persons of ordinary skill in the art based on the embodiments of the present invention without inventive effort are intended to fall within the scope of protection of the present invention.

[0032] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used in this specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention.

[0033] Please refer to Figure 1. The present invention provides a method for selecting AC / DC switching action time parameters, including the following steps: S1. Collecting data; S2. Data processing; S3. Training and building a support vector machine model; S4. Outputting the optimal value.

[0034] S1. The data collection includes collecting the AC / DC switching action time data of the train and the AC / DC switching action device data of the train.

[0035] The AC / DC switching action time data of the train may be any one of: AC / DC pantograph raising action time data, AC / DC pantograph lowering action time data, AC / DC transfer switch action time data, main circuit breaker closing action time data or main circuit breaker opening action time data.

[0036] Time data may include the duration required to complete each action, as well as the start and end times of the action.

[0037] Device data refers to the device information that implements AC / DC switching on the train.

[0038] The device for implementing AC / DC switching on the train may be at least one of a pantograph, an AC / DC transfer switch or a main circuit breaker.

[0039] The device information may be at least one of the model information, brand information, activation date, usage time, rated life, maintenance record or maintenance date of the device.

[0040] S2. Data processing includes feature extraction and optimization of the time data of the AC / DC switching action, feature extraction and optimization of the device data of the AC / DC switching action, and associating the device data with the time data.

[0041] Since the time required to complete an action is related to the device model, service life, and other information, the device data needs to be associated with the time data.

[0042] Since the support vector machine algorithm realizes linear separability of at least two groups of data, and the time data and device data collected in the above steps are basically data for successfully completing the AC / DC switching action, it is necessary to supplement and improve the collected time data and device data.

[0043] Specifically, taking the pantograph raising action time data of AC and DC pantographs as an example, the values ​​of the collected time data are directly classified into a success group and the values ​​that do not appear in the collected time data are classified into a failure group.

[0044] S3. Training and building a support vector machine model includes training the support vector machine model based on the processed data and building a support vector machine model.

[0045] S4. Outputting the optimal value includes outputting the optimal value of the action time parameter. Specifically, the optimal value of the action time parameter is output according to the device data of the current train.

[0046] In some other embodiments, the optimal value of the output action time parameter may be at least one of the optimal value of the AC / DC pantograph raising action time parameter, the optimal value of the AC / DC pantograph lowering action time parameter, the optimal value of the AC / DC transfer switch action time parameter, the optimal value of the main circuit breaker closing action time parameter, or the optimal value of the main circuit breaker opening action time parameter.

[0047] Specifically, if the time data used is the AC / DC pantograph raising action time data, the basis for support vector machine model training is the AC / DC pantograph raising action time data and pantograph device data after data processing, then the optimal value can be output based on the pantograph device data of the current train set.

[0048] The optimal value can be used as a factor in the train control system's determination of the success of the AC / DC pantograph raising operation. For example, an alarm threshold can be set, and the optimal value can be used. If the alarm threshold is exceeded and no pantograph raising completion signal is received, the train control system can determine that the AC / DC pantograph raising operation has failed.

[0049] In some other embodiments, an extension value may be set, and the alarm threshold may be composed of the optimal value and the extension value.

[0050] In some other embodiments, an update condition can be set. When the update condition is met, the latest AC / DC switching action time data of the train is re-collected; feature extraction and optimization are performed on the latest AC / DC switching action time data; the support vector machine model is trained; a probabilistic support vector machine model is constructed; and the latest optimal value of the action time parameter is output.

[0051] The update condition may be at least one of when the train starts running, when the train stops running, when the train travels in a special geographical environment, and when the train travels a specific number of kilometers.

[0052] According to different requirements, the order of the steps in the method can be changed, and some steps can be omitted.

[0053] Referring to FIG. 2 , the present invention further provides a system 1 for selecting time parameters for AC / DC switching action. The above-mentioned method for selecting time parameters for AC / DC switching action can be applied to the system. The system includes:

[0054] Data acquisition module 2, configured to collect AC / DC switching action time data and / or AC / DC switching action device data of the train;

[0055] a data processing module 3 configured to perform standardization processing on the time data of the AC / DC switching action and extract characteristic values, and / or perform feature extraction and optimization on the AC / DC switching action device data and associate it with the AC / DC switching action time data;

[0056] A model training module 4 is configured to use the time data of the AC / DC switching action and / or the optimized features of the AC / DC switching action device data as training data and to construct a probabilistic support vector machine model;

[0057] The result output module 5 is configured to calculate the optimal value of the action time parameter.

[0058] The AC / DC switching action time parameter selection method and AC / DC switching action time parameter selection system of the present invention can be practically applied to a variety of electronic devices. The electronic device is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions. Its hardware includes but is not limited to microprocessors, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, etc.

[0059] The electronic device may also be any electronic product capable of human-computer interaction with a user, such as a personal computer, a tablet computer, a smart phone, a personal digital assistant (PDA), a game console, an interactive network television (IPTV), a smart wearable device, etc. The smart wearable device may be a wearable watch, wearable glasses, or other wearable devices.

[0060] The electronic device may further include a network device and / or a user device, wherein the network device includes, but is not limited to, a single network server, a server group consisting of multiple network servers, or a cloud based on cloud computing consisting of a large number of hosts or network servers.

[0061] The network where the electronic device is located includes but is not limited to the Internet, a wide area network, a metropolitan area network, a local area network, a virtual private network (VPN), etc.

[0062] The above is a detailed introduction to the embodiments of the present application. Specific examples are used herein to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and core idea of ​​the present application.

[0063] It is obvious to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-restrictive, and the scope of the invention is defined by the appended claims rather than the above description, and it is intended that all changes that fall within the meaning and scope of the equivalent elements of the claims be included in the present invention. Any reference to the accompanying figures in the claims should not be regarded as limiting the claims involved. In addition, it is obvious that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices stated in the system claim may also be implemented by one unit or device through software or hardware. The words first, second, etc. are used to indicate names and do not indicate any particular order.

[0064] At the same time, for those skilled in the art, according to the concept of this application, there may be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A method for selecting time parameters of AC / DC switching action, characterized in that: The method comprises the following steps: collecting AC / DC switching action time data of a train; extracting and optimizing features of the AC / DC switching action time data; training a support vector machine model; constructing a probabilistic support vector machine model; and outputting an optimal value of an action time parameter.

2. According to the method for selecting AC / DC switching action time parameters as described in claim 1, it is characterized in that: The AC / DC switching action time data may be at least one of AC / DC pantograph raising action time data, AC / DC pantograph lowering action time data, AC / DC conversion switch action time data, main circuit breaker closing action time data or main circuit breaker opening action time data.

3. According to the method for selecting AC / DC switching action time parameters as described in claim 1, it is characterized in that: The method further includes: collecting AC / DC switching action device data of the train; extracting and optimizing features of the AC / DC switching action device data, and associating the data with the AC / DC switching action time data.

4. A method for selecting AC / DC switching action time parameters according to claim 3, characterized in that: The training of the support vector machine model includes: using the optimized features of the AC / DC switching action time data and the AC / DC switching action device data as training data and constructing a probabilistic support vector machine model.

5. A method for selecting AC / DC switching action time parameters according to claim 4, characterized in that: The method further comprises: setting an alarm threshold for determining that the AC / DC switching action is unsuccessful based on the optimal value of the action time parameter.

6. A method for selecting AC / DC switching action time parameters according to claim 5, characterized in that: The method further comprises: setting an extension value, wherein the alarm threshold is the optimal value of the action time parameter plus the extension value.

7. The method for selecting time parameters of AC / DC switching action according to claim 1, characterized in that: The method further includes: setting update conditions, and when the update conditions are met, re-collecting the latest AC / DC switching action time data of the train; performing feature extraction and optimization on the latest AC / DC switching action time data; training a support vector machine model; constructing a probabilistic support vector machine model; and outputting the latest optimal value of the action time parameter.

8. A method for selecting AC / DC switching action time parameters according to claim 7, characterized in that: The update condition may be at least one of when the train starts running, when the train stops running, when the train travels in a special geographical environment, and when the train travels a specific number of kilometers.

9. A method for selecting AC / DC switching action time parameters according to claim 8, characterized in that: The optimal value of the output action time parameter can be any at least one of the optimal value of the AC / DC pantograph raising action time parameter, the optimal value of the AC / DC pantograph lowering action time parameter, the optimal value of the AC / DC conversion switch action time parameter, the optimal value of the main circuit breaker closing action time parameter or the optimal value of the main circuit breaker opening action time parameter.

10. A system for selecting time parameters of AC / DC switching action, characterized in that: The system comprises: A data acquisition module is configured to collect AC / DC switching action time data and / or AC / DC switching action device data of the train; A data processing module, configured to perform standardization processing on the time data of the AC / DC switching action and extract characteristic values, and / or perform feature extraction and optimization on the AC / DC switching action device data and associate it with the AC / DC switching action time data; A model training module is configured to use the time data of the AC / DC switching action and / or the optimized features of the AC / DC switching action device data as training data and construct a probabilistic support vector machine model; The result output module is configured to calculate the optimal value of the action time parameter.

Images