A method and system for diagnosing railway power supply faults

Abstract

This application relates to the field of railway power supply technology, and discloses a railway power supply fault diagnosis method and system. The method first acquires monitoring data from first and second transformer monitors. The second monitoring data is stored in different ways depending on the train network status; when the network status does not meet preset conditions, it is stored in the train's local data platform; when it does meet the conditions, it is directly stored in a cloud server. The acquired data is then cleaned to obtain target monitoring data, which is then input into a pre-trained fault diagnosis model for evaluation. This yields a fault diagnosis result that includes at least a first diagnosis result (indicating that the second transformer currently has no power supply fault or its fault is not affected by the first transformer) and a second diagnosis result (indicating that the second transformer's current power supply fault is affected by the first transformer). If the diagnosis is the second diagnosis result, a power supply adjustment control command is sent to the first transformer to attempt to convert it into the first diagnosis result.

Description

Technical Field

[0001] This invention relates to the field of railway power supply technology, and specifically to a railway power supply fault diagnosis method and system. Background Technology

[0002] As a vital component of modern transportation, the stable operation of the railway power supply system is crucial for ensuring the safety, efficiency, and punctuality of railway operations. A railway power supply fault diagnosis system typically consists of multiple transformers, a complex power supply network, and related electrical equipment. The first transformer is responsible for stepping up the mains voltage to meet the long-distance power supply needs of the railway, while the second transformer steps down the railway power supply network to provide suitable voltage for the trains. However, due to the long length of railway lines, the large number of devices, and the complex and variable operating environment, the power supply system is prone to various faults. These faults not only affect the normal operation of trains but may even lead to safety accidents, causing significant economic losses and adverse social impacts on railway operations.

[0003] Traditional railway power supply fault diagnosis mainly relies on manual inspections and experience-based judgment. Maintenance personnel need to conduct regular on-site inspections of equipment such as transformers, identifying potential faults by observing the equipment's appearance and measuring electrical parameters. This approach has many drawbacks: for example, it is inefficient, manual inspections consume a lot of time and manpower, and it is difficult to achieve real-time monitoring and rapid diagnosis of the power supply system. Summary of the Invention

[0004] The main objective of this invention is to provide a method and system for diagnosing railway power supply faults, aiming to solve the technical problem of low fault detection efficiency caused by reliance on manual inspection and experience-based judgment in the prior art.

[0005] To achieve the above objectives, in a first aspect, this application provides a railway power supply fault diagnosis method, applied to a railway power supply fault diagnosis system. The railway power supply fault diagnosis system includes a first transformer, a first transformer monitor, a second transformer, a second transformer monitor, a train local data platform, and a cloud server. The first transformer is used to step up the mains power for railway power supply, and the second transformer is used to step down the railway power grid for train power supply. The method includes:

[0006] The monitoring data of the first transformer monitor and the monitoring data of the second transformer monitor are obtained to obtain the first monitoring data and the second monitoring data. The second monitoring data includes the first sub-monitoring data when the train's network status does not meet the preset conditions and the second sub-monitoring data when the train's network status meets the preset conditions. The first sub-monitoring data is the monitoring data collected by the second transformer monitor and temporarily stored in the train's local data platform. The second sub-monitoring data is the monitoring data collected by the second transformer monitor and directly stored in the cloud server.

[0007] The target monitoring data is obtained by cleaning the first and second monitoring data.

[0008] The target monitoring data is input into a pre-trained fault diagnosis model to perform fault diagnosis evaluation on the railway power supply fault diagnosis system to obtain fault diagnosis results. The fault diagnosis results include at least a first diagnosis result and a second diagnosis result. The first diagnosis result indicates that the second transformer does not currently have a power supply fault or the current power supply fault of the second transformer is not affected by the first transformer. The second diagnosis result indicates that the current power supply fault of the second transformer is affected by the first transformer.

[0009] If the fault diagnosis result is the second diagnosis result, a power supply adjustment control command is sent to the first transformer to change the second diagnosis result into the first diagnosis result.

[0010] In one possible implementation, before obtaining the first monitoring data and the second monitoring data by acquiring the monitoring data from the first transformer monitor and the second transformer monitor, the method further includes:

[0011] According to the railway power supply fault diagnosis instruction, the first transformer monitor and the second transformer monitor are activated to monitor transformer status data;

[0012] Obtain the network status of the target train corresponding to the second transformer, the network status including normal network status and abnormal network status;

[0013] When the network status of the target train is abnormal, the monitoring data collected by the second transformer monitor is temporarily stored in the train's local data platform to obtain the first sub-monitoring data.

[0014] When the network status of the target train is normal, the monitoring data collected by the second transformer monitor is directly sent and stored on the cloud server to obtain the second sub-monitoring data.

[0015] In one possible implementation, the step of activating the first transformer monitor and the second transformer monitor to monitor transformer status data according to the railway power supply fault diagnosis command includes:

[0016] After starting the first transformer monitor and the second transformer monitor, adjust the sampling frequency of the first transformer monitor and / or the second transformer monitor according to the fluctuation range of the transformer status data;

[0017] When the fluctuation range of transformer status data is greater than or equal to the threshold, the sampling frequency is increased; when the fluctuation range of transformer status data is less than the threshold, the sampling frequency is decreased or the preset sampling frequency is maintained.

[0018] In one possible implementation, the step of activating the first transformer monitor and the second transformer monitor to monitor transformer status data according to the railway power supply fault diagnosis command includes:

[0019] After activating the first transformer monitor and the second transformer monitor, adjust the sampling frequency of the first transformer monitor and / or the second transformer monitor according to the vibration state of the target train;

[0020] When the vibration frequency of the target train is greater than or equal to the frequency threshold, the sampling frequency is increased; when the vibration frequency of the target train is less than the frequency threshold, the sampling frequency is decreased or the preset sampling frequency is maintained.

[0021] In one possible implementation, when the network status of the target train is abnormal, temporarily storing the monitoring data collected by the second transformer monitor in the train's local data platform to obtain the first sub-monitoring data includes:

[0022] The local storage capacity of the train local data platform is obtained in real time. When the local storage capacity reaches a preset threshold, the local storage data of the train local data platform is selectively filtered according to the data collection time order or importance level to obtain the data to be processed.

[0023] The first sub-monitoring data is quickly analyzed by the lightweight analysis unit of the train local data platform, and the key feature information in the analysis results is extracted and saved.

[0024] After the analysis is completed, the data to be processed is deleted or compressed for storage.

[0025] In one possible implementation, obtaining the network status of the target train corresponding to the second transformer includes:

[0026] Obtain the signal strength parameters, bandwidth parameters, and delay parameters of the target train network link;

[0027] The signal strength parameters, bandwidth parameters, and delay parameters of the target train network link are input into the network status evaluation model to obtain a comprehensive network status score.

[0028] If the comprehensive network status score is less than a preset threshold, the target train is determined to be in an abnormal network state; if the comprehensive network status score is greater than or equal to the preset threshold, the target train is determined to be in a normal network state. The network status evaluation model satisfies the following expression:

[0029] T = β1*X(S) + β2*Y(B) + β3*Z(D), where T is the comprehensive network state score, X(S), Y(B), and Z(D) are the normalization functions for signal strength, bandwidth, and delay, respectively, and β1, β2, and β3 are the weighting coefficients for the influence of network link signal strength, bandwidth, and delay on network state, respectively.

[0030]

[0031]

[0032] In one possible implementation, when the fault diagnosis result is a second diagnosis result, sending a power supply adjustment control command to the first transformer to change the second diagnosis result into a first diagnosis result includes:

[0033] If the second transformer still has a power supply fault when the power supply adjustment control of the first transformer is performed, a power supply fault self-check prompt message is sent to the target train corresponding to the second transformer.

[0034] In one possible implementation, the method further includes:

[0035] After sending a power supply adjustment control command to the first transformer, the power supply status changes of the second transformer and the changes in fault diagnosis results are monitored in real time.

[0036] If the power supply status of the second transformer does not change or the fault diagnosis result does not change within a preset time, the first transformer will be switched to the third transformer to use the third transformer for railway power supply.

[0037] In one possible implementation, the target monitoring data includes transformer electrical parameter data or transformer environmental parameter data. The electrical parameter data includes the transformer's output voltage and current, and the transformer environmental parameter data includes the transformer's temperature. The step of inputting the target monitoring data into a pre-trained fault diagnosis model to perform fault diagnosis evaluation on the railway power supply fault diagnosis system and obtain fault diagnosis results includes:

[0038] The electrical parameter data from the target monitoring data is input into a pre-trained first sub-fault diagnosis model to perform electrical parameter fault diagnosis evaluation on the railway power supply fault diagnosis system, thereby obtaining the fault diagnosis result; and / or,

[0039] The environmental parameter data from the target monitoring data is input into the pre-trained second sub-fault diagnosis model to perform environmental parameter fault diagnosis evaluation on the railway power supply fault diagnosis system and obtain the fault diagnosis result.

[0040] Secondly, this application provides a railway power supply fault diagnosis system, including: a memory and a processor, wherein the memory is used to store program code; and the processor is used to call the program code to execute the method described in the first aspect.

[0041] Unlike existing technologies, the railway power supply fault diagnosis scheme provided in this application consists of a first transformer, a first transformer monitor, a second transformer, a second transformer monitor, a train local data platform, and a cloud server. The first transformer is responsible for stepping up the mains power for railway power supply, and the second transformer steps down the railway power supply network to supply power to the train. In terms of the fault diagnosis method, monitoring data from the first and second transformer monitors are first acquired. The second monitoring data is stored in different ways depending on the train network status; when the network status does not meet preset conditions, it is stored in the train local data platform; when it does meet the conditions, it is directly stored in the cloud server. The acquired data is then cleaned, and the target monitoring data is input into a pre-trained fault diagnosis model for evaluation. This yields a fault diagnosis result that includes at least a first diagnosis result (indicating that the second transformer currently has no power supply fault or its fault is not affected by the first transformer) and a second diagnosis result (indicating that the second transformer's current power supply fault is affected by the first transformer). If the diagnosis is the second diagnosis result, a power supply adjustment control command is sent to the first transformer to try to convert it into the first diagnosis result. If the second transformer still has a power supply fault after adjustment, it can be determined that the fault of the second transformer is no longer affected by the first transformer. At this time, a power supply fault self-check prompt message is sent to the target train. This helps to promptly investigate potential problems of the train itself, further clarify the cause of the fault, improve the efficiency, accuracy and comprehensiveness of railway power supply fault diagnosis, and ensure the stable operation of the railway power supply system. Attached Figure Description

[0042] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the structures shown in these drawings without creative effort.

[0043] Figure 1 This is a schematic diagram illustrating the application scenarios of the railway power supply fault diagnosis method in some embodiments of this application;

[0044] Figure 2 This is a schematic diagram of the railway power supply fault diagnosis system in some embodiments of this application;

[0045] Figure 3 This is a flowchart illustrating the railway power supply fault diagnosis method in some embodiments of this application;

[0046] Figure 4 This is a flowchart illustrating a railway power supply fault diagnosis method in other embodiments of this application;

[0047] Figure 5 This is a schematic diagram of the hardware structure of a railway power supply fault diagnosis system in some embodiments of this application.

[0048] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0049] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0050] It should be noted that all directional indications (such as up, down, left, right, front, back, etc.) in the embodiments of the present invention are only used to explain the relative positional relationship and movement of each component in a certain specific posture (as shown in the figure). If the specific posture changes, the directional indication will also change accordingly.

[0051] Furthermore, the use of terms such as "first" and "second" in this invention is for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined with "first" or "second" may explicitly or implicitly include at least one of those features. Additionally, the term "and / or" throughout the text includes three solutions; taking A and / or B as an example, it includes technical solution A, technical solution B, and a technical solution that simultaneously satisfies A and B. Furthermore, the technical solutions of various embodiments can be combined with each other, but this must be based on the ability of a person skilled in the art to implement them. When the combination of technical solutions is contradictory or impossible to implement, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection claimed by this invention.

[0052] As a vital component of modern transportation, the stable operation of the railway power supply system is crucial for ensuring the safety, efficiency, and punctuality of railway operations. A railway power supply fault diagnosis system typically consists of multiple transformers, a complex power supply network, and related electrical equipment. The first transformer is responsible for stepping up the mains voltage to meet the long-distance power supply needs of the railway, while the second transformer steps down the railway power supply network to provide suitable voltage for the trains. However, due to the long length of railway lines, the large number of devices, and the complex and variable operating environment, the power supply system is prone to various faults. These faults not only affect the normal operation of trains but may even lead to safety accidents, causing significant economic losses and adverse social impacts on railway operations.

[0053] Traditional railway power supply fault diagnosis mainly relies on manual inspections and experience-based judgment. Maintenance personnel need to conduct regular on-site inspections of equipment such as transformers, identifying potential faults by observing the equipment's appearance and measuring electrical parameters. This approach has many drawbacks: for example, it is inefficient, manual inspections consume a lot of time and manpower, and it is difficult to achieve real-time monitoring and rapid diagnosis of the power supply system.

[0054] like Figure 1 As shown, this figure is a schematic diagram of the application scenario of the railway power supply fault diagnosis method in some embodiments of this application. It should be noted that this figure is a simplified schematic diagram of the railway power supply principle. In the figure, the first transformer 100 serves as the main transformer, and the third transformer 500 serves as the backup transformer; both are used to step up the mains power to achieve railway power supply. S1 represents the railway power supply network, S3 is the train pantograph, and S2 represents the rail. The train 300 is equipped with a second transformer 200, whose function is to step down the power transmitted from the railway power supply network S1, thereby providing suitable power to the train 300.

[0055] To solve the above problems, such as Figure 2 As shown, Figure 2 The diagram below shows the structure of a railway power supply fault diagnosis system in some embodiments of this application. This application provides a railway power supply fault diagnosis system, which includes a first transformer 100, a first transformer monitor 110, a first wireless gateway 120, a second transformer 200, a second transformer monitor 210, a second wireless gateway 220, a train local data platform 310, and a cloud server 400.

[0056] The system comprises two transformer monitoring devices: a first transformer monitor 110 for collecting status data of the first transformer 100, and a second transformer monitor 210 for collecting status data of the second transformer 200. The status data may include electrical parameters such as transformer output voltage and current, as well as environmental parameters such as transformer temperature. It may also include transformer image data. A first wireless gateway 120 transmits the status data of the first transformer 100 collected by the first transformer monitor 110 to the cloud server 400. A train local data platform 310 receives and temporarily stores the status data of the second transformer 200 collected by the second transformer monitor 210 when the train network status does not meet preset conditions. A second wireless gateway 220 transmits the status data of the second transformer 200 collected by the second transformer monitor 210, along with the temporarily stored data in the train local data platform 310, to the cloud server 400 when the train network status meets preset conditions. The cloud server 400 processes the received data to obtain target monitoring data and inputs this target monitoring data into a pre-trained fault diagnosis model to perform fault diagnosis evaluation on the railway power supply fault diagnosis system, obtaining the fault diagnosis result. The fault diagnosis result includes at least a first diagnosis result and a second diagnosis result. The first diagnosis result indicates that the second transformer does not currently have a power supply fault or that the current power supply fault of the second transformer is not affected by the first transformer. The second diagnosis result indicates that the current power supply fault of the second transformer is affected by the first transformer.

[0057] like Figures 1-4 As shown, the following explanation uses a railway power supply fault diagnosis system as an example to illustrate the execution of this railway power supply fault diagnosis method. It should be noted that although the logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here. Please refer to the appendix. Figure 3 The method includes the following steps S200-S800:

[0058] Step S200: Obtain monitoring data from the first transformer monitor and monitoring data from the second transformer monitor to obtain first monitoring data and second monitoring data. The second monitoring data includes first sub-monitoring data when the train's network status does not meet preset conditions and second sub-monitoring data when the train's network status meets preset conditions. The first sub-monitoring data is monitoring data collected by the second transformer monitor and temporarily stored in the train's local data platform. The second sub-monitoring data is monitoring data collected by the second transformer monitor and directly stored in the cloud server.

[0059] It is understood that the first and second monitoring data form the data foundation for railway power supply fault diagnosis. In other words, the first and second monitoring data provide an accurate data basis for diagnosing the fault status of the first and second transformers. This application utilizes the powerful computing capabilities of cloud servers and advanced diagnostic models to diagnose faults in railway power supply systems. However, the first and second monitoring data are typically local data, and because the train is in motion, the second monitoring data is highly susceptible to the influence of the train's current network status during transmission. Therefore, to prevent loss, packet loss, or damage during the transmission of the second monitoring data, in one embodiment, before obtaining the first and second monitoring data in step S200: acquiring the monitoring data from the first transformer monitor and the monitoring data from the second transformer monitor, the following further step is included:

[0060] Step S110: Activate the first transformer monitor and the second transformer monitor to monitor transformer status data according to the railway power supply fault diagnosis instruction;

[0061] Step S120: Obtain the network status of the target train corresponding to the second transformer, the network status including normal network status and abnormal network status;

[0062] Step S130: When the network status of the target train is abnormal, the monitoring data collected by the second transformer monitor is temporarily stored in the train's local data platform to obtain the first sub-monitoring data.

[0063] Step S140: When the network status of the target train is normal, the monitoring data collected by the second transformer monitor is directly sent and stored in the cloud server to obtain the second sub-monitoring data.

[0064] Specifically, firstly, according to the railway power supply fault diagnosis instruction, the first transformer monitor and the second transformer monitor are activated to begin collecting transformer status data. This is the foundation of the entire data processing flow. Simultaneously, the network status of the target train corresponding to the second transformer is acquired. Network status is divided into normal and abnormal states. If the target train's network status is abnormal, the monitoring data collected by the second transformer monitor will not be immediately sent to the cloud server. Instead, this data will be temporarily stored in the train's local data platform, forming the first sub-monitoring data. This prevents data loss or corruption in the event of network instability. If the target train's network status is normal, the monitoring data collected by the second transformer monitor will be directly sent to and stored on the cloud server, forming the second sub-monitoring data. After completing the above steps, the monitoring data from the first transformer monitor (i.e., the first monitoring data) and the monitoring data from the second transformer monitor (including the first and second sub-monitoring data, which are merged into the second monitoring data) can be obtained. This data will be used in subsequent fault diagnosis processes.

[0065] In one embodiment, step S110, which involves activating the first transformer monitor and the second transformer monitor to monitor transformer status data according to the railway power supply fault diagnosis instruction, includes: after activating the first transformer monitor and the second transformer monitor, adjusting the sampling frequency of the first transformer monitor and / or the second transformer monitor according to the fluctuation amplitude of the transformer status data; increasing the sampling frequency when the fluctuation amplitude of the transformer status data is greater than or equal to a threshold, and decreasing the sampling frequency or maintaining a preset sampling frequency when the fluctuation amplitude of the transformer status data is less than the threshold.

[0066] Specifically, according to the railway power supply fault diagnosis instruction, the first transformer monitor and the second transformer monitor are activated to begin collecting transformer status data. After the monitors are activated, the sampling frequency can be dynamically adjusted based on the fluctuation range of the transformer status data. When the fluctuation range of the transformer status data is greater than or equal to a preset threshold, the sampling frequency is increased. This ensures that more data points can be captured when the transformer status changes significantly, thus more accurately reflecting the actual state of the transformer. When the fluctuation range of the transformer status data is less than the threshold, the sampling frequency is decreased or the preset sampling frequency is maintained. This reduces unnecessary data collection, lowers the data transmission load, and improves data processing efficiency. In other embodiments, the sampling frequency can also be adjusted according to the train network status. For example, when the train network status is good (e.g., low network latency, low packet loss rate), the sampling frequency can be appropriately increased to collect transformer status data more frequently, thereby more accurately reflecting the real-time status of the transformer. When the train network status is poor (e.g., high network latency, high packet loss rate), the sampling frequency can be appropriately decreased to reduce the data transmission failure rate and load. This reduces unnecessary data collection and transmission, improving data processing efficiency.

[0067] In another embodiment, step S110: starting the first transformer monitor and the second transformer monitor to monitor transformer status data according to the railway power supply fault diagnosis instruction includes: after starting the first transformer monitor and the second transformer monitor, adjusting the sampling frequency of the first transformer monitor and / or the second transformer monitor according to the vibration state of the target train; increasing the sampling frequency when the vibration frequency of the target train is greater than or equal to a frequency threshold, and decreasing the sampling frequency or maintaining a preset sampling frequency when the vibration frequency of the target train is less than the frequency threshold.

[0068] Specifically, based on the railway power supply fault diagnosis instruction, the first and second transformer monitors are activated to begin collecting transformer status data. Simultaneously, the vibration status of the target train is monitored after the monitors are activated. This can be achieved, for example, through vibration sensors installed on the train. When the train's vibration frequency is greater than or equal to a preset frequency threshold, it indicates that the train may be in an unstable or high-speed running state; in this case, the sampling frequency of the transformer monitors should be increased. This allows for more frequent data collection to capture potential changes in transformer status caused by vibration. When the train's vibration frequency is less than the frequency threshold, it indicates that the train is in a relatively stable or low-speed running state; in this case, the sampling frequency can be appropriately reduced or maintained at the preset sampling frequency. This reduces unnecessary data collection and lowers the data processing load.

[0069] In one embodiment, step S130: when the network status of the target train is abnormal, temporarily storing the monitoring data collected by the second transformer monitor in the train local data platform to obtain the first sub-monitoring data includes: real-time acquisition of the local storage capacity of the train local data platform; when the local storage capacity reaches a preset threshold, selectively filtering the local storage data of the train local data platform according to the data collection time order or importance level to obtain the data to be processed; quickly analyzing the first sub-monitoring data through the lightweight analysis unit of the train local data platform, and extracting and saving the key feature information in the analysis results; after the analysis is completed, deleting or compressing the data to be processed.

[0070] Specifically, based on the railway power supply fault diagnosis instruction, the first and second transformer monitors are activated to begin collecting transformer status data. Simultaneously, the network status of the target train is assessed for abnormalities. When the train's network status is abnormal, the local storage capacity information of the train's local data platform is acquired in real time. When the local storage capacity reaches a preset threshold, to prevent data overflow or loss, the locally stored data in the train's local data platform can be selectively filtered according to the data collection time sequence or importance level. This ensures that the latest or most important data is retained, while older or less important data is deleted or compressed. To prevent data deletion from affecting the data analysis results, the lightweight analysis unit of the train's local data platform can be used to quickly analyze the first sub-monitoring data. The purpose of the analysis is to extract key feature information from the data, which is crucial for subsequent fault diagnosis (providing a certain reference basis for subsequent complete data analysis). The extracted key feature information can be saved separately for quick access when needed. After the analysis is completed, the filtered data to be processed is deleted or compressed for storage. Deletion frees up storage space, while compression reduces the data's footprint while preserving its integrity.

[0071] In one embodiment, step S120: obtaining the network status of the target train corresponding to the second transformer includes: obtaining the signal strength parameters, bandwidth parameters, and delay parameters of the target train's network link; inputting the signal strength parameters, bandwidth parameters, and delay parameters of the target train's network link into a network status evaluation model to obtain a comprehensive network status score; determining that the comprehensive network status score is less than a preset threshold, indicating that the target train is in an abnormal network state; determining that the comprehensive network status score is greater than or equal to the preset threshold, indicating that the target train is in a normal network state; the network status evaluation model satisfies the following expression:

[0072] T = β1*X(S) + β2*Y(B) + β3*Z(D), where T is the comprehensive network status score, X(S), Y(B), and Z(D) are the normalization functions for signal strength, bandwidth, and delay, respectively, and β1, β2, and β3 are the weighting coefficients for the influence of network link signal strength, bandwidth, and delay on network status, respectively.

[0073] In one embodiment, the functions X(S), Y(B), and Z(D) are expressed as follows:

[0074]

[0075] Specifically, when the signal strength S is less than or equal to the minimum signal strength S min When the signal strength is below a certain lower limit, X(S) = 0. This indicates that if the signal strength is below a certain lower limit, its normalized score is 0. When the signal strength S is at the minimum signal strength S... min and maximum signal strength S max When the signal strength is between 0 and 1, the signal strength is linearly mapped to the range of 0 to 1. When the signal strength S is greater than or equal to the maximum signal strength Smax... max When X(S) = 1, it indicates that if the signal strength is higher than a certain upper limit, its normalized score is 1. Since the bandwidth B has a very large range, from very low bandwidth (e.g., a few kbps) to very high bandwidth (e.g., several Gbps or even higher), the logarithmic function can compress this large range of data into a relatively small range, making it easier to process and compare. Its normalization process is similar to that of the signal strength normalization process, and will not be elaborated here. Similarly, the normalization process for delay will also not be elaborated here. It can be understood that when the comprehensive network status score exceeds the preset threshold, it indicates that the train's network status is normal; when the comprehensive network status score is lower than the preset threshold, it indicates that the train's network status is abnormal.

[0076] It should be noted that since transformer monitoring instruments may collect large amounts of data such as images, the bandwidth requirements for this type of data transmission are high. In this embodiment, the value of β2 is appropriately increased to make the network status assessment model more reasonable, that is, β1 is 0.3, β2 is 0.4, and β3 is 0.3.

[0077] In this embodiment, by combining the normalization processing functions of signal strength, bandwidth, and delay with their respective weighting coefficients, the network status assessment model can comprehensively consider the impact of these three key network parameters on the train network status. This allows for a simple and effective determination of whether the train is in a normal network state, providing a strong basis for train network management and power supply fault diagnosis.

[0078] Step S400: Perform data cleaning processing on the first monitoring data and the second monitoring data to obtain the target monitoring data;

[0079] Specifically, data cleaning can include, but is not limited to, processing duplicate records, missing data, outliers, or erroneous data. For example, for missing data, processing strategies can be formulated based on the missing percentage and the importance of the field. Unimportant fields or data with excessively high missing rates are directly deleted. Important fields or data with a reasonable missing rate are imputed. Imputation methods include mean imputation, median imputation, mode imputation, interpolation, or predictive model imputation.

[0080] Step S600: Input the target monitoring data into the pre-trained fault diagnosis model to perform fault diagnosis evaluation on the railway power supply fault diagnosis system to obtain fault diagnosis results. The fault diagnosis results include at least a first diagnosis result and a second diagnosis result. The first diagnosis result indicates that the second transformer does not currently have a power supply fault or the current power supply fault of the second transformer is not affected by the first transformer. The second diagnosis result indicates that the current power supply fault of the second transformer is affected by the first transformer.

[0081] In one embodiment, the target monitoring data includes transformer electrical parameter data or transformer environmental parameter data. The electrical parameter data includes the transformer's output voltage and current, and the transformer environmental parameter data includes the transformer's temperature. Step S600, which involves inputting the target monitoring data into a pre-trained fault diagnosis model to perform fault diagnosis evaluation on the railway power supply fault diagnosis system and obtain fault diagnosis results, includes: inputting the electrical parameter data from the target monitoring data into a pre-trained first sub-fault diagnosis model to perform electrical parameter fault diagnosis evaluation on the railway power supply fault diagnosis system and obtain fault diagnosis results; and / or, inputting the environmental parameter data from the target monitoring data into a pre-trained second sub-fault diagnosis model to perform environmental parameter fault diagnosis evaluation on the railway power supply fault diagnosis system and obtain fault diagnosis results.

[0082] Specifically, electrical parameter data from the target monitoring data can be input into a pre-trained first sub-fault diagnosis model to perform electrical parameter fault diagnosis and assessment on the railway power supply fault diagnosis system, thereby obtaining corresponding fault diagnosis results. Alternatively, environmental parameter data from the target monitoring data can be input into a pre-trained second sub-fault diagnosis model to perform environmental parameter fault diagnosis and assessment on the railway power supply fault diagnosis system, ultimately obtaining relevant fault diagnosis results. This allows for more targeted diagnosis and assessment using specialized sub-fault diagnosis models based on different types of parameter data, improving the accuracy and effectiveness of fault diagnosis and providing more reliable guarantees and support for the stable operation of the railway power supply system.

[0083] For example, suppose that in a railway power supply system, the first transformer (main transformer) is operating normally, with its output voltage stable at the rated value and the current within the normal range. The electrical parameters monitored by the second transformer (train transformer) are as follows: the output voltage is 80% of the normal supply voltage, and the current is slightly higher than during normal operation. Meanwhile, environmental parameters show that the temperature of the second transformer is 60 degrees Celsius, within the normal operating temperature range. Inputting these electrical parameters into a pre-trained first sub-fault diagnosis model, the model analyzes and calculates, finding that the decrease in the output voltage of the second transformer is likely due to a sudden increase in the train's load (such as a large number of passengers simultaneously using high-power electrical appliances), and the increase in current is a normal response to the increased load. Furthermore, the output voltage and current of the first transformer are both normal. Therefore, the first diagnostic result is that the second transformer currently does not have a power supply fault, or its current power supply fault is not affected by the first transformer.

[0084] For example, if the output voltage of the first transformer suddenly drops by 20%, the output voltage of the second transformer will also drop significantly, making it almost impossible to supply power to the train normally. Simultaneously, the current in the second transformer will fluctuate abnormally, and the transformer temperature will rise rapidly in the environmental parameters. After inputting this data into the first and second sub-fault diagnosis models respectively, the first sub-fault diagnosis model finds a clear correlation between the fault in the second transformer and the abnormal drop in the output voltage of the first transformer. The second sub-fault diagnosis model also fails to detect faults caused by environmental factors within the second transformer itself. Therefore, the second diagnostic result is that the current power supply fault of the second transformer is affected by the first transformer.

[0085] Step S800: If the fault diagnosis result is the second diagnosis result, send a power supply adjustment control command to the first transformer to change the second diagnosis result into the first diagnosis result.

[0086] After sending a power supply adjustment control command to the first transformer, aiming to convert it into a first diagnostic result, two possible outcomes may occur: the second transformer resumes normal power supply or the second transformer still has a power supply fault. Therefore, in one embodiment, after sending the power supply adjustment control command to the first transformer, the changes in the power supply status of the second transformer and the change in the fault diagnosis result can be monitored in real time. If the second transformer resumes normal power supply within a preset time, no further measures are required. If the power supply status of the second transformer does not change or the fault diagnosis result does not change within the preset time (the second transformer still has a power supply fault), it may be that the power supply fault of the first transformer cannot be automatically eliminated. In this case, the first transformer can be switched to the third transformer to utilize the third transformer for railway power supply.

[0087] In another embodiment, step S800: when the fault diagnosis result is the second diagnosis result, sending a power supply adjustment control command to the first transformer to change the second diagnosis result into the first diagnosis result includes: when the power supply adjustment control is performed on the first transformer, if the second transformer still has a power supply fault, sending a power supply fault self-check prompt information to the target train corresponding to the second transformer.

[0088] Specifically, if the diagnosis is the second diagnostic result, a power supply adjustment control command is sent to the first transformer to try to convert it into the first diagnostic result. If the second transformer still has a power supply fault after adjustment, it can be determined that the fault of the second transformer is no longer affected by the first transformer. At this time, a power supply fault self-check prompt message is sent to the target train. This helps to promptly investigate potential problems of the train itself, further clarify the cause of the fault, improve the accuracy and comprehensiveness of railway power supply fault diagnosis, and ensure the stable operation of the railway power supply system.

[0089] Based on this, the railway power supply fault diagnosis scheme provided in this application consists of a first transformer, a first transformer monitor, a second transformer, a second transformer monitor, a train local data platform, and a cloud server. The first transformer is responsible for stepping up the mains power for railway power supply, and the second transformer steps down the railway power supply network to supply power to the train. In terms of the fault diagnosis method, monitoring data from the first and second transformer monitors are first acquired. The second monitoring data is stored in different ways depending on the train network status; when the network status does not meet preset conditions, it is stored in the train local data platform; when it does meet the conditions, it is directly stored in the cloud server. Then, the acquired data is cleaned, and the target monitoring data is input into a pre-trained fault diagnosis model for evaluation. This yields a fault diagnosis result that includes at least a first diagnosis result (indicating that the second transformer currently has no power supply fault or its fault is not affected by the first transformer) and a second diagnosis result (indicating that the second transformer's current power supply fault is affected by the first transformer). If the diagnosis is the second diagnosis result, a power supply adjustment control command is sent to the first transformer to try to convert it into the first diagnosis result. If the second transformer still has a power supply fault after adjustment, it can be determined that the fault of the second transformer is no longer affected by the first transformer. At this time, a power supply fault self-check prompt message is sent to the target train. This helps to promptly investigate potential problems of the train itself, further clarify the cause of the fault, improve the efficiency, accuracy and comprehensiveness of railway power supply fault diagnosis, and ensure the stable operation of the railway power supply system.

[0090] like Figure 5 As shown, Figure 5The diagram below shows the hardware structure of a railway power supply fault diagnosis system in some embodiments of this application. The railway power supply fault diagnosis system provided in the embodiments of this application further includes a memory 1000 and a processor 2000. The memory 1000 is used to store computer-readable instructions, and the processor 2000 is used to call the computer-readable instructions to execute the railway power supply fault diagnosis method as described above.

[0091] The processor 2000 provides computing and control capabilities to control the railway power supply fault diagnosis system to perform corresponding tasks. For example, it controls the railway power supply fault diagnosis system to perform the railway power supply fault diagnosis method in any of the above method embodiments. The method includes: acquiring monitoring data from a first transformer monitor and monitoring data from a second transformer monitor to obtain first monitoring data and second monitoring data. The second monitoring data includes first sub-monitoring data when the train's network status does not meet preset conditions and second sub-monitoring data when the train's network status meets preset conditions. The first sub-monitoring data is monitoring data collected by the second transformer monitor and temporarily stored in the train's local data platform. The second sub-monitoring data is monitoring data collected by the second transformer monitor and directly stored. The monitoring data is collected from the cloud server; the first and second monitoring data are cleaned to obtain target monitoring data; the target monitoring data is input into a pre-trained fault diagnosis model to perform fault diagnosis evaluation on the railway power supply fault diagnosis system to obtain fault diagnosis results, wherein the fault diagnosis results include at least a first diagnosis result and a second diagnosis result, the first diagnosis result indicating that the second transformer currently has no power supply fault or the current power supply fault of the second transformer is not affected by the first transformer, and the second diagnosis result indicating that the current power supply fault of the second transformer is affected by the first transformer; if the fault diagnosis result is the second diagnosis result, a power supply adjustment control command is sent to the first transformer to change the second diagnosis result into the first diagnosis result.

[0092] The processor 2000 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), a hardware chip, or any combination thereof; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The aforementioned PLD can be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL), or any combination thereof.

[0093] The memory 1000, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs, non-transitory computer-executable programs, and modules, such as the program instructions / modules corresponding to the railway power supply fault diagnosis method in the embodiments of this application. The processor 2000 can implement the railway power supply fault diagnosis method in any of the above method embodiments by running the non-transitory software programs, instructions, and modules stored in the memory 1000.

[0094] Specifically, memory 1000 may include volatile memory (VM), such as random access memory (RAM); memory 1000 may also include non-volatile memory (NVM), such as read-only memory (ROM), flash memory, hard disk drive (HDD), solid-state drive (SSD), or other non-transitory solid-state storage devices; memory 1000 may also include combinations of the above types of memory.

[0095] In summary, the railway power supply fault diagnosis system of this application adopts the technical solution of any of the above-mentioned railway power supply fault diagnosis method embodiments. Therefore, it has at least the beneficial effects brought about by the technical solutions of the above embodiments, which will not be elaborated here.

[0096] This application also provides a computer-readable storage medium, such as a memory including program code, which can be executed by a processor to complete the railway power supply fault diagnosis method described in the above embodiments. For example, the computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a compact disc read-only memory (CDROM), magnetic tape, floppy disk, and optical data storage device, etc.

[0097] This application also provides a computer program product comprising one or more lines of program code stored in a computer-readable storage medium. The processor of the railway power supply fault diagnosis system reads the program code from the computer-readable storage medium and executes the program code to complete the steps of the railway power supply fault diagnosis method provided in the above embodiments.

[0098] Those skilled in the art will understand that all or part of the steps of the above embodiments can be implemented by hardware, or by a program or program code related to hardware. The program can be stored in a computer-readable storage medium, such as a read-only memory, a disk, or an optical disk.

[0099] It should be noted that the device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0100] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented using software and a general-purpose hardware platform, or of course, using hardware. Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), or random access memory (RAM), etc.

[0101] The above description is merely a preferred embodiment of the present invention and does not limit the patent scope of the present invention. Any equivalent structural transformations made using the contents of the present invention's specification and drawings under the inventive concept of the present invention, or direct / indirect applications in other related technical fields, are included within the patent protection scope of the present invention.

Claims

1. A method of diagnosing a power supply failure of a railway, characterized by, The application is applied to a railway power supply fault diagnosis system, the railway power supply fault diagnosis system comprises a first transformer, a first transformer monitor, a second transformer, a second transformer monitor, a train local data center and a cloud server, the first transformer is used for step-up processing of commercial power to supply power to the railway, the second transformer is used for step-down processing of the railway power supply network to supply power to the train, and the method comprises: obtaining monitoring data of the first transformer monitor and monitoring data of the second transformer monitor to obtain first monitoring data and second monitoring data, wherein the second monitoring data comprises first sub-monitoring data of the train under the condition that the network state does not meet the preset condition and second sub-monitoring data of the train under the condition that the network state meets the preset condition, the first sub-monitoring data is monitoring data collected by the second transformer monitor and temporarily stored in the train local data center, and the second sub-monitoring data is monitoring data collected by the second transformer monitor and directly stored in the cloud server; performing data cleaning processing on the first monitoring data and the second monitoring data to obtain target monitoring data; inputting the target monitoring data into a pre-trained fault diagnosis model to perform fault diagnosis evaluation on the railway power supply fault diagnosis system to obtain a fault diagnosis result; wherein the fault diagnosis result at least comprises a first diagnosis result and a second diagnosis result, the first diagnosis result indicates that there is no power supply fault in the second transformer at present or the current power supply fault of the second transformer is not affected by the first transformer, and the second diagnosis result indicates that the current power supply fault of the second transformer is affected by the first transformer; in the case that the fault diagnosis result is the second diagnosis result, sending a power supply adjustment control instruction to the first transformer to make the second diagnosis result change to the first diagnosis result; the method further comprises: after sending the power supply adjustment control instruction to the first transformer, monitoring the power supply state change of the second transformer and the change of the fault diagnosis result in real time; if the power supply state of the second transformer does not change or the fault diagnosis result does not change within a preset time, the first transformer is switched to a third transformer to supply power to the railway by using the third transformer.

2. The method of diagnosing a power supply fault of a railway according to claim 1, wherein before the method of obtaining the monitoring data of the first transformer monitor and the monitoring data of the second transformer monitor to obtain the first monitoring data and the second monitoring data, the method further comprises: starting the first transformer monitor and the second transformer monitor to monitor the transformer state data according to the railway power supply fault diagnosis instruction; obtaining the network state of the target train corresponding to the second transformer, the network state comprises a normal network state and an abnormal network state; in the case that the network state of the target train is the abnormal state, temporarily storing the monitoring data collected by the second transformer monitor in the train local data center to obtain the first sub-monitoring data; in the case that the network state of the target train is the normal state, directly sending and storing the monitoring data collected by the second transformer monitor in the cloud server to obtain the second sub-monitoring data.

3. The method of diagnosing a power supply fault of a railway according to claim 2, wherein The first transformer monitor and the second transformer monitor are started to monitor transformer state data according to the railway power supply fault diagnosis instruction, and the starting includes: After starting the first transformer monitor and the second transformer monitor, the sampling frequency of the first transformer monitor and / or the second transformer monitor is adjusted according to the fluctuation amplitude of the transformer state data; When the fluctuation amplitude of the transformer state data is greater than or equal to a threshold value, the sampling frequency is increased, and when the fluctuation amplitude of the transformer state data is less than the threshold value, the sampling frequency is decreased or a preset sampling frequency is maintained.

4. The method of diagnosing a power supply fault of a railway of claim 2, wherein, The first transformer monitor and the second transformer monitor are started to monitor transformer state data according to the railway power supply fault diagnosis instruction, and the starting includes: After starting the first transformer monitor and the second transformer monitor, the sampling frequency of the first transformer monitor and / or the second transformer monitor is adjusted according to the vibration state of the target train; When the vibration frequency of the target train is greater than or equal to a frequency threshold value, the sampling frequency is increased, and when the vibration frequency of the target train is less than the frequency threshold value, the sampling frequency is decreased or a preset sampling frequency is maintained.

5. The method of diagnosing a power supply fault of a railway of claim 2, wherein, In the case that the network state of the target train is an abnormal state, the monitoring data collected by the second transformer monitor is temporarily stored in the train local data center to obtain first sub-monitoring data, and the obtaining includes: The local storage capacity of the train local data center is acquired in real time, and when the local storage capacity reaches a preset threshold value, the local storage data of the train local data center is selectively filtered according to the collection time sequence or importance level of the data to obtain to-be-processed data; The first sub-monitoring data is quickly analyzed by a lightweight analysis unit of the train local data center, and key feature information in the analysis result is extracted and saved; After the analysis is completed, the to-be-processed data is deleted or compressed and stored.

6. The method of diagnosing a power supply fault of a railway of claim 2, wherein, The network state of the target train corresponding to the second transformer is acquired, and the acquiring includes: Signal strength parameters, bandwidth parameters, and delay parameters of the target train network link are acquired; The signal strength parameters, bandwidth parameters, and delay parameters of the target train network link are input into a network state evaluation model to obtain a network state comprehensive score value; It is determined that the target train is in a network abnormal state when the network state comprehensive score value is less than a preset threshold value, and it is determined that the target train is in a network normal state when the network state comprehensive score value is greater than or equal to the preset threshold value; the network state evaluation model satisfies the following expression: T = β1*X(S) + β2*Y(B) + β3*Z(D), wherein T is a network state comprehensive score value, functions X(S), Y(B), and Z(D) are normalization processing functions of signal strength, bandwidth, and delay respectively, β1, β2, and β3 are influence weight coefficients of network link signal strength, bandwidth, and delay on network state; and 7. The method of diagnosing a power supply fault of a railway of claim 1, wherein, In the case that the fault diagnosis result is a second diagnosis result, a power supply adjustment control instruction is sent to the first transformer to make the second diagnosis result change into a first diagnosis result, and the sending includes: In the case of power supply adjustment control of the first transformer, if the second transformer still has a power supply failure, a power supply failure self-check prompt message is sent to a target train corresponding to the second transformer.

8. The method of diagnosing a power supply fault of a railway of claim 1, wherein, The third transformer is a backup transformer, which is used to boost the mains to supply power to the railway.

9. The method of diagnosing a power supply fault of a railway of claim 1, wherein, The target monitoring data includes transformer electrical parameter data or transformer environmental parameter data, the electrical parameter data includes the output voltage and current of the transformer, and the transformer environmental parameter data includes the temperature of the transformer. The electrical parameter data in the target monitoring data is input into a pre-trained first sub-fault diagnosis model to perform electrical parameter fault diagnosis evaluation on the railway power supply fault diagnosis system to obtain a fault diagnosis result; and / or The environmental parameter data in the target monitoring data is input into a pre-trained second sub-fault diagnosis model to perform environmental parameter fault diagnosis evaluation on the railway power supply fault diagnosis system to obtain a fault diagnosis result.

10. A railway power supply fault diagnostic system characterized by comprising: Comprise: a memory and a processor, the memory being used to store program code; The processor is used to call the program code to execute the method of any one of claims 1 to 9.

Images