A fault detection method of a railway transformer box, an electronic device and a storage medium

Abstract

This application relates to the field of substation fault detection technology, and discloses a fault detection method, electronic equipment, and storage medium for railway substations. This application, considering the operating conditions of railway substations along the railway line, adopts a temperature acquisition frequency positively correlated with the frequency of train passage. This accurately captures the impact of external excitation on the substation temperature when trains pass, improving the relevance and effectiveness of temperature data acquisition. By maximizing heat dissipation intervention and calculating the temperature drop coefficient, it can clearly distinguish whether the excessive temperature is due to a fault in the heat dissipation system itself or other factors causing heat dissipation failure. This solves the problem in related technologies where temperature monitoring alone cannot determine the root cause of excessive temperature and results in low fault detection accuracy. Simultaneously, by introducing vibration parameters and the temperature drop coefficient for joint judgment, it accurately identifies coupled thermal faults caused by vibration, achieving precise fault type localization and avoiding misjudgment and missed judgment.

Description

Technical Field

[0001] This invention relates to the field of substation fault detection technology, specifically to a fault detection method, electronic equipment, and storage medium for railway substations. Background Technology

[0002] As a core component of my country's transportation system, the safe and stable operation of railways is directly related to the safety of people's travel and the smooth flow of national logistics. The railway power supply system is the "lifeline" that ensures the normal operation of railways. Among them, railway substations, as key nodes of the power supply system, undertake the important functions of power conversion, distribution and equipment protection. They are widely distributed along the railway line, with one set every few kilometers, directly providing a stable power supply for loads such as railway communication, signaling and train operation equipment, tunnel lighting and police stations along the line. The reliability of their operation directly determines the overall stability and safety of the railway power supply system.

[0003] Railway substations are characterized by prefabrication, flexible assembly, intelligence, and enclosure safety. They integrate various power devices such as high-voltage switchgear, transformers, and low-voltage power distribution equipment. During long-term operation, these devices are inevitably affected by complex operating conditions, which can easily lead to various faults, such as thermal faults caused by overheating.

[0004] In related technologies, temperature monitoring alone cannot determine whether the excessive temperature is due to a fault in the heat dissipation system itself or a coupling problem caused by heat dissipation failure due to other reasons. This results in low accuracy in fault detection of railway substations and fails to meet the requirements for safe and reliable operation of railway power supply systems. Summary of the Invention

[0005] The main objective of this invention is to provide a fault detection method, electronic device, and storage medium for railway substations, aiming to solve the technical problem of low accuracy in fault detection of railway substations in the prior art.

[0006] To achieve the above objectives, in a first aspect, this application provides a fault detection method for railway substations, the method comprising:

[0007] The temperature data of the target power devices inside the transformer box is obtained to obtain the first target temperature, where the temperature acquisition frequency is positively correlated with the frequency of railway train passage;

[0008] If the first target temperature is greater than or equal to the warning temperature, the heat dissipation power of the built-in cooling fan of the transformer box is increased to the preset maximum power. After the maximum heat dissipation power is maintained for a preset time, the temperature data of the target power device is acquired again to obtain the second target temperature.

[0009] A first temperature drop coefficient is determined based on the second target temperature and the first target temperature. The first temperature drop coefficient characterizes the temperature drop capability of the target power device under maximum heat dissipation intervention.

[0010] The target vibration parameters of the target power device are obtained, and the target vibration parameters include at least one of the external excitation vibration parameters when a railway train passes by and the electromagnetic vibration parameters of the target power device itself.

[0011] If the first temperature drop coefficient is less than or equal to the temperature drop coefficient threshold, and the target vibration parameter is greater than the vibration parameter threshold, it is determined that the substation has a coupled thermal fault caused by vibration.

[0012] The fault detection method for railway substations as described in claim 1, characterized in that, obtaining the target vibration parameters of the target electrical device includes:

[0013] The first vibration parameter and the second vibration parameter are obtained by acquiring the external excitation vibration parameters when the railway train passes by and the electromagnetic vibration parameters of the target power device itself.

[0014] The first vibration parameter and the second vibration parameter are fused to obtain the target vibration parameter.

[0015] In one possible implementation, the vibration parameters include the energy value of the corresponding frequency band after the vibration signal has undergone time-frequency transformation, and the fusion processing of the first vibration parameters and the second vibration parameters to obtain the target vibration parameters includes:

[0016] Obtain the transit time identifier of the railway train, which is used to distinguish whether the current time belongs to the transit time of the train or the non-transit time of the train;

[0017] The first vibration parameter and the second vibration parameter are transformed by time and frequency to extract the energy time series data of the first frequency band corresponding to the external excitation and the energy time series data of the second frequency band corresponding to the electromagnetic vibration of the power device, respectively.

[0018] If the current time is within the train passing period, then the preset first weighting coefficient and second weighting coefficient are obtained. Within the time window of the train passing period, the first frequency band energy time series data and the second frequency band energy time series data are weighted and fused and energy aggregated to obtain the first fused total energy value as the target vibration parameter.

[0019] If the current time is within a period when the train has not yet passed through, then within the preset vibration monitoring time window, the energy time series data of the second frequency band is aggregated and calculated to obtain the total energy value of the second frequency band as the target vibration parameter.

[0020] In one possible implementation, after obtaining the target vibration parameters of the target power device, the method further includes:

[0021] If the first temperature drop coefficient is less than or equal to the temperature drop coefficient threshold, and the target vibration parameter is less than or equal to the vibration parameter threshold, it is determined that the substation has a conventional thermal fault.

[0022] If the first temperature drop coefficient is determined to be greater than the temperature drop coefficient threshold, it is determined that there is no thermal fault in the transformer box.

[0023] In one possible implementation, the railway substation is provided with a heat dissipation flap and a wind direction sensor on its side. The heat dissipation flap includes a first heat dissipation flap on the left side and a second heat dissipation flap on the right side. After determining that the substation has a coupled thermal fault caused by vibration, the method further includes:

[0024] The wind direction information of the environment in which the railway substation is located is obtained based on the wind direction sensor.

[0025] Based on the wind direction information, the opening angles of the first heat dissipation flap and the second heat dissipation flap are determined to obtain the first target angle and the second target angle.

[0026] The first and second heat dissipation flip plates are opened according to the first and second target angles to assist the railway substation in heat dissipation.

[0027] After the heat dissipation cover is opened and continues to assist in heat dissipation for a preset time, the temperature data of the target power device is acquired again to obtain the third target temperature;

[0028] A second temperature drop coefficient is determined based on the first target temperature and the third target temperature, and the determination result of the coupled thermal fault caused by the vibration is verified according to the second temperature drop coefficient.

[0029] In one possible implementation, verifying the determination result of the vibration-induced coupled thermal fault based on the second temperature drop coefficient includes:

[0030] The second temperature drop coefficient is compared with a preset temperature drop coefficient threshold.

[0031] If the second temperature drop coefficient is less than the temperature drop coefficient threshold, the determination result of the coupled thermal fault caused by vibration is confirmed, and a first-level maintenance warning is generated. The first-level maintenance warning is used to prompt the mechanical connection status check or electromagnetic component status check of the target power device.

[0032] In one possible implementation, after generating the Level 1 maintenance early warning, the method further includes:

[0033] Obtain the historical temperature variation curve and historical vibration parameter variation curve of the target power device;

[0034] Based on the historical variation curves, the current temperature drop coefficient, and the target vibration parameters, a fault development trend model is constructed.

[0035] Based on the fault development trend model, predict the remaining time window for the vibration-induced coupled thermal fault to develop from its current state to a severe fault;

[0036] If the remaining time window is less than a preset safe time threshold, a level two emergency warning is generated, which is used to prompt immediate maintenance.

[0037] In one possible implementation, determining the opening angles of the first and second heat dissipation flaps based on the wind direction information to obtain the first target angle and the second target angle includes:

[0038] Based on the wind direction information, determine the angle between the wind direction and the normal direction of the side of the railway substation;

[0039] Based on the included angle, the current wind direction is determined relative to the incoming direction of the railway substation. The side directly exposed to the wind is determined as the air intake side, and the other side is determined as the air outlet side.

[0040] If the left side of the first heat dissipation flip plate is the air intake side, then the first target angle of the first heat dissipation flip plate is set to the air intake guide angle parallel to the airflow direction according to the included angle; at the same time, the second target angle of the second heat dissipation flip plate is set to the air outlet heat exhaust angle of 90° so that the right side is completely open to form a heat exhaust channel.

[0041] If the right side of the second heat dissipation flip plate is the air intake side, then the second target angle of the second heat dissipation flip plate is set to the air intake guide angle parallel to the airflow direction according to the included angle; at the same time, the first target angle of the first heat dissipation flip plate is set to the air outlet heat exhaust angle of 90° so that the left side is completely open to form a heat exhaust channel.

[0042] In one possible implementation, the first temperature drop coefficient is calculated using the formula K=(T1-T2) / T1×100%, where T1 is the first target temperature and T2 is the second target temperature.

[0043] Secondly, embodiments of this application also provide an electronic device, including:

[0044] Memory, the memory being used to store program code; and

[0045] A processor, the processor being configured to invoke the program code to execute the method as described in the first aspect.

[0046] Thirdly, embodiments of this application also provide a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the method described in the first aspect.

[0047] Unlike existing technologies, the fault detection method for railway substations provided in this application first acquires temperature data of the target power device inside the substation to obtain a first target temperature, wherein the temperature acquisition frequency is positively correlated with the frequency of railway train passage; when the first target temperature is greater than or equal to a warning temperature, the heat dissipation power of the built-in cooling fan in the substation is increased to a preset maximum power, and after maintaining the maximum heat dissipation power for a preset duration, the temperature data of the target power device is acquired again to obtain a second target temperature; a first temperature drop coefficient is determined based on the second target temperature and the first target temperature, the first temperature drop coefficient characterizing the temperature reduction capability of the target power device under maximized heat dissipation intervention; target vibration parameters of the target power device are acquired, the target vibration parameters including at least one of external excitation vibration parameters when railway trains pass and electromagnetic vibration parameters of the target power device itself; if the first temperature drop coefficient is less than or equal to a temperature drop coefficient threshold, and the target vibration parameter is greater than a vibration parameter threshold, it is determined that the substation has a coupled thermal fault caused by vibration. Thus, this application, combining the operating conditions of railway substations along the railway line, adopts a temperature acquisition frequency positively correlated with the frequency of train passage. This allows for accurate capture of the impact of external excitation on the substation temperature during train passage, improving the relevance and effectiveness of temperature data acquisition. By maximizing heat dissipation intervention and calculating the temperature drop coefficient, it can clearly distinguish whether the excessive temperature is due to a fault in the heat dissipation system itself or to heat dissipation failure caused by other factors. This solves the problem in related technologies where temperature monitoring alone cannot determine the root cause of excessive temperature and has low fault detection accuracy. Simultaneously, by introducing vibration parameters and the temperature drop coefficient for joint judgment, it accurately identifies coupled thermal faults caused by vibration, achieving precise fault type location and avoiding misjudgment and omission. Ultimately, this significantly improves the accuracy and reliability of railway substation fault detection, ensuring the stable operation of railway substations and providing support for the safe and reliable operation of the railway power supply system, thus meeting the high standards of power supply safety requirements of the railway transportation system. Attached Figure Description

[0048] 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.

[0049] Figure 1This is a cross-sectional structural diagram of a railway substation in some embodiments of this application;

[0050] Figure 2 This is a three-dimensional structural diagram of a railway substation in some embodiments of this application;

[0051] Figure 3 This is a flowchart illustrating the fault detection method for railway substations in some embodiments of this application;

[0052] Figure 4 This is a flowchart illustrating step S400 of the fault detection method for railway substations in some embodiments of this application.

[0053] Figure 5 This is a schematic diagram showing the open state of the heat dissipation flip cover of the railway substation in some embodiments of this application;

[0054] Figure 6 This is a schematic diagram of the hardware structure of an electronic device in some embodiments of this application.

[0055] 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

[0056] 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.

[0057] 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.

[0058] 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.

[0059] As a core component of my country's transportation system, the safe and stable operation of railways is directly related to the safety of people's travel and the smooth flow of national logistics. The railway power supply system is the "lifeline" that ensures the normal operation of railways. Among them, railway substations, as key nodes of the power supply system, undertake the important functions of power conversion, distribution and equipment protection. They are widely distributed along the railway line, with one set every few kilometers, directly providing a stable power supply for loads such as railway communication, signaling and train operation equipment, tunnel lighting and police stations along the line. The reliability of their operation directly determines the overall stability and safety of the railway power supply system.

[0060] Railway substations are characterized by prefabrication, flexible assembly, intelligence, and enclosure safety. They integrate various power devices such as high-voltage switchgear, transformers, and low-voltage power distribution equipment. During long-term operation, these devices are inevitably affected by complex operating conditions, which can easily lead to various faults, such as thermal faults caused by overheating.

[0061] In related technologies, temperature monitoring alone cannot determine whether the excessive temperature is due to a fault in the heat dissipation system itself or a coupling problem caused by heat dissipation failure due to other reasons. This results in low accuracy in fault detection of railway substations and fails to meet the requirements for safe and reliable operation of railway power supply systems.

[0062] To address the aforementioned technical problems, this application provides a fault detection method for railway substations. This method can be applied to a fault detection system, which includes a railway substation and its control module.

[0063] like Figures 1-2 As shown, the railway substation of this application includes a box 100, a transformer 200 installed inside the box 100, power distribution devices 300, and a wind direction sensor 400 installed outside the box 100.

[0064] The enclosure 100 is made of vibration-resistant and corrosion-resistant materials, suitable for the complex outdoor environment along railway lines. It effectively isolates external dust, rainwater, and debris from intrusion, while reducing the impact of external vibrations from passing trains on internal components. The sides (left and right sides) of the enclosure 100 are equipped with heat dissipation structures, including main heat dissipation holes 110 and auxiliary heat dissipation holes 120. The main heat dissipation hole 110 is equipped with a built-in cooling fan (not shown), which can adjust its cooling power according to the internal temperature, reaching a preset maximum power for active heat dissipation intervention when component temperatures are abnormal. The auxiliary heat dissipation hole 120 has an automatically flipping heat dissipation cover 130 on its outer side. This cover is automatically flipped by a drive motor (drive unit not shown) for auxiliary heat dissipation, improving heat dissipation efficiency.

[0065] The heat dissipation flip-top 130 includes a first heat dissipation flip-top located on the left side of the enclosure 100 and a second heat dissipation flip-top located on the right side. The two can be independently adjusted to open at different angles to adapt to different air intake and exhaust requirements according to the ambient wind direction information, forming an efficient heat dissipation channel to assist in cooling.

[0066] As the core power supply conversion component of the substation, transformer 200 generates heat and electromagnetic vibration during operation. Its temperature change and electromagnetic vibration parameters are key indicators for fault detection and are the main monitoring objects for vibration-induced coupled thermal faults and conventional thermal faults.

[0067] The power distribution device 300 is used to distribute and transmit railway power. It will also generate operating heat and slight electromagnetic vibration. Together with the transformer 200, it forms the core working unit of the substation. Its temperature and vibration status are also included in the fault detection range.

[0068] The wind direction sensor 400 is used to acquire wind direction information of the environment where the substation is located, including wind direction, such as the angle between the wind direction and the normal of the side of the substation.

[0069] In addition, the enclosure is equipped with a temperature acquisition module (not shown) to acquire temperature data of the target power devices (transformer 200, power distribution device 300, etc.). The temperature acquisition frequency is positively correlated with the frequency of railway train passage. The higher the frequency of train passage, the higher the acquisition frequency, which can capture the temperature changes of the devices under the influence of train vibration in real time. At the same time, a vibration acquisition module (not shown) is also configured to acquire the vibration parameters of the target power devices, including the external excitation vibration parameters when railway trains pass by and the electromagnetic vibration parameters of the target power devices themselves, to provide data support for fault diagnosis.

[0070] For example, the temperature acquisition module can be an infrared temperature detector. The infrared detector can collect temperature data from the target power devices (transformer 200, distribution device 300, etc.) non-contactly, avoiding direct contact with high-temperature devices and ensuring the accuracy of temperature acquisition. The vibration acquisition module can use a multi-axis accelerometer. This sensor can accurately collect the vibration parameters of the target power devices, including external excitation vibration parameters when a railway train passes and the electromagnetic vibration parameters of the target power devices themselves, providing data support for fault diagnosis. The detection method for the electromagnetic vibration of the target power device itself is as follows: A multi-axis accelerometer is directly fixed on the surface of the target power device such as transformer 200 and power distribution device 300. Utilizing the coupling characteristics of electromagnetic vibration and mechanical vibration, it captures the minute mechanical vibration signals generated by the electromagnetic force during device operation. Since the frequency and amplitude of electromagnetic vibration are closely related to the working state of the electromagnetic coil inside the device and the core loss, after the sensor collects the vibration signal, it extracts the characteristic parameters (such as the frequency band energy value) of the corresponding electromagnetic vibration frequency band through subsequent signal processing (such as time-frequency transformation). This completes the detection of electromagnetic vibration, thereby distinguishing electromagnetic vibration from external excitation vibration caused by the passing of a train, and providing accurate vibration data for the determination of coupled thermal faults.

[0071] It should be noted that under normal operating conditions, the heat dissipation cover 130 is in the closed state, that is, the heat dissipation cover 130 closes the auxiliary heat dissipation hole 120, which serves to prevent water and dust.

[0072] The following explanation uses the fault detection system's execution of the fault detection method for this railway substation as an example. It should be noted that although the logical sequence is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order. Please refer to the appendix. Figure 3 The method includes the following steps S100-S500:

[0073] Step S100: Obtain the temperature data of the target power device in the transformer box to obtain the first target temperature, wherein the temperature acquisition frequency is positively correlated with the frequency of railway train passing by;

[0074] In the substation fault detection process, the fault detection system first activates the temperature acquisition module configured inside the substation to continuously monitor the temperature of the target electrical components inside, providing basic temperature data for subsequent fault determination. During this stage, the temperature acquisition module (exemplarily an infrared temperature detector) initiates temperature acquisition, employing a non-contact acquisition method to accurately obtain temperature data from the target electrical components (transformer 200, distribution components 300, etc.) inside the substation. This avoids direct contact with high-temperature operating electrical components, preventing damage to the acquisition module and effectively mitigating temperature conduction errors caused by contact acquisition, ensuring the accuracy of the acquired temperature data. After acquisition, the system performs simple preprocessing on the raw temperature data (such as noise reduction and calibration) to obtain the first target temperature, which is then transmitted to the system processor in real time, providing raw temperature data support for subsequent temperature drop coefficient calculation and fault type determination.

[0075] It is understandable that the primary target temperature directly reflects the current operating temperature state of the target electrical device. The temperature acquisition frequency is positively correlated with the frequency of railway train passage, making it a key acquisition strategy designed based on the characteristics of the railway scenario. Because railway trains generate external excitation vibrations, these vibrations may lead to poor contact in electrical devices. Poor contact increases the resistance at the device connections. According to Joule's law, increased resistance directly leads to increased power loss and exacerbated heat generation, thus causing abnormal temperature fluctuations in the target electrical device. The higher the frequency of train passage, the greater the frequency and intensity of vibration, and the higher the probability of temperature anomalies. Therefore, by dynamically adjusting the acquisition frequency—increasing the acquisition frequency when the train passage frequency is high—the temperature mutations of the device under vibration can be captured in real time. When the train passage frequency is low, the acquisition frequency can be appropriately reduced, ensuring detection accuracy while reducing system energy consumption and data redundancy. This achieves accurate and efficient temperature monitoring, laying the foundation for accurate identification of subsequent coupled thermal faults and conventional thermal faults.

[0076] Step S200: When the first target temperature is greater than or equal to the warning temperature, increase the heat dissipation power of the built-in cooling fan of the substation to the preset maximum power, maintain the maximum heat dissipation power for a preset time, and then obtain the temperature data of the target power device again to obtain the second target temperature.

[0077] In the substation fault detection process, the system compares the first target temperature with the preset warning temperature in real time to determine whether the target power device is at risk of overheating. When the first target temperature is greater than or equal to the warning temperature (or greater than or equal to the warning temperature for a certain period of time), it indicates that the current operating temperature of the target power device is too high, posing a potential thermal anomaly. The system then activates an active heat dissipation intervention mechanism. During this stage, the system controls the substation's built-in cooling fan to increase its power from normal operation to a preset maximum power, forcibly cooling the target power device with the strongest cooling capacity. This maximum cooling power is maintained for a preset duration to ensure that the cooling effect is fully applied to the target power device, avoiding temperature data distortion due to insufficient cooling time. After the preset duration, the system again acquires the real-time temperature data of the target power device through the temperature acquisition module, preprocesses it to obtain the second target temperature, and synchronously transmits the second target temperature to the system processor.

[0078] It is understandable that increasing the heat dissipation power to the preset maximum power and running it continuously for a preset time is a key detection method set up in this solution for vibration-coupled thermal faults in railway substations. The abnormal temperature of the target electrical components may originate from either vibration-induced poor contact leading to increased self-heating, or from conventional causes such as insufficient heat dissipation. Only under uniform and maximized heat dissipation excitation conditions can the temperature drop of the components truly reflect their internal heat intensity and fault characteristics. Therefore, by using the maximum heat dissipation power for uniform heat dissipation intervention, interference from differences in conventional heat dissipation capabilities can be eliminated, highlighting the temperature change characteristics under different fault types. This makes subsequent fault determination based on the temperature drop coefficient more accurate and reliable, thereby effectively distinguishing between vibration-induced coupled thermal faults and conventional thermal faults, and improving the targeting and accuracy of fault detection.

[0079] Step S300: Determine a first temperature drop coefficient based on the second target temperature and the first target temperature. The first temperature drop coefficient characterizes the temperature drop capability of the target power device under maximum heat dissipation intervention.

[0080] In the substation fault detection process, after the system completes maximum heat dissipation intervention and acquires the first and second target temperatures, it enters the temperature change characteristic quantitative analysis stage. In this stage, the system processor substitutes the acquired first and second target temperatures into preset calculation logic, performs calculations based on the relative relationship between the temperature difference and the initial temperature, obtains the first temperature drop coefficient, and uses this first temperature drop coefficient in real time for subsequent fault determination, providing a quantitative evaluation index for distinguishing different types of thermal faults.

[0081] It is understandable that the first temperature drop coefficient can intuitively and quantitatively characterize the temperature reduction capability of a target power device under unified and maximized heat dissipation intervention. Different target power devices have different self-heating intensity and fault states, resulting in significant differences in temperature drop under the same heat dissipation conditions. For devices whose self-heating is aggravated due to poor contact and increased resistance caused by vibration, even with maximum heat dissipation, the temperature drop is still limited. However, for devices with non-organic abnormalities such as insufficient conventional heat dissipation, a more obvious temperature drop trend can be observed under the same maximum heat dissipation conditions. Therefore, by introducing the first temperature drop coefficient, the temperature change of the device can be transformed into a unified quantitative evaluation index, effectively eliminating the judgment error caused by initial temperature differences. This enables an objective evaluation of the root cause of heat generation and the degree of fault in the target power device, providing accurate and reliable quantitative basis for subsequently distinguishing between vibration-induced coupled thermal faults and conventional thermal faults.

[0082] For example, the first temperature drop coefficient can be calculated using the formula K=(T1-T2) / T1×100%, where T1 is the first target temperature and T2 is the second target temperature.

[0083] Step S400: Obtain the target vibration parameters of the target power device, wherein the target vibration parameters include at least one of the external excitation vibration parameters when the railway train passes by and the electromagnetic vibration parameters of the target power device itself.

[0084] In the substation fault detection process, the fault detection system uses a vibration acquisition module continuously operating inside the substation to acquire real-time vibration status data of the target power devices, providing vibration characteristic support for the accurate determination of subsequent coupled thermal faults. At this stage, the vibration acquisition module (exemplarily a multi-axis accelerometer) adopts a contact-type acquisition method, directly mounted on the surface of the target power device (transformer 200, distribution device 300, etc.) housing, continuously acquiring and buffering the real-time vibration signals of the target power device to avoid signal attenuation caused by external environmental interference, while ensuring the continuity and stability of vibration data acquisition. For example, external excitation vibration parameters can be acquired through a first accelerometer, and electromagnetic vibration parameters through a second accelerometer; or, the raw data acquired by the same accelerometer can be processed through signal separation and feature extraction to obtain external excitation vibration parameters and electromagnetic vibration parameters. Further, the system reads and extracts valid vibration data from the vibration acquisition module, preprocesses it (such as denoising, filtering, time-frequency transformation, etc.) to obtain the target vibration parameters, and transmits these target vibration parameters to the system processor in real time, providing raw vibration data support for subsequent fault type determination and vibration-coupled thermal fault identification.

[0085] It is understandable that target vibration parameters directly reflect the source and intensity of vibration excitation currently experienced by the target power device. Dividing the target vibration parameters into external excitation vibration parameters caused by passing trains and electromagnetic vibration parameters of the target power device itself is a key acquisition design adapted to the special working conditions of railways. Because the sources of vibration along railway lines are complex, including both external excitation vibration from passing trains and electromagnetic vibration generated by normal device operation, vibration-induced coupled thermal faults are typical faults caused by poor device contact and increased heat generation under the action of external excitation vibration. Therefore, by distinguishing and acquiring external excitation vibration parameters and electromagnetic vibration parameters, it is possible to accurately identify the source and abnormal characteristics of vibration, eliminate irrelevant environmental vibration interference, and highlight vibration signals strongly correlated with the device's own faults. This provides a reliable and accurate basis for subsequent differentiation between vibration-induced coupled thermal faults and conventional thermal faults.

[0086] Step S500: If the first temperature drop coefficient is less than or equal to the temperature drop coefficient threshold, and the target vibration parameter is greater than the vibration parameter threshold, it is determined that there is a coupled thermal fault caused by vibration in the substation.

[0087] In the substation fault detection process, the system processor compares the first temperature drop coefficient calculated in step S300 and the target vibration parameter obtained in step S400 with preset temperature drop coefficient thresholds and vibration parameter thresholds in real time. Through a dual-parameter collaborative judgment method, it accurately identifies vibration-induced coupled thermal faults. At this stage, the system first judges the first temperature drop coefficient to determine whether the temperature reduction capability of the target power device under maximized heat dissipation intervention meets the standard; then it judges the target vibration parameter to determine whether the vibration excitation intensity of the target power device exceeds the safe range. Only when both judgment conditions are met simultaneously—that is, the first temperature drop coefficient is less than or equal to the temperature drop coefficient threshold and the target vibration parameter is greater than the vibration parameter threshold—will the system ultimately determine that the substation has a vibration-induced coupled thermal fault and feed the fault judgment result back to the control terminal in real time, providing a basis for subsequent maintenance warnings, auxiliary heat dissipation, and other operations.

[0088] It is understandable that this step adopts a dual-parameter collaborative judgment method of "temperature drop coefficient + vibration parameter" which is the key to the design of vibration-coupled thermal faults in railway substations. As mentioned above, the first temperature drop coefficient characterizes the temperature reduction capability of the target power device under maximum heat dissipation intervention. If it is less than or equal to the temperature drop coefficient threshold, it indicates that the device has a weak temperature reduction capability, which is essentially due to excessive heat generation that cannot be effectively alleviated by forced heat dissipation, confirming that the device has a continuous abnormal heat generation. On the other hand, if the target vibration parameter is greater than the vibration parameter threshold, it means that the vibration excitation of the device has exceeded the safe range. This vibration will lead to poor contact of the power device. Poor contact will increase the resistance at the device connection. According to Joule's law, the increased resistance will directly lead to increased power loss and aggravated heat generation, forming a coupled fault chain of "vibration → poor contact → aggravated heat generation → decreased temperature drop capability". Therefore, by using dual-parameter collaborative judgment, the limitations of single-parameter judgment can be effectively avoided, the coupling relationship between vibration and thermal anomaly can be accurately captured, the coupled thermal faults caused by vibration can be distinguished from conventional thermal faults, misjudgment and missed judgment can be avoided, the accuracy and reliability of fault detection can be significantly improved, and it can be adapted to the special operating conditions of railway substations.

[0089] In other embodiments, after obtaining the target vibration parameters of the target power device, the fault detection method of this application further includes:

[0090] S600. If the first temperature drop coefficient is less than or equal to the temperature drop coefficient threshold and the target vibration parameter is less than or equal to the vibration parameter threshold, it is determined that the transformer box has a conventional thermal fault.

[0091] S700: If the first temperature drop coefficient is greater than the temperature drop coefficient threshold, it is determined that there is no thermal fault in the transformer box.

[0092] In the substation fault detection process, after the system processor completes the calculation of the first temperature drop coefficient (step S300) and the acquisition of the target vibration parameters (step S400), in addition to performing the coupled thermal fault determination in step S500, it will also use the above two supplementary determination steps to achieve a comprehensive determination of the thermal state of the substation, avoiding omissions or misjudgments of fault types, and further improving the comprehensiveness and reliability of fault detection. At this stage, the system still uses the dual-parameter comparison logic to synchronously compare the first temperature drop coefficient with the temperature drop coefficient threshold and the target vibration parameter with the vibration parameter threshold. Based on different comparison results, different states are determined: For S600, when the first temperature drop coefficient is less than or equal to the temperature drop coefficient threshold and the target vibration parameter is less than or equal to the vibration parameter threshold, the system determines that the substation has a conventional thermal fault and feeds back the determination result to the control terminal; For S700, when the first temperature drop coefficient is greater than the temperature drop coefficient threshold, regardless of the range of the target vibration parameter, the system determines that the substation does not have a thermal fault, only records the current operating status, and does not need to initiate subsequent heat dissipation intervention or maintenance early warning operations.

[0093] It is understandable that S600 and S700, as supplementary judgment logic to step S500, are key designs for this solution to achieve "full-condition, no-blind-spot fault detection". The core purpose is to distinguish between the three states of "vibration-induced coupled thermal fault", "conventional thermal fault" and "no thermal fault", and solve the technical pain point that existing detection methods cannot accurately distinguish the type of thermal fault and are prone to misjudgment and missed judgment. The S600 judgment logic corresponds to a conventional thermal fault scenario: if the first temperature drop coefficient is less than or equal to the temperature drop coefficient threshold, it indicates that the target power device has a weak temperature reduction capability and a persistent abnormal heating. However, if the target vibration parameters do not exceed the safe range, it is highly likely that the abnormal heating is unrelated to vibration, but is caused by conventional factors such as the aging of the device's own heat dissipation structure and abnormal operation of the cooling fan. This is a conventional thermal fault, and conventional heat dissipation maintenance measures can be taken accordingly. The S700 judgment logic corresponds to a no-thermal-fault scenario: if the first temperature drop coefficient is greater than the temperature drop coefficient threshold, it indicates that the target power device has a sufficient temperature reduction capability under maximum heat dissipation intervention. Even if there is some vibration excitation, it does not cause abnormal heating of the device. The device is in normal operating condition and no fault response operation needs to be initiated.

[0094] In summary, through the coordinated operation of steps S600, S700, and S500, this solution achieves accurate classification and judgment of thermal faults in substations. It can accurately identify coupled thermal faults caused by vibration, and effectively distinguish between conventional thermal faults and non-thermal faults, avoiding the limitations of a single judgment logic. At the same time, it is adapted to the special working conditions of complex vibration interference and diverse fault types in railway substations, providing accurate judgment basis for subsequent targeted maintenance and heat dissipation control, and further improving the practicality and reliability of fault detection.

[0095] Based on this, this application, taking into account the operating conditions of railway substations along the railway line, adopts a temperature acquisition frequency positively correlated with the frequency of train passage. This allows for accurate capture of the impact of external excitation on the substation temperature when trains pass, improving the relevance and effectiveness of temperature data acquisition. By maximizing heat dissipation intervention and calculating the temperature drop coefficient, it can clearly distinguish whether the excessive temperature is due to a fault in the heat dissipation system itself or to heat dissipation failure caused by other factors. This solves the problem in related technologies where temperature monitoring alone cannot determine the root cause of excessive temperature and has low fault detection accuracy. Simultaneously, by introducing vibration parameters and the temperature drop coefficient for joint judgment, it accurately identifies coupled thermal faults caused by vibration, achieving precise fault type location and avoiding misjudgment and missed judgment. Ultimately, this significantly improves the accuracy and reliability of railway substation fault detection, ensuring the stable operation of railway substations and providing support for the safe and reliable operation of the railway power supply system, thus meeting the high standards of power supply safety requirements of the railway transportation system.

[0096] In one embodiment, such as Figure 4 As shown, step S400: Obtaining the target vibration parameters of the target power device includes:

[0097] S410. Obtain the external excitation vibration parameters when the railway train passes by and the electromagnetic vibration parameters of the target power device itself to obtain the first vibration parameter and the second vibration parameter.

[0098] S420. The first vibration parameter and the second vibration parameter are fused to obtain the target vibration parameter.

[0099] Specifically, this application first obtains the external excitation vibration parameters when a railway train passes by and the electromagnetic vibration parameters of the target power device itself, thus obtaining the first vibration parameter and the second vibration parameter. These parameters can be acquired by a vibration acquisition module (exemplarily a multi-axis accelerometer) that runs continuously inside the enclosure. The first vibration parameter is used to characterize the magnitude of the external excitation vibration caused by the passing of the train, and the second vibration parameter is used to characterize the strength of the electromagnetic vibration generated by the operation of the power device itself. The two types of vibration parameters reflect the vibration state under different excitation sources, providing raw data for subsequent vibration fusion processing.

[0100] Subsequently, the first vibration parameter and the second vibration parameter are fused to obtain the target vibration parameter. The vibration parameter includes the energy value of the corresponding frequency band after the vibration signal is transformed by time and frequency. The steps are as follows: The first vibration parameter and the second vibration parameter are fused to obtain the target vibration parameter. Specifically, this includes: First, obtaining the transit time identifier of the railway train. The transit time identifier is used to distinguish whether the current time belongs to the transit time or the non-transit time, so as to adopt a differentiated vibration fusion strategy according to different time periods; Then, the first vibration parameter and the second vibration parameter are transformed by time and frequency to extract the energy time series data of the first frequency band corresponding to the external excitation and the energy time series data of the second frequency band corresponding to the electromagnetic vibration of the power device, respectively. By distinguishing the frequency bands, the external excitation vibration and the electromagnetic vibration are effectively separated, avoiding mutual interference between different vibration signals.

[0101] If the current time is within the train's passing period, the preset first weighting coefficient and second weighting coefficient are obtained. Within the time window of the train's passing period, the first frequency band energy time series data and the second frequency band energy time series data are weighted and fused and energy aggregated to obtain the first fused total energy value as the target vibration parameter, so as to comprehensively reflect the overall vibration intensity under the combined action of external excitation of the train and the electromagnetic vibration of the device itself.

[0102] If the current time is within a period when the train has not passed, then within the preset vibration monitoring time window, the energy time series data of the second frequency band is aggregated and calculated to obtain the total energy value of the second frequency band as the target vibration parameter, so as to reflect the electromagnetic vibration state of the device itself.

[0103] In this system, if the current time falls within a train-passing period, the weighting coefficient can be adjusted according to the actual operating conditions, emphasizing the impact of external excitation vibration (since external vibration is the main cause of coupling faults when a train passes). If the current time does not fall within a train-passing period, the system performs energy aggregation calculations only on the energy time-series data of the second frequency band within a preset vibration monitoring time window, obtaining the total energy value of the second frequency band as the target vibration parameter. Since there is no external excitation vibration at this time, only the electromagnetic vibration state of the device itself needs to be monitored. After fusion, the system transmits the target vibration parameter to the system processor in real time, providing accurate data support for subsequent fault determination.

[0104] Understandably, this step employs a design of "separate acquisition + time-segmented and frequency-segmented fusion," with the core aim of addressing the technical pain points of complex vibration sources, susceptibility to interference, and difficulty in accurately characterizing the true vibration state of devices in railway scenarios. Each step of the design has a clear purpose. The reason for separately acquiring external excitation vibration parameters and electromagnetic vibration parameters (S410) is that the vibration sources of railway substations are mainly divided into two categories: external excitation vibration caused by passing trains (which can easily lead to poor device contact) and electromagnetic vibration generated by the device's own operation (reflecting the device's own working state). The two types of vibration have different impacts on faults, and separate acquisition is necessary to accurately locate the fault cause and avoid data distortion caused by the superposition of different vibration signals. The reason for time-segmented fusion processing (S420) is that the vibration environment differs greatly between the time when trains pass and the time when they do not: when trains pass, the intensity of external excitation vibration is high, which is the main factor causing coupled thermal faults. Therefore, it is necessary to use weighted fusion to take into account both external excitation and electromagnetic vibration, highlighting the impact of external vibration; when trains do not pass, there is no external excitation interference, and only the device's own electromagnetic vibration needs to be considered to avoid invalid data redundancy and reduce the system's computational load.

[0105] Extracting frequency band energy time-series data through time-frequency transformation is crucial because different frequency bands of vibration signals correspond to different vibration sources (external excitation vibration and electromagnetic vibration have significantly different frequency bands). Extracting the energy value of the corresponding frequency band allows for precise quantification of the intensity of various vibrations, avoiding interference from non-target frequency bands. Through energy aggregation calculation, discrete energy data in time series can be integrated into a comprehensive energy value, more intuitively and accurately representing the vibration intensity at the current moment, facilitating subsequent comparison and judgment with vibration parameter thresholds. In summary, this step's design is not only suitable for the special operating conditions of railway substations but also effectively eliminates interference, accurately quantifies vibration states, and obtains target vibration parameters that meet the actual fault judgment requirements. This provides reliable support for subsequent collaborative judgment using "temperature drop coefficient + vibration parameters," avoiding misjudgments and missed judgments due to inaccurate vibration data, and further improving the accuracy and reliability of fault detection.

[0106] To further improve the accuracy of vibration-induced coupled thermal fault determination and avoid potential misjudgments from a single determination logic, and to promptly implement auxiliary heat dissipation measures after fault determination to alleviate abnormal thermal conditions of components and buy time for subsequent maintenance, in one embodiment, after determining that the substation box has a vibration-induced coupled thermal fault in step S500, the method further includes:

[0107] The wind direction information of the environment in which the railway substation is located is obtained based on the wind direction sensor.

[0108] Based on the wind direction information, the opening angles of the first heat dissipation flap and the second heat dissipation flap are determined to obtain the first target angle and the second target angle.

[0109] The first and second heat dissipation flip plates are opened according to the first and second target angles to assist the railway substation in heat dissipation.

[0110] After the heat dissipation cover is opened and continues to assist in heat dissipation for a preset time, the temperature data of the target power device is acquired again to obtain the third target temperature;

[0111] A second temperature drop coefficient is determined based on the first target temperature and the third target temperature, and the determination result of the coupled thermal fault caused by the vibration is verified according to the second temperature drop coefficient.

[0112] Specifically, this embodiment first uses a wind direction sensor mounted on the side of the railway substation to acquire real-time wind direction information of the environment in which the substation is located. The wind direction sensor can collect key data such as wind direction and the angle between the wind direction and the normal to the side of the substation, providing a precise basis for determining the opening angle of the subsequent heat dissipation flaps and avoiding poor auxiliary heat dissipation due to blind adjustments. Then, based on the acquired wind direction information and the installation positions of the first heat dissipation flap (located on the left side of the substation) and the second heat dissipation flap (located on the right side of the substation), the opening angles of the two flaps are determined, resulting in a first target angle (corresponding to the first heat dissipation flap) and a second target angle (corresponding to the second heat dissipation flap). The angles can be adapted to the direction of the incoming wind to ensure the formation of an efficient ventilation and heat dissipation channel, maximizing the use of natural ventilation for auxiliary heat dissipation. Next, the system uses a drive motor to control the first and second heat dissipation flaps to open synchronously according to the determined first and second target angles. This works in conjunction with the cooling fan already operating at its preset maximum power inside the substation, achieving a combination of forced heat dissipation and natural ventilation-assisted heat dissipation, quickly removing heat from the substation and alleviating the abnormal thermal state of the target electrical components. After the heat dissipation cover is opened and continuous auxiliary heat dissipation is performed for a preset time (the preset time can be set according to the actual working conditions to ensure that the heat dissipation effect is fully applied to the target power device), the system again obtains the temperature data of the target power device through the temperature acquisition module (exemplarily an infrared temperature detector). After preprocessing (such as noise reduction and calibration), the third target temperature is obtained. Finally, based on the first target temperature obtained in step S100 and the third target temperature obtained this time, the second temperature drop coefficient is determined by referring to the calculation logic of the first temperature drop coefficient (such as by the formula K=(T1-T3) / T1×100%, where T1 is the first target temperature and T3 is the third target temperature). The vibration-induced coupled thermal fault result determined in step S500 is verified according to the second temperature drop coefficient to ensure the accuracy of the fault determination.

[0113] Specifically, the verification of the fault determination result can be achieved in the following ways: for example, comparing the second temperature drop coefficient with the preset temperature drop coefficient threshold; if the second temperature drop coefficient is less than the temperature drop coefficient threshold, the determination result of the coupled thermal fault caused by vibration is confirmed, and a first-level maintenance warning is generated. The first-level maintenance warning is used to prompt the mechanical connection status check or electromagnetic component status check of the target power device. The temperature drop coefficient threshold is consistent with the threshold used in steps S300 and S500 to ensure the uniformity of the judgment standard and avoid verification errors caused by threshold differences. The second temperature drop coefficient is compared with this threshold. The core is to verify the authenticity of the fault by reverse verification through the temperature drop effect after auxiliary heat dissipation. If the second temperature drop coefficient is still less than the temperature drop coefficient threshold, it means that even with the auxiliary heat dissipation of the heat dissipation cover, the temperature drop capability of the target power device is still weak. This further confirms that the abnormal heating of the device is caused by poor contact due to vibration (which is a continuous fault that cannot be completely relieved by simple heat dissipation). Therefore, the coupled thermal fault judgment is confirmed. The generation of the first-level maintenance warning is to clarify the subsequent maintenance direction and remind the staff to focus on checking the mechanical connection status of the target power device (such as terminals, fixing bolts, etc., to check for poor contact problems) and the status of electromagnetic components (such as coils, iron cores, etc., to check for abnormal electromagnetic vibration problems). This realizes the closed loop of "accurate judgment → accurate warning → accurate maintenance" and avoids the waste of manpower and material resources caused by blind maintenance.

[0114] To further improve the auxiliary heat dissipation efficiency of the heat dissipation flip cover, and to fully utilize outdoor natural wind to form a directional and smooth heat dissipation airflow, avoiding air intake obstruction and exhaust obstruction caused by unreasonable opening angle of the flip cover, thereby improving the stability and sufficiency of the auxiliary heat dissipation effect. The more stable and sufficient the auxiliary heat dissipation effect, the more accurately the third target temperature can reflect the heating characteristics of the device, and the more accurate and reliable the subsequent fault verification results based on the second temperature drop coefficient will be. Therefore, in one embodiment, the step of determining the opening angle of the first and second heat dissipation flip covers based on the wind direction information to obtain the first target angle and the second target angle includes:

[0115] Based on the wind direction information, determine the angle between the wind direction and the normal direction of the side of the railway substation;

[0116] Based on the included angle, the current wind direction is determined relative to the incoming direction of the railway substation. The side directly exposed to the wind is determined as the air intake side, and the other side is determined as the air outlet side.

[0117] If the left side of the first heat dissipation flip plate is the air intake side, then the first target angle of the first heat dissipation flip plate is set to the air intake guide angle parallel to the airflow direction according to the included angle; at the same time, the second target angle of the second heat dissipation flip plate is set to the air outlet heat exhaust angle of 90° so that the right side is completely open to form a heat exhaust channel.

[0118] If the right side of the second heat dissipation flip plate is the air intake side, then the second target angle of the second heat dissipation flip plate is set to the air intake guide angle parallel to the airflow direction according to the included angle; at the same time, the first target angle of the first heat dissipation flip plate is set to the air outlet heat exhaust angle of 90° so that the left side is completely open to form a heat exhaust channel.

[0119] Specifically, this embodiment first determines the angle between the wind direction and the normal direction of the side of the transformer box based on the wind direction information of the environment where the transformer box is located, obtained above. This angle can be calculated by combining the wind direction data collected by the wind direction sensor with the preset normal reference on the side of the box. This angle can quantify the incident posture of the natural wind relative to the side of the box, providing a reliable quantitative reference for the subsequent determination of the air inlet and outlet sides and the precise setting of the flip-up cover angle, avoiding the blindness of angle adjustment. Then, based on the calculated angle, the current wind direction relative to the incoming direction of the transformer box is determined, clarifying which side of the box can directly withstand the wind, and this side is determined as the air inlet side, while the other side is determined as the air outlet side. The core purpose is to establish a directional convection mode of "air inlet on one side and air outlet on the other side", laying the foundation for efficient auxiliary heat dissipation.

[0120] Next, depending on the air intake side, a corresponding angle setting strategy is adopted: if the left side where the first heat dissipation flip cover is located is the air intake side, then according to the angle between the wind direction and the side normal, the first target angle of the first heat dissipation flip cover is set to an air intake guide angle parallel to the wind direction. This setting can minimize the wind resistance when natural wind enters the cabinet, guide the external cold air to flow smoothly into the cabinet along the flip cover surface, and make full use of the kinetic energy of natural wind to improve air intake efficiency; at the same time, the second target angle of the second heat dissipation flip cover is set to a 90° exhaust heat angle, so that the right side is completely open, forming an unobstructed heat exhaust channel, allowing the hot air forced out of the cabinet by the cooling fan to be quickly and smoothly discharged from the cabinet, avoiding the accumulation of hot air that leads to a decrease in heat dissipation effect. Conversely, if the right side where the second heat dissipation cover is located is the air intake side, then a symmetrical adjustment logic is adopted, setting the second heat dissipation cover to an air intake guide angle parallel to the airflow direction, and setting the first heat dissipation cover to an air outlet heat exhaust angle of 90°, thus achieving the optimal effect of directional convection heat dissipation.

[0121] For example, such as Figure 5As shown, the dashed lines represent the left and right heat dissipation flaps, and the solid lines with arrows represent the airflow direction. In the figure, 5A and 5B represent the left side air intake, and 5C and 5D represent the right side air intake.

[0122] Thus, by accurately calculating the wind direction angle and distinguishing between the air inlet and outlet sides, the opening angle of the heat dissipation flip cover is specifically set. This allows for full utilization of outdoor natural wind to form a directional and smooth heat dissipation channel, effectively improving auxiliary heat dissipation efficiency and ensuring the stability and sufficiency of the auxiliary heat dissipation effect. Consequently, the acquisition of the third target temperature can more accurately reflect the heating characteristics of the device, providing precise support for subsequent fault verification based on the second temperature drop coefficient, improving the reliability of fault verification results, and adapting to the complex outdoor wind field operating conditions of railway substations.

[0123] In one embodiment, after generating a Level 1 maintenance warning, the fault detection method of this application further includes:

[0124] Obtain the historical temperature variation curve and historical vibration parameter variation curve of the target power device;

[0125] Based on the historical variation curves, the current temperature drop coefficient, and the target vibration parameters, a fault development trend model is constructed.

[0126] Based on the fault development trend model, predict the remaining time window for the vibration-induced coupled thermal fault to develop from its current state to a severe fault;

[0127] If the remaining time window is less than a preset safe time threshold, a level two emergency warning is generated, which is used to prompt immediate maintenance.

[0128] Specifically, after generating a Level 1 maintenance warning, this embodiment first obtains the historical temperature change curve and historical vibration parameter change curve corresponding to the target power device. This can be achieved by retrieving historical monitoring data within a preset time period from the system's local storage or cloud database. For example, it can extract the device's recent temperature time-series data and vibration energy time-series data to form a historical change curve that reflects the device's long-term operating status, providing historical data support for subsequent fault trend analysis. Subsequently, based on the aforementioned historical change curve, the currently calculated temperature drop coefficient, and the currently acquired target vibration parameters, data fusion and trend fitting are performed to construct a fault development trend model. This model can comprehensively integrate historical operating patterns and current fault characteristics to quantitatively characterize the development speed and deterioration degree of vibration-coupled thermal faults. Then, based on the constructed fault development trend model, fault evolution prediction is performed to estimate the remaining time window for the vibration-induced coupled thermal fault to develop from the current abnormal state to serious faults such as overheating and burnout, achieving early prediction of the fault's danger level and development speed. Finally, the predicted remaining time window is compared with the preset safe time threshold. If the remaining time window is less than the safe time threshold, it indicates that the fault is deteriorating rapidly and the degree of danger is high. The system immediately generates a level-two emergency warning to prompt maintenance personnel to arrange for the target power device to be repaired immediately to avoid the fault from further expanding and causing a safety accident.

[0129] Thus, based on the generation of a first-level maintenance early warning, this embodiment of the application constructs a fault development trend model by combining historical operating data and current fault characteristics, thereby predicting the remaining time window of the fault and generating a second-level emergency early warning based on the prediction results. This enables early prediction of the risk of fault deterioration, achieving graded, time-based, and precise early warning, thereby improving the timeliness and safety of railway substation fault handling and reducing the operational risks caused by fault spread.

[0130] like Figure 6 As shown, Figure 6 The diagram below illustrates the hardware structure of an electronic device in some embodiments of this application. The electronic device provided in the embodiments of this application 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 fault detection method for railway substations as described above.

[0131] The processor 2000 provides computing and control capabilities to control electronic devices to perform corresponding tasks, such as controlling the electronic devices to perform the fault detection method for a railway substation in any of the above method embodiments. The method includes: acquiring temperature data of a target power device inside the substation to obtain a first target temperature, wherein the temperature acquisition frequency is positively correlated with the frequency of railway train passage; when the first target temperature is greater than or equal to a warning temperature, increasing the heat dissipation power of the built-in cooling fan of the substation to a preset maximum power, maintaining the maximum heat dissipation power for a preset duration, and then acquiring the temperature data of the target power device again to obtain a second target temperature; determining a first temperature drop coefficient based on the second target temperature and the first target temperature, wherein the first temperature drop coefficient characterizes the temperature drop capability of the target power device under maximized heat dissipation intervention; acquiring target vibration parameters of the target power device, wherein the target vibration parameters include at least one of external excitation vibration parameters when railway trains pass and electromagnetic vibration parameters of the target power device itself; determining that the first temperature drop coefficient is less than or equal to a temperature drop coefficient threshold, and the target vibration parameter is greater than a vibration parameter threshold, and determining that the substation has a coupled thermal fault caused by vibration.

[0132] 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.

[0133] 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 substation fault detection method in the embodiments of this application. The processor 2000 can implement the railway substation fault detection method in any of the above method embodiments by running the non-transitory software programs, instructions, and modules stored in the memory 1000.

[0134] 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.

[0135] In summary, the electronic device of this application adopts the technical solution of any of the above-described embodiments of the fault detection method for railway substations. Therefore, it has at least the beneficial effects brought about by the technical solutions of the above embodiments, which will not be elaborated further here.

[0136] 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 fault detection method for railway substations 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, or optical data storage device, etc.

[0137] This application also provides a computer program product comprising one or more lines of program code stored in a computer-readable storage medium. A processor reads the program code from the computer-readable storage medium and executes the program code to complete the fault detection method steps for a railway substation provided in the above embodiments.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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 fault detection method for railway substations, characterized in that, The method includes: The temperature data of the target power devices inside the transformer box is obtained to obtain the first target temperature, where the temperature acquisition frequency is positively correlated with the frequency of railway train passage; If the first target temperature is greater than or equal to the warning temperature, the heat dissipation power of the built-in cooling fan of the transformer box is increased to the preset maximum power. After the maximum heat dissipation power is maintained for a preset time, the temperature data of the target power device is acquired again to obtain the second target temperature. A first temperature drop coefficient is determined based on the second target temperature and the first target temperature. The first temperature drop coefficient characterizes the temperature drop capability of the target power device under maximum heat dissipation intervention. The target vibration parameters of the target power device are obtained, and the target vibration parameters include at least one of the external excitation vibration parameters when a railway train passes by and the electromagnetic vibration parameters of the target power device itself. If the first temperature drop coefficient is less than or equal to the temperature drop coefficient threshold, and the target vibration parameter is greater than the vibration parameter threshold, it is determined that the substation has a coupled thermal fault caused by vibration.

2. The fault detection method for railway substations as described in claim 1, characterized in that, The acquisition of the target vibration parameters of the target power device includes: The first vibration parameter and the second vibration parameter are obtained by acquiring the external excitation vibration parameters when the railway train passes by and the electromagnetic vibration parameters of the target power device itself. The first vibration parameter and the second vibration parameter are fused to obtain the target vibration parameter.

3. The fault detection method for railway substations as described in claim 2, characterized in that, The vibration parameters include the energy value of the corresponding frequency band after the vibration signal has undergone time-frequency transformation. The process of fusing the first vibration parameters and the second vibration parameters to obtain the target vibration parameters includes: Obtain the transit time identifier of the railway train, which is used to distinguish whether the current time belongs to the transit time of the train or the non-transit time of the train; The first vibration parameter and the second vibration parameter are transformed by time and frequency to extract the energy time series data of the first frequency band corresponding to the external excitation and the energy time series data of the second frequency band corresponding to the electromagnetic vibration of the power device, respectively. If the current time is within the train passing period, then the preset first weighting coefficient and second weighting coefficient are obtained. Within the time window of the train passing period, the first frequency band energy time series data and the second frequency band energy time series data are weighted and fused and energy aggregated to obtain the first fused total energy value as the target vibration parameter. If the current time is within a period when the train has not yet passed through, then within the preset vibration monitoring time window, the energy time series data of the second frequency band is aggregated and calculated to obtain the total energy value of the second frequency band as the target vibration parameter.

4. The fault detection method for railway substations as described in claim 1, characterized in that, After obtaining the target vibration parameters of the target power device, the method further includes: If the first temperature drop coefficient is less than or equal to the temperature drop coefficient threshold, and the target vibration parameter is less than or equal to the vibration parameter threshold, it is determined that the substation has a conventional thermal fault. If the first temperature drop coefficient is determined to be greater than the temperature drop coefficient threshold, it is determined that there is no thermal fault in the transformer box.

5. The fault detection method for railway substations as described in claim 1, characterized in that, The railway substation is equipped with a heat dissipation flip-top and a wind direction sensor on its side. The heat dissipation flip-top includes a first heat dissipation flip-top on the left side and a second heat dissipation flip-top on the right side. After determining that the substation has a coupled thermal fault caused by vibration, the method further includes: The wind direction information of the environment in which the railway substation is located is obtained based on the wind direction sensor. Based on the wind direction information, the opening angles of the first heat dissipation flap and the second heat dissipation flap are determined to obtain the first target angle and the second target angle. The first and second heat dissipation flip plates are opened according to the first and second target angles to assist the railway substation in heat dissipation. After the heat dissipation cover is opened and continues to assist in heat dissipation for a preset time, the temperature data of the target power device is acquired again to obtain the third target temperature; A second temperature drop coefficient is determined based on the first target temperature and the third target temperature, and the determination result of the coupled thermal fault caused by the vibration is verified according to the second temperature drop coefficient.

6. The fault detection method for railway substations as described in claim 5, characterized in that, The verification of the determination result of the vibration-induced coupled thermal fault based on the second temperature drop coefficient includes: The second temperature drop coefficient is compared with a preset temperature drop coefficient threshold. If the second temperature drop coefficient is less than the temperature drop coefficient threshold, the determination result of the coupled thermal fault caused by vibration is confirmed, and a first-level maintenance warning is generated. The first-level maintenance warning is used to prompt the mechanical connection status check or electromagnetic component status check of the target power device.

7. The fault detection method for railway substations as described in claim 6, characterized in that, After generating the Level 1 maintenance early warning, the method further includes: Obtain the historical temperature variation curve and historical vibration parameter variation curve of the target power device; Based on the historical variation curves, the current temperature drop coefficient, and the target vibration parameters, a fault development trend model is constructed. Based on the fault development trend model, predict the remaining time window for the vibration-induced coupled thermal fault to develop from its current state to a severe fault; If the remaining time window is less than a preset safe time threshold, a level two emergency warning is generated, which is used to prompt immediate maintenance.

8. The fault detection method for railway substations as described in claim 5, characterized in that, The step of determining the opening angles of the first and second heat dissipation flaps based on the wind direction information to obtain the first target angle and the second target angle includes: Based on the wind direction information, determine the angle between the wind direction and the normal direction of the side of the railway substation; Based on the included angle, the current wind direction is determined relative to the incoming direction of the railway substation. The side directly exposed to the wind is determined as the air intake side, and the other side is determined as the air outlet side. If the left side of the first heat dissipation flip plate is the air intake side, then the first target angle of the first heat dissipation flip plate is set to the air intake guide angle parallel to the airflow direction according to the included angle; at the same time, the second target angle of the second heat dissipation flip plate is set to the air outlet heat exhaust angle of 90° so that the right side is completely open to form a heat exhaust channel. If the right side of the second heat dissipation flip plate is the air intake side, then the second target angle of the second heat dissipation flip plate is set to the air intake guide angle parallel to the airflow direction according to the included angle; at the same time, the first target angle of the first heat dissipation flip plate is set to the air outlet heat exhaust angle of 90° so that the left side is completely open to form a heat exhaust channel.

9. The fault detection method for railway substations as described in claim 1, characterized in that, The first temperature drop coefficient is calculated using the formula K=(T1-T2) / T1×100%, where T1 is the first target temperature and T2 is the second target temperature.

10. An electronic device, characterized in that, include: The memory is used to store program code; as well as A processor, the processor being configured to invoke the program code to perform the method as described in any one of claims 1 to 9.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 9.

Images