Digital twin detection method, system, equipment and medium for train operation status

Abstract

The present application relates to the field of train equipment detection, and provides a digital twin detection method, system, equipment and medium for train running status, taking the lowest temperature in the temperature data as the environmental input, taking the current data as the rated current input, inputting the environmental input and the rated current input into the digital twin model, and obtaining the electrothermal simulation distribution data of the high-voltage system; extracting the highest actual temperature and the simulated temperature of the target position corresponding to the actual temperature from the temperature data and the electrothermal simulation distribution data, respectively, and generating the corresponding actual temperature curve and simulated temperature curve based on the time change; by comparing the actual temperature and the simulated temperature, alarming the fault and outputting the infrared image of the corresponding position or area. The accuracy and real-time performance of the status monitoring of the train high-voltage system are improved, so as to timely discover the defects of the high-voltage system of the high-speed train, and provide a strong guarantee for the safe and stable operation of the train.

Description

Technical Field

[0001] The present application relates to the field of train equipment detection, and specifically, to a digital twin detection method, system, equipment and medium for train running status. Background Art

[0002] The contents of this section merely provide background information related to the present application and may not constitute prior art.

[0003] In the railway transportation system, the safe operation of trains is of vital importance. To ensure this, train status detection technology came into being, which aims to monitor the key performance indicators of the train in real time to promptly discover and resolve potential safety hazards. From a historical perspective, train status detection technology has undergone a significant transformation from traditional manual inspection to modern automated and intelligent detection. In the early days, the evaluation of train status mainly relied on manual inspection, which was not only inefficient but also prone to missing some subtle faults. With the development of electronic information technology, sensors and data acquisition technology have been introduced into train status detection, which has significantly improved the detection efficiency and accuracy.

[0004] In the prior art, a Chinese patent with announcement number CN111487558A discloses a train high-voltage system fault location device and method, which collects the current value of the high-voltage bus by respectively setting the first and second current detection components at the roof high-voltage bus of the first to-be-located car and the second to-be-located car of the train. The current acquisition module collects these current values ​​and transmits them to the analysis module. The analysis module combines the first fault information obtained from the traction converter and determines the location of the grounding fault point of the train high-voltage system according to the collected current value. This method improves the accuracy of fault location, especially in cars without pantographs, and can diagnose faults more effectively. However, in the process of detecting the running status of the train, this method relies on other equipment to directly access the high-voltage system for data collection and analysis. Although such a design is effective, it also brings potential risks: once a component inside the high-voltage system is damaged, due to the complex interactions and signal interference inside the system, it is difficult to determine the specific location of the damaged component based on existing data and analysis methods alone. Therefore, in view of the above-mentioned technical problems, a digital twin detection method for the running status of a train is needed. Summary of the invention

[0005] In order to solve the above-mentioned technical problems, the purpose of this application is to provide a digital twin detection method, system, equipment and medium for the running status of a train. By establishing a digital twin model to simulate the temperature changes in the high-voltage system and comparing the simulated temperature with the actual temperature, defects in the high-voltage system of the high-speed train can be discovered in time.

[0006] The purpose of this application is achieved through the following technical solutions:

[0007] In a first aspect, the present invention provides a digital twin detection method for a train running state, comprising a plurality of dual-spectrum thermal imagers and a current transformer, the method comprising:

[0008] Through multiple dual-spectrum thermal imagers, infrared images of different areas in the train high-voltage system and temperature data of each area are obtained; current data of the high-voltage system is obtained through current transformers;

[0009] The lowest temperature in the temperature data is used as the environmental input, and the current data is used as the rated current input. The environmental input and the rated current input are input into the digital twin model to obtain the electric and thermal simulation distribution data of the high-voltage system.

[0010] The digital twin model includes a geometric model and a thermodynamic model. The geometric model is constructed based on the size and assembly information of each component of the high-voltage system. The thermodynamic model calculates the heat generated by the heating device under different currents based on the size of the heating device in the geometric model. The heat generated is calculated based on the heat conduction equation corresponding to different materials in the geometric model to calculate the electric heat simulation distribution data of each point or area.

[0011] The highest actual temperature and the simulated temperature of the target position corresponding to the actual temperature are extracted from the temperature data and the electrothermal simulation distribution data respectively, and the corresponding actual temperature curve and simulated temperature curve are generated based on the time change; the actual temperature and the simulated temperature at any time are compared. If the difference between the actual temperature and the simulated temperature is greater than the preset range, or any actual temperature or simulated temperature is greater than the preset threshold, an alarm is issued and an infrared image of the corresponding position or area is output.

[0012] Furthermore, the digital twin model is constructed through the following steps:

[0013] According to the size and matching relationship of each component in the high-pressure system, a geometric model of the high-pressure system is established;

[0014] Based on Joule's law, a heat generation calculation formula is established according to the size and current of the heat generating device in the geometric model; based on Fourier's heat conduction law, a heat conduction equation is established;

[0015] Based on the coordinates of each point in the geometric model, taking the heat-generating device as the heat source and the calculation result of the heat conduction equation as the value of each point or area within the thermal radiation range of the heat source, an electrothermal simulation distribution formula is established.

[0016] Furthermore, the electrothermal simulation distribution formula is:

[0017]

[0018] in, To the target location and time The temperature, is the minimum temperature, is the heat of the ith heat source point, is the thermal conductivity, is a dummy time variable, The target location To the heat source The distance is the rated current flowing through the heating device, is the resistance of the heating device, and n is the number of heat source points.

[0019] Furthermore, after the alarm is issued and the infrared image of the corresponding position or area is output, the method further includes:

[0020] When the difference between the actual temperature and the simulated temperature is greater than the preset range, an alarm message indicating that the simulation result of the digital twin model is distorted is issued;

[0021] When the actual temperature is greater than the preset threshold, an alarm message indicating a high-voltage system failure is issued;

[0022] When the simulation temperature is greater than the preset threshold, an alarm message indicating that the digital twin model prediction is wrong is issued.

[0023] Furthermore, after the alarm information of the high voltage system failure is issued, it also includes:

[0024] Based on the edge detection algorithm, the contours of each component position on the infrared image are identified;

[0025] Compare the contour of each component with multiple preset models, where the multiple preset models are contour templates of different devices; record the contours whose comparison results are greater than a threshold value as the names of the corresponding preset models and save them to a name set;

[0026] The geometric model also includes the location information of each component. The name of the component at the target location or the corresponding area is obtained according to the coordinates of the target location.

[0027] According to the name of the component, the target contour corresponding to the matching same name is obtained, and the target contour is highlighted on the infrared image.

[0028] Furthermore, after highlighting the target contour on the infrared image, the method further includes:

[0029] According to the name corresponding to the target location, based on the current temperature of the target location, the corresponding execution program is found in the preset operation and maintenance strategy, which is used to control the corresponding components through the execution program to keep the temperature of the target location within the preset range.

[0030] Furthermore, after the alarm is issued and the infrared image of the corresponding position or area is output, the method further includes:

[0031] The target position triggering the alarm and the corresponding infrared image are stored in a preset storage unit as abnormal history data;

[0032] When new abnormal data is generated, the new abnormal data is matched with the abnormal historical data. If the same abnormal data is matched, the operation and maintenance plan adopted at that time is queried according to the maintenance log corresponding to the same abnormal data, and the operation and maintenance plan is displayed as a recommended plan; if the same abnormal data is not matched, it will not be processed.

[0033] In a second aspect, the present invention provides a digital twin detection system for train running status, comprising:

[0034] The data acquisition module is used to obtain infrared images of different areas of the high-voltage system and temperature data of each area through multiple dual-spectrum thermal imagers; and to obtain current data of the high-voltage system through current transformers;

[0035] A simulation module is used to use the lowest temperature in the temperature data as the environmental input and the current data as the rated current input, input the environmental input and the rated current input into the digital twin model, and obtain the electric and thermal simulation distribution data of the high-voltage system;

[0036] The digital twin model includes a geometric model and a thermodynamic model. The geometric model is constructed based on the size and assembly information of each component of the high-voltage system. The thermodynamic model calculates the heat generated by the heating device under different currents based on the size of the heating device in the geometric model. The heat generated is calculated based on the heat conduction equation corresponding to different materials in the geometric model to calculate the electric heat simulation distribution data of each point or area.

[0037] The alarm module is used to extract the highest actual temperature and the simulated temperature of the target position corresponding to the actual temperature from the temperature data and the electrothermal simulation distribution data, and generate the corresponding actual temperature curve and simulated temperature curve based on the time change; compare the actual temperature and the simulated temperature at any time, if the difference between the actual temperature and the simulated temperature is greater than the preset range, or any actual temperature or simulated temperature is greater than the preset threshold, an alarm is issued and an infrared image of the corresponding position or area is output.

[0038] In a third aspect, the present invention provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method steps of the first aspect when executing the computer program.

[0039] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the method steps of the first aspect.

[0040] In summary, the technical solution of the embodiment of the present application has at least the following advantages and beneficial effects:

[0041] The present invention uses multiple dual-spectrum thermal imagers to capture infrared images of different areas in the high-voltage system, and synchronously records the temperature data of these areas. At the same time, the current data of the high-voltage system is accurately obtained through the current transformer. These data together constitute a comprehensive perception of the current state of the high-voltage system. Then, the lowest value in the temperature data is regarded as the ambient temperature input, and the current data is regarded as the rated current input, and they are input into the digital twin model together. This model integrates the geometric model and thermodynamic model of the high-voltage system. The geometric model accurately reflects the size and assembly relationship of each component of the high-voltage system, while the thermodynamic model simulates and calculates the electrothermal simulation distribution data of each point under different currents based on the size of the heating device and the thermal conductivity characteristics of different materials. By comparing the actual temperature data with the highest temperature and its position in the electrothermal simulation distribution data, the actual temperature curve and the simulated temperature curve that change with time are generated. If at any time, the difference between the actual temperature and the simulated temperature exceeds the preset safety range, or any temperature value exceeds the preset threshold, the system will immediately trigger an alarm and output an infrared image of the corresponding position or area, so that the operator can quickly locate and deal with potential overheating or abnormal conditions. It improves the accuracy and real-time performance of the train's high-voltage system status monitoring and effectively reduces the risk of failure due to overheating, providing a strong guarantee for the safe and stable operation of the train. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 A flow chart of the digital twin detection method for train running status provided by the present invention;

[0043] Figure 2 It is a block diagram of the digital twin detection method of the train running status in the present invention;

[0044] Figure 3 It is a schematic diagram of the comparison between the simulated temperature and the actual temperature in the present invention;

[0045] Figure 4 A schematic diagram of the structure of the digital twin detection system for the train running status provided by the present invention. DETAILED DESCRIPTION

[0046] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various different configurations.

[0047] The embodiment of the present application proposes a digital twin detection method for the running status of a train, such as Figure 1 and 2 As shown, including:

[0048] S101, using multiple dual-spectrum thermal imagers, obtain infrared images of different areas in the train high-voltage system and temperature data of each area; and obtain current data of the high-voltage system through a current transformer.

[0049] The system uses multiple dual-spectrum thermal imagers to monitor different areas of the train's high-voltage system in real time, which can capture infrared images and temperature data at the same time, providing the system with an intuitive and detailed view of the thermal distribution. Infrared images reveal the temperature differences between areas, which is crucial for identifying hot spots. At the same time, current transformers are used to accurately obtain current data from the high-voltage system, which reflects the system's workload status. This step is the basis for data collection and provides key input for subsequent analysis.

[0050] S102, taking the lowest temperature in the temperature data as the environmental input, taking the current data as the rated current input, inputting the environmental input and the rated current input into the digital twin model to obtain the electrothermal simulation distribution data of the high voltage system.

[0051] The digital twin model consists of two parts: a geometric model and a thermodynamic model. The geometric model accurately replicates the size and assembly relationship of each component in the high-voltage system, ensuring the accuracy and authenticity of the simulation. The thermodynamic model calculates the heat generation at different current levels based on geometric information, especially the size of the heating device. Then, using the heat conduction equations corresponding to different materials in the geometric model, the model can calculate the electrothermal simulation distribution data for each point or area, thereby simulating the thermal state of the high-voltage system in actual operation. The digital twin model is constructed through the following steps:

[0052] According to the size and matching relationship of each component in the high-voltage system, a geometric model of the high-voltage system is established. Specifically, according to the actual size of each component in the high-voltage system and the matching relationship between each other, professional CAD (computer-aided design) software or similar modeling tools are used to accurately replicate the three-dimensional geometric model of the high-voltage system. This model not only includes the shape and size of each component, but also accurately reflects the assembly relationship and spatial position between them. Such a geometric model provides the necessary physical basis for subsequent thermodynamic analysis.

[0053] Based on Joule's law, a heat generation calculation formula is established according to the size and current of the heat generating device in the geometric model; based on Fourier's law of heat conduction, a heat conduction equation is established. Specifically, based on Joule's law, combined with the size of the heat generating device in the geometric model (such as the cross-sectional area and length of components such as resistors and inductors) and the current value passing through them, the heat generation of each heat generating device at different current levels can be calculated. The heat conduction equation is based on Fourier's law of heat conduction (the rate of heat transfer is proportional to the temperature gradient, and is related to the thermal conductivity, heat transfer area and temperature difference of the material), combined with the physical properties such as thermal conductivity of different materials in the geometric model. This equation describes how heat is transferred between different materials inside a high-voltage system.

[0054] Based on the coordinates of each point in the geometric model, the heat source is taken as the heat source, and the result of the heat conduction equation is taken as the value of each point or area within the heat radiation range of the heat source to establish the electric heat simulation distribution formula. The specific calculation steps are as follows:

[0055] Heat The calculation formula is:

[0056]

[0057] The heat conduction equation is based on Fourier's heat conduction law and can be expressed as:

[0058]

[0059] in, is the material density, is the specific heat capacity of the material; is the temperature; It’s time; is the thermal conductivity; is the heat source term per unit volume.

[0060] Considering that the heating devices such as wires run through the entire geometric model, there are multiple heat source points. We need to calculate the heat after the multiple heat source points are superimposed. Suppose there are n heat source points, and their coordinates are , then the target position Temperature It can be expressed as:

[0061]

[0062] in, By Heat source point at time The heat generated.

[0063] The variation of heat conduction with distance and time can be described by the solution of the heat conduction equation. For steady-state conditions, the solution to the heat conduction equation can be expressed as:

[0064]

[0065] in, The target location To the heat source The distance is the heat of the ith heat source point, To the target location and time The temperature, is the ambient temperature (minimum temperature).

[0066] Combining formulas (1) to (4), the electric heat simulation distribution formula is:

[0067]

[0068] in, is the rated current flowing through the heating device, is the resistance of the heating element, is the number of heat source points.

[0069] S103, extracting the highest actual temperature and the simulated temperature of the target position corresponding to the actual temperature from the temperature data and the electrothermal simulation distribution data, and generating corresponding actual temperature curves and simulated temperature curves based on time changes; comparing the actual temperature and the simulated temperature at any time, if the difference between the actual temperature and the simulated temperature is greater than a preset range, or any actual temperature or simulated temperature is greater than a preset threshold, an alarm is issued and an infrared image of the corresponding position or area is output.

[0070] Specifically, the system extracts the highest temperature value and the simulated temperature of its corresponding position (or area) from the actual temperature data and the electrothermal simulation distribution data, and generates an actual temperature curve and a simulated temperature curve over time. By comparing these two curves, the system can evaluate in real time whether the thermal state of the high-voltage system deviates from normal expectations. If the difference between the actual temperature and the simulated temperature at any time exceeds the preset safety range, or the temperature of either side exceeds the preset threshold alone, this will be regarded as a signal of potential failure. The system will immediately trigger the alarm mechanism and output an infrared image of the corresponding position or area so that the operator can quickly locate the problem and take appropriate measures.

[0071] In addition, after the alarm is triggered and the infrared image of the corresponding position or area is output, an alarm mechanism is added, including:

[0072] When the difference between the actual temperature and the simulated temperature is greater than the preset range, such as Figure 3As shown in area b, an alarm message is issued for distorted simulation results of the digital twin model. Specifically, this situation is caused by inaccurate model parameter settings, sensor data errors, or the model itself fails to fully reflect the complexity of the actual system. In order to remind operators to pay attention to the accuracy of the model, the system will issue an alarm message for distorted simulation results of the digital twin model. This alarm helps to promptly discover and correct problems in the model and ensure the effectiveness of subsequent analysis and prediction.

[0073] When the actual temperature is greater than the preset threshold, Figure 3 As shown in the middle c area, an alarm message of a high-voltage system failure is issued. Specifically, the failure may be caused by electrical problems such as overload, short circuit, poor contact, etc., or by thermal management problems such as excessive ambient temperature and poor heat dissipation. In order to respond to and handle these potential failures in a timely manner, the system will issue an alarm message of a high-voltage system failure. This alarm can prompt operators to take quick action to check and repair the fault point to ensure the safety and reliability of train operation.

[0074] When the simulation temperature is greater than the preset threshold, such as Figure 3 As shown in area a, an alarm message of a digital twin model prediction error is issued. Specifically, this is caused by the model failing to accurately reflect the dynamic changes of the actual system, or the deviation between the model parameters and the actual system. In order to remind operators to pay attention to the prediction ability of the model, the system will issue an alarm message of a digital twin model prediction error. This alarm helps to discover and adjust the model in a timely manner, and improve the prediction accuracy and robustness of the model.

[0075] Furthermore, after the alarm information of the high voltage system failure is issued, it also includes:

[0076] Based on the edge detection algorithm, the outline of the position of each component on the infrared image is identified. Specifically, when a high-voltage system fails and triggers an alarm, the system will first use infrared imaging technology to obtain a real-time image of the system. On this basis, through the edge detection algorithm, the system can automatically identify the outline of each key component in the infrared image. The edge detection algorithm outlines the shape of the object by detecting areas in the image where the pixel values ​​change significantly, that is, the edges. In the infrared image of the high-voltage system, this means that the edges of key components such as transformers, circuit breakers, and busbars will be accurately identified, providing basic data for subsequent steps. The effect is to ensure that the system can accurately capture the position and form of each component, providing an accurate basis for subsequent comparison and positioning.

[0077] The outline of each component is compared with multiple preset models, which are contour templates of different devices; the contours with a similarity greater than a threshold are recorded as the names of the corresponding preset models and saved in the name set. Specifically, after identifying the contours of each component, the system compares them with multiple preset models stored in the database. These preset models are templates made based on the contour features of different devices, representing the typical contours of specific devices. By calculating the similarity between the actual contour and the preset model, the system can identify each component in the image, and record the contours with a similarity greater than a preset threshold as the names of the corresponding preset models, and save them in the name set. The effect is that each component in the image can be quickly and accurately identified, providing accurate component names for subsequent highlighting.

[0078] The geometric model also includes the location information of each component, and the name of the component at the target location or the corresponding area is obtained according to the coordinates of the target location. Specifically, in the geometric model of the high-voltage system, the location information of each component is known. Therefore, when the system receives the coordinates of a target location, it can quickly determine which component the coordinates correspond to based on the location information in the geometric model. The coordinates of the target location can be converted into a specific component name, providing the necessary information for highlighting the component on the infrared image later.

[0079] According to the name of the component, the system matches the target contour corresponding to the same name in the name set, and highlights the target contour on the infrared image. Specifically, the system will find the corresponding contour in the name set according to the obtained component name, and highlight it on the infrared image. Highlighting highlights the edge or the entire area of ​​the target contour with a color or brightness different from other parts. It intuitively displays the location of the fault, allowing operators to quickly locate and take appropriate measures.

[0080] Furthermore, after highlighting the target contour on the infrared image, the method further includes:

[0081] According to the name corresponding to the target location, based on the current temperature of the target location, the corresponding execution program is found in the preset operation and maintenance strategy, which is used to control the corresponding components through the execution program to keep the temperature of the target location within the preset range.

[0082] After realizing the rapid location and visualization of the high-voltage system fault alarm, simply identifying the faulty component is not enough to ensure the stable operation of the system. Further measures need to be taken to control the temperature of the faulty component to prevent the fault from further deteriorating. Specifically, first, according to the name corresponding to the target location (that is, the highlighted faulty component), find the execution program that matches the current temperature of the component in the preset operation and maintenance strategy. These operation and maintenance strategies are formulated in advance based on the operating characteristics of the high-voltage system and the temperature tolerance range of each component, and include specific response measures for different temperature ranges.

[0083] For example, if the temperature of a component exceeds the normal operating range but has not yet reached a dangerous level, the operation and maintenance strategy will start the cooling system of the component or adjust its workload instructions. If the temperature is already extremely high, the operation and maintenance strategy will immediately cut off the power supply of the component to prevent it from being damaged or causing a larger failure. In addition, once an execution program that matches the current temperature is found, the system will immediately execute the program through the corresponding control mechanism (such as remote control system, automation equipment, etc.), thereby achieving temperature control of the faulty component, thereby effectively preventing the further development and expansion of the fault.

[0084] Furthermore, after the alarm is issued and the infrared image of the corresponding position or area is output, the method further includes:

[0085] The target location that triggered the alarm and the corresponding infrared image are stored in a preset storage unit as abnormal history data. When new abnormal data is generated, the new abnormal data is matched with the abnormal history data. If the same abnormal data is matched, the operation and maintenance plan adopted at that time is queried according to the maintenance log corresponding to the same abnormal data, and the operation and maintenance plan is displayed as a recommended plan; if the same abnormal data is not matched, it will not be processed.

[0086] Specifically, when the system detects new abnormal data again, it will match the new abnormal data with the stored abnormal historical data. This matching process may be based on a variety of factors, including but not limited to the location where the abnormality occurred, the features in the infrared image, and the specific values ​​of the abnormal data. If the system can match the abnormal historical data that is exactly the same as the new abnormal data, it will automatically query the operation and maintenance plan adopted at that time based on the maintenance log recorded in the abnormal historical data. This operation and maintenance plan has been verified in practice and is considered to be an effective solution for this type of abnormality.

[0087] The system then displays the operation and maintenance plan as a recommended plan, providing direct operation and maintenance guidance to the operator. This step greatly shortens the time for operators to find and formulate operation and maintenance plans, and improves the efficiency of troubleshooting. At the same time, since the recommended plan is based on historical data, it also has a certain degree of reliability and accuracy. If the system fails to match the abnormal historical data that is the same as the new abnormal data, it will not perform any processing, but wait for the operator to make judgments and decisions based on the current situation. This design not only ensures the flexibility of the system, but also avoids the recommendation of incorrect operation and maintenance plans due to mismatching.

[0088] Based on the same inventive concept, Figure 4 As shown, the present invention provides a digital twin detection system for train running status, comprising:

[0089] The data acquisition module 201 is used to acquire infrared images of different areas of the high-voltage system and temperature data of each area through multiple dual-spectrum thermal imagers; and to acquire current data of the high-voltage system through current transformers;

[0090] The simulation module 202 is used to use the lowest temperature in the temperature data as the environmental input and the current data as the rated current input, input the environmental input and the rated current input into the digital twin model, and obtain the electric and thermal simulation distribution data of the high-voltage system;

[0091] The digital twin model includes a geometric model and a thermodynamic model. The geometric model is constructed based on the size and assembly information of each component of the high-voltage system. The thermodynamic model calculates the heat generated by the heating device under different currents based on the size of the heating device in the geometric model. The heat generated is calculated based on the heat conduction equation corresponding to different materials in the geometric model to calculate the electric heat simulation distribution data of each point or area.

[0092] The alarm module 203 is used to extract the highest actual temperature and the simulated temperature of the target position corresponding to the actual temperature from the temperature data and the electrothermal simulation distribution data, and generate the corresponding actual temperature curve and simulated temperature curve based on the time change; compare the actual temperature and the simulated temperature at any time, if the difference between the actual temperature and the simulated temperature is greater than the preset range, or any actual temperature or simulated temperature is greater than the preset threshold, an alarm is issued and an infrared image of the corresponding position or area is output.

[0093] Based on the same inventive concept, the present invention provides an electronic device, characterized in that the electronic device includes: a memory, a processor, and a computer program stored in the memory and runnable on the processor, and when the processor executes the computer program, a digital twin detection method for the train running status is implemented.

[0094] Based on the same inventive concept, the present invention provides a computer-readable storage medium on which a computer program is stored, characterized in that when the program is executed by a processor, a digital twin detection method for a train running status is implemented.

[0095] The above are only preferred embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A digital twin detection method for train running status, characterized in that: The method comprises a plurality of dual-spectrum thermal imagers and a current transformer, and comprises: Acquire infrared images of different areas in the train high-voltage system and temperature data of each area through a plurality of the dual-spectrum thermal imagers; acquire current data of the high-voltage system through the current transformer; Taking the lowest temperature in the temperature data as the environmental input, taking the current data as the rated current input, inputting the environmental input and the rated current input into the digital twin model, and obtaining the electrothermal simulation distribution data of the high-voltage system; The digital twin model includes a geometric model and a thermodynamic model. The geometric model is constructed according to the size and assembly information of each component of the high-voltage system. The thermodynamic model calculates the calorific value of the heating device under different currents according to the size of the heating device in the geometric model. The calorific value is calculated according to the heat conduction equation corresponding to different materials in the geometric model. The electric heat simulation distribution data of each point or area is calculated. The highest actual temperature and the simulated temperature of the target position corresponding to the actual temperature are extracted from the temperature data and the electrothermal simulation distribution data respectively, and the corresponding actual temperature curve and simulated temperature curve are generated based on the time change; the actual temperature and the simulated temperature at any time are compared, and if the difference between the actual temperature and the simulated temperature is greater than a preset range, or any actual temperature or simulated temperature is greater than a preset threshold, an alarm is issued and an infrared image of the corresponding position or area is output; wherein the digital twin model is constructed by the following steps: Establishing a geometric model of the high-pressure system according to the size and matching relationship of each component in the high-pressure system; Based on Joule's law, a heat generation calculation formula is established according to the size and current of the heat generating device in the geometric model; based on Fourier's law of heat conduction, a heat conduction equation is established; Based on the coordinates of each point in the geometric model, taking the heating device as the heat source and the calculation result of the heat conduction equation as the value of each point or area within the heat radiation range of the heat source, an electrothermal simulation distribution formula is established; The electrothermal simulation distribution formula is: in, To the target location and time The temperature, is the minimum temperature, is the heat of the ith heat source point, is the thermal conductivity, is a dummy time variable, The target location To the heat source The distance is the rated current flowing through the heating device, is the resistance of the heating element, Indicates the number of heat source points.

2. The digital twin detection method according to claim 1, characterized in that: After the alarm is given and the infrared image of the corresponding position or area is output, the method further includes: When the difference between the actual temperature and the simulated temperature is greater than a preset range, an alarm message indicating that the simulation result of the digital twin model is distorted is issued; When the actual temperature is greater than a preset threshold, an alarm message indicating that the high-voltage system has a fault is issued; When the simulation temperature is greater than a preset threshold, an alarm message indicating that the digital twin model prediction is wrong is issued.

3. The digital twin detection method according to claim 2, characterized in that: After the alarm information of the high voltage system failure is issued, the method further includes: Based on an edge detection algorithm, identifying the contours of the positions of the components on the infrared image; Compare the contour of each component with a plurality of preset models, where the plurality of preset models are contour templates of different devices respectively; record the contours whose comparison results are similarities greater than a threshold as the names of the corresponding preset models, and save them into a name set; The geometric model also includes the location information of each component, and the name of the component where the target position or the corresponding area is located is obtained according to the coordinates of the target position. According to the matching of the names of the components in the name set, the target contour corresponding to the matching identical name is obtained, and the target contour is highlighted on the infrared image.

4. The digital twin detection method according to claim 3, characterized in that: After highlighting the target outline on the infrared image, the method further includes: According to the name corresponding to the target location, based on the current temperature of the target location, a corresponding execution program is searched in the preset operation and maintenance strategy, so as to control the corresponding components through the execution program to keep the temperature of the target location within a preset range.

5. The digital twin detection method according to claim 1, characterized in that: After the alarm is given and the infrared image of the corresponding position or area is output, the method further includes: The target position triggering the alarm and the corresponding infrared image are stored in a preset storage unit as abnormal history data; When new exception data is generated, the new exception data is matched with the exception historical data. If the same exception data is matched, the operation and maintenance plan adopted at that time is queried according to the maintenance log corresponding to the same exception data, and the operation and maintenance plan is displayed as a recommended plan; if the same exception data is not matched, it will not be processed.

6. A digital twin detection system for train running status, characterized in that: Applied to the digital twin detection method according to claim 1, the system comprises: A data acquisition module, used to acquire infrared images of different areas of the high-voltage system and temperature data of each area through a plurality of the dual-spectrum thermal imagers; and to acquire current data of the high-voltage system through the current transformer; A simulation module, used for taking the lowest temperature in the temperature data as an environmental input quantity and the current data as a rated current input quantity, inputting the environmental input quantity and the rated current input quantity into a digital twin model, and obtaining the electrothermal simulation distribution data of the high voltage system; The digital twin model includes a geometric model and a thermodynamic model. The geometric model is constructed according to the size and assembly information of each component of the high-voltage system. The thermodynamic model calculates the calorific value of the heating device under different currents according to the size of the heating device in the geometric model. The calorific value is calculated according to the heat conduction equation corresponding to different materials in the geometric model. The electric heat simulation distribution data of each point or area is calculated. An alarm module is used to extract the highest actual temperature and the simulated temperature of the target position corresponding to the actual temperature from the temperature data and the electrothermal simulation distribution data, respectively, and generate corresponding actual temperature curves and simulated temperature curves based on time changes; compare the actual temperature and the simulated temperature at any time, if the difference between the actual temperature and the simulated temperature is greater than a preset range, or any actual temperature or simulated temperature is greater than a preset threshold, an alarm is issued and an infrared image of the corresponding position or area is output; wherein the digital twin model is constructed by the following steps: Establishing a geometric model of the high-pressure system according to the size and matching relationship of each component in the high-pressure system; Based on Joule's law, a heat generation calculation formula is established according to the size and current of the heat generating device in the geometric model; based on Fourier's law of heat conduction, a heat conduction equation is established; Based on the coordinates of each point in the geometric model, taking the heating device as the heat source and the calculation result of the heat conduction equation as the value of each point or area within the heat radiation range of the heat source, an electrothermal simulation distribution formula is established; The electrothermal simulation distribution formula is: in, To the target location and time The temperature, is the minimum temperature, is the heat of the ith heat source point, is the thermal conductivity, is a dummy time variable, The target location To the heat source The distance is the rated current flowing through the heating device, is the resistance of the heating element, Indicates the number of heat source points.

7. An electronic device, characterized in that: The electronic device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps corresponding to the digital twin detection method described in any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps corresponding to the digital twin detection method as described in any one of claims 1 to 5 are implemented.

Images