Locomotive circuit detection method and device, computer equipment, readable storage medium and program product

Abstract

The application relates to a locomotive circuit detection method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: obtaining circuit structure information, real-time running information of a circuit and a pre-constructed circuit state feature map of a locomotive; generating a three-dimensional circuit model of the locomotive based on the circuit structure information; comparing and analyzing the real-time running information of the circuit and the circuit state feature map to determine a circuit detection result of the locomotive; and presenting the circuit detection result in the three-dimensional circuit model. The method can improve the accuracy of locomotive circuit detection.

Description

Technical Field

[0001] This application relates to the field of electric locomotive technology, and in particular to a locomotive circuit detection method, apparatus, computer equipment, computer-readable storage medium, and computer program product. Background Technology

[0002] With the development of electric locomotive technology, intelligent locomotive operation and maintenance and fault diagnosis technology has emerged. This technology aims to achieve dynamic monitoring of the locomotive's health status and early warning of faults by collecting and analyzing the operating data of various locomotive systems in real time, thereby improving the safety and reliability of locomotive operation and reducing operation and maintenance costs.

[0003] In traditional technology, several sensors and detection devices are usually deployed in the locomotive circuit to collect electrical parameters such as voltage, current, and temperature, which are then presented to maintenance personnel in the form of two-dimensional tables, curves, or text reports. Maintenance personnel then analyze and judge based on their own experience or by referring to paper circuit diagrams to determine whether there are any abnormalities in the circuit and the specific location and type of the abnormality. However, the process of judging based on the maintenance personnel's own experience is prone to subjectivity. Therefore, the traditional locomotive circuit detection process has the problem of inaccurate detection. Summary of the Invention

[0004] Therefore, it is necessary to provide a locomotive circuit testing method, apparatus, computer equipment, computer-readable storage medium, and computer program product that can improve the accuracy of locomotive circuit testing in response to the above-mentioned technical problems.

[0005] In a first aspect, this application provides a locomotive circuit testing method, including:

[0006] Acquire the locomotive's circuit structure information, real-time circuit operation information, and pre-constructed circuit state characteristic map;

[0007] A three-dimensional circuit model of the locomotive is generated based on the circuit structure information;

[0008] The real-time operating information of the circuit is compared and analyzed with the circuit state feature map to determine the circuit detection results of the locomotive;

[0009] The circuit detection results are presented in the three-dimensional circuit model.

[0010] In one embodiment, generating a three-dimensional circuit model of the locomotive based on the circuit structure information includes:

[0011] The structural parameters of the locomotive are determined by performing feature recognition on the circuit structure information.

[0012] The structural parameters are converted into a structured netlist;

[0013] Based on the component connection relationships in the structured netlist, a three-dimensional circuit model of the locomotive is generated.

[0014] In one embodiment, the circuit state feature map includes a normal circuit state feature map and a circuit abnormal state feature map; the step of comparing and analyzing the real-time circuit operation information with the circuit state feature map to determine the locomotive's circuit detection result includes:

[0015] Extract the operating feature vector of the real-time operating information of the circuit;

[0016] The running feature vector is matched with the circuit normal state feature map and the circuit abnormal state feature map respectively. The circuit state of the circuit state feature map with the highest matching degree is taken as the circuit state of the real-time running information of the circuit.

[0017] When the circuit is in an abnormal state, the circuit detection result of the locomotive is determined based on the matching relationship between the operating feature vector and the circuit abnormal state feature map.

[0018] In one embodiment, the circuit abnormal state feature map includes multiple map nodes; determining the locomotive's circuit detection result based on the matching relationship between the operating feature vector and the circuit abnormal state feature map includes:

[0019] The running feature vector is matched with the plurality of graph nodes respectively to determine the degree of matching between the running feature vector and the plurality of graph nodes respectively;

[0020] The circuit test results of the locomotive are determined based on the target node with the highest matching degree.

[0021] In one embodiment, the method is applied to terminal glasses; the method further includes:

[0022] Acquire the locomotive image captured by the terminal glasses;

[0023] The three-dimensional circuit model is fused with the locomotive image, and the fused image is displayed on the display interface of the terminal glasses.

[0024] The interactive terminal performs a marking operation on the fused image; the interactive terminal interacts with the terminal glasses.

[0025] The labeling operation is displayed in the fused image.

[0026] In one embodiment, the method further includes:

[0027] Obtain maintenance operations performed on the locomotive;

[0028] If the maintenance operation does not match the circuit test results, a reminder signal corresponding to the circuit test results will be issued.

[0029] Secondly, this application also provides a locomotive circuit testing device, comprising:

[0030] The information acquisition module is used to acquire the locomotive's circuit structure information, real-time circuit operation information, and pre-constructed circuit state feature map.

[0031] The model generation module is used to generate a three-dimensional circuit model of the locomotive based on the circuit structure information.

[0032] The circuit test result determination module is used to compare and analyze the real-time operation information of the circuit with the circuit state feature map to determine the circuit test result of the locomotive.

[0033] The circuit detection result presentation module is used to present the circuit detection results in the three-dimensional circuit model.

[0034] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of the method described above.

[0035] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, implements the steps of the method described above.

[0036] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the steps of the method described above.

[0037] The aforementioned locomotive circuit detection methods, devices, computer equipment, computer-readable storage media, and computer program products, by acquiring the locomotive's circuit structure information, real-time circuit operation information, and pre-constructed circuit state feature maps, provide a comprehensive and multi-dimensional data foundation for subsequent 3D modeling and intelligent diagnosis. This enables the diagnostic process to possess both static structural cognition and dynamic operational perception. Based on the circuit structure information, a 3D circuit model of the locomotive is generated, transforming abstract circuit topology relationships into an intuitive 3D spatial visualization. This allows maintenance personnel to clearly understand the connection relationships and spatial layout between various electrical components, reducing reliance on specialized knowledge. By comparing and analyzing real-time circuit operation information with the pre-constructed circuit state feature maps, deep correlation matching of real-time data can be performed using historical operating patterns and typical fault characteristics. This accurately identifies early anomalies and hidden faults that are difficult to detect using traditional threshold methods, significantly improving the accuracy and comprehensiveness of circuit detection results. Finally, the circuit detection results are presented in the 3D circuit model, directly mapping fault information to specific components and locations in the 3D model, achieving visualized fault location. This allows maintenance personnel to quickly and intuitively pinpoint the fault point, improving the accuracy of locomotive circuit detection. Attached Figure Description

[0038] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0039] Figure 1 This is a diagram illustrating the application environment of a locomotive circuit detection method in one embodiment;

[0040] Figure 2 This is a flowchart illustrating a locomotive circuit detection method in one embodiment;

[0041] Figure 3 This is a system architecture diagram of the system required to implement the locomotive circuit detection method in one embodiment;

[0042] Figure 4 This is a schematic diagram illustrating the 3D dynamic graphics generation principle of a locomotive circuit detection method in one embodiment.

[0043] Figure 5 This is a natural language interaction diagram of a locomotive circuit detection method in one embodiment;

[0044] Figure 6 This is a flowchart illustrating the locomotive circuit detection method in another embodiment;

[0045] Figure 7 This is a structural block diagram of a locomotive circuit detection device in one embodiment;

[0046] Figure 8 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0047] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0048] The locomotive circuit detection method provided in this application embodiment can be applied to, for example... Figure 1 In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be integrated onto server 104 or located on the cloud or other network servers. Terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, projection devices, etc. Portable wearable devices can include smartwatches, smart bracelets, head-mounted devices, etc. Head-mounted devices can be virtual reality (VR) devices, augmented reality (AR) devices, smart glasses, etc. Server 104 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. Specifically, during the locomotive circuit detection process, server 104 obtains the locomotive's circuit structure information, real-time circuit operation information, and pre-constructed circuit state feature map from terminal 102; generates a three-dimensional circuit model of the locomotive based on the circuit structure information; compares and analyzes the real-time circuit operation information with the circuit state feature map to determine the locomotive's circuit detection results; and presents the circuit detection results in the three-dimensional circuit model.

[0049] In one exemplary embodiment, such as Figure 2 As shown, a locomotive circuit testing method is provided, which is applied to... Figure 1 Taking server 102 as an example, the explanation includes the following steps S202 to S208. Wherein:

[0050] Step S202: Obtain the locomotive's circuit structure information, real-time circuit operation information, and pre-constructed circuit state feature map.

[0051] The locomotive's circuit structure information refers to the composition of all electrical circuits within the locomotive, including the model, serial number, and location coordinates of each electrical component (such as contactors, relays, circuit breakers, resistors, capacitors, transformers, etc.), as well as the connection relationships between these components via wires or busbars—that is, which terminal of which component is connected to which terminal of another component, forming a complete circuit topology. This information is typically derived from the locomotive's electrical design drawings and bill of materials data at the time of manufacture. Real-time circuit operation information refers to the electrical parameter data actually collected from each circuit circuit at the current operating moment or within a recent period, including but not limited to voltage, current, power, and temperature values, switch on / off states, and the operational status of each protection device. This data is obtained in real-time from sensors, acquisition modules, and the network control system installed on the locomotive. A pre-constructed circuit state feature map refers to a set of feature maps summarizing the normal and various abnormal states of a circuit, compiled before the locomotive is put into service or during long-term operation and maintenance, based on a large amount of historical operating data, typical fault cases, and expert experience. This circuit state feature map can be in the form of a feature image or a feature lookup table. A feature image is a pre-built graph structure database where each node represents a circuit state, and there are connections between nodes, indicating transitions or associations between different states. It is not a series of tables, but a structured graph. By matching the current feature vector against this image and seeing which node the vector falls near, the current circuit state can be determined. The role of the map is to organize the relationships between various circuit states together, which is more complete than a single feature lookup table. The comparison is not just with a fixed value, but finds the best match within the entire graph structure. The feature lookup table records the range of electrical parameters, the relationships between parameters, and the judgment rules for each circuit state (normal, overload, short circuit, open circuit, poor contact, component aging, etc.). It is equivalent to a known "standard answer library" used to compare with real-time data.

[0052] Specifically, the system first retrieves circuit structure information from the locomotive's electrical design database or onboard control system to obtain a list of all electrical components and their connections. Then, the server collects real-time operational data such as voltage, current, switch status, and temperature from various sensors and detection modules via the locomotive's network communication interface. Simultaneously, it retrieves a pre-constructed circuit state characteristic map from local storage or a cloud database. This map contains parameter characteristics and judgment conditions corresponding to various normal and abnormal circuit states. All three types of data are loaded into the system memory to prepare for subsequent modeling and analysis.

[0053] Step S204: Generate a three-dimensional circuit model of the locomotive based on the circuit structure information.

[0054] Among them, the three-dimensional circuit model refers to a digital model constructed in a computer according to the actual spatial proportions and relative positions of the various electrical components and connecting wires inside the locomotive, based on the circuit structure information. In this model, each electrical component has a corresponding three-dimensional shape and spatial coordinates, and the wires connect the components in the form of three-dimensional lines or pipes, presenting the true layout of the locomotive's circuit system in physical space.

[0055] Specifically, based on the circuit structure information obtained in step S202, the server first locates all electrical components in spatial coordinates according to their actual installation positions on the locomotive. Then, based on the physical dimensions and appearance of each component in the component list, a corresponding three-dimensional geometric model is generated in three-dimensional space; for example, circuit breakers are generated as cubes, contactors as cubes with contact points, and cables as cylindrical lines. Next, based on the connection relationship information, three-dimensional connections are drawn between the corresponding terminals of each component to form a complete circuit trace. Finally, all components and connections are combined to generate a complete, rotatable, scalable, and viewable three-dimensional circuit model of the locomotive. This model not only reflects the topological connections of the circuit but also the actual spatial positions of each component on the locomotive. For example, the server can perform feature recognition on the circuit structure information to determine the structural parameters of the locomotive, convert the structural parameters into a structured netlist, and generate a three-dimensional circuit model of the locomotive based on the component connection relationships in the structured netlist. Alternatively, the circuit structure information can be input into a pre-trained neural network model, and the output of the model is the three-dimensional circuit model of the locomotive.

[0056] Step S206: Compare and analyze the real-time circuit operation information with the circuit status characteristic map to determine the circuit detection results of the locomotive.

[0057] The circuit test results refer to the conclusions drawn after comparison and analysis, including whether each circuit loop is in a normal state or has some kind of abnormality, and if there is an abnormality, what type of abnormality it is (such as overload, short circuit, open circuit, poor contact, etc.), and which loop and which component the abnormality occurred in.

[0058] Specifically, the server needs to compare the real-time voltage, current, temperature, and switch status data of each circuit collected in step S202 with the various status features recorded in the circuit status feature map. For example, if the circuit status feature map is in the form of a feature lookup table, the server can directly compare each piece of the real-time circuit operation information with the various status features recorded in the circuit status feature map. For instance, if the real-time current value of a certain circuit is 120A, the server searches the feature map for the anomaly type corresponding to a current of 120A with low voltage and high temperature. It finds that this combination of features matches the anomaly state of "local overheating caused by poor contact." The server needs to perform this comparison and matching operation on all circuits one by one, and finally summarize the detection results of all circuits in the entire locomotive, clearly indicating which circuits are normal, which circuits have anomalies, and the specific type and location of the anomalies. When the circuit state feature map is in the form of a feature image, the server can extract the running feature vector of the circuit's real-time operation information, match the running feature vector with the circuit's normal state feature map and circuit's abnormal state feature map respectively, and take the circuit state of the circuit state feature map with the highest matching degree as the circuit state of the circuit's real-time operation information. When the circuit state is abnormal, the circuit detection result of the locomotive is determined based on the matching relationship between the running feature vector and the circuit abnormal state feature map.

[0059] Step S208: Present the circuit test results in the three-dimensional circuit model.

[0060] Specifically, the server maps the detection results of each circuit obtained in step S206 back to the corresponding components and circuits in the 3D circuit model generated in step S204. Circuits with normal detection results have their corresponding components and wires displayed in the 3D model in normal colors (e.g., green); circuits with abnormal detection results have their corresponding components and wires highlighted in abnormal colors (e.g., red or yellow), with the specific abnormality type (e.g., "overload," "short circuit," "poor contact") and real-time abnormal parameter values ​​labeled next to the component. Users can directly click on the highlighted components in the 3D model to view detailed detection data and abnormal descriptions, and can also rotate and zoom the model to view the abnormal distribution of the entire locomotive circuit from different angles, thereby quickly locating the fault point.

[0061] The aforementioned locomotive circuit detection method, by acquiring the locomotive's circuit structure information, real-time circuit operation information, and pre-constructed circuit state feature maps, provides a comprehensive and multi-dimensional data foundation for subsequent 3D modeling and intelligent diagnosis. This enables the diagnostic process to possess both static structural cognition and dynamic operational perception. Based on the circuit structure information, a 3D circuit model of the locomotive is generated, transforming abstract circuit topology relationships into an intuitive 3D spatial visualization. This allows maintenance personnel to clearly understand the connection relationships and spatial layout between various electrical components, reducing reliance on specialized knowledge. Comparing and analyzing real-time circuit operation information with the pre-constructed circuit state feature maps allows for deep correlation matching of real-time data, combining historical operating patterns and typical fault characteristics. This accurately identifies early anomalies and hidden faults that are difficult to detect using traditional threshold methods, significantly improving the accuracy and comprehensiveness of circuit detection results. Finally, the circuit detection results are presented in the 3D circuit model, directly mapping fault information to specific components and locations in the 3D model, achieving visualized fault location. This enables maintenance personnel to quickly and intuitively pinpoint the fault point, improving the accuracy of locomotive circuit detection.

[0062] In one exemplary embodiment, generating a three-dimensional circuit model of a locomotive based on circuit structure information includes: performing feature recognition on the circuit structure information to determine the structural parameters of the locomotive; converting the structural parameters into a structured netlist; and generating a three-dimensional circuit model of the locomotive based on the component connection relationships in the structured netlist.

[0063] Feature recognition involves automatically parsing the text or data in the circuit structure information to identify components, connections, and parameters, transforming unstructured design information into structured data that can be processed by a computer. Structural parameters, extracted after feature recognition, describe the physical layout of the locomotive's circuitry, including the coordinates of each component in three-dimensional space, the physical dimensions of each component, and the length and direction of each conductor. A structured netlist is a standard format data file that records all components in the circuit and their connections in a list format, with each line representing a component or connection. Computers can directly read this data and use it to generate graphical models.

[0064] Specifically, after receiving the locomotive's circuit structure information, the server first performs feature recognition on this information. This means the server automatically reads the data and identifies which content represents electrical components, which represents connections between components, and which represents the installation location and dimensions of components. This information is extracted from the original design documents to determine the structural parameters of the locomotive's circuitry, including the location of each component, its size, and the routing of each line segment. Then, the server converts these structural parameters into a structured netlist in a standardized format. This netlist is a clear list indicating what each component is, where it is located, and what it is connected to. Finally, the server reads this structured netlist and, based on the component connection relationships recorded in the netlist, draws each component in three-dimensional space according to its coordinates and dimensions. Then, it connects the components with lines according to their connection relationships, ultimately generating a complete three-dimensional circuit model of the locomotive that can be rotated and viewed on a computer.

[0065] In this embodiment, by performing feature recognition first, then converting to a netlist, and then modeling, the original circuit design data can be automatically converted into an interactive 3D model. This eliminates the need for manual modeling, improves modeling efficiency, and ensures the consistency between the model and the actual locomotive circuit structure. This provides an accurate base map for presenting the detection results on the 3D model.

[0066] In an exemplary embodiment, the circuit state feature map includes a normal circuit state feature map and a circuit abnormal state feature map. The real-time circuit operation information is compared and analyzed with the circuit state feature map to determine the locomotive's circuit detection result, including: extracting the operation feature vector of the real-time circuit operation information; matching the operation feature vector with the normal circuit state feature map and the circuit abnormal state feature map respectively, and taking the circuit state of the circuit state feature map with the highest matching degree as the circuit state of the real-time circuit operation information; when the circuit state is an abnormal circuit state, the locomotive's circuit detection result is determined based on the matching relationship between the operation feature vector and the circuit abnormal state feature map.

[0067] The circuit normal state feature map is a pre-constructed map composed of feature vectors describing the locomotive circuit under various normal operating conditions. Each node in the map represents a normal state, such as normal traction, normal braking, and normal auxiliary machinery. The circuit abnormal state feature map is a pre-constructed map composed of feature vectors describing the locomotive circuit under various abnormal fault states. Each node in the map represents an abnormal state, such as overload, short circuit, open circuit, and poor contact. The operational feature vector is a set of feature values ​​extracted from the real-time operating information of the circuit. It is a vector composed of key parameters of the current circuit in a unified order, used to represent the actual state of the current circuit. The circuit state is determined after matching to determine which state the current circuit belongs to—whether it is normal or an abnormal state.

[0068] Specifically, the server extracts parameters such as current voltage, current, temperature, and switch status of each circuit from the real-time circuit operation information, arranges them in a uniform order to form an operational feature vector, which represents the current actual state of the circuit. Then, based on this operational feature vector, the server first matches it with the circuit's normal state feature map, calculating its proximity to each normal state node in the normal map, finding the node closest to it, and recording the matching degree. Next, the same operational feature vector is compared with the circuit's abnormal state feature map, calculating its proximity to each abnormal state node in the abnormal map, finding the node closest to it, and recording the matching degree as well. Finally, the two matching degrees are compared. If the matching degree with the normal state feature map is higher, the current circuit is determined to be in a normal state; if the matching degree with the abnormal state feature map is higher, the current circuit is determined to be in that abnormal state. In the case of an abnormal circuit state, the server also needs to determine the locomotive's circuit detection result based on the matching relationship between the operational feature vector and the circuit abnormal state feature map. It is understandable that if the circuit is in a normal state, the server can directly determine that the locomotive's circuit test result is normal.

[0069] In this embodiment, by matching the running feature vector with two sets of feature maps, one normal and one abnormal, and taking the state of the map with the highest matching degree as the judgment result, it can cover both normal and abnormal situations at the same time, avoiding the possible omissions or misjudgments that may occur when comparing with only a single standard, and improving the accuracy of locomotive circuit detection.

[0070] In an exemplary embodiment, the circuit abnormal state feature map includes multiple map nodes; the circuit detection result of the locomotive is determined based on the matching relationship between the running feature vector and the circuit abnormal state feature map, including: matching the running feature vector with multiple map nodes respectively, and determining the matching degree between the running feature vector and the multiple map nodes respectively; and determining the circuit detection result of the locomotive based on the target node with the highest matching degree.

[0071] In this system, each node in the circuit anomaly feature map corresponds to a known circuit anomaly state. The node itself uses a feature vector to represent the typical behavior of various electrical parameters under that anomaly state. Multiple nodes in the map indicate the inclusion of various known anomaly state types. The matching degree is the similarity score between the running feature vector and a given map node; a higher score indicates a closer similarity, meaning the actual state of the current circuit matches the anomaly state represented by that node more closely. The target node is the map node with the highest matching degree to the running feature vector, representing the node that best embodies the actual anomaly state of the current circuit.

[0072] Specifically, the circuit anomaly state feature map contains multiple map nodes, each representing a known circuit anomaly state, and each node has its own corresponding feature vector. The system takes the operational feature vector extracted from real-time operational information and matches it against each map node in the map, calculating the similarity between the operational feature vector and the feature vector of each node, recording the matching degree for each node. Then, the server selects the node with the highest matching degree from these calculated results; this node is the target node, indicating that the current circuit's actual operational state is closest to the anomaly state represented by this target node. Finally, the system uses the anomaly state represented by this target node as the detection result for the current circuit, clearly informing the user of the specific anomaly.

[0073] In this embodiment, by matching the running feature vector with each node in the abnormal state feature map one by one, and selecting the target node with the highest matching degree to determine the detection result, it is possible to accurately find the one that best matches the current situation among a variety of known abnormal states, avoiding the misjudgment that may occur when comparing with only a single fixed standard, and improving the accuracy and precision of abnormal state determination.

[0074] In one exemplary embodiment, the method is applied to a terminal glasses; the method further includes: acquiring a locomotive image captured by the terminal glasses; fusing a three-dimensional circuit model with the locomotive image and displaying the fused image on the display interface of the terminal glasses; acquiring a marking operation performed by an interactive terminal on the fused image; the interactive terminal interacting with the terminal glasses; and displaying the marking operation in the fused image.

[0075] The terminal glasses are wearable smart display devices worn on the head. Maintenance personnel can see superimposed digital information in real-world scenarios while simultaneously capturing the actual scene in front of them using a camera. The locomotive image is the actual view of the locomotive captured by the camera on the terminal glasses – the locomotive as seen by the maintenance personnel. The fused image is a composite image created by overlaying a 3D circuit model onto the locomotive image. Maintenance personnel see not only the real locomotive in the terminal glasses but also the circuit model displayed at corresponding locations on the locomotive. The display interface is the area on the lenses of the terminal glasses used to display the image, allowing maintenance personnel to see the fused image. The interaction terminal is the device used by maintenance personnel to interact with the terminal glasses. This can be the touch or voice controls built into the terminal glasses, or a handheld remote control, mobile phone, etc. Marking operations are actions performed on the interaction terminal to annotate specific locations in the fused image, such as drawing a circle or marking a point with a finger on a component location to record or label a position.

[0076] Specifically, when this method is applied to terminal glasses, maintenance personnel wearing the glasses walk next to the locomotive. The camera on the glasses captures a real-time image of the locomotive. Simultaneously, the system retrieves a previously generated 3D circuit model and fuses it with the locomotive image captured by the camera, ensuring that the positions of components in the 3D model correspond one-to-one with the positions of components on the actual locomotive. The fused image is then displayed on the terminal glasses' interface, allowing maintenance personnel to see the circuit model superimposed on the corresponding locations while viewing the actual locomotive. When maintenance personnel discover a problem in a certain location, they can mark that location in the fused image using an interactive interface (such as voice, gestures, or a handheld remote control), for example, by drawing a circle on a component. This mark is displayed in real-time on the fused image and is linked to that location. Others viewing the same fused image can also see this mark, facilitating the transfer of location information during collaborative maintenance.

[0077] In this embodiment, by integrating a 3D circuit model and a real locomotive image on the terminal glasses, maintenance personnel do not need to look down at the screen and then look up at the locomotive. They can directly see the circuit model superimposed on the real locomotive in their field of vision, achieving an intuitive display that combines virtual and real elements. At the same time, the marking operation allows maintenance personnel to directly mark the location of the problem on-site and share it with others, improving the efficiency and collaboration of on-site maintenance.

[0078] In one exemplary embodiment, the method further includes: acquiring maintenance operations performed on the locomotive; and issuing a reminder signal corresponding to the circuit test results if the maintenance operations do not match the circuit test results.

[0079] Maintenance operations refer to the actual maintenance actions performed by maintenance personnel on the locomotive, such as replacing a component, tightening a terminal block, or adjusting a switch. These operations are recorded by the system. Alert signals are warning messages automatically issued by the system when mismatches occur. These can be pop-up notifications on the terminal glasses, audible alarms, vibrations, etc., aimed at alerting maintenance personnel to potential operational errors.

[0080] Specifically, during maintenance, the server continuously monitors the maintenance operations performed by the personnel on the locomotive, recording where and what the personnel are currently repairing. The server then compares this repair operation with the previously obtained circuit test results to see if the location of the repairs matches the fault location indicated in the test results. If they match, the repair direction is correct, and the server takes no further action. If they do not match—for example, if the test results indicate a fault in the main circuit contactor, but the personnel are actually repairing a fuse in the auxiliary circuit—the server determines this as a mismatch and immediately sends a warning signal. A pop-up notification or sound will appear on the terminal's display screen, clearly informing the personnel that "your current repair operation does not match the test results; please confirm if you are repairing the wrong location." This prevents personnel from repairing the wrong area and avoids unresolved faults or even new problems caused by misoperation.

[0081] In this embodiment, by comparing the actual operation of the maintenance personnel with the circuit test results in real time, and issuing a reminder when the two do not match, it can effectively prevent the maintenance personnel from repairing the wrong location or the wrong component, avoid ineffective repair or even secondary damage, ensure the accuracy of the maintenance operation, and at the same time make the test results truly play a guiding role in the maintenance.

[0082] In a specific embodiment, such as Figure 3As shown, this method is implemented by the following system, which adopts a layered architecture design from bottom to top: Data Perception Layer, AI (Artificial Intelligence) Core Engine Layer, 3D (Three Dimensions) Visualization Layer, and Application Service Layer. The Data Perception Layer is responsible for collecting physical data of the locomotive circuit, including data on lines, nodes, switches, voltage, current, etc., as well as on-site images captured by cameras. The AI ​​Core Engine Layer is the "brain" of the system, containing a fault diagnosis model, a circuit behavior simulation model, and a natural language processing module. The 3D Visualization Layer is responsible for rendering abstract data and simulation results into intuitive 3D dynamic graphics, providing a user interface. The Application Service Layer provides specific functions for different users (such as maintenance technicians, designers, and trainees), such as fault warning, auxiliary maintenance, and virtual training. The intelligent fault diagnosis and prediction module, such as... Figure 4 As shown, this module is based on AI algorithms, with its input connected to the data perception layer and its output connected to the 3D visualization layer and application service layer. Its internal structure includes a data preprocessing unit, a feature extraction unit, a fault classifier, and a prediction model.

[0083] Specifically, the system first models the vehicle's circuitry. An AI model (such as a deep neural network) learns from historical fault data and real-time data to establish feature maps of normal and abnormal circuit states. When real-time data is input, the model quickly identifies abnormal points deviating from the normal pattern and locates the fault source by comparing the feature maps. The 3D dynamic graphics generation and simulation module consists of a drawing parser, a 3D model generator, and a physics simulation engine. The drawing parser receives 2D circuit diagrams (CAD / PDF), the 3D model generator constructs the geometric model, and the physics simulation engine assigns realistic physical properties to the model. Utilizing computer vision technology (such as Qwen3-VL), the system automatically identifies component symbols, connections, and parameter values ​​in the circuit diagram, converting them into a structured netlist. For example, in the 3D generation process, the system primarily uses the parsed netlist to call a pre-built library of component 3D models and automatically performs spatial layout and wiring based on the connections to generate an initial 3D circuit scene. This process borrows from ReelMind.ai's AI video generation capabilities, which can convert static schematics into dynamic 3D rendering. In physics simulation, physics simulation engines (such as the Fysics engine) inject physical laws into 3D models, calculating and simulating dynamic processes such as current flow, electromagnetic field distribution, and heat conduction. The Natural Language Interaction and Assisted Design module, driven by a Large Language Model (LLM), includes a Natural Language Understanding (NLU) unit and an instruction execution unit. It serves as an intelligent interface between the user and the system. Figure 5 As shown in the diagram, this example (such as "check for short circuit risk") illustrates how user commands are parsed by the LLM and transformed into system operations, ultimately resulting in a visually appealing feedback. Specifically, the LLM, trained on a vast amount of locomotive circuit technical documents, maintenance manuals, and design specifications, is able to understand the natural language of the specialized domain. When a user inputs a command, the NLU unit parses its intent and translates it into an internal command that the system can execute. For instance, a maintenance technician might input into the system: "Check if this circuit has any historical faults." After analysis, the AI ​​would reply in natural language: "Found that a fault occurred in vehicle xx at xx time." Simultaneously, the potential fault path would be marked with a red dashed line in the 3D model.

[0084] Specifically, the implementation process of this system in a real-world scenario includes: the user uploads a 2D drawing of a locomotive headlight control circuit. The system automatically parses the drawing and generates a 3D circuit model containing a power supply, switch, relay, and headlight within seconds. The user clicks "Close Switch" in the 3D interface, and the simulation engine immediately calculates the circuit response. The visualization interface shows current flowing from the positive terminal of the power supply cabinet, through the closed switch and relay coil, forming a complete closed circuit, ultimately illuminating the headlight in the 3D model. The current path is clearly presented as a flowing light effect.

[0085] In a specific embodiment, such as Figure 6 As shown, a locomotive circuit testing method is also provided, including:

[0086] Step S601: Obtain the locomotive's circuit structure information, real-time circuit operation information, and pre-constructed circuit state feature map;

[0087] Step S602: Perform feature recognition on the circuit structure information to determine the structural parameters of the locomotive;

[0088] Step S603: Convert the structural parameters into a structured netlist;

[0089] Step S604: Generate a three-dimensional circuit model of the locomotive based on the component connection relationships in the structured netlist;

[0090] Step S605: Extract the operating feature vector of the circuit's real-time operating information;

[0091] Step S606: Match the running feature vector with the circuit normal state feature map and the circuit abnormal state feature map respectively, and take the circuit state of the circuit state feature map with the highest matching degree as the circuit state of the real-time running information of the circuit.

[0092] Step S607: When the circuit state is an abnormal state, the running feature vector is matched with multiple graph nodes respectively to determine the degree of matching between the running feature vector and the multiple graph nodes respectively.

[0093] Step S608: Determine the locomotive's circuit test results based on the target node with the highest matching degree;

[0094] Step S609: Present the circuit detection results in the three-dimensional circuit model;

[0095] Step S610: Obtain maintenance operations performed on the locomotive;

[0096] Step S611: If the maintenance operation and the circuit test results do not match, issue a reminder signal corresponding to the circuit test results.

[0097] In some optional embodiments, the method is applied to a terminal glasses, and the method includes: acquiring a locomotive image captured by the terminal glasses; fusing a three-dimensional circuit model with the locomotive image and displaying the fused image on the display interface of the terminal glasses; acquiring a marking operation performed by an interactive terminal on the fused image; the interactive terminal interacting with the terminal glasses; and displaying the marking operation in the fused image.

[0098] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0099] Based on the same inventive concept, this application also provides a locomotive circuit testing device for implementing the locomotive circuit testing method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more locomotive circuit testing device embodiments provided below can be found in the limitations of the locomotive circuit testing method described above, and will not be repeated here.

[0100] In one exemplary embodiment, such as Figure 7 As shown, a locomotive circuit testing device 700 is provided, including: an information acquisition module 702, a model generation module 704, a circuit testing result determination module 706, and a circuit testing result presentation module 708, wherein:

[0101] The information acquisition module 702 is used to acquire the locomotive's circuit structure information, real-time circuit operation information, and pre-constructed circuit state feature map;

[0102] Model generation module 704 is used to generate a three-dimensional circuit model of the locomotive based on circuit structure information;

[0103] The circuit test result determination module 706 is used to compare and analyze the real-time circuit operation information with the circuit state characteristic spectrum to determine the circuit test result of the locomotive.

[0104] The circuit test result presentation module 708 is used to present the circuit test results in the three-dimensional circuit model.

[0105] In one exemplary embodiment, the model generation module 704 is specifically used for:

[0106] Feature recognition is performed on the circuit structure information to determine the structural parameters of the locomotive;

[0107] Convert the structural parameters into a structured netlist;

[0108] A three-dimensional circuit model of the locomotive is generated based on the component connection relationships in the structured netlist.

[0109] In an exemplary embodiment, the circuit state feature map includes a normal circuit state feature map and an abnormal circuit state feature map. In this embodiment, the circuit detection result determination module 706 includes:

[0110] The feature vector extraction unit is used to extract the running feature vectors of the circuit's real-time operating information;

[0111] The circuit state determination unit is used to match the running feature vector with the circuit normal state feature map and the circuit abnormal state feature map respectively, and take the circuit state of the circuit state feature map with the highest matching degree as the circuit state of the real-time running information of the circuit.

[0112] The circuit detection result determination unit is used to determine the locomotive's circuit detection result based on the matching relationship between the operating feature vector and the circuit abnormality feature map when the circuit state is an abnormal circuit state.

[0113] In an exemplary embodiment, the circuit abnormal state feature map includes multiple map nodes. In this embodiment, the circuit detection result determination unit is specifically used for:

[0114] The running feature vector is matched with multiple graph nodes respectively to determine the degree of matching between the running feature vector and the multiple graph nodes respectively;

[0115] The circuit test results of the locomotive are determined based on the target node with the highest matching degree.

[0116] In one exemplary embodiment, the locomotive circuit detection device 700 is applied to terminal glasses and further includes an interaction module, specifically used for:

[0117] Acquire locomotive images captured by the terminal glasses;

[0118] The 3D circuit model is fused with the locomotive image, and the fused image is displayed on the terminal glasses' display interface.

[0119] Acquire the labeling operations performed by the interactive terminal on the fused image; the interactive terminal interacts with the terminal glasses;

[0120] Display the marking operations in the fused image.

[0121] In one exemplary embodiment, the locomotive circuit detection device 700 further includes a maintenance module, specifically used for:

[0122] To obtain maintenance operations performed on the locomotive;

[0123] If the maintenance operation does not match the circuit test results, a reminder signal corresponding to the circuit test results will be issued.

[0124] Each module in the aforementioned locomotive circuit testing device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0125] In one exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 8 As shown, the computer device includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The input / output interface is used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When the computer program is executed by the processor, it implements a locomotive circuit detection method. The display unit is used to form a visually visible image and can be a display screen, projection device, or virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0126] Those skilled in the art will understand that Figure 8The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0127] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the method described above.

[0128] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-described method.

[0129] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps of the method described above.

[0130] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0131] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0132] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0133] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for detecting locomotive circuits, characterized in that, The method includes: Acquire the locomotive's circuit structure information, real-time circuit operation information, and pre-constructed circuit state characteristic map; A three-dimensional circuit model of the locomotive is generated based on the circuit structure information; The real-time operating information of the circuit is compared and analyzed with the circuit state feature map to determine the circuit detection results of the locomotive; The circuit detection results are presented in the three-dimensional circuit model.

2. The method according to claim 1, characterized in that, The process of generating a three-dimensional circuit model of the locomotive based on the circuit structure information includes: The structural parameters of the locomotive are determined by performing feature recognition on the circuit structure information. The structural parameters are converted into a structured netlist; Based on the component connection relationships in the structured netlist, a three-dimensional circuit model of the locomotive is generated.

3. The method according to claim 1, characterized in that, The circuit state feature map includes a normal circuit state feature map and an abnormal circuit state feature map; the step of comparing and analyzing the real-time circuit operation information with the circuit state feature map to determine the locomotive's circuit detection results includes: Extract the operating feature vector of the real-time operating information of the circuit; The running feature vector is matched with the circuit normal state feature map and the circuit abnormal state feature map respectively. The circuit state of the circuit state feature map with the highest matching degree is taken as the circuit state of the real-time running information of the circuit. When the circuit is in an abnormal state, the circuit detection result of the locomotive is determined based on the matching relationship between the operating feature vector and the circuit abnormal state feature map.

4. The method according to claim 3, characterized in that, The circuit abnormal state feature map includes multiple map nodes; determining the locomotive's circuit detection result based on the matching relationship between the operating feature vector and the circuit abnormal state feature map includes: The running feature vector is matched with the plurality of graph nodes respectively to determine the degree of matching between the running feature vector and the plurality of graph nodes respectively; The circuit test results of the locomotive are determined based on the target node with the highest matching degree.

5. The method according to claim 1, characterized in that, The method is applied to terminal glasses; the method further includes: Acquire the locomotive image captured by the terminal glasses; The three-dimensional circuit model is fused with the locomotive image, and the fused image is displayed on the display interface of the terminal glasses. The interactive terminal performs a marking operation on the fused image; the interactive terminal interacts with the terminal glasses. The labeling operation is displayed in the fused image.

6. The method according to claim 5, characterized in that, The method further includes: Obtain maintenance operations performed on the locomotive; If the maintenance operation does not match the circuit test results, a reminder signal corresponding to the circuit test results will be issued.

7. A locomotive circuit testing device, characterized in that, The device includes: The information acquisition module is used to acquire the locomotive's circuit structure information, real-time circuit operation information, and pre-built circuit state feature map; The model generation module is used to generate a three-dimensional circuit model of the locomotive based on the circuit structure information. The circuit test result determination module is used to compare and analyze the real-time operation information of the circuit with the circuit state feature map to determine the circuit test result of the locomotive. The circuit detection result presentation module is used to present the circuit detection results in the three-dimensional circuit model.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. 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 6.

10. A computer program product, comprising a computer program, 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 6.

Images