Vehicle-mounted train control data multi-dimensional association method based on knowledge graph and related device

Abstract

The invention discloses a vehicle-mounted train control data multi-dimensional association method based on a knowledge graph and a related device, and relates to the technical field of vehicle-mounted train control data analysis. Braking and speed core data and other associated auxiliary data are obtained firstly, and the data are divided into a core association layer and an auxiliary association layer according to the association degree with the core data; after the entities are defined, the entities are accurately extracted in a mixed mode of rules and machine learning, and an incidence relation is extracted in combination with an attention mechanism model and a domain dictionary; after knowledge fusion, constructing a vehicle-mounted train control data knowledge graph and storing the vehicle-mounted train control data knowledge graph in a graph database; multi-dimensional analysis such as brake and speed real-time association and abnormal traceability is achieved based on the map, a structured report and a visual map are output, operation monitoring, fault diagnosis and operation optimization scenes are adapted, and map data are stored after a train stops. According to the method, accurate association of multi-source heterogeneous data is realized, the fault processing time is greatly shortened, the train energy consumption is reduced, and the train operation safety, reliability and operation efficiency are effectively improved.

Description

Technical Field

[0001] This application relates to the field of onboard train control data analysis technology, and in particular to a knowledge graph-based method and related apparatus for multidimensional association of onboard train control data. Background Technology

[0002] With the development of train operation control systems, onboard train control equipment generates massive amounts of multi-source heterogeneous data during operation, covering braking system data, speed data, communication data, equipment status data, and fault log data. Currently, onboard train control data processing often employs single-dimensional or simple correlation methods, failing to fully explore the deep correlation between braking and speed data. Furthermore, insufficient multi-source data integration capabilities result in low data utilization. When abnormal speed fluctuations or emergency braking warnings occur, it is difficult to quickly trace related data, hindering comprehensive support for fault location and impacting the safety and reliability of train operation. Summary of the Invention

[0003] The purpose of this application is to provide a knowledge graph-based method and related device for multi-dimensional association of onboard train control data, which can effectively improve the safety and reliability of train operation.

[0004] To achieve the above objectives, this application provides the following solution: Firstly, this application provides a knowledge graph-based method for multi-dimensional association of onboard train control data, comprising the following steps: The train's operating status is checked cyclically at preset time intervals. If the train has not stopped, multi-source onboard train control data from the onboard train control system is obtained. The multi-source onboard train control data includes braking core data, speed core data, and associated auxiliary data. The associated auxiliary data includes communication data, equipment status data, environmental data, and fault log data.

[0005] Based on the data type and correlation between the data and the core data in the multi-source on-board train control data, the data are classified into a core data layer and an auxiliary correlation layer; the core data is braking or speed-related data.

[0006] Core entities and auxiliary entities are defined based on the core data layer and the auxiliary association layer, respectively. A hybrid approach, which is mainly based on rules and supplemented by machine learning, is used to extract core entities and auxiliary entities from multi-source vehicle-mounted train control data.

[0007] An attention-based relation extraction model combined with a vehicle-mounted train control domain dictionary is used to extract the relationships between entities. The results are then manually verified and corrected to obtain the relationships contained in the knowledge graph.

[0008] Knowledge fusion is performed on the extracted entities and their relationships to construct a vehicle-mounted train control data knowledge graph, which is then stored in a graph database. The knowledge fusion includes handling entity duplication and relationship conflicts.

[0009] Based on the knowledge graph of onboard train control data, multidimensional data correlation analysis is performed, and the correlation analysis results are output and adapted to specific application scenarios.

[0010] If the train stops, data collection is halted and the latest onboard train control data knowledge graph is saved.

[0011] Optionally, the core data layer includes braking core data and speed core data; the auxiliary correlation layer includes communication data, equipment status data, environmental data, and fault log data; a hybrid approach, primarily rule-based and supplemented by machine learning, is used to extract core and auxiliary entities from multi-source on-board train control data, specifically including the following steps: For structured data in multi-source onboard train control data, core entities are directly extracted based on preset extraction rules. The preset extraction rules are to extract entities of the corresponding type based on field identifiers. Core entities include brake pressure entity, brake command level entity, brake actuator entity, real-time speed entity, target speed entity, and speed change rate entity.

[0012] For unstructured data in multi-source onboard train control data, an entity extraction model is used to extract auxiliary entities. The entity extraction model is a model trained on an LSTM model using several multi-source onboard train control data sets labeled with entity categories as a training corpus. Auxiliary entities include command entities, coordination information entities, onboard host entities, speed sensor entities, brake valve entities, track gradient entities, external temperature entities, abnormal brake pressure entities, and speed sensor fault entities.

[0013] Optionally, knowledge fusion is performed on each extracted entity and each relationship, specifically including the following steps: Entity linking is used to match duplicate entities based on attribute similarity or semantic similarity, merging duplicate entities into a single entity.

[0014] Relationship reconciliation is adopted, and conflicting association relationships are corrected based on preset timestamp priority rules; the timestamp priority rule is that the timestamps of the core data layer have higher priority than the timestamps of the auxiliary association layers.

[0015] Optionally, constructing an on-board train control data knowledge graph and storing the on-board train control data knowledge graph in a graph database specifically includes the following steps: Each entity is used as a node in the vehicle-mounted train control data knowledge graph; node attributes include collection timestamp, numerical / status description, and data source.

[0016] Each relationship is treated as a directed edge between nodes in the vehicle-mounted train control data knowledge graph; the edge attributes include the relationship confidence and the number of historical matches.

[0017] A graph database storing the knowledge graph of onboard train control data is deployed on the onboard server to support real-time multi-dimensional data correlation analysis requests.

[0018] Optionally, the knowledge graph includes the following relationships: the relationship between braking and speed, the relationship between core entities and auxiliary entities, and the relationship between auxiliary entities. The relationship between braking and speed includes: the braking pressure entity is associated with the real-time speed entity, the braking command level entity is associated with the target speed entity, and the braking actuator entity is associated with the speed change rate entity. The relationship between core entities and auxiliary entities includes: the command-related core entities are associated with the command entity and the coordination information entity, and the state-related core entities are associated with all auxiliary entities except the command entity and the coordination information entity. The command-related entities include the braking command level entity and the target speed entity. The state-related core entities include the braking pressure entity, the braking actuator entity, the real-time speed entity, and the speed change rate entity.

[0019] Braking and speed are linked in real time, specifically including the following steps: Real-time braking pressure data is collected. When the braking pressure data reaches the preset braking pressure threshold, the real-time speed nodes associated with the braking pressure node are traversed through the on-board train control data knowledge graph.

[0020] By invoking historical correlation patterns, when the change pattern of the real-time speed node exceeds the range of the pattern, it is marked as "braking-speed correlation anomaly" and the abnormal data correlation tracing process is triggered.

[0021] Speed ​​deviation and braking command tracing specifically includes the following steps: When a speed deviation value is detected to be greater than the preset speed deviation threshold, the braking actuator node and braking command level node are traced back in reverse through the on-board train control data knowledge graph.

[0022] Verify whether the braking command has been issued and whether the braking level meets the standard. At the same time, trace the command nodes associated with the braking command level node to confirm whether the target speed has not been updated due to command transmission delay.

[0023] Abnormal data association and source tracing: When the real-time speed fluctuates abnormally within 10 seconds, the root cause of the abnormality is determined by inferring the speed sensor status, brake actuator status and external temperature nodes based on the on-board train control data knowledge graph and using preset inference rules.

[0024] Historical data correlation mining specifically involves: traversing the historical data of any slope line within three months in the onboard train control data knowledge graph to mine historical correlation patterns of track gradient, braking pressure, and speed reduction, which serve as the data basis for optimizing braking strategies for slope lines.

[0025] Optionally, multidimensional data correlation analysis includes real-time correlation between braking and speed, tracing speed deviation and braking commands, tracing the source of abnormal data, and mining historical data correlations; the correlation analysis results include structured reports and visualization maps; specific application scenarios include train operation monitoring, fault diagnosis, and operation optimization; outputting the correlation analysis results and adapting them to specific application scenarios includes the following steps: The correlation analysis results are output in the form of a structured report, along with a visualization map. The structured report includes a braking and speed correlation status report and an anomaly data tracing report. In the visualization map, the nodes of the core entities are red, the nodes of the auxiliary entities are blue, and the nodes of the track slope entity, the external temperature entity, the braking pressure anomaly entity, and the speed sensor fault entity are green. The directed edges are labeled with the relationship type and confidence level.

[0026] In train operation monitoring scenarios, when an abnormal marker is detected, the onboard terminal will issue an audible and visual alarm with beeping and flashing.

[0027] In fault diagnosis scenarios, an abnormal data tracing report is output to identify the components associated with the fault.

[0028] In operational optimization scenarios, historical correlation patterns are output to support parameter adjustments in the onboard train control system, thereby reducing train energy consumption.

[0029] Secondly, this application provides a knowledge graph-based multi-dimensional association device for onboard train control data, including the following functional modules: The multi-source onboard train control data acquisition module is used to cyclically determine the train's operating status at preset time intervals. If the train is not stopped, it acquires multi-source onboard train control data from the onboard train control system. The multi-source onboard train control data includes braking core data, speed core data, and associated auxiliary data. The associated auxiliary data includes communication data, equipment status data, environmental data, and fault log data. If the train stops, it stops data acquisition and saves the latest onboard train control data knowledge graph.

[0030] The multi-source data classification module is used to classify the data according to the data type and correlation of each data in the multi-source on-board train control data with the core data, resulting in a core data layer and an auxiliary correlation layer; the core data is braking or speed-related data.

[0031] The entity definition and extraction module is used to define core entities and auxiliary entities based on the core data layer and the auxiliary association layer, respectively, and to extract core entities and auxiliary entities from multi-source vehicle-mounted train control data using a hybrid approach that is primarily rule-based and secondarily machine learning-based.

[0032] The relationship extraction module is used to extract the relationships between entities by using an attention-based relationship extraction model combined with a vehicle-mounted train control domain dictionary. The results are then manually verified and corrected to obtain the relationships contained in the knowledge graph.

[0033] The knowledge graph construction module is used to perform knowledge fusion on the extracted entities and their relationships to construct a vehicle-mounted train control data knowledge graph and store the vehicle-mounted train control data knowledge graph in a graph database; knowledge fusion includes handling entity duplication and relationship conflict.

[0034] The data multidimensional correlation analysis module is used to perform multidimensional correlation analysis based on the vehicle-mounted train control data knowledge graph, output the correlation analysis results and adapt them to specific application scenarios.

[0035] Thirdly, this application provides a computer device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the knowledge graph-based multidimensional association method for vehicle-mounted train control data described above.

[0036] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the knowledge graph-based multidimensional association method for vehicle-mounted train control data described above.

[0037] Fifthly, this application provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the knowledge graph-based multidimensional association method for vehicle-mounted train control data described above.

[0038] According to the specific embodiments provided in this application, the following technical effects are disclosed: This application provides a knowledge graph-based multi-dimensional association method and related device for onboard train control data. The method first acquires multi-source onboard train control data, comprehensively covering core and auxiliary data, solving the problem of fragmented data sources in traditional data acquisition and laying a complete data foundation for subsequent deep association mining. Then, the data is classified according to its relevance to the core data, dividing it into a core data layer and an auxiliary association layer. By clarifying data priorities and association weights, the inefficiency of association caused by data clutter is avoided, improving the targeting and accuracy of data processing. Next, entities are defined, and a hybrid approach using rules as the primary method and machine learning as a supplement is adopted to extract core and auxiliary entities from the multi-source onboard train control data. Finally, an attention mechanism is used to focus on the core entities between them. By employing core associations, domain-specific dictionaries tailored to specific scenarios, and manual error correction, this system addresses the shortcomings and low accuracy of traditional relation extraction methods in deep relation mining, constructing a precise entity association network. Through entity linking and merging of duplicate entities, and relation reconciliation and conflict correction, it eliminates data redundancy and contradictions, ensuring the consistency and integrity of the knowledge graph. The graph database, deployed on an onboard server, supports real-time relational queries, resolving the slow response time of traditional data storage and relational querying, providing an efficient platform for rapid data analysis. Multi-dimensional relational analysis based on the knowledge graph enables real-time monitoring of braking and speed, rapid tracing of anomaly root causes, and in-depth mining of historical patterns. Structured reports and visualized graphs make the results intuitive and easy to understand. Multi-scenario adaptation meets diverse needs for operation monitoring, fault diagnosis, and operational optimization. The system cyclically checks the train's operating status at preset intervals. If the train is not stopped, the above steps are repeated to ensure real-time updates of data associations, continuously providing dynamic support for train operation. If the train stops, data collection ceases and the latest knowledge graph is saved. Independent storage of the knowledge graph supports power outage recovery, providing complete data support for subsequent historical data mining and system restart, ensuring data continuity. Attached Figure Description

[0039] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0040] Figure 1 This is a flowchart illustrating a knowledge graph-based multidimensional association method for vehicle-mounted train control data, provided as an embodiment of this application.

[0041] Figure 2 This is a schematic diagram of the data structure of multi-source on-board train control data in a knowledge graph-based multi-dimensional association method for on-board train control data provided in an embodiment of this application.

[0042] Figure 3 This is a schematic diagram of the functional modules of a knowledge graph-based multi-dimensional association device for vehicle-mounted train control data, provided in one embodiment of this application.

[0043] Figure 4 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. Detailed Implementation

[0044] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0045] Currently, the processing of onboard train control data often employs single-dimensional or simple correlation methods, such as only detecting anomalies in speed data or simply linearly matching braking commands with speed changes. This approach has significant drawbacks: firstly, it fails to fully explore the deep correlations between braking and speed data, such as the nonlinear relationship between the rate of change in braking pressure and the magnitude of speed decrease, or the differences in speed regulation under different braking modes, resulting in low data utilization. Secondly, it lacks the ability to integrate multi-source data. When abnormal train speed fluctuations or emergency braking warnings occur, it is difficult to quickly trace related communication commands, equipment status, and other data, failing to provide comprehensive data support for fault location, thus affecting the safety and reliability of train operation.

[0046] Knowledge graphs, as a structured semantic network, possess powerful entity association and relationship mining capabilities, transforming multi-source heterogeneous data into semantically related knowledge nodes and relational edges. Applying knowledge graph technology to the field of onboard train control data association can effectively solve the current problems of fragmented data association and insufficient deep relationship mining. In particular, building an association system centered on braking and speed data can further enhance the application value of onboard train control data and provide intelligent support for train operation management. This application aims to utilize knowledge graphs to solve the problems of fragmented data and low value utilization in traditional data processing.

[0047] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0048] This application provides a knowledge graph-based multi-dimensional association method for onboard train control data. In one exemplary embodiment, such as... Figure 1 As shown, it includes the following steps: A1. Acquire multi-source onboard train control data from the onboard train control system; multi-source onboard train control data includes braking core data, speed core data, and associated auxiliary data; associated auxiliary data includes communication data, equipment status data, environmental data, and fault log data.

[0049] In an exemplary embodiment, the braking control unit, speed measurement unit, communication unit, and equipment status monitoring unit of the on-board train control system collect data in real time and form multi-source on-board train control data. All data are synchronously marked based on the time axis, with a timestamp accuracy of less than 100ms. Specific data items include core braking data, core speed data, and associated auxiliary data.

[0050] The core braking data includes brake cylinder data, wheel cylinder data, brake command level data, emergency brake trigger signal data, brake valve switch status data, and brake response delay time data.

[0051] The core speed data includes real-time train speed data fused from multiple speed sensors, target speed data issued by ground commands, train acceleration / deceleration data, and speed deviation data (the difference between real-time speed and target speed).

[0052] Associated auxiliary data includes interaction command data with the ground, speed coordination information data for communication with the ground, onboard host information data, speed sensor operating data, track gradient data, ambient temperature data, historical braking fault record data, and speed sensor anomaly log data.

[0053] A2. Based on the data type and correlation between the multi-source onboard train control data and the core data, the data is classified to obtain a core data layer and an auxiliary correlation layer; for example... Figure 2 As shown, the core data is braking or speed-related data; the core data layer contains braking core data and speed core data; the auxiliary correlation layer contains communication data, equipment status data, environmental data, and fault log data.

[0054] Specifically, the core data layer, as the core interconnected entity of the knowledge graph, has a correlation weight of 0.7. Within the core data layer, the weight of braking core data is set at 0.6, and the weight of speed core data is set at 0.4.

[0055] The auxiliary correlation layer includes communication data (including the interaction command data with the ground and the speed coordination information data collected in step A1), equipment status data (including the on-board host information data and speed sensor working data collected in step A1), environmental data (including the track gradient data and the outside temperature data collected in step A1), and fault log data (including the historical braking fault record data and speed sensor abnormal log data collected in step A1). As a supplement to the core data, the correlation weight is set according to the closeness of the correlation with the core data.

[0056] In the auxiliary correlation layer, communication data is closely related to the target speed value, with a weight of 0.3. In equipment status data, sensor operating voltage is closely related to the real-time speed acquisition accuracy, with a weight of 0.2. In environmental data, track gradient is closely related to braking pressure requirements, with a weight of 0.2, while the external temperature in environmental data has a lower correlation, with a weight of 0.1. Fault log data has a weight of 0.2.

[0057] A3. Based on the core data layer and auxiliary association layer, core entities and auxiliary entities are defined respectively. A hybrid approach, primarily rule-based and supplemented by machine learning, is used to extract core entities and auxiliary entities from multi-source onboard train control data. Specifically, the extraction priority is core entities over auxiliary entities, and structured data over unstructured data. Core entities include brake pressure entities (corresponding to brake cylinder data and wheel cylinder data collected in step A1), brake command level entities (corresponding to brake command level data and brake response delay time data collected in step A1), brake actuator entities (corresponding to emergency brake trigger signal data and brake valve switch status data collected in step A1), real-time speed entities (corresponding to real-time train running speed data collected in step A1), target speed entities (corresponding to target speed data collected in step A1), and speed change rate entities (corresponding to speed deviation value data and train acceleration / deceleration data collected in step A1). Auxiliary entities include command entities, coordination information entities, onboard host entities, speed sensor entities, brake valve entities, track gradient entities, external temperature entities, brake pressure anomaly entities, and speed sensor fault entities.

[0058] Specifically, in this embodiment, step A3, "extracting core entities and auxiliary entities from multi-source on-board train control data using a hybrid approach that is primarily rule-based and secondarily machine learning," includes the following steps: A31. For structured data in multi-source onboard train control data, core entities are directly extracted based on preset extraction rules. The preset extraction rules are to extract entities of the corresponding type based on field identifiers. The structured data is stored in a relational database with clearly defined field identifiers, and each core entity can be obtained directly based on the field identifiers.

[0059] A32. For unstructured data in multi-source onboard train control data, an entity extraction model is used to extract auxiliary entities. The entity extraction model is a model obtained by training an LSTM model with several multi-source onboard train control data labeled with entity category tags as a training corpus.

[0060] In this embodiment, the training corpus consists of 10,000 annotated multi-source vehicle-mounted train control data. The annotation format includes entity category labels. After the LSTM model is trained, the entity extraction accuracy on the test set is ≥95%, and the recall rate is ≥90%.

[0061] In an exemplary embodiment, firstly, three braking entities are extracted based on field identifiers, including a braking pressure entity (corresponding to brake cylinder data and wheel cylinder data), a braking command level entity (corresponding to braking command level data and braking response delay time data), and a braking actuator entity (corresponding to emergency braking trigger signal data and brake valve switch status data). Then, three speed entities are extracted based on the remaining field identifiers, including a real-time speed entity (corresponding to real-time train running speed data), a target speed entity (corresponding to target speed data issued by ground commands), and a speed change rate entity (corresponding to speed deviation value data and train acceleration / deceleration data).

[0062] Secondly, unstructured data is extracted, including communication data (including the interaction command data with the ground and the speed coordination information data collected in step A1), equipment status data (including the on-board host information data and speed sensor working data collected in step A1), environmental data (including the track gradient data and the outside temperature data collected in step A1), and fault log data (including the historical braking fault record data and speed sensor abnormal log data collected in step A1), as a supplement to the structured entities.

[0063] A4. An attention-based relation extraction model is used in conjunction with a vehicle-mounted train control domain dictionary to extract the relationships between entities. The results are then manually verified and corrected to obtain the relationships contained in the knowledge graph. The relationships include the relationship between braking and speed, the relationship between core entities and auxiliary entities, and the relationship between auxiliary entities.

[0064] Specifically, in this embodiment, the first type of association is the association between braking and speed, including: the braking pressure entity is associated with the real-time speed entity, the braking command level entity is associated with the target speed entity, and the braking actuator entity is associated with the speed change rate entity.

[0065] The second type of relationship is the relationship between core entities and auxiliary entities, including: command-related core entities are associated with command entities and coordination information entities, and state-related core entities are associated with all auxiliary entities other than command entities and coordination information entities (including on-board host entity, speed sensor entity, track gradient entity, external temperature entity, brake pressure anomaly entity, and speed sensor failure entity); command-related entities include brake command level entity and target speed entity; state-related core entities include brake pressure entity, brake actuator entity, real-time speed entity, and speed change rate entity.

[0066] The third type of relationship is the relationship between auxiliary entities, including the relationship between the instruction entity and the coordination information entity, and the relationship between the on-board host entity and the speed sensor entity, the track gradient entity, the external temperature entity, the brake pressure abnormality entity, and the speed sensor failure entity.

[0067] Specifically, the input to the relation extraction model is the entities extracted in step A3 and the context data. These entities that have relationships are called entity pairs. The relation extraction model extracts local features of entity pairs and focuses on various types of relationships defined in step A4 through an attention mechanism, such as the numerical matching degree between braking change amplitude and speed change rate, and other key relationship features.

[0068] After extraction, the results are manually verified and corrected using rules. In an exemplary embodiment, the manual rule is set so that the braking command trigger time must be later than the speed deviation exceeding the threshold time, and the time difference must be <1 second. For example, if the real-time speed entity in the speed entity shows an increase in real-time speed within a small time difference (time difference <1 second) when the braking entity is triggered, it is considered erroneous data. Through this manual rule, erroneous relationships that do not conform to the rule are eliminated, and the final association relationship extraction accuracy is ≥95%.

[0069] A5. Knowledge fusion is performed on the extracted entities and their relationships to construct a knowledge graph of onboard train control data. This knowledge graph is then stored in a graph database. Knowledge fusion includes handling entity duplication and relationship conflicts. For example, if a braking command-level entity and a coordination information entity issue similar braking commands within a small time difference (<100ms), they are considered to be the same duplicate entity. Additionally, if a braking pressure entity experiences a rise in braking pressure, and a real-time speed entity within the speed entity experiences a rise in real-time speed within a small time difference (<1s), this is considered a relationship conflict.

[0070] Specifically, in this embodiment, step A5, "performing knowledge fusion on each extracted entity and each associated relationship," includes the following steps: A51. Entity linking is used, and duplicate entities are matched based on attribute similarity or semantic similarity to merge them into a single entity. For example, based on entity attribute similarity matching, if the error between the real-time speed values ​​collected by two sensors is less than 1 km / h, they are determined to be the same real-time speed entity. If the monitoring feedback indicates normal braking status and the fault log records no brake abnormality, and the semantic similarity is ≥90%, they are merged into the same brake status entity.

[0071] A52. A relationship reconciliation method is adopted, which corrects conflicting association relationships based on a preset timestamp priority rule. The timestamp priority rule is that the timestamp of the core data layer has higher priority than the timestamp of the auxiliary association layer. For example, when the communication command displays the difference between the target speed and the time recorded by the vehicle host, the timestamp of the brake control unit is used (the timestamp of the core data layer has higher priority than the timestamp of the auxiliary association layer; specifically, the timestamp of the brake core data is better than the timestamp of the speed core data, and both are better than the timestamp of the associated auxiliary data, while the timestamp of the data at the same level is based on the timestamp with higher accuracy from the acquisition device). The relationship of the vehicle host data is corrected so that the command is associated with the target speed.

[0072] Furthermore, step A5, "constructing the onboard train control data knowledge graph and storing it in a graph database," specifically includes the following steps: A53. Each entity is treated as a node in the vehicle-mounted train control data knowledge graph; node attributes include collection timestamp, numerical / status description, and data source.

[0073] A54. Treat each relationship as a directed edge between nodes in the vehicle-mounted train control data knowledge graph; the edge attributes include the relationship confidence and the number of historical matches.

[0074] A55. Deploy a graph database storing the knowledge graph of onboard train control data on the onboard server to support real-time multi-dimensional data association analysis requests. The graph database, deployed on the onboard server, supports real-time association query requests with short response times.

[0075] A6. Perform multi-dimensional data correlation analysis based on the on-board train control data knowledge graph, output correlation analysis results and adapt them to specific application scenarios; multi-dimensional data correlation analysis includes real-time correlation between braking and speed, speed deviation and braking command tracing, abnormal data correlation tracing and historical data correlation mining; correlation analysis results include structured reports and visualization graphs; specific application scenarios include train operation monitoring scenarios, fault diagnosis scenarios and operation optimization scenarios.

[0076] In one exemplary embodiment, braking is correlated with speed in real time, specifically including the following steps: B1. Real-time acquisition of braking pressure data. When the braking pressure data reaches the preset braking pressure threshold, the real-time speed nodes associated with the braking pressure node are traversed through the on-board train control data knowledge graph.

[0077] B2. Call historical correlation patterns. When the change pattern of the real-time speed node exceeds the pattern range, mark it as "braking-speed correlation anomaly" and trigger the abnormal data correlation tracing process.

[0078] Speed ​​deviation and braking command tracing specifically includes the following steps: C1. When the detected speed deviation value is greater than the preset speed deviation threshold, the brake actuator node and brake command level node are traced back in reverse through the on-board train control data knowledge graph.

[0079] C2. Verify whether the braking command has been issued and whether the braking level meets the standard. At the same time, trace the command node associated with the braking command level node to confirm whether the target speed has not been updated due to command transmission delay.

[0080] The abnormal data correlation and source tracing process involves: when real-time speed fluctuates abnormally within 10 seconds, the system uses a knowledge graph of onboard train control data to correlate speed sensor status, brake actuator status, and external temperature nodes, and then uses preset inference rules to determine the root cause of the anomaly. For example, through rule-based inference, it is deduced that abnormal sensor voltage causes speed acquisition deviation, brake valve sticking causes unstable speed regulation, and low temperature exacerbates actuator malfunction, thus determining the root cause of the anomaly as sensor failure.

[0081] Historical data correlation mining specifically involves: traversing the historical data of any slope line within three months in the onboard train control data knowledge graph to mine historical correlation patterns of track gradient, braking pressure, and speed reduction, which serve as the data basis for optimizing braking strategies for slope lines.

[0082] In an exemplary embodiment, step A6, "outputting the correlation analysis results and adapting them to specific application scenarios," specifically includes the following steps: The system outputs correlation analysis results in a structured report format, along with a visual graph. The structured report includes a braking and speed correlation status report (containing real-time correlation status, anomaly markers, and confidence levels) and an anomaly data tracing report (containing anomaly nodes, related entities, and fault cause inferences). In the visual graph, nodes representing core entities are red, nodes representing auxiliary entities are blue, and nodes representing track gradient, external temperature, abnormal braking pressure, and speed sensor faults are green. Directed edges are labeled with relationship types and confidence levels. The system supports real-time display on vehicle terminals and remote retrieval by ground control centers.

[0083] In train operation monitoring scenarios, when an anomaly marker is detected, the onboard terminal emits an audible and visual alarm with beeping and flashing lights to assist the driver in assessing operational safety. In fault diagnosis scenarios, it outputs an anomaly data tracing report to identify the associated components, guiding maintenance personnel to prioritize troubleshooting, reducing fault handling time by ≥60% compared to traditional algorithms. In operation optimization scenarios, it outputs historical correlation patterns and supports parameter adjustments for the onboard train control system, reducing train energy consumption.

[0084] A7. Every preset time interval (e.g., 100ms), check whether the train is stopped. If the train is not stopped (real-time speed > 0km / h), repeat steps A1 to A6 to ensure real-time updates of data association and provide continuous dynamic support for train operation. If the train is stopped (real-time speed is 0km / h and lasts for 30s), proceed to step A8.

[0085] A8. Stop data acquisition and save the latest onboard train control data knowledge graph, supporting power failure recovery.

[0086] In another exemplary embodiment, when this application uses the distribution information of sleepers for speed measurement, since the distribution information of sleepers is a type of absolute positioning method, the position of the maglev train can be directly updated while performing accurate speed measurement, thus fulfilling the positioning requirements of the maglev train.

[0087] The knowledge graph-based multi-dimensional association method for onboard train control data provided in the above embodiments of this application constructs a knowledge graph with braking and speed data as the core. It can accurately associate multi-source heterogeneous onboard train control data, achieving high data association accuracy. Relying on entity association networks and dual mechanisms, the diagnostic results are more reliable. Simultaneously, it can mine historical association patterns to support train control strategy optimization, reduce train energy consumption, and flexibly adapt to multiple scenarios while remaining compatible with existing hardware, exhibiting strong adaptability and low deployment costs.

[0088] Based on the same inventive concept, this application also provides an apparatus for implementing the knowledge graph-based multi-dimensional association method for vehicle-mounted train control data as described above. The solution provided by this apparatus is similar to the implementation scheme described in the above method. In an exemplary embodiment, such as... Figure 3 As shown, a knowledge graph-based multi-dimensional association device for vehicle-mounted train control data is provided, including the following functional modules: The multi-source onboard train control data acquisition module is used to cyclically determine the train's operating status at preset time intervals. If the train is not stopped, it acquires multi-source onboard train control data from the onboard train control system. The multi-source onboard train control data includes braking core data, speed core data, and associated auxiliary data. The associated auxiliary data includes communication data, equipment status data, environmental data, and fault log data. If the train stops, it stops data acquisition and saves the latest onboard train control data knowledge graph.

[0089] The multi-source data classification module is used to classify the data according to the data type and correlation of each data in the multi-source on-board train control data with the core data, resulting in a core data layer and an auxiliary correlation layer. The core data is braking or speed-related data. The core data layer includes braking core data and speed core data. The auxiliary correlation layer includes communication data, equipment status data, environmental data, and fault log data.

[0090] The entity definition and extraction module is used to define core entities and auxiliary entities based on the core data layer and auxiliary association layer, respectively. It uses a hybrid approach, primarily rule-based and supplemented by machine learning, to extract core and auxiliary entities from multi-source onboard train control data. Core entities include braking pressure entity, braking command level entity, braking actuator entity, real-time speed entity, target speed entity, and speed change rate entity. Auxiliary entities include command entity, coordination information entity, onboard host entity, speed sensor entity, brake valve entity, track gradient entity, external temperature entity, abnormal braking pressure entity, and speed sensor fault entity.

[0091] The relationship extraction module is used to extract the relationships between entities by using an attention-based relationship extraction model combined with a vehicle-mounted train control domain dictionary. The results are then manually verified and corrected to obtain the relationships contained in the knowledge graph. The relationships include the relationship between braking and speed, the relationship between core entities and auxiliary entities, and the relationship between auxiliary entities.

[0092] The knowledge graph construction module is used to fuse the extracted entities and their relationships to construct a knowledge graph of the vehicle-mounted train control data and store it in a graph database. The knowledge fusion includes handling entity duplication and relationship conflicts.

[0093] The multidimensional data correlation analysis module is used to perform multidimensional data correlation analysis based on the on-board train control data knowledge graph, output correlation analysis results and adapt them to specific application scenarios; the multidimensional data correlation analysis includes real-time correlation between braking and speed, speed deviation and braking command tracing, abnormal data correlation tracing and historical data correlation mining; the correlation analysis results include structured reports and visualization graphs; specific application scenarios include train operation monitoring scenarios, fault diagnosis scenarios and operation optimization scenarios.

[0094] certainly, Figure 3 The architecture shown is merely exemplary; it can be omitted as needed when implementing different functionalities. Figure 3 One or at least two components of the system shown.

[0095] In one exemplary embodiment, a computer device is provided, which may be a server or a terminal, and its internal structure diagram may be as follows. Figure 4 As shown, the computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores a knowledge graph of onboard train control data and other intermediate data. The I / O interfaces are used for information exchange between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it can implement the knowledge graph-based multi-dimensional association method for onboard train control data provided in the previous embodiment.

[0096] Those skilled in the art will understand that Figure 4 The 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.

[0097] In one exemplary embodiment, a computer device is also 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 in the above-described method embodiments.

[0098] In one exemplary embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0099] In one exemplary embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0100] 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.

[0101] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile 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).

[0102] 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, etc., and are not limited to these.

[0103] 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 specification.

[0104] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A multi-dimensional association method for onboard train control data based on knowledge graphs, characterized in that, include The train's operating status is checked cyclically at preset time intervals. If the train has not stopped, multi-source onboard train control data from the onboard train control system is acquired. The multi-source onboard train control data includes braking core data, speed core data, and associated auxiliary data. The associated auxiliary data includes communication data, equipment status data, environmental data, and fault log data. The data are classified according to the data type and correlation with the core data in the multi-source on-board train control data, resulting in a core data layer and an auxiliary correlation layer; the core data is braking or speed-related data. Core entities and auxiliary entities are defined based on the core data layer and the auxiliary association layer, respectively, and a hybrid approach of rule-based and machine learning-based methods is used to extract core entities and auxiliary entities from the multi-source vehicle-mounted train control data. An attention-based relation extraction model combined with a vehicle-mounted train control domain dictionary is used to extract the relationships between entities. The results are then manually verified and corrected to obtain the relationships contained in the knowledge graph. Knowledge fusion is performed on the extracted entities and their relationships to construct a vehicle-mounted train control data knowledge graph, which is then stored in a graph database. The knowledge fusion includes handling entity duplication and relationship conflicts. Based on the on-board train control data knowledge graph, perform multi-dimensional data correlation analysis, output correlation analysis results, and adapt them to specific application scenarios; If the train stops, data collection is halted and the latest onboard train control data knowledge graph is saved.

2. The knowledge graph-based multi-dimensional association method for onboard train control data according to claim 1, characterized in that, The core data layer includes braking core data and speed core data; the auxiliary association layer includes communication data, equipment status data, environmental data, and fault log data; a hybrid approach, primarily rule-based and supplemented by machine learning, is used to extract core and auxiliary entities from the multi-source on-board train control data, specifically including: For the structured data in the multi-source on-board train control data, core entities are directly extracted based on preset extraction rules; the preset extraction rules are to extract entities of the corresponding type according to field identifiers; the core entities include braking pressure entity, braking command level entity, braking actuator entity, real-time speed entity, target speed entity, and speed change rate entity. For the unstructured data in the multi-source onboard train control data, an entity extraction model is used to extract auxiliary entities. The entity extraction model is a model obtained by training an LSTM model with several multi-source onboard train control data labeled with entity category tags in advance. The auxiliary entities include command entities, coordination information entities, onboard host entities, speed sensor entities, brake valve entities, track gradient entities, external temperature entities, abnormal brake pressure entities, and speed sensor fault entities.

3. The method for multi-dimensional association of onboard train control data based on knowledge graphs according to claim 1, characterized in that, Knowledge fusion is performed on the extracted entities and their relationships, specifically including: Entity linking is used to match duplicate entities based on attribute similarity or semantic similarity, merging duplicate entities into a single entity; Relationship reconciliation is adopted, and conflicting association relationships are corrected based on a preset timestamp priority rule; the timestamp priority rule is that the timestamp of the core data layer has a higher priority than the timestamp of the auxiliary association layer.

4. The method for multi-dimensional association of onboard train control data based on knowledge graphs according to claim 1, characterized in that, Constructing a knowledge graph of onboard train control data and storing it in a graph database specifically includes: Each entity is used as a node in the vehicle-mounted train control data knowledge graph; node attributes include collection timestamp, numerical / status description, and data source; Each relationship is represented as a directed edge between nodes in the vehicle-mounted train control data knowledge graph; the edge attributes include the relationship confidence and the number of historical matches. The graph database storing the vehicle-mounted train control data knowledge graph is deployed on the vehicle-mounted server, supporting real-time multi-dimensional data correlation analysis requests.

5. The method for multi-dimensional association of vehicle-mounted train control data based on knowledge graphs according to claim 2, characterized in that, The knowledge graph includes relationships between braking and speed, between core entities and auxiliary entities, and between auxiliary entities. The braking and speed relationship includes: the braking pressure entity is associated with the real-time speed entity, the braking command level entity is associated with the target speed entity, and the braking actuator entity is associated with the speed change rate entity. The core entity and auxiliary entity relationship includes: command-related core entities are associated with the command entity and the coordination information entity, and state-related core entities are associated with all auxiliary entities except the command entity and the coordination information entity. The command-related entities include the braking command level entity and the target speed entity; the state-related core entities include the braking pressure entity, the braking actuator entity, the real-time speed entity, and the speed change rate entity. The braking and speed are correlated in real time, specifically including: Real-time acquisition of braking pressure data; when the braking pressure data reaches a preset braking pressure threshold, the real-time speed nodes associated with the braking pressure nodes are traversed through the vehicle-mounted train control data knowledge graph. By calling historical correlation patterns, when the change pattern of the real-time speed node is determined to be outside the range of the pattern, it is marked as "braking-speed correlation anomaly" and the abnormal data correlation tracing process is triggered; The speed deviation and braking command tracking specifically includes: When the detected speed deviation value is greater than the preset speed deviation threshold, the braking actuator node and braking command level node are traced back in reverse through the on-board train control data knowledge graph; Verify whether the braking command has been issued and whether the braking level meets the standard. At the same time, trace the command nodes associated with the braking command level node to confirm whether the target speed has not been updated due to command transmission delay. The abnormal data association and source tracing specifically involves: when the real-time speed fluctuates abnormally within 10 seconds, the root cause of the abnormality is determined by inferring the speed sensor status, brake actuator status, and external temperature nodes based on the vehicle-mounted train control data knowledge graph and using preset inference rules. The historical data correlation mining specifically involves: traversing the historical data of any slope line within three months in the on-board train control data knowledge graph, and mining the historical correlation patterns of track gradient, braking pressure, and speed reduction, which serve as the data basis for optimizing the braking strategy of the slope line.

6. The method for multi-dimensional association of onboard train control data based on knowledge graphs according to claim 1, characterized in that, The multidimensional data correlation analysis includes real-time correlation between braking and speed, tracing speed deviation and braking command, tracing the source of abnormal data, and mining historical data correlations; the correlation analysis results include structured reports and visualization maps; the specific application scenarios include train operation monitoring, fault diagnosis, and operation optimization. Output correlation analysis results and adapt them to specific application scenarios, including: The correlation analysis results are output in the form of a structured report, and a visualization map is also output. The structured report includes a braking and speed correlation status report and an anomaly data tracing report. In the visualization map, the nodes of the core entities are red, the nodes of the auxiliary entities are blue, and the nodes of the track slope entity, the external temperature entity, the braking pressure anomaly entity, and the speed sensor failure entity are green. The directed edges are labeled with the relationship type and confidence level. In train operation monitoring scenarios, when an abnormal marker is present, the on-board terminal will issue an audible and visual alarm with beeping and flashing. In fault diagnosis scenarios, an abnormal data tracing report is output to identify the components associated with the fault; In operational optimization scenarios, historical correlation patterns are output to support parameter adjustments in the onboard train control system, thereby reducing train energy consumption.

7. A knowledge graph-based multi-dimensional association device for onboard train control data, characterized in that, include: The multi-source onboard train control data acquisition module is used to cyclically determine the train's operating status at preset time intervals. If the train is not stopped, it acquires multi-source onboard train control data from the onboard train control system. The multi-source onboard train control data includes braking core data, speed core data, and associated auxiliary data. The associated auxiliary data includes communication data, equipment status data, environmental data, and fault log data. If the train stops, it stops data acquisition and saves the latest onboard train control data knowledge graph. The multi-source data classification module is used to classify each data according to the data type and correlation degree between each data in the multi-source on-board train control data and the core data, to obtain a core data layer and an auxiliary correlation layer; the core data is braking or speed-related data. The entity definition and extraction module is used to define core entities and auxiliary entities based on the core data layer and the auxiliary association layer respectively, and to extract core entities and auxiliary entities from the multi-source vehicle-mounted train control data using a hybrid approach that is primarily rule-based and secondarily machine learning-based. The relationship extraction module is used to extract the relationships between entities by using an attention-based relationship extraction model combined with a vehicle-mounted train control domain dictionary, and to obtain the relationships contained in the knowledge graph by manually verifying and correcting the results through rules. The knowledge graph construction module is used to perform knowledge fusion on the extracted entities and their relationships to construct a vehicle-mounted train control data knowledge graph and store the vehicle-mounted train control data knowledge graph in a graph database; the knowledge fusion includes handling entity duplication and relationship conflict. The data multidimensional correlation analysis module is used to perform multidimensional correlation analysis on the vehicle-mounted train control data knowledge graph, output the correlation analysis results and adapt them to specific application scenarios.

8. A computer device, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor executes the computer program to implement the knowledge graph-based multidimensional association method for vehicle-mounted train control data as described in any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the knowledge graph-based multidimensional association method for vehicle-mounted train control data as described in any one of claims 1-6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the knowledge graph-based multidimensional association method for vehicle-mounted train control data as described in any one of claims 1-6.

Images