Heavy haul railway train control multi-device cooperative performance distributed detection method and detection system

Abstract

This application relates to a distributed detection method and system for the collaborative performance of multiple train control devices in heavy-haul railways. The method includes: acquiring operational data of each train control device during the actual operation of the train control system; identifying train control device pairs exhibiting interactive behavior based on the operational data; for each train control device pair, determining collaborative performance parameters for the interactive behavior based on the operational data; determining the collaborative performance deviation ratio of the interactive behavior based on the collaborative performance parameters and the corresponding expected collaborative performance parameters; and determining the collaborative performance detection result of the train control system based on the collaborative performance deviation ratio of each train control device pair. This method can improve the accuracy of collaborative performance detection.

Description

Technical Field

[0001] This application relates to the field of testing technology, and in particular to a distributed testing method, testing system, computer equipment, computer-readable storage medium, and computer program product for the collaborative performance of multiple equipment in heavy-haul railway train control. Background Technology

[0002] With the continuous expansion of heavy-haul railway transportation and the constant improvement of its intelligent level, heavy-haul railways have placed higher demands on the real-time performance, reliability, and consistency of the collaborative work among various train control equipment in the train operation control system (hereinafter referred to as the train control system). This has also driven the continuous increase in the complexity and integration of the train control system itself. These changes have significantly increased the difficulty of testing the collaborative performance of the train control system.

[0003] Currently, the collaborative performance testing of train control systems involves independently testing each train control device, such as onboard equipment, ground transponders, and Radio Block Centers (RBCs), followed by manual evaluation of the test results to arrive at the final test result. However, this method, which tests each train control device independently, fails to reflect the true synchronization and linkage relationships between them. Furthermore, manual evaluation is prone to subjectivity and inconsistency, resulting in low accuracy of the test results. Summary of the Invention

[0004] Based on this, it is necessary to provide a distributed detection method, detection system, computer equipment, computer-readable storage medium, and computer program product for the collaborative performance of multiple equipment in heavy-haul railway train control, which can improve the accuracy of collaborative performance detection, in response to the above-mentioned technical problems.

[0005] Firstly, this application provides a distributed detection method for the collaborative performance of multiple equipment in heavy-haul railway train control, including:

[0006] During the actual operation of the train control system, the operating data of each train control device is acquired;

[0007] Based on the operational data, identify train control equipment pairs exhibiting interactive behavior;

[0008] For each of the train control device pairs, based on the operating data of the train control device pairs, the collaborative performance parameters for the train control device pairs to perform the interactive behavior are determined;

[0009] Based on the collaborative performance parameters of the train control device for performing the interactive behavior and the corresponding expected collaborative performance parameters, the collaborative performance deviation ratio of the train control device for performing the interactive behavior is determined.

[0010] The collaborative performance test result of the train control system is determined based on the proportion of collaborative performance deviation of each of the train control devices in performing the interactive behavior.

[0011] Secondly, this application also provides a detection system, comprising:

[0012] The acquisition module is used to acquire the operating data of each train control device during the actual operation of the train control system;

[0013] The first determining module is used to identify train control device pairs with interactive behavior based on the operating data, and associate the train control device pairs with the target operating data of the train control device pairs performing the interactive behavior.

[0014] The second determining module is used to determine, for each of the train control equipment pairs, the collaborative performance parameters for the train control equipment pairs to perform the interactive behavior based on the operating data of the train control equipment pairs;

[0015] The first detection module is used to determine the proportion of the collaborative performance deviation of the train control device in performing the interactive behavior based on the collaborative performance parameters of the train control device in performing the interactive behavior and the corresponding expected collaborative performance parameters.

[0016] The second detection module is used to determine the collaborative performance detection result of the train control system based on the proportion of collaborative performance deviation of each of the train control devices in performing the interactive behavior.

[0017] Thirdly, this application also provides a computer device, 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 any of the methods described in the first aspect.

[0018] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described in any one of the first aspects.

[0019] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the method described in any of the first aspects.

[0020] The aforementioned distributed detection method, system, computer equipment, computer-readable storage medium, and computer program product for the collaborative performance of multiple train control devices in heavy-haul railways acquires operational data generated by each train control device during the actual operation of the train control system. This enables the collaborative performance detection results determined based on the operational data to reflect the true synchronization and linkage relationships between the train control devices. Then, based on the operational data, train control device pairs exhibiting interactive behavior are identified. For each train control device pair, based on the operational data of the pair, the collaborative performance parameters for the interactive behavior are determined. Furthermore, based on the collaborative performance parameters and corresponding expected collaborative performance parameters, the collaborative performance deviation ratio of the interactive behavior is determined. Finally, based on the collaborative performance deviation ratio of each train control device pair, the collaborative performance detection result of the train control system is determined. The entire detection process does not involve manual operation, avoiding deviations introduced by human factors. Therefore, the collaborative performance detection results can comprehensively reflect the overall true collaborative performance of all equipment groups in the train control system under various interactive behaviors, significantly improving accuracy. Attached Figure Description

[0021] 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.

[0022] Figure 1 This is an application environment diagram of a distributed detection method for the collaborative performance of multiple equipment in heavy-haul railway train control, as illustrated in one embodiment.

[0023] Figure 2 This is a flowchart illustrating a distributed detection method for the collaborative performance of multiple train control devices in a heavy-haul railway, as shown in one embodiment.

[0024] Figure 3 This is a flowchart illustrating a distributed detection method for the collaborative performance of multiple train control devices in a heavy-haul railway, as shown in one embodiment.

[0025] Figure 4 This is a flowchart illustrating a distributed detection method for the collaborative performance of multiple train control devices in a heavy-haul railway, as shown in one embodiment.

[0026] Figure 5 This is a flowchart illustrating a distributed detection method for the collaborative performance of multiple train control devices in a heavy-haul railway, as shown in one embodiment.

[0027] Figure 6 Here is a block diagram of the detection system in one embodiment;

[0028] Figure 7This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0029] 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.

[0030] The distributed detection method for the collaborative performance of multiple equipment in heavy-haul railway train control 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 placed on a cloud or other network server. Both the terminal and server can be used independently to execute the process parameter prediction model determination method provided in this embodiment. The terminal and server can also work together to execute the distributed detection method for the collaborative performance of multiple train control devices in heavy-haul railways provided in this embodiment. For example, during the actual operation of the train control system, terminal 102 acquires the operating data of each train control device; identifies train control device pairs with interactive behaviors based on the operating data, and associates the train control device pairs with the target operating data of the train control device pairs performing interactive behaviors; for each train control device pair, based on the target operating data associated with the train control device pair, determines the collaborative performance parameters of the train control device pair performing interactive behaviors; based on the collaborative performance parameters of the train control device pair performing interactive behaviors and the corresponding expected collaborative performance parameters, determines the collaborative performance deviation ratio of the train control device pair performing interactive behaviors; and based on the collaborative performance deviation ratio of each train control device pair performing interactive behaviors, determines the collaborative performance detection result of the train control system. The 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, projectors, etc. Portable wearable devices can include smartwatches, smart bracelets, head-mounted displays, etc. Head-mounted displays can be virtual reality (VR) devices, augmented reality (AR) devices, smart glasses, etc. The 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.

[0031] In one exemplary embodiment, such as Figure 2 As shown, a distributed detection method for the collaborative performance of multiple equipment in heavy-haul railway train control is provided. Taking the application of this method to computer equipment as an example, the method includes the following steps 202 to 206. Wherein:

[0032] Step 202: During the actual operation of the train control system, acquire the operating data of each train control device;

[0033] The operational data is collected in real time from each train control device during the actual operation of the train control system. Therefore, the acquired operational data reflects the true synchronization and linkage relationships between the train control devices, significantly improving the accuracy of the collaborative performance test results of the train control system determined based on the operational data.

[0034] In one embodiment, the operational data includes the timestamp of each control command sent by the train control device, the command content, and the timing data of status variables.

[0035] Among them, state variable time-series data refers to the numerical sequence of key state parameters recorded in chronological order during the operation of the train control equipment. Key state parameters refer to measurable physical quantities that are affected by or participate in the interactive response when the train control equipment performs interactive behavior, such as traction current, signal strength, and braking pressure.

[0036] For example, the on-board device A controls the following: send timestamp 10:00:01.000, instruction content 0x01 (request location), receive timestamp 10:00:01.025, and the status variable (traction current) increases from 500A to 510A between 10:00:01.000 and 10:00:01.025.

[0037] Train control equipment refers to the physical equipment used to realize train operation control functions, including on-board equipment, ground equipment, and communication equipment. Examples include Automatic Train Protection (ATP) radio block center, ground transponders, and track circuits.

[0038] Step 204: Identify train control device pairs exhibiting interactive behavior based on the operational data;

[0039] This process involves identifying all existing interactive behaviors based on operational data, then combining train control devices with interactive behaviors into train control device pairs, and associating the operational data corresponding to the interactive behaviors performed by each train control device pair. Interactive behaviors between train control devices include message sending and receiving, status feedback, and logical interlocking.

[0040] In one embodiment, step 204 further includes: determining an initial candidate train control device pair with potential interactive behavior based on whether the difference in the transmission timestamps between the control commands of each train control device meets a preset threshold; then determining a target candidate train control device pair based on whether the instruction content of the candidate train control devices for their respective control commands meets a preset mapping relationship; and finally determining a train control device pair with interactive behavior based on whether the time sequence data of the state variables of the target candidate train control devices for their respective control commands meets a preset state coupling relationship.

[0041] For example, the control command from vehicle-mounted device A is sent at timestamp 10:00:01.000, with command content 0x01 (requested location), and received at timestamp 10:00:01.025. The status variable timing data shows that the traction current increased from 500A to 510A between 10:00:01.000 and 10:00:01.025. The control command from transponder B is sent at timestamp 10:00:01.025, with command content 0x81 (location information). The status variable timing data shows that the signal strength increased from 65dBm to 58dBm between 10:00:01.000 and 10:00:01.025, and the operating current increased from 20mA to 35mA. The time difference between the transmission times of vehicle-mounted device A and transponder B is 25ms, which meets the preset threshold of ≤50ms. Therefore, {vehicle-mounted device A, transponder B} is determined as the initial candidate train control device pair. Furthermore, the instruction content 0x01 of onboard device A and the instruction content 0x81 of transponder B conform to the preset mapping relationship (location information returned below the request location instruction). Therefore, {onboard device A, transponder B} is identified as the target candidate train control device pair. Finally, after the request location instruction is sent to onboard device A, its state changes from "idle" to "send". After transponder B receives the request location instruction, its state changes from "standby" to "responding". This conforms to the preset state coupling relationship. Therefore, {onboard device A, transponder B} is ultimately identified as the train control device pair with interactive behavior.

[0042] In one embodiment, before step 106, the method further includes: aligning each piece of running data according to a standard spatiotemporal reference to obtain spatiotemporally consistent running data.

[0043] Among them, a unified spatiotemporal coordinate system is used as the standard spatiotemporal reference to finely align the operating data from different train control equipment. On the one hand, this compensates for signal transmission delays and sampling period differences, and on the other hand, it corrects coordinate offsets caused by installation deviations of train control equipment or map update lags. Redundant and conflicting information in the operating data is eliminated through data fusion algorithms, thereby obtaining operating data that is strictly synchronized in time, accurately corresponds in space, and is highly consistent in structure, providing a reliable and complete input basis for subsequent collaborative performance testing.

[0044] Step 206: For each train control device pair, determine the collaborative performance parameters for the train control device pair to perform the interactive behavior based on the operating data of the train control device pair;

[0045] Among them, the collaborative performance parameter can be a key parameter characterizing the response latency of the train control equipment to the execution of interactive behavior.

[0046] In one embodiment, the collaborative performance parameters can also be key parameters characterizing the response latency, control command transmission path, and / or state coupling mode of the train control equipment in performing interactive behaviors. This allows for the determination of collaborative performance parameters from three dimensions: time consistency, logical integrity, and response reliability, thereby improving the accuracy of collaborative performance detection. It should be noted that the state coupling mode refers to the causal relationship where, when the state of one train control equipment changes, the state of one or more other train control equipment that interacts with it also changes accordingly.

[0047] In one embodiment, the operational data of the train control equipment pair is analyzed to determine the collaborative performance feature vector of the train control equipment pair in at least one dimension of response delay, control command transmission path, and / or state coupling response mode. The collaborative performance feature vectors are then weighted and fused to obtain collaborative performance parameters. Thus, these collaborative performance parameters can comprehensively reflect the collaborative performance of the train control equipment pair in executing interactive behaviors from multiple dimensions, avoiding the one-sidedness of single-dimensional evaluation and improving the accuracy and comprehensiveness of collaborative performance detection.

[0048] For example, taking the interaction between the onboard equipment and the radio block center as an example, in terms of response latency, the time interval between the onboard equipment sending the "train position report" to the radio block center and the time the radio block center responds with "movement authorization (MA)" is 200ms. In terms of the control command transmission path, the interaction logic flow between the onboard equipment and the radio block center is "onboard equipment (initiates request) → GSM-R (Global System for Mobile Communications – Railway) network (transmission) → radio block center (logical operation) → GSM-R network → onboard equipment (receives and executes)". This complete control command transmission path sequence ensures that no routing errors or loss of commands occur. In terms of the state-coupled response mode, after the "train speed" status reported by the onboard equipment changes, the "movement authorization calculation" status of the radio block center is logically triggered to be updated accordingly.

[0049] In one embodiment, after determining the cooperative performance feature vector of the train control equipment in at least one dimension of response latency, control command transmission path, and / or state coupling response mode, the method further includes:

[0050] The collaborative performance feature vector is compared with the baseline collaborative performance feature vector corresponding to the interactive behavior of the train control equipment pair in the collaborative rule base to determine the deviation vector; then, all deviation vectors are weighted and fused to obtain the collaborative performance parameter. The collaborative performance parameter obtained here represents the comprehensive deviation between the actual collaborative performance and the expected collaborative performance. The collaborative rule base stores the baseline collaborative performance feature vectors of each train control equipment pair with interactive behavior.

[0051] Step 208: Determine the proportion of the collaborative performance deviation of the train control device in performing the interactive behavior based on the collaborative performance parameters of the train control device in performing the interactive behavior and the corresponding expected collaborative performance parameters;

[0052] Among them, the expected collaborative performance parameter for each train control device performing the corresponding interactive behavior refers to the benchmark value or benchmark range used to measure whether the actual collaborative performance meets the standard. It can be understood that a larger collaborative performance deviation ratio indicates a worse collaborative performance of the train control device in performing that interactive behavior, and a smaller collaborative performance deviation ratio indicates a better collaborative performance. Therefore, the collaborative performance deviation ratio of the train control devices performing the interactive behavior represents the collaborative performance of a single train control device pair.

[0053] In one embodiment, the expected parameters of collaborative performance are obtained in advance through statistical analysis of industry standards, system design indicators, product technical specifications, or historical operating data on the interaction behavior between train control equipment. For example, the maximum allowable communication delay between the radio block center and the on-board equipment in a specific section of a certain type of heavy-haul train, the legal time window for transponder information activation, or the interlocking constraints between multiple devices, etc. This embodiment does not make specific limitations on these.

[0054] In one embodiment, the collaborative performance deviation ratio is obtained by calculating the difference between the collaborative performance parameters of the train control device performing interactive behavior and the expected collaborative performance parameters, and then dividing the difference by the sum of the expected parameters and a preset constant. The collaborative performance deviation ratio is expressed as:

[0055]

[0056] in, Indicates the proportion of collaborative deviation. Indicates the first Collaborative performance parameters of interactive behaviors, Indicates the first The expected parameters of the collaborative performance of the interaction behavior. This represents a preset constant.

[0057] Step 210: Determine the collaborative performance test result of the train control system based on the collaborative performance deviation ratio of each train control device in performing the interactive behavior.

[0058] In this step, step 208 only yields the proportion of collaborative performance deviation for each train control device pair performing corresponding interactive behaviors. This only represents the collaborative performance of a single train control device pair and cannot represent the collaborative performance of the entire train control system. Therefore, in this step, the proportions of collaborative performance deviation for each train control device pair performing each interactive behavior are weighted and fused to obtain a collaborative performance test result that represents the overall true collaborative performance of the train control system. Furthermore, the entire test process does not involve human intervention, avoiding bias introduced by human factors, and significantly improving the accuracy of the collaborative performance test result. Specifically, a larger collaborative performance test result indicates worse collaborative performance of the train control system, while a smaller result indicates better collaborative performance.

[0059] In one embodiment, the weighted deviation ratio of the collaborative performance of each train control device pair performing each interactive behavior is multiplied by its corresponding weighting coefficient to obtain the weighted deviation ratio of each train control device pair. Different weighting coefficients correspond to different interactive behaviors, representing the varying importance of each interactive behavior to the overall collaborative performance of the train control system. Then, all weighted deviation ratios are summed to obtain the collaborative performance detection result representing the overall collaborative performance of the train control system. Based on this collaborative performance detection result, the overall true collaborative performance of all device groups in the train control system under each interactive behavior can be comprehensively reflected, and the accuracy is significantly improved. The collaborative performance detection result is expressed as follows:

[0060]

[0061] in, This indicates the results of the collaborative performance test. Indicates the first The weight coefficient of each interactive behavior, where n represents the total number of interactive behaviors.

[0062] In the aforementioned distributed detection method for the collaborative performance of multiple train control devices in heavy-haul railways, operational data of each train control device is acquired during the actual operation of the train control system. Based on this data, pairs of train control devices exhibiting interactive behavior are identified, and these pairs are associated with the target operational data of the interactive behavior. For each pair, collaborative performance parameters are determined based on the associated target operational data. Then, based on these parameters and the corresponding expected collaborative performance parameters, the collaborative performance deviation ratio is determined. Finally, the collaborative performance detection result of the train control system is determined based on the collaborative performance deviation ratio of each pair. By acquiring operational data generated by each train control device during the actual operation of the train control system, the collaborative performance detection result based on this data reflects the true synchronization and linkage between the train control devices. Furthermore, the entire detection process does not involve manual operation, avoiding deviations introduced by human factors. Therefore, the collaborative performance detection result comprehensively reflects the overall true collaborative performance of all equipment groups in the train control system under various interactive behaviors, significantly improving accuracy.

[0063] In one exemplary embodiment, such as Figure 3 As shown, after step 206, steps 302 to 308 are also included.

[0064] Step 302: Construct a collaborative interaction relationship representation of the train control system based on the collaborative performance parameters of each train control device pair; the collaborative interaction relationship representation uses the train control device as a node, the interaction behavior between the train control devices as directed edges, and the collaborative performance parameters as edge attributes.

[0065] By constructing a representation of the collaborative interaction relationship of the train control system, the interaction topology and performance distribution of each train control device node in the train control system can be reflected, laying the foundation for subsequent comparative analysis with the benchmark collaborative interaction relationship representation.

[0066] Step 304: Determine the collaborative performance deviation ratio between the same interactive behaviors based on the edge attributes of the same interactive behaviors in the collaborative interaction relationship representation and the benchmark collaborative interaction relationship representation.

[0067] The baseline collaborative interaction relationship representation is pre-constructed using train control equipment as nodes, the interaction behaviors between train control equipment as directed edges, and the expected collaborative performance parameters as edge attributes. This representation reflects the interaction topology and baseline performance distribution of the train control system under the expected performance, facilitating item-by-item comparison with the actual collaborative interaction relationship representation. Compared to directly retrieving and matching the collaborative performance parameters of each interaction behavior, this interaction relationship representation organizes the dispersed train control equipment interactions into a unified node-edge model. This eliminates the need to repeatedly traverse all data for locating and comparing the same interaction behavior, thereby improving detection efficiency.

[0068] In one embodiment, the detection method further includes: comparing the global interaction behavior of each connection path in the collaborative interaction relationship representation with the baseline global interaction behavior of the baseline connection path corresponding to the baseline collaborative interaction relationship representation, and determining the proportional deviation of the collaborative performance between the global interaction behavior and the baseline global interaction behavior, thereby avoiding the potential omission of cross-device and cross-path global collaborative performance issues due to local evaluation only for a single train control device.

[0069] It should be noted that the aforementioned global interaction behavior does not refer to the interaction behavior between individual train control devices, but rather to the whole consisting of multiple continuous interaction behaviors within the connection path in the representation of collaborative interaction relationship.

[0070] In one embodiment, comparing the global interaction behavior of each connection path in the collaborative interaction relationship representation with the baseline global interaction behavior of the baseline connection path corresponding to that connection path in the baseline collaborative interaction relationship representation to determine the collaborative performance ratio deviation between the global interaction behavior and the baseline global interaction behavior further includes: comparing the global interaction behavior with the baseline global interaction behavior to determine the same interaction behavior and the newly added and / or missing interaction behavior in the global interaction behavior and the baseline global interaction behavior; determining a first collaborative performance deviation ratio based on the edge attributes of the same interaction behavior in the global interaction behavior and the baseline global interaction behavior; determining a second collaborative performance deviation ratio based on the newly added and / or missing interaction behavior in the global interaction behavior; and weighting the first collaborative performance deviation ratio and the second collaborative performance deviation ratio to obtain the collaborative performance detection result of the train control system.

[0071] In this embodiment, a collaborative interaction relationship representation of the train control system is constructed by using train control equipment as nodes, the interaction behaviors between train control equipment as directed edges, and collaborative performance parameters as edge attributes. The collaborative interaction relationship representation is compared with the edge attributes of the same interaction behaviors in the baseline interaction relationship representation to determine the collaborative performance deviation ratio between the same interaction behaviors. Since the above interaction relationship representation organizes the scattered interaction behaviors and corresponding collaborative performance parameters into a unified node-edge model, the location and comparison of the same interaction behaviors do not need to repeatedly traverse all the data, thereby improving the detection efficiency.

[0072] In one exemplary embodiment, such as Figure 4 As shown, step 202 also includes steps 402 to 406.

[0073] Step 402: During the actual operation of the train control system, acquire the initial operating data of each train control device and add a collection timestamp to the operating data;

[0074] The timestamp is used to identify the time of data collection during operation, serving as a time reference for subsequent spatiotemporal correlation. Initial operational data refers to raw data directly collected from the train control equipment, which has not undergone any processing.

[0075] For example, the initial operating data of the on-board device A obtained includes control commands: sending timestamp 10:00:01.000, command content 0x01 (request location), receiving timestamp 10:00:01.025, and the status variable (traction current) increasing from 500A to 510A between 10:00:01.000 and 10:00:01.025.

[0076] In one embodiment, step 402 further includes: combining the absolute time reference provided by BeiDou / GNSS (Global Navigation Satellite System) with the local nanosecond-level synchronization achieved by the PTP (Precision Time Protocol), adding a globally consistent timestamp to each initial running data, thereby solving the timing misalignment problem caused by clock drift or network jitter across regions and devices, avoiding errors in judging the order of interaction behaviors or confusion of causal relationships due to time deviation, and thus improving the accuracy of subsequent collaborative performance detection.

[0077] In one embodiment, the absolute time provided by BeiDou / GNSS is used as the absolute time reference of the train control system. In the local acquisition network, the acquisition timestamps of each initial operation data are calibrated through the PTP protocol, and the calibrated acquisition timestamps are added to the initial operation data.

[0078] Step 404: Obtain spatial topology positioning information corresponding to the initial running data based on the collection timestamp, and combine the spatial topology positioning information with the initial running data to obtain the running data;

[0079] Specifically, using the timestamp of the operational data as an index, and combining the railway line geographic information system (GIS) and the train control equipment topology database, the system queries the spatial topology location information corresponding to the collection timestamp. This includes the line section where the train is located at the current collection timestamp, such as the kilometer marker interval; the physical coordinates of each train control device in that line section, such as latitude and longitude or trackside location; and the topological relationships of each train control device in that line section, such as which radio block center a certain transponder belongs to. This spatial topology location information gives the operational data a locationable and traceable spatial context.

[0080] In one embodiment, spatial topology positioning information can also be associated with initial running data; this embodiment does not specifically limit this.

[0081] Step 406: Analyze the running data to determine the train control device pair with interactive behavior and the collaborative performance parameters of the train control device pair in performing the interactive behavior.

[0082] In one embodiment, the operating data of the train control equipment pair is parsed to determine the train control equipment pair with interactive behavior and the collaborative performance feature vector of the train control equipment pair in at least one dimension of response delay, control command transmission path and / or state coupling response mode; the collaborative performance feature vectors are fused to obtain collaborative performance parameters.

[0083] In this embodiment, the running data can be input into a pre-trained interactive behavior recognition model for parsing. This embodiment does not specifically limit the interactive recognition model, and those skilled in the art can select the corresponding model according to actual needs.

[0084] In this embodiment, by adding a collection timestamp to the initial operational data and combining it with spatial topology positioning information, operational data with a unified spatiotemporal reference is formed. Then, the operational data is parsed to automatically identify train control equipment pairs exhibiting interactive behavior and their corresponding collaborative performance parameters. This achieves fully automated processing from raw data acquisition to collaborative performance parameter extraction, ensuring both spatiotemporal consistency of the data and avoiding subjective biases introduced by manual intervention. This provides an accurate and reliable data foundation for subsequent collaborative performance testing, thereby improving the accuracy and efficiency of the testing results.

[0085] In one exemplary embodiment, such as Figure 5 As shown, step 210 is followed by steps 502 to 506.

[0086] Step 502: Determine the degradation level based on the collaborative performance test results;

[0087] Among them, the degradation level is used to characterize the degree of degradation of the collaborative performance of the train control system, that is, the severity of the deviation of the actual collaborative performance from the expected performance.

[0088] In one embodiment, as mentioned above, a larger collaborative performance test result indicates poorer collaborative performance of the train control system, while a smaller collaborative performance test result indicates better collaborative performance. The collaborative performance test result is compared with a preset risk range to determine the target risk range it falls into. Each risk range has a pre-recorded degradation level and the corresponding range of collaborative performance test results. The degradation level associated with the target risk range is used as the degradation level of the collaborative performance test result.

[0089] In one embodiment, the degradation level includes normal, warning, severe, fault, etc., and this embodiment does not specifically limit it.

[0090] Step 504: Determine the detection configuration parameters based on the degradation level;

[0091] Step 506: Based on the detection configuration parameters, continue to execute the step of obtaining the operating data of each train control device.

[0092] The detection configuration parameters specify the exact data type and detection frequency of the operational data from the train control equipment to be acquired. This allows for adaptive adjustment of the detection granularity and frequency for each collaborative performance test based on the degradation level of the previous test. The detection configuration parameters follow a rule: the higher the degradation level, the larger the detection granularity and frequency; the lower the degradation level, the smaller the detection granularity and frequency.

[0093] In one embodiment, after step 502, the method further includes: acquiring the operating environment data of the train control system, fusing the operating environment data to obtain the operating environment feature vector, determining the detection configuration parameters based on the operating environment feature vector and the collaborative performance detection results, and continuing to execute the step of acquiring the operating data of each train control device based on the detection configuration parameters.

[0094] The operational environment data includes train operation density (e.g., the number of trains passing through a certain line section per unit time), line conditions (e.g., gradients, curves, and construction sections), online / offline status of train control equipment, historical fault records of train control equipment, and external disturbance data such as weather or track conditions. Based on this, this operational environment data is encoded into a dynamically evolving operational environment feature vector, reflecting the actual operational environment of the current detection task. The determination of detection configuration parameters considers not only the degree of degradation of the train control system's own collaborative performance but also the severity of the external environment in which the train control system operates. This makes the determination of detection configuration parameters more comprehensive and scientific, enabling adaptive adjustment of detection strategies according to the actual risk level and avoiding waste of detection resources or insufficient detection.

[0095] For example, the operating environment is characterized by high-density heavy-load intersections in the line section where the train control system is located, single-point operation of the train control equipment, and the superposition of harsh environments. The current collaborative performance test results of the train control system indicate a high degree of degradation in collaborative performance. At this time, the detection frequency of the detection configuration parameters is reduced and the detection granularity is increased.

[0096] In one embodiment, the collaborative performance detection results are fused with the operating environment feature vector to determine the safety risk level of the train control system, and then the detection configuration parameters are determined based on the safety risk level.

[0097] Among them, the safety risk level reflects the degree of deterioration of the collaborative performance of the train control system and the severity of the external environment.

[0098] In this embodiment, the degradation level is determined based on the collaborative performance test results, and the test configuration parameters are determined based on the degradation level. The test is then performed again based on the test configuration parameters. This ensures that the test accuracy is guaranteed, and the test resources are allocated reasonably. This avoids excessive testing when the degradation level is low, which would cause a waste of resources. At the same time, it ensures that the test granularity and frequency meet the safety requirements when the degradation level is high.

[0099] It should be understood that although the steps in the flowcharts of the embodiments described above 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 embodiments described above 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.

[0100] In an exemplary embodiment, a first detection system based on cloud-edge collaboration is provided, which is applied to the distributed detection method for collaborative performance of multiple equipment in heavy-haul railway train control in any of the above embodiments. The first detection system includes an edge service layer and a cloud service layer, wherein the edge service layer is set along the railway line and the cloud service layer is set at a remote location.

[0101] In one embodiment, the edge service layer includes multiple edge servers, which are respectively located in various sections along the railway line, and the cloud service layer includes one or more cloud servers.

[0102] In one embodiment, the edge service layer handles tasks with high response speed requirements, while the cloud service layer handles tasks with low response speed requirements, thereby improving real-time detection efficiency.

[0103] In one embodiment, the edge service layer is used to acquire the operating data of each train control device during the actual operation of the train control system; identify train control device pairs with interactive behavior based on the operating data; for each train control device pair, determine the collaborative performance parameters of the train control device pair performing interactive behavior based on the operating data of the train control device pair; determine the collaborative performance deviation ratio of the train control device pair performing interactive behavior based on the collaborative performance parameters of the train control device pair performing interactive behavior and the corresponding expected collaborative performance parameters; and determine the collaborative performance detection result of the train control system based on the collaborative performance deviation ratio of each train control device pair performing interactive behavior.

[0104] In one embodiment, the edge service layer is further configured to determine initial candidate train control device pairs with potential interactive behavior based on whether the difference in transmission timestamps between control commands between each train control device meets a preset threshold; determine target candidate train control device pairs based on whether the instruction content of each control command of the candidate train control devices meets a preset mapping relationship; and determine train control device pairs with interactive behavior based on whether the time-series data of the state variables of each control command of the target candidate train control devices meets a preset state coupling relationship.

[0105] In one embodiment, the edge service layer is further configured to construct a collaborative interaction relationship representation of the train control system based on the collaborative performance parameters of each train control device pair; the collaborative interaction relationship representation uses the train control device as a node, the interaction behavior between the train control devices as directed edges, and the collaborative performance parameters as edge attributes; based on the edge attributes of the same interaction behavior in the collaborative interaction relationship representation and the baseline collaborative interaction relationship representation, the collaborative performance deviation ratio between the same interaction behavior is determined; the baseline collaborative interaction relationship representation uses the train control device as a node, the interaction behavior between the train control devices as directed edges, and the expected collaborative performance parameters as edge attributes.

[0106] In one embodiment, the edge service layer is also used to acquire the initial operating data of each train control device during the actual operation of the train control system, and add a collection timestamp to the initial operating data; acquire the spatial topology positioning information corresponding to the initial operating data according to the collection timestamp, combine the spatial topology positioning information with the initial operating data to obtain the operating data; parse the operating data to determine the train control device pairs with interactive behavior and the collaborative performance parameters of the train control device pairs performing interactive behavior.

[0107] In one embodiment, the edge service layer is also used to align the various operational data according to a standard spatiotemporal reference to obtain spatiotemporally consistent operational data.

[0108] In one embodiment, the cloud service layer is used to determine the degradation level based on the collaborative performance detection results; determine the detection configuration parameters based on the degradation level; and continue to execute the steps of obtaining the operating data of each train control device based on the detection configuration parameters.

[0109] In one embodiment, the cloud service layer is used to acquire the operating environment data of the train control system; encode the operating environment data into an operating environment feature vector; and determine the detection configuration parameters based on the operating environment feature vector and the collaborative performance detection results.

[0110] In this embodiment, tasks with high response speed requirements are executed by the edge service layer, while tasks with low response speed requirements are executed by the cloud service layer. This rationally allocates computing resources, avoids network congestion and processing delays caused by uploading large amounts of data to the cloud service layer, and improves detection efficiency.

[0111] In one exemplary embodiment, the detection system further includes a scheduling layer for allocating detection tasks to corresponding edge servers for processing; wherein the allocation strategy may be determined based on one or more of the following allocation data: the real-time load of the edge server, task priority, data source location, network latency, etc.

[0112] In one embodiment, the scheduling layer determines the amount of operational data to be acquired by each edge server based on at least one of the following: real-time load of the edge server, task priority, data source location, and network latency. Each edge server is used to acquire operational data from each train control device that meets the acquisition quantity during the actual operation of the train control system. Based on the operational data, train control device pairs with interactive behavior are identified. For each train control device pair, based on the operational data of the train control device pair, the collaborative performance parameters for the train control device pair to perform interactive behavior are determined. Based on the collaborative performance parameters for the train control device pair to perform interactive behavior and the corresponding expected collaborative performance parameters, the collaborative performance deviation ratio for the train control device pair to perform interactive behavior is determined.

[0113] When the allocated data includes at least two data points, the allocated data is first fused to obtain an allocation feature vector, and then the amount of running data to be acquired by each edge server is determined based on the allocation feature vector.

[0114] In one embodiment, after each edge server determines the collaborative performance deviation ratio based on the acquired operational data, the collaborative performance deviation ratios are synchronized with each other. Then, one of the edge servers determines the collaborative performance detection result of the train control system based on all the synchronized collaborative performance deviation ratios.

[0115] In this embodiment, the scheduling layer dynamically allocates the amount of running data to be acquired based on the real-time load of the edge servers, thereby achieving load balancing and resource optimization. Each edge server performs running data acquisition and collaborative performance deviation ratio calculation in parallel, improving detection efficiency. The calculated collaborative performance deviation ratios of each edge server are synchronized with each other and aggregated by one edge server. The collaborative performance detection results of the train control system can be obtained at the edge service layer, reducing data transmission latency and improving detection efficiency and resource utilization.

[0116] Based on the same inventive concept, this application also provides a detection system for implementing the distributed detection method for the collaborative performance of multiple equipment in heavy-haul railway train control as described above. The solution provided by this detection system is similar to the implementation scheme described in the above method. Therefore, the specific limitations in one or more detection system embodiments provided below can be found in the limitations of the distributed detection method for the collaborative performance of multiple equipment in heavy-haul railway train control described above, and will not be repeated here.

[0117] In one exemplary embodiment, such as Figure 6 As shown, a detection system is provided, including: an acquisition module 602, a first determination module 604, a second determination module 606, a first detection module 608, and a second detection module 610, wherein:

[0118] The acquisition module 602 is used to acquire the operating data of each train control device during the actual operation of the train control system;

[0119] The first determining module 604 is used to identify train control equipment pairs with interactive behavior based on the operating data, and associate the train control equipment pairs with the target operating data of the train control equipment pairs performing interactive behavior.

[0120] The second determining module 606 is used to determine the collaborative performance parameters of the train control equipment pair's interactive behavior based on the train control equipment pair's operating data for each train control equipment pair.

[0121] The first detection module 608 is used to determine the proportion of the collaborative performance deviation of the train control equipment for the interactive behavior based on the collaborative performance parameters of the train control equipment for the interactive behavior and the corresponding expected collaborative performance parameters.

[0122] The second detection module 610 is used to determine the collaborative performance detection result of the train control system based on the proportion of collaborative performance deviation of each train control device in performing interactive behavior.

[0123] In one embodiment, the first determining module 604 is further configured to determine an initial candidate train control device pair with potential interactive behavior based on whether the difference in the transmission timestamps between the control commands of each train control device meets a preset threshold; determine a target candidate train control device pair based on whether the instruction content of the candidate train control devices for their respective control commands meets a preset mapping relationship; and determine a train control device pair with interactive behavior based on whether the time sequence data of the state variables of the target candidate train control devices for their respective control commands meets a preset state coupling relationship.

[0124] In one embodiment, the second determining module 606 is further configured to construct a collaborative interaction relationship representation of the train control system based on the collaborative performance parameters of each train control device pair; the collaborative interaction relationship representation uses the train control device as a node, the interaction behavior between the train control devices as directed edges, and the collaborative performance parameters as edge attributes; based on the edge attributes of the same interaction behavior in the collaborative interaction relationship representation and the benchmark collaborative interaction relationship representation, the collaborative performance deviation ratio between the same interaction behavior is determined; the benchmark collaborative interaction relationship representation uses the train control device as a node, the interaction behavior between the train control devices as directed edges, and the expected collaborative performance parameters as edge attributes.

[0125] In one embodiment, the acquisition module 602 is further configured to acquire the initial operating data of each train control device during the actual operation of the train control system, and add a collection timestamp to the initial operating data; acquire the spatial topology positioning information corresponding to the initial operating data according to the collection timestamp, and combine the spatial topology positioning information with the initial operating data to obtain the operating data.

[0126] In one embodiment, the second determining module 606 is further configured to parse the operating data to determine the train control equipment pairs that have interactive behavior and the collaborative performance parameters of the train control equipment pairs performing interactive behavior.

[0127] In one embodiment, the alignment module is used to align the various running data according to a standard spatiotemporal reference to obtain spatiotemporally consistent running data.

[0128] In one embodiment, the configuration module is used to determine the degradation level based on the collaborative performance test results; determine the test configuration parameters based on the degradation level; and continue to execute the steps of obtaining the operating data of each train control device based on the test configuration parameters.

[0129] In one embodiment, the configuration module is further configured to acquire the operating environment data of the train control system; encode the operating environment data into an operating environment feature vector; and determine the detection configuration parameters based on the operating environment feature vector and the collaborative performance detection results.

[0130] Each module in the aforementioned detection system can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of the computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0131] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 7 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 computational 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 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, NFC (Near Field Communication), or other technologies. When executed by the processor, the computer program implements a distributed detection method for the collaborative performance of multiple devices in heavy-haul railway train control. 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.

[0132] Those skilled in the art will understand that Figure 7 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.

[0133] 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 in the above-described method embodiments.

[0134] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above method embodiments.

[0135] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0136] 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.

[0137] 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.

[0138] 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 distributed detection method for the collaborative performance of multiple equipment in heavy-haul railway train control, characterized in that, The method includes: During the actual operation of the train control system, the operating data of each train control device is acquired; Based on the operational data, identify train control equipment pairs exhibiting interactive behavior; For each of the train control device pairs, based on the operating data of the train control device pairs, the collaborative performance parameters for the train control device pairs to perform the interactive behavior are determined; Based on the collaborative performance parameters of the train control device for performing the interactive behavior and the corresponding expected collaborative performance parameters, the collaborative performance deviation ratio of the train control device for performing the interactive behavior is determined. The collaborative performance test result of the train control system is determined based on the proportion of collaborative performance deviation of each of the train control devices in performing the interactive behavior.

2. The method according to claim 1, characterized in that, After determining the collaborative performance parameters for the train control device pair to perform the interactive behavior based on the operating data of the train control device pair for each pair, the method further includes: The collaborative interaction relationship representation of the train control system is constructed based on the collaborative performance parameters of each train control device pair; the collaborative interaction relationship representation uses the train control device as a node, the interaction behavior between the train control devices as directed edges, and the collaborative performance parameters as edge attributes. Based on the edge attributes of the same interactive behaviors in the aforementioned collaborative interaction relationship representation and the benchmark collaborative interaction relationship representation, the collaborative performance deviation ratio between the same interactive behaviors is determined; the benchmark collaborative interaction relationship representation takes the train control equipment as nodes, the interactive behaviors between the train control equipment as directed edges, and the expected collaborative performance parameters as edge attributes.

3. The method according to claim 1, characterized in that, The method further includes: During the actual operation of the train control system, the initial operating data of each train control device is acquired, and a collection timestamp is added to the initial operating data; Based on the collection timestamp, spatial topology positioning information corresponding to the initial running data is obtained, and the spatial topology positioning information is combined with the initial running data to obtain the running data; The operational data is parsed to determine the train control device pair that exhibits interactive behavior and the collaborative performance parameters of the train control device pair in executing the interactive behavior.

4. The method according to claim 1, characterized in that, The step of identifying train control equipment with interactive behavior based on the operational data also includes: The operational data are aligned according to a standard spatiotemporal reference to obtain spatiotemporally consistent operational data.

5. The method according to claim 1, characterized in that, After determining the collaborative performance detection result of the train control system based on the collaborative performance deviation ratio of each of the train control devices for performing the interactive behavior, the method further includes: The degradation level is determined based on the results of the collaborative performance test. Determine the detection configuration parameters based on the aforementioned degradation level; Based on the detection configuration parameters, continue to execute the step of obtaining the operating data of each train control device.

6. The method according to claim 5, characterized in that, After determining the collaborative performance detection result of the train control system based on the collaborative performance deviation ratio of each of the train control devices for performing the interactive behavior, the method further includes: Obtain the operating environment data of the train control system; The runtime environment data is fused to obtain a runtime environment feature vector; The detection configuration parameters are determined based on the operating environment feature vector and the collaborative performance detection results. Based on the detection configuration parameters, continue to execute the step of obtaining the operating data of each train control device.

7. The method according to claim 1, characterized in that, The operational data includes the timestamp of each control command sent by the train control device, the command content, and the timing data of status variables; the step of identifying train control devices with interactive behavior based on the operational data also includes: Based on whether the difference in the timestamps of the transmission of each control command between the train control devices meets a preset threshold, an initial candidate train control device pair with potential interactive behavior is determined; Based on whether the instruction content of the candidate train control devices for their respective control commands conforms to a preset mapping relationship, the target candidate train control device pair is determined; Based on whether the timing data of the state variables of the target candidate train control devices for their respective control commands conform to the preset state coupling relationship, the train control device pairs with interactive behavior are determined.

8. A detection system, characterized in that, include: The acquisition module is used to acquire the operating data of each train control device during the actual operation of the train control system; The first determining module is used to identify train control device pairs with interactive behavior based on the operating data, and associate the train control device pairs with the target operating data of the train control device pairs performing the interactive behavior. The second determining module is used to determine, for each train control device pair, the collaborative performance parameters for the train control device pair to perform the interactive behavior based on the operating data of the train control device pair; The first detection module is used to determine the proportion of the collaborative performance deviation of the train control device in performing the interactive behavior based on the collaborative performance parameters of the train control device in performing the interactive behavior and the corresponding expected collaborative performance parameters. The second detection module is used to determine the collaborative performance detection result of the train control system based on the proportion of collaborative performance deviation of each of the train control devices in performing the interactive behavior.

9. 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 7.

10. 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 7.

Images