Signal equipment position deviation detection method and system based on theoretical position coordinates and actual position coordinates

Abstract

The invention discloses a position deviation detection method and system for signal equipment based on theoretical position coordinates and actual position coordinates, and relates to the technical field of position deviation detection. Corresponding dynamic tolerance parameters are determined according to equipment types and corresponding equipment functions of the signal equipment; determining a deviation event of the signal equipment according to the content of the position deviation, the dynamic tolerance parameter of the signal equipment and the actual position coordinate, determining corresponding geometric deviation and functional deviation based on the detection of the deviation event, and determining a corresponding multi-layer decision system according to the geometric deviation and functional deviation of the signal equipment and the working process of the signal equipment. The accuracy of the multi-layer decision-making system is improved, the final deviation value of the corresponding signal equipment is determined based on recognition of the decision-making result, and the corresponding dynamic maintenance content is determined according to the final deviation value of each signal equipment, the current work task of the train and the multi-layer decision-making system so as to dynamically maintain the corresponding signal system database.

Description

Technical Field

[0001] This invention relates to the technical field of position deviation detection, and more particularly to a method and system for detecting position deviation of a signal device based on theoretical and actual position coordinates. Background Technology

[0002] Currently, the industry mainly relies on manual operation to check the conformity between the installation location and the design location of signal equipment. The specific process is as follows: after obtaining the actual location coordinates of the signal equipment measured on site, technicians manually review the design drawings and internal technical specifications, and make a judgment on whether the database needs to be updated based on experience or manual comparison of the tolerance thresholds of various devices. Finally, the corresponding system database is updated based on the judgment result, which affects the accuracy of the final deviation of the signal equipment and the dynamic maintenance of the corresponding signal system database. Summary of the Invention

[0003] The purpose of this invention is to overcome the shortcomings of the prior art. This invention provides a method and system for detecting position deviation of a signal device based on theoretical position coordinates and actual position coordinates.

[0004] This invention provides a method for detecting position deviation of a signal device based on theoretical and actual position coordinates, comprising: Based on the design documents, determine the theoretical coordinates of the signal equipment on the plan, and collect the actual coordinates of the train's signal equipment; determine the position information based on the basic information, theoretical coordinates, and actual coordinates of the signal equipment. Based on the identification of the location information, the corresponding location deviation content is determined. At the same time, the corresponding dynamic tolerance parameters are determined according to the equipment type and corresponding equipment function of the signal equipment. The deviation event of the signal equipment is determined based on the location deviation content, the dynamic tolerance parameters of the signal equipment, and the actual location coordinates. The deviation event includes the equipment ID, deviation content, actual coordinates, dynamic tolerance parameters, and frame judgment result. Based on the detection of this deviation event, the corresponding geometric deviation and functional deviation are determined. According to the geometric deviation, functional deviation and working history of the signal equipment, the corresponding multi-level decision system is determined, and the multi-level decision path of the multi-level decision system is marked. Multiple decision nodes are identified based on the multi-layer decision path identification. The corresponding decision progression relationship is determined based on the decision content of each decision node, the corresponding node position, and the deviation event of the signal device, and the corresponding decision result is marked. The decision hierarchy relationship includes identifying parent-child relationship, parallel relationship, and priority relationship. Based on the identification of the decision results, the final deviation of the corresponding signal equipment is determined. According to the final deviation of each signal equipment, the current work task of the train, and the multi-level decision-making system, the corresponding dynamic maintenance content is determined to dynamically maintain the corresponding signal system database.

[0005] This invention provides a position deviation detection system for signal devices based on theoretical and actual position coordinates. This system is applied to the aforementioned position deviation detection method for signal devices based on theoretical and actual position coordinates.

[0006] Compared with the prior art, the beneficial effects of the present invention are: (1) Based on the design documents, determine the theoretical position coordinates of the signal equipment on the plan and collect the actual position coordinates of the train's signal equipment; determine the position information based on the basic information, theoretical position coordinates and actual position coordinates of the signal equipment; determine the corresponding position deviation content based on the identification of the position information; at the same time, determine the corresponding dynamic tolerance parameters based on the equipment type and corresponding equipment function of the signal equipment; determine the deviation event of the signal equipment based on the position deviation content, the dynamic tolerance parameters of the signal equipment and the actual position coordinates; introduce dynamic tolerance parameters and realize further control over position deviation, thereby improving the accuracy of the deviation event of the signal equipment.

[0007] (2) Based on the detection of the deviation event, the corresponding geometric deviation and functional deviation are determined. Based on the geometric deviation, functional deviation and working history of the signal equipment, the corresponding multi-level decision system is determined. The overall consideration of the geometric deviation, functional deviation and working history of the signal equipment is realized, the accuracy of the multi-level decision system is improved, and the multi-level decision path of the multi-level decision system is further marked.

[0008] (3) Based on the identification of the multi-level decision path, multiple decision nodes are identified. Based on the decision content of each decision node, the corresponding node position and the deviation event of the signal equipment, the corresponding decision progression relationship is determined and the corresponding decision result is marked. Based on the identification of the decision result, the final deviation of the corresponding signal equipment is determined. Based on the final deviation of each signal equipment, the current work task of the train and the multi-level decision system, the corresponding dynamic maintenance content is determined. The decision progression relationship is introduced, and the decision content of each decision node is controlled in stages. This improves the accuracy of the final deviation of the signal equipment and controls the dynamic maintenance content to dynamically maintain the corresponding signal system database. Attached Figure Description

[0009] Figure 1 This is a flowchart illustrating the position deviation detection method of the signal device based on theoretical and actual position coordinates in an embodiment of the present invention. Figure 2 This is a flowchart illustrating step S11 of the position deviation detection method for a signal device based on theoretical and actual position coordinates in an embodiment of the present invention. Figure 3 This is a flowchart illustrating step S12 in the position deviation detection method of the signal device based on theoretical position coordinates and actual position coordinates in an embodiment of the present invention. Figure 4 This is a flowchart illustrating step S13 of the position deviation detection method for a signal device based on theoretical and actual position coordinates in an embodiment of the present invention. Figure 5 This is a flowchart illustrating step S14 of the position deviation detection method for signal devices based on theoretical and actual position coordinates in an embodiment of the present invention. Figure 6 This is a flowchart illustrating step S15 of the position deviation detection method for signal devices based on theoretical and actual position coordinates in an embodiment of the present invention. Figure 7 This is a schematic diagram of the structural composition of the position deviation detection system of the signal device based on theoretical position coordinates and actual position coordinates in an embodiment of the present invention. Detailed Implementation

[0010] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.

[0011] Please see Figures 1 to 7 A method for detecting position deviation of a signal device based on theoretical and actual position coordinates, applied to position deviation detection scenarios; the method for detecting position deviation of a signal device based on theoretical and actual position coordinates includes: Step S11: Determine the theoretical position coordinates of the signal equipment on the plan based on the design documents, and collect the actual position coordinates of the train's signal equipment; determine the position information based on the basic information, theoretical position coordinates, and actual position coordinates of the signal equipment; Step S12: Based on the identification of the location information, determine the corresponding location deviation content. At the same time, determine the corresponding dynamic tolerance parameters based on the equipment type and corresponding equipment function of the signal equipment. Based on the location deviation content, the dynamic tolerance parameters of the signal equipment, and the actual location coordinates, determine the deviation event of the signal equipment. Step S13: Based on the detection of the deviation event, determine the corresponding geometric deviation and functional deviation, determine the corresponding multi-level decision system according to the geometric deviation and functional deviation of the signal equipment, and mark the multi-level decision path of the multi-level decision system; Step S14: Based on the identification of the multi-layer decision path, determine multiple decision nodes, determine the corresponding decision progression relationship based on the decision content of each decision node, the corresponding node position and the deviation event of the signal device, and mark the corresponding decision result; Step S15: Based on the identification of the decision result, determine the final deviation of the corresponding signal equipment, and determine the corresponding dynamic maintenance content according to the final deviation of each signal equipment and the multi-level decision system, so as to dynamically maintain the corresponding signal system database.

[0012] refer to Figure 2 In step S11, the specific steps are as follows: S111: Collect design documents, determine the signal equipment distribution table based on the design documents, and determine the theoretical coordinates of the signal equipment on the plan view based on the signal equipment distribution table; S112: Conduct on-site testing of the signal equipment, mark the corresponding actual location coordinates during the on-site testing, collect the basic information of the signal equipment, and determine the location information based on the basic information, theoretical location coordinates and actual location coordinates of the signal equipment.

[0013] In the embodiments of this application, design documents are collected, a signal device distribution table is determined based on the design documents, and the theoretical position coordinates of the signal devices on the plan are determined according to the signal device distribution table. This approach takes into account the overall consideration of the identification of the signal device distribution table and ensures the accuracy of the plan of each signal device.

[0014] At this point, the system establishes a connection with the train's core database (usually the ATS Automatic Train Monitoring System or ZC Area Controller Database) through a standardized database interface (such as ODBC, JDBC, or a specific API). The system executes a Structured Query Language (SQL) statement designed to precisely filter out all signaling equipment information on the target line. The query results are loaded into a temporary, structured data table, namely the "Signaling Equipment Distribution Table," which serves as an index for subsequent operations. This table clearly lists the unique identifier, equipment type, line, section, and crucial mileage information for each signaling device. Optionally, the signaling equipment distribution table can be determined through identification of the design documents.

[0015] The system uses the line ID and section ID fields in the "signal equipment distribution table" generated in the previous step as indexes to retrieve the corresponding line plan map from the stored line geographic information system (GIS). These plan maps are usually high-precision CAD files or vector graphics files (such as DXF format), which have accurately drawn key infrastructure elements such as the line centerline, tracks, platforms, and turnouts. The system loads the retrieved plan map file into memory.

[0016] The system needs to solve the conversion problem between mileage (one-dimensional linear distance) and planar coordinates (two-dimensional X, Y coordinates). To this end, the system integrates an algorithm that can accurately convert mileage values ​​(e.g., 12543.78 meters) into two-dimensional coordinates (X, Y) on the planar map based on the geometric model of the route's centerline. Once the coordinate calculation is complete, the system marks the calculated (X, Y) position on the loaded planar map using specific symbols (e.g., crosshairs or device icons). At the same time, this coordinate value (e.g., X: 345678.90, Y: 567890.12) is recorded and stored in association with the device's device_id, thus completing the final determination of the theoretical position.

[0017] Specifically, the system connects to the train's ATS database and executes the aforementioned SQL query. In the returned query results, the system will find a record related to the signal, for example: device_id:'SIG_A_001', device_type:'B', line_id:'A', section_id:'S1', installation_mileage:12543.78. This record is then added to the "Signal Equipment Distribution Table," clearly indicating that there is a signal with the ID SIG_A_001 at mileage 12543.78 in section S1 of line A.

[0018] The system reads from the "Signal Equipment Distribution Table" that SIG_A_001 has a line_id of A and a section_id of S1. Based on this information, the system searches in the GIS system and successfully locates the plan view file (e.g., A_Line_S1.dxf) for section S1 of line A. The system loads this file into memory, and at this point, an accurate map containing the layout of all tracks and facilities at the location of SIG_A_001 is ready.

[0019] The system reads the installation_mileage value of SIG_A_001 from the distribution table as 12543.78 meters. Then, the system calls its internal mileage-coordinate conversion algorithm, which calculates the exact coordinates of this mileage point on the plan view based on the centerline model of section S1 of Line A. The final coordinates are (X:345678.90, Y:567890.12). The system places a signal icon at coordinates (345678.90, 567890.12) on the A_Line_S1.dxf plan view and associates this theoretical position coordinate with the device ID 'SIG_A_001'. At this point, the task of establishing the theoretical position reference for this signal is complete.

[0020] Furthermore, the signal equipment is tested on-site, and the corresponding actual location coordinates are marked during the on-site testing. At the same time, the basic information of the signal equipment is collected, and the location information is determined based on the basic information, theoretical location coordinates, and actual location coordinates of the signal equipment. This comprehensive consideration of the basic information, theoretical location coordinates, and actual location coordinates of the signal equipment ensures the accuracy of the location information.

[0021] At this point, on-site technicians or automated measurement equipment (such as total stations, GPS-RTK, and 3D laser scanners) perform the task beside the track to accurately locate the physical installation position of the target signal equipment. The operators or equipment will use a known, stable reference point (such as a fixed mileage marker on the centerline of the line or a known point in the national geodetic coordinate system) as a benchmark to measure and record the three-dimensional coordinates (X,Y,Z) or two-dimensional plane coordinates (X,Y) of the center point of the signal equipment's mounting base in physical space. To ensure the accuracy of subsequent analysis, the measurement accuracy is usually required to reach the millimeter level. The measured actual coordinates will be strictly recorded and associated with on-site photos of the equipment, equipment ID tags, etc.

[0022] While conducting on-site coordinate testing, technicians need to collect basic metadata of the signal equipment by reading the equipment nameplate or consulting on-site technical documents. The collected content covers the equipment's identification and attribute information, including but not limited to: device_id (a unique identifier for the device, used to associate with the database), device_model (equipment model), and manufacturer.

[0023] The system associates the theoretical position coordinates obtained in S111 with the actual position coordinates and basic information obtained in sub-steps 1 and 2 through a common identifier (such as device_id) and integrates them into a unified data structure. This integrated "position information" is usually a structured data object or record that fully encapsulates all the fields required for deviation analysis.

[0024] Specifically, the on-site measurement team, equipped with a total station, arrived at the S1 section of the train line based on the information provided in step S111 and precisely located the physical position of signal SIG_A_001. They used a known mileage marker on the centerline of the line (e.g., at mileage 12544.00 meters) as a backsight reference point and measured the center of the mounting base of SIG_A_001. The measurement results showed that the actual plane coordinates of the center of the signal base were (X: 345679.15, Y: 567890.85). This coordinate value was recorded in detail in the electronic measurement log and bound to the device ID 'SIG_A_001' and the on-site photograph of the device.

[0025] While completing the coordinate measurement, the surveyors carefully checked the nameplate on the SIG_A_001 device and confirmed its key information by scanning the QR code on the device: the device ID was indeed 'SIG_A_001', the model was "signal machine", the manufacturer was "XX Company", and the installation date was "October 15, 2023". This basic metadata was synchronously entered into the same measurement log and closely associated with the actual coordinates and device ID that had just been measured.

[0026] The theoretical coordinates (X:345678.90, Y:567890.12) recorded for SIG_A_001 in S111 are matched with the actual coordinates (X:345679.15, Y:567890.85) obtained from this field inspection, as well as basic information (device ID, model, manufacturer, installation date, etc.) using device_id; the system generates a complete "location information" record for SIG_A_001, which contains theoretical, actual, and attribute information.

[0027] refer to Figure 3 In step S12, the specific steps are as follows: S121: Dynamically identify the location information and mark the corresponding deviation keywords during the identification. Determine the corresponding location deviation content based on the tracing of the deviation keywords. At this time, the location deviation content presents the sub-deviation content of the signal device in each directional dimension. S122: Collect the equipment type of the signal equipment and mark the corresponding equipment function. Determine the corresponding dynamic tolerance parameter according to the mapping relationship between the equipment type, the corresponding equipment function and the dynamic tolerance parameter. The dynamic tolerance parameter presents the dynamic controllable range of the position deviation of the signal equipment. Determine the first deviation framework based on the position deviation content and the dynamic tolerance parameter of the signal equipment. Determine the deviation event of the signal equipment based on the first deviation framework and the actual position coordinates of the signal equipment.

[0028] In the embodiments of this application, the location information is dynamically identified, and the corresponding deviation keywords are marked during the identification. The corresponding location deviation content is determined based on the tracing of the deviation keywords. At this time, the location deviation content presents the sub-deviation content of the signal device in various directional dimensions, which is compatible with the overall consideration of tracing the deviation keywords and ensures the accuracy of the corresponding location deviation content.

[0029] At this point, the system receives and parses the "location information" data structure generated in step S112, which contains theoretical and actual position coordinates. The system's internal "dynamic recognition engine" begins to work. Its core logic is to automatically determine the vector direction of the deviation by comparing the theoretical coordinates (X_theo, Y_theo) and the actual coordinates (X_actual, Y_actual). Based on the comparison results, the engine will label the deviation with predefined, standardized "keywords." These keywords are basic terms describing the direction of the deviation, such as: X_POSITIVE (actual X coordinate is greater than theoretical value), X_NEGATIVE (actual X coordinate is less than theoretical value), Y_POSITIVE (actual Y coordinate is greater than theoretical value), Y_NEGATIVE (actual Y coordinate is less than theoretical value), and NO_DEVIATION (coordinates are completely consistent). This recognition process not only generates keywords but also accurately records which coordinate axis has deviated, indicating the direction for the next step of quantization calculation.

[0030] The system triggers the corresponding calculation module based on the marked deviation keywords. For each marked keyword, the system calculates the corresponding sub-deviation value. In a two-dimensional plane coordinate system, this is mainly manifested as: X-axis sub-deviation ΔX = X_actual - X_theo and Y-axis sub-deviation ΔY = Y_actual - Y_theo. In addition, to provide a comprehensive deviation metric, the system usually also calculates the total deviation (i.e., Euclidean distance) ΔD = sqrt(ΔX). 2 +ΔY 2 The calculated sub-deviation values ​​(ΔX, ΔY) and total deviation value (ΔD) are organized into a highly structured "position deviation content" data object. This object clearly presents the specific offset of the device in each directional dimension, so that the deviation is no longer a vague concept, but precise data that can be understood and processed by the system.

[0031] Specifically, the system receives complete location information for SIG_A_001, with a theoretical location of (X:345678.90, Y:567890.12) and an actual location of (X:345679.15, Y:567890.85). The system's "dynamic recognition engine" immediately starts and begins comparison: comparing the X coordinates: X_actual (345679.15) is greater than X_theo (345678.90), so the system automatically marks the keyword X_POSITIVE; comparing the Y coordinates: Y_actual (567890.85) is greater than Y_theo (567890.12), so the system automatically marks the keyword Y_POSITIVE; the system generates two keywords for the deviation of SIG_A_001: X_POSITIVE and Y_POSITIVE, indicating that the device has an offset in the positive directions of both the X and Y axes.

[0032] Based on the keywords X_POSITIVE and Y_POSITIVE marked in the previous step, the system triggers the corresponding calculation module to precisely quantify the deviation of SIG_A_001: Calculate the X-axis deviation: ΔX = 345679.15 - 345678.90 = +0.25 meters; Calculate the Y-axis deviation: ΔY = 567890.85 - 567890.12 = +0.73 meters; Calculate the total deviation: ΔD = sqrt(0.25... 2 +0.73 2 The system generates the final "position deviation content" data structure for SIG_A_001. The position deviation of SIG_A_001 is accurately identified and decomposed into: a deviation of 0.25 meters in the positive X-axis direction and a deviation of 0.73 meters in the positive Y-axis direction, with a total deviation of 0.77 meters. This structured output provides a clear and quantitative basis for subsequent intelligent analysis.

[0033] Furthermore, the types of signal equipment are collected, and their corresponding functions are marked. Based on the mapping relationship between the types of signal equipment, their corresponding functions, and dynamic tolerance parameters, the corresponding dynamic tolerance parameters are determined. These dynamic tolerance parameters represent the dynamically controllable range of the positional deviation of the signal equipment. Based on this positional deviation content and the dynamic tolerance parameters of the signal equipment, a first-level deviation framework is determined. Based on this first-level deviation framework and the actual position coordinates of the signal equipment, the deviation events of the signal equipment are determined. This approach considers both the first-level deviation framework and the actual position coordinates of the signal equipment as a whole, ensuring the accuracy of the deviation events. At the same time, the introduction of dynamic tolerance parameters further controls the positional deviation and improves the accuracy of the deviation events of the signal equipment.

[0034] At this point, the system extracts two key attributes from the "position information" data structure generated in step S112: device_type and device_function. device_function describes the specific role of the device in the train control system, directly determining its sensitivity to position accuracy. For example, a transponder, serving as an absolute position reference for the train, requires far higher accuracy than a signal used only for signal display. The system maintains a core "dynamic tolerance parameter mapping table," which defines the allowable deviation ranges for different combinations of device types and functions based on industry design standards, safety regulations, and historical data. The system queries this mapping table based on the extracted device attributes to determine a specific set of dynamic tolerance parameters for the device, typically in a multi-dimensional form.

[0035] The system compares the "position deviation content" (i.e., sub-deviation values ​​ΔX, ΔY) calculated in step S121 with the "dynamic tolerance parameters" determined in sub-step 1. This process constructs a "first-level deviation framework." The judgment logic of this framework is very clear: it judges whether the absolute deviation values ​​of the X-axis and Y-axis exceed the corresponding maximum allowable values. Based on the comparison results, the framework generates a preliminary judgment conclusion, such as "qualified" (all deviations are within the tolerance range) or "unqualified" (deviations in at least one direction exceed the tolerance range). If the final judgment result of the framework is "unqualified," the system formally determines that the signal device has generated a deviation event. The deviation event is a structured data object that includes the device ID, deviation content, actual coordinates, dynamic tolerance parameters, and the framework judgment result. This indicates that the problem has been escalated and needs to proceed to the next step (S13) for more in-depth analysis and processing.

[0036] Specifically, the system extracts key attributes from the "location information" of SIG_A_001: device_type is "B" (signal) and device_function is "entry signal display". The system queries the internal "dynamic tolerance parameter mapping table" to find records that match the combination of these attributes. Assuming that the parameters defined in the mapping table for the "entry signal display" function of the signal are: tolerance_X_max: 0.30 meters and tolerance_Y_max: 0.50 meters, the system determines its own dynamic tolerance parameters for SIG_A_001: the allowable deviation in the X-axis direction is no more than 0.30 meters and the allowable deviation in the Y-axis direction is no more than 0.50 meters.

[0037] The system obtains the "position deviation content" calculated by SIG_A_001 in step S121: ΔX: +0.25 meters, ΔY: +0.73 meters; the system compares these deviation values ​​with the dynamic tolerance parameters just determined, constructs the "first-level deviation framework" and performs the judgment: check the X-axis deviation: |ΔX| (0.25 meters) is less than or equal to tolerance_X_max (0.30 meters), and is judged as "qualified"; check the Y-axis deviation: |ΔY| (0.73 meters) is greater than tolerance_Y_max (0.50 meters), and is judged as "unqualified".

[0038] Because the deviation in the Y-axis direction exceeded the allowable range, the final comprehensive judgment result of the first deviation frame was "unqualified". Based on this result, the system officially determined that SIG_A_001 generated a "deviation event". This event was recorded and included the device ID 'SIG_A_001', its specific deviation content, actual coordinates, the dynamic tolerance parameters on which it was based, and the "unqualified" frame judgment result. This event object was then marked by the system.

[0039] refer to Figure 4 In step S13, the specific steps are as follows: S131: Dynamically detect the deviation event and mark multiple deviation contents during the detection process. Determine the corresponding geometric deviation and functional deviation based on the identification of each deviation content. The geometric deviation and functional deviation serve as the deviation contents of the signal device in different dimensions. S132: Acquire the working history of the signal equipment, which presents multiple working tasks of the signal equipment in its working state; determine the first level of decision content based on the working history of the signal equipment and the geometric deviation of the signal equipment, and determine the second level of decision content based on the working history of the signal equipment and the functional deviation of the signal equipment. S133: Determine the corresponding multi-level decision-making system based on the first-level and second-level decision-making content; determine the corresponding decision-making hierarchy relationship based on the identification of the multi-level decision-making system, and mark the multi-level decision-making path of the multi-level decision-making system by traversing the decision-making hierarchy relationship.

[0040] In the embodiments of this application, the deviation event is dynamically detected, and multiple deviation contents are marked during the detection process. The corresponding geometric deviation and functional deviation are determined based on the identification of each deviation content. The geometric deviation and functional deviation, as deviation contents of the signal device in different dimensions, take into account the overall consideration of the identification of each deviation content, and ensure the accuracy of the corresponding geometric deviation and functional deviation.

[0041] At this point, the system parses the "deviation event" data structure generated in step S122 to obtain the positional deviation content and equipment layout information. The system's "dynamic detection engine" then begins to work. Instead of simply confirming the existence of the deviation, it analyzes the physical direction and potential impact of the deviation. The detection process combines the vector direction of the deviation (such as the X-axis and Y-axis) with the standard orientation of the equipment in the line, transforming the abstract coordinate offset into a specific physical direction. The system assigns standardized "content" labels to the detected deviations, such as AXIAL_DEVIATION (axial deviation along the line direction, usually affecting positioning or trigger points) and LATERAL_DEVIATION (lateral deviation perpendicular to the line direction, usually affecting visibility or safety clearances). This process gives the original coordinate difference a clear engineering meaning.

[0042] The system triggers the corresponding analysis module based on the tagged deviation content. At the geometric deviation level, the system calculates precise geometric deviation values ​​for each tagged deviation, such as axial geometric deviation ΔX_geom and lateral geometric deviation ΔY_geom. These are objective and measurable physical offsets. At the functional deviation level, the system invokes its internal "functional impact assessment model," an expert system based on domain knowledge and rules. This model infers the actual impact of the geometric deviation on the expected function of the equipment based on the equipment type, core function, and the direction and magnitude of the deviation. For example, for signal controllers, lateral deviation affects visibility; for axle counters, axial deviation affects detection accuracy. The calculated geometric deviation values ​​and assessed functional deviation states are integrated into a structured "deviation content" data object, providing a complete information chain for subsequent decision analysis.

[0043] Specifically, the system receives the deviation event SIG_A_001, which includes positional deviations: ΔX: +0.25 meters, ΔY: +0.73 meters. The system's "dynamic detection engine" analyzes the position and orientation of SIG_A_001 on the line plan: ΔX (+0.25 meters) is identified as an offset along the line direction, so the system labels the content with the keyword AXIAL_DEVIATION; ΔY (+0.73 meters) is identified as an offset perpendicular to the line direction and towards the outside of the line, so the system labels the content with the keyword LATERAL_DEVIATION. At this point, the system successfully interprets the deviation of SIG_A_001 from the abstract X / Y coordinate offset into axial and lateral deviations with clear physical meaning.

[0044] Based on the AXIAL_DEVIATION and LATERAL_DEVIATION keywords marked in the previous step, the system performs a geometric and functional analysis on SIG_A_001: Geometric deviation: Axial geometric deviation ΔX_geom = +0.25 meters; Lateral geometric deviation ΔY_geom = +0.73 meters; Functional deviation: The system invokes the "Functional Impact Assessment Model," which recognizes that SIG_A_001, as an "entry signal," has the core function of ensuring that the signal can be clearly and promptly seen by the driver; the model assessment concludes that a lateral offset of 0.73 meters (towards the track) will significantly reduce... The short effective visibility distance for drivers makes it impossible to clearly identify signals before the designated braking point, thus constituting a functional impact. In contrast, the 0.25-meter axial offset has a minimal impact on signal display functionality. The system generates a detailed "deviation content" data structure for SIG_A_001, successfully decomposing the deviation event into: geometrically, it is offset by 0.25 meters along the track direction and 0.73 meters laterally; functionally, this offset has had a real impact on its signal display function. This structured, multi-dimensional deviation description provides a solid data foundation for subsequently developing targeted maintenance or adjustment strategies.

[0045] Furthermore, the operational history of the signal equipment is collected, which presents multiple tasks performed by the signal equipment during its operation. Based on the operational history and geometric deviation of the signal equipment, the first level of decision-making content is determined, and based on the operational history and functional deviation of the signal equipment, the second level of decision-making content is determined. This approach takes into account both the operational history and functional deviation of the signal equipment, ensuring the accuracy of the second level of decision-making content.

[0046] At this point, the system extracts the "working history" of the target signal equipment from multiple data sources, such as equipment management databases, computerized maintenance management systems (CMMS), or operation logs. This is typically a time-series dataset covering a period of time (such as the past 6 months or 1 year). Its content mainly includes: task load (frequency of equipment being triggered, percentage of working time), historical stability (past fault records, alarms, or performance degradation), maintenance records (time, type, content, and results of the last maintenance), and environmental factors (line conditions in the section, impact of extreme weather, etc.). The system aggregates and analyzes this raw data to form a quantitative summary of the equipment's "operating status" and "working pressure," such as calculating key indicators like "Mean Time Between Failures (MTBF)," "failure rate," or "maintenance frequency."

[0047] For the first level of decision content, the "geometric deviation" (such as axial and lateral offset) determined in S131 is combined with the "working history" collected in sub-step 1 and evaluated through a predefined decision logic. This logic mainly focuses on the objective size of the physical offset and the historical stability of the equipment. For example, if a geometric deviation that exceeds the tolerance range occurs on a historically stable equipment with normal load, a decision content of "physical adjustment is required" will be generated.

[0048] For the second level of decision-making, the "functional deviation" (such as "existence of functional impact") determined in S131 is combined with the "work history" and evaluated through another set of decision-making logic. This logic focuses more on the impact of the deviation on the core functions of the equipment and the current criticality of the equipment. For example, if a judgment of "existence of functional impact" occurs on a critical equipment with a high load, even if its historical performance is good, it will generate the decision content of "functional impact must be eliminated". Through these two independent decision-making paths, the system provides two different perspectives and preliminary judgments based on historical data for the final intelligent decision.

[0049] Specifically, the system queries the SIG_A_001 work history database to obtain all relevant records for the past year and analyzes them to obtain the following summary: Task load: As a key entry signal in the S1 section of Line A, this device is triggered an average of about 200 times per day, and the time it is in operation accounts for as much as 95%, which is a high-load device; Historical stability: In the past year, this device has no fault or alarm records, and its historical performance is very stable and reliable; Maintenance records: The last planned maintenance was 6 months ago, and the inspection and test results at that time were all "qualified". No abnormalities were found after the maintenance.

[0050] The system retrieves the deviations decomposed from SIG_A_001 in step S131: geometric deviation (ΔX_geom: +0.25 m, ΔY_geom: +0.73 m) and functional deviation (EXISTING_FUNCTIONAL_IMPACT); combined with the work history summary obtained in the previous step, the system begins to generate decision content.

[0051] The first decision-making content: System analysis found that the lateral geometric deviation (0.73 meters) of SIG_A_001 significantly exceeded the tolerance range; considering that the equipment has a very stable historical performance, this deviation is caused by recent foundation changes or external forces, rather than the aging of the equipment itself; therefore, the first decision-making content generated by the system is "physical adjustment is required", which means that from the perspective of physical location, measures must be taken to move it back to the design position.

[0052] The second decision-making element: System analysis revealed that the functional deviation of SIG_A_001 "has a functional impact," meaning that the visibility range of its signal display has been affected. More importantly, this device is a high-load, historically stable, critical entry signal, and its functional failure risk is extremely high. Therefore, the second decision-making element generated by the system is "the functional impact must be eliminated," indicating that from the perspective of operational safety, resolving its functional impact is the highest priority task.

[0053] Therefore, a multi-level decision-making system is determined based on the first and second levels of decision-making content; the corresponding decision hierarchy is determined based on the identification of the multi-level decision-making system, and the multi-level decision-making path of the multi-level decision-making system is marked along the traversal of the decision hierarchy. This approach is compatible with the overall consideration of the identification of the multi-level decision-making system, ensuring the accuracy of the corresponding decision hierarchy. At the same time, it realizes the overall consideration of the geometric deviation and functional deviation of the signal equipment, improves the accuracy of the multi-level decision-making system, and further marks the multi-level decision-making path of the multi-level decision-making system.

[0054] At this point, the system receives two decision contents generated by S132: the first decision content (based on geometric deviation) and the second decision content (based on functional deviation). The system does not store a fixed decision process internally, but maintains a general "multi-layer decision system model" that includes multiple decision rules, priorities, and logical branches. When specific decision contents are received, the system will determine a specific decision system based on the nature and priority of these contents (for example, functional impact usually takes precedence over physical offset). This means that the system will activate the rules and nodes in the model that are most relevant to the current input, forming a dynamic and customized decision structure for the current deviation event, which is usually presented as a tree or network.

[0055] In a multi-level decision-making system, the system automatically analyzes the logical relationships between each decision node to determine their "decision hierarchy relationship". The decision hierarchy relationship includes identifying parent-child relationship (the output of one node is the input of another node), parallel relationship (multiple sub-problems need to be considered at the same time), and priority relationship (certain rules must be satisfied first).

[0056] Starting from the root node of the decision-making system, the system "traverses" along the established decision hierarchy based on the specific data of the current deviation event (such as functional deviation status, equipment working history, etc.). At each decision node, the system makes a judgment based on the input data and selects a branch to continue execution downwards. The sequence of nodes traversed in this traversal process is completely recorded by the system and marked as a "multi-level decision path". This path is not only the result of the decision, but also a complete logical reasoning record of the decision-making process, which has a high degree of traceability. The endpoint of the path is usually a specific and executable decision result, such as "immediate adjustment", "planned adjustment", or "strengthening observation".

[0057] Specifically, the system receives two decision messages from SIG_A_001: the first decision message is "physical adjustment is required," and the second decision message is "functional impact must be eliminated." The system inputs these two messages into a general multi-layered decision-making system model. The model identifies "functional impact" as a higher priority driver than "physical adjustment" because it is directly related to operational safety. Therefore, the system instantiates a specific decision-making system whose top-level logic revolves around "functional impact," while "physical adjustment" is incorporated into the system architecture as a potential means to achieve this goal.

[0058] In the decision-making system instantiated for SIG_A_001, the system identifies a clear hierarchical relationship: Top level (highest priority): Determine "whether there is a functional impact," which is the core concern of security operations; Second level: If the top level determines "yes," then proceed to the next level to determine "the urgency of the functional impact," which depends on the criticality of the equipment; Third level: Based on the urgency assessment, determine the final maintenance strategy; At this point, "physical adjustment" is taken into consideration as a specific operational option. This hierarchical relationship clarifies the order of decision-making: security issues must be addressed first, followed by consideration of specific implementation methods.

[0059] The system begins to traverse the decision system built for SIG_A_001 and marks the decision path: Root node: [Judgment: Does functional impact exist?] > Input data: EXISTING_FUNCTIONAL_IMPACT > Select branch: [Yes]; Second-level node: [Judgment: How critical is the equipment?] > Input data: High load (critical equipment) > Select branch: [Critical equipment]; Third-level node: [Decision: How to eliminate the impact?] > Input data: The first-level decision content is "Physical adjustment is required" > Select branch: [Execute physical adjustment].

[0060] The system marks this traversal path [is]>[critical equipment]>[execute physical adjustment] as a "multi-level decision path" of SIG_A_001; the endpoint of the path, i.e. the final decision result, is determined as "execute physical adjustment immediately". This result is not only clear, but the logical reasoning process behind it is also fully recorded, which is convenient for subsequent review and optimization.

[0061] refer to Figure 5 In step S14, the specific steps are as follows: S141: Monitor the multi-layer decision path in real time, determine multiple decision nodes based on the multi-layer decision path and the previous decision content of the signal equipment, and mark the decision content of each decision node. S142: Collect deviation events of the signal equipment, determine the corresponding combination of deviation content based on the identification of the deviation events of the signal equipment, and determine the first-level decision relationship based on the combination of deviation content and the decision content of each decision node; S143: Determine the second-level decision relationship based on the combination of the deviation content and the node position of each decision node, determine the corresponding decision progression relationship based on the first-level decision relationship, and mark the corresponding decision results.

[0062] In the embodiments of this application, the multi-layer decision path is monitored in real time, and multiple decision nodes are determined based on the multi-layer decision path and the previous decision content of the signal equipment. The multiple decision nodes have corresponding correlations, and the decision content of each decision node is marked. This approach takes into account the overall consideration of the multi-layer decision path and the previous decision content of the signal equipment, ensuring the accuracy of the multiple decision nodes.

[0063] At this point, the system instantiates the "multi-layer decision path" generated for the deviation event in S13 from a static logical plan into an active "decision instance" with a unique identifier. This instance is immediately placed into the tracking list of a real-time monitoring engine, and its status is set to "ACTIVE". The monitoring engine continuously subscribes to all key data streams related to this decision instance, including real-time location data from field sensors, equipment operating status data, and work order execution status (such as "dispatched", "in progress", "completed") from the maintenance management system (CMMS). The monitoring engine is responsible for managing the entire lifecycle of this decision instance from creation, activation, execution to final completion or archiving, and can trigger timeout or escalation alarms for abnormal situations during execution (such as tasks that have not been completed for a long time).

[0064] The system retrieves "past decision content" related to the current signal equipment or similar equipment from the decision history database. This is valuable experience data for the system. The system performs semantic analysis and pattern matching between the current multi-level decision path and this historical decision content, identifies those recurring and key logical branch points on the path, and formally determines these points as "decision nodes". A decision node usually corresponds to a core judgment problem or a key choice point. The final number of decision nodes depends on the complexity of the decision path and the richness of the historical data.

[0065] After identifying multiple decision nodes, the system establishes "relationships" between nodes based on their logical order and dependencies in the decision path. The most common relationship is the parent-child relationship, where the output of the parent node is the input of the child node. The system labels each decision node with its specific "decision content," which is a fusion of current decision rules and historical experience. It defines the judgment criteria and selection standards for that node. These nodes with decision content and relationships together constitute a structured, dynamic decision framework that can be understood and executed by machines.

[0066] Specifically, the system creates an instance named DECISION_INSTANCE_SIG_A_001_001 for the decision path of SIG_A_001 (from "functional impact" to "immediate physical adjustment") and sets its state to "ACTIVE". This instance is placed into the real-time monitoring engine, which begins to continuously monitor two key data streams: the real-time location coordinate data stream of SIG_A_001, and the status of the work order to be created for SIG_A_001 in the Maintenance Management System (CMMS). At this point, the system is ready to track the entire execution process of this decision.

[0067] The system queries the decision history database and finds that other signals on Line A have also experienced similar deviation problems in the past year, with their decision paths and results fully recorded. The system compares the current decision path of SIG_A_001 with these historical paths and identifies two recurring key logical branch points that play a decisive role in the decision outcome through pattern matching. Based on this, the system determines two decision nodes: Node N1: the judgment point regarding "functional impact"; Node N2: the selection point regarding "maintenance strategy".

[0068] The system establishes a relationship between the two decision nodes of SIG_A_001: node N1 is the parent node and node N2 is the child node, because it is necessary to first determine whether there is a functional impact (N1) before deciding on the maintenance strategy (N2). The system labels each node with its decision content that incorporates historical experience: Node N1: [Functional Impact Judgment], its decision content is labeled as: "Based on the signal type and visibility distance model, assess whether geometric deviations prevent the driver from clearly identifying the signal display within the specified distance"; Node N2: [Maintenance Strategy Selection], its decision content is labeled as: "Combining the equipment's historical stability records, select the optimal strategy among 'immediate adjustment,' 'planned adjustment,' and 'intensified observation'." Thus, the decision path of SIG_A_001 is formally transformed into a dynamic decision framework consisting of two interconnected nodes with clearly defined decision content, under real-time monitoring. This framework lays a solid foundation for subsequent dynamic adjustments and progressive decisions.

[0069] Furthermore, deviation events of the signal equipment are collected, and the corresponding combination of deviation content is determined based on the identification of the deviation events of the signal equipment. The first-level decision relationship is determined according to the combination of deviation content and the decision content of each decision node, which takes into account the overall consideration of the combination of deviation content and the decision content of each decision node, and ensures the accuracy of the first-level decision relationship.

[0070] At this time, the system continuously monitors high-frequency data streams from the field sensor network (such as GPS, total station automated monitoring system), which provide the real-time position coordinates of the signal equipment; the system runs a "deviation event trigger", which continuously compares the real-time coordinates with the theoretical coordinates; once the calculated deviation value exceeds the preset "event trigger threshold" (this threshold is usually lower than or equal to the dynamic tolerance parameter, used for early warning), the trigger will immediately generate a new "deviation event". This event is a structured data packet containing event ID, device ID, timestamp, real-time position coordinates and the preliminary calculated deviation value, indicating that a new abnormal situation that needs attention has occurred.

[0071] Upon receiving a new deviation event, the system immediately identifies and analyzes it. This process is essentially a rapid analysis of the new event, performing a complete S11-S131 procedure. Based on the deviation data of the new event, the system redetermines its "deviation content combination." This combination is a multi-dimensional data structure that includes not only new geometric deviation values ​​(such as ΔX_geom_new, ΔY_geom_new) but also the re-evaluated functional deviation state (functional_deviation_new). It comprehensively describes all the key attributes of the current deviation state, providing the latest and most complete information input for subsequent decision relationship comparisons.

[0072] The system performs deep semantic matching and logical comparison between the newly generated "deviation content combination" and the "decision content" of each decision node marked in S141. This is far from a simple numerical comparison, but rather intelligent reasoning based on domain knowledge. The "first-level decision relationship" is defined as the interaction between new information and the existing decision framework at the content level, mainly divided into three categories: strong consistency (new information strongly verifies and reinforces the judgment basis of a certain decision node), weak consistency (new information does not conflict with the content of the decision node, but does not provide stronger support), and conflict (new information contradicts the judgment basis of the decision node, challenging the effectiveness of the existing decision). Through comparison, the system determines the specific relationship type between the new deviation content combination and each decision node, and marks this relationship as the "first-level decision relationship," pointing the way for subsequent decision adjustments.

[0073] Specifically, during the period when the "Immediately Execute Physical Adjustment" decision of SIG_A_001 is issued but not yet executed, the on-site automated monitoring system continuously reports its location. At a certain point in time, the system receives the latest location coordinates of SIG_A_001 and calculates a new lateral deviation value ΔY that reaches +0.80 meters. This value exceeds the preset event trigger threshold (e.g., 0.75 meters), and the system immediately generates a new deviation event, denoted as DEVIATION_EVENT_SIG_A_001_002. This event includes the device ID, timestamp, and new deviation data.

[0074] The system performs a rapid analysis on the new event DEVIATION_EVENT_SIG_A_001_002, generating its "deviation content combination": Geometric deviation: ΔY_geom_new is determined to be +0.80 meters; Functional deviation: The system calls the functional impact assessment model and finds that the 0.80-meter lateral offset has seriously exceeded the safe visibility range, causing the signal to be completely invisible under certain conditions; therefore, the functional deviation status is updated to CRITICAL_FUNCTIONAL_IMPACT (severe functional impact); The system generates a new deviation content combination for SIG_A_001: {ΔY_geom:+0.80 meters,functional_deviation:'CRITICAL_FUNCTIONAL_IMPACT'}.

[0075] The system compares this new deviation with two decision nodes in the SIG_A_001 decision framework: With node N1 (functional impact judgment): Node N1's decision is "to assess whether the geometric deviation prevents the driver from clearly recognizing signals within a specified distance"; the new "severe functional impact" state is an extreme reinforcement and direct verification of this judgment criterion; therefore, the system determines that there is a strong consistency relationship between them; With node N2 (maintenance strategy selection): Node N2's decision is "to combine historical stability and choose between 'immediate adjustment,' 'planned adjustment,' and 'intensified observation.'" The new 0.80-meter deviation and "severe" impact, while still pointing to "adjustment," have a severity exceeding the risk scope covered by the conventional "immediate adjustment," suggesting the need for a higher-level contingency plan. Therefore, the system determines that there is a weak consistency relationship between them (the conclusions are consistent, but the severity has escalated). The system determines the first level of decision relationship for SIG_A_001: the new deviation event is "strongly consistent" with node N1 and "weakly consistent" with node N2. This relationship indicates that the general direction of the current decision path is correct, but the urgency and level of the specific implementation strategy need to be upgraded.

[0076] Therefore, the second-level decision relationship is determined based on the combination of the deviation content and the node position of each decision node. The corresponding decision progression relationship is determined based on the first-level decision relationship and the first-level decision relationship, and the corresponding decision results are marked. This approach is compatible with the overall consideration of the first-level decision relationship and ensures the accuracy of the corresponding decision progression relationship.

[0077] At this point, the system will re-examine the "node position" of the decision nodes in the multi-layer decision path. This refers not only to their physical order, but more importantly, to their hierarchy and importance (e.g., the hierarchy of a safety node is higher than that of a cost node). At the same time, the system will assess the "impact" of the information carried by the new "deviation content combination". The impact of a "serious functional impact" is far greater than that of a slight geometric deviation. Based on this, the system defines a "second-level decision relationship", which describes whether the new information requires a change in the topology of the decision path. It is mainly divided into three categories: path maintenance (the new information is insufficient to change the existing path structure), path enhancement (the new information strengthens the existing branches, but does not require a change in structure), and path reconstruction (the new information overturns the core logic, requiring the addition of new branches or the creation of a completely new path).

[0078] The system comprehensively weighs the "first-level decision relationship" (content level) determined in S142 and the "second-level decision relationship" (structural level) determined in sub-step 1 to form a final instruction on how the decision should evolve, namely the "decision progression relationship". This relationship clearly defines the dynamic evolution mode of the decision framework, and the main types include: maintenance and confirmation (when both relationships support the original path), enhancement and optimization (when the content is consistent but the structure needs to be enhanced), and reconstruction and upgrading (when the content verifies the severity and the structure needs to be reconstructed).

[0079] Based on the "decision progression relationship" determined in the previous step, the system will execute the corresponding actions and generate the final "decision result". This result is a dynamically adjusted and executable final instruction. The system will immediately mark this new decision result on the decision instance of the deviation event, overwriting or updating the previous decision result. This new result contains all the necessary action instructions and will automatically trigger the corresponding downstream systems (such as maintenance management system and operation control system), thereby transforming intelligent decision-making into actual business operations.

[0080] Specifically, the system analyzes the decision node position of SIG_A_001: Node N1 (functional impact judgment) is the top-level foundation of the entire decision path and has the highest importance; at the same time, the system assesses the impact of the combination of new deviation content and rates "severe functional impact" as the highest level; since this information with the highest impact directly affects the highest-level node N1, its severity has exceeded the normal scope of the lower-level node N2 (maintenance strategy selection); therefore, the system determines the second layer of decision relationship as path reconstruction.

[0081] The system integrates two decision relationships of SIG_A_001: the first decision relationship is "strongly consistent" with node N1 and "weakly consistent" with node N2; the second decision relationship is "path reconstruction". The system conducts a comprehensive analysis: the new information strongly verifies the severity of the problem in terms of content (strong consistency), and at the same time requires an upgrade to the existing decision framework in terms of structure (path reconstruction). Based on this, the system determines that the final decision progression relationship is reconstruction and upgrade, which means that the system cannot simply stay at the level of "immediate adjustment" and must build a more comprehensive response strategy.

[0082] Based on the progressive decision-making relationship of "reconstruction and upgrade", the system performs the following actions: On the original decision path, a new, higher-priority decision branch is created to specifically handle "severe functional impacts". The logic of this new branch is: in addition to correcting the position of the equipment itself, the root cause of the deviation must also be identified and eliminated; the system calls the knowledge base and combines it with the geographical information of the area where SIG_A_001 is located to determine the risk of foundation settlement; the system generates and marks the final decision result: the original "immediately execute physical adjustment" is upgraded to "immediately execute physical adjustment and simultaneously start the foundation stability assessment and reinforcement plan". This new decision result is immediately issued, an assessment work order for the foundation is automatically created and linked with the adjustment work order of SIG_A_001, forming a complete, closed-loop risk response plan.

[0083] refer to Figure 6 In step S15, the specific steps are as follows: S151: Collect the decision result, identify multiple deviation components in different dimensions based on the identification of the decision result, and determine the final deviation of the signal device based on the multiple deviation components and the corresponding signal device; S152: Collect the current work tasks of the train, identify multiple work items based on the identification of the current work tasks of the train, determine the dynamic maintenance path according to the multiple work items and the final deviation of each signaling device, and determine the corresponding dynamic maintenance content based on the dynamic maintenance path, the multi-level decision-making system and the working status of the signaling device. Based on the detection of the dynamic maintenance content, determine multiple dynamic maintenance items and trigger the dynamic maintenance of the signaling device.

[0084] In the embodiments of this application, the decision result is collected, and multiple deviation components in different dimensions are determined by identifying the decision result. The final deviation of the signal device is determined based on the multiple deviation components and the corresponding signal device, which takes into account the overall consideration of multiple deviation components and the corresponding signal device, and ensures the accuracy of the final deviation of the signal device.

[0085] At this point, the system obtains the final labeled "decision result" from the output of S143, which is usually a structured instruction containing one or more action items. The system uses the logical reasoning ability based on the domain knowledge model to perform deep semantic analysis on this decision result, identifying the core issues that are implicit and need to be measured and corrected. Based on the analysis results, the system decomposes the decision result into multiple independent "deviation components". Each deviation component represents a dimension that needs to be processed independently. It goes beyond simple positional deviations and includes: geometric components (direct physical position offset), attitude components (deviation of equipment installation angle), functional components (deviation of equipment functional parameters), and environmentally related components (deviations derived from the decision and related to the equipment environment, such as foundation settlement).

[0086] The system strictly binds each deviation component identified in the previous step to its corresponding signal device. For each bound deviation component, the system calls the corresponding calculation model or data source to determine its precise "final deviation". For geometric components, the final deviation is a correction vector pointing from the current actual position of the device to its theoretical design position, containing precise direction and distance, and is the direct basis for on-site adjustments. For attitude components, it is the difference between the current attitude angle of the device and the standard attitude angle. For environmentally related components, the final deviation is usually the current measurement value obtained from the environmental monitoring system (such as the foundation settlement monitoring point), such as the cumulative settlement or settlement rate. This process transforms abstract decision-making actions into specific and measurable technical parameters.

[0087] Furthermore, the system collects the train's current work tasks, identifies multiple work items based on the identification of these tasks, determines a dynamic maintenance path based on the final deviation of each work item and each signaling device, and determines the corresponding dynamic maintenance content based on this dynamic maintenance path, the multi-layer decision-making system, and the working status of the signaling devices. Multiple dynamic maintenance items are determined based on the detection of these dynamic maintenance items, triggering dynamic maintenance of the signaling devices. This approach incorporates a holistic consideration of dynamic maintenance content detection, ensuring the accuracy of multiple dynamic maintenance items. Simultaneously, a decision progression relationship is introduced to control the decision content at each decision node in stages, improving the accuracy of the final deviation of the signaling devices and controlling the dynamic maintenance content to dynamically maintain the corresponding signaling system database.

[0088] At this time, the system synchronizes data in real time with the Train Dispatch Management System (TMS) or Operation Control Center (OCC) through the API interface to obtain a high-precision digital train timetable. The system parses this timetable and identifies "work items" that can be used for maintenance operations. A work item is essentially a "spatiotemporal resource window", whose key attributes include: time window (a continuous track idle time in a specific section without trains passing through), spatial section (the track section corresponding to the time window that can be physically operated), and window type (such as planned "maintenance window", short "train interval" or "station dwell time" at a specific location).

[0089] The system intelligently matches the equipment's "final deviation" (i.e., the vector or task complexity that needs adjustment) calculated in S151 with the currently available "work items." The matching is based on the task's complexity, required duration, and impact on operations. Based on the matching results, the system plans an optimized "dynamic maintenance path." This path is an ordered sequence of operations that clearly defines "which time window, which location, and which maintenance to complete." Its optimization objectives typically include minimizing the impact on operations, maximizing the efficiency of the maintenance team, and prioritizing high-risk equipment.

[0090] The system integrates three aspects of information to generate detailed and actionable "dynamic maintenance content": dynamic maintenance path (providing the spatiotemporal constraints for performing maintenance), multi-level decision-making system (providing the priority and logic of decisions, such as whether the root cause problem needs to be addressed), and the working status of signal equipment (providing the real-time operating status of the equipment). Based on this information, the system generates specific technical work instructions, including the tools to be used, the safety procedures to be followed, and the technical standards to be met, transforming macro strategies into actionable steps.

[0091] The system breaks down the relatively complex "dynamic maintenance content" task package generated in the previous step into multiple independent, assignable, and traceable "dynamic maintenance projects." Each project follows the SMART principle and is structured as a standard work unit, including project name, person in charge / team, required resources (tools, spare parts), estimated working hours, safety briefing content, and clear acceptance criteria, ensuring the manageability and traceability of the task.

[0092] The system uses the Enterprise Service Bus (ESB) or API to convert structured "dynamic maintenance projects" into standard electronic work orders, which are then automatically pushed to the Maintenance Management System (CMMS) or the mobile terminal app of frontline personnel. The generation and issuance of work orders mark the formal triggering of "dynamic maintenance". Relevant personnel will receive an immediate notification and can begin to perform maintenance tasks within the specified time window. The system will continuously track the execution status of the work orders until the task is completed and closed, forming a complete management loop.

[0093] Please see Figure 7 , Figure 7 This is a schematic diagram of the structural composition of a position deviation detection system for a signal device based on theoretical and actual position coordinates, as described in an embodiment of the present invention. The position deviation detection system for the signal device based on theoretical and actual position coordinates includes: The location information module 21 is used to determine the theoretical position coordinates of the train's signaling equipment on the plan based on the design documents, and to collect the actual position coordinates of the signaling equipment; and to determine the location information based on the basic information, theoretical position coordinates and actual position coordinates of the signaling equipment. The deviation event module 22 is used to determine the corresponding position deviation content based on the identification of the position information. At the same time, it determines the corresponding dynamic tolerance parameter based on the equipment type and corresponding equipment function of the signal equipment, and determines the deviation event of the signal equipment based on the position deviation content, the dynamic tolerance parameter of the signal equipment and the actual position coordinates. The multi-level decision system module 23 is used to determine the corresponding geometric deviation and functional deviation based on the detection of the deviation event, determine the corresponding multi-level decision system according to the geometric deviation, functional deviation and working history of the signal equipment, and mark the multi-level decision path of the multi-level decision system. The decision progression module 24 is used to determine multiple decision nodes based on the identification of the multi-level decision path, determine the corresponding decision progression relationship based on the decision content of each decision node, the corresponding node position and the deviation event of the signal device, and mark the corresponding decision result. The dynamic maintenance module 25 is used to determine the final deviation of the corresponding signal equipment based on the identification of the decision result, and to determine the corresponding dynamic maintenance content according to the final deviation of each signal equipment, the current working task of the train and the multi-level decision system, so as to dynamically maintain the corresponding signal system database.

[0094] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all 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.

Claims

1. A method for detecting position deviation of a signal device based on theoretical and actual position coordinates, characterized in that, include: Based on the design documents, determine the theoretical coordinates of the train's signaling equipment on the plan, and collect the actual coordinates of the signaling equipment. The location information is determined based on the basic information, theoretical location coordinates, and actual location coordinates of the signal equipment. Based on the identification of the location information, the corresponding location deviation content is determined. At the same time, the corresponding dynamic tolerance parameters are determined according to the equipment type and corresponding equipment function of the signal equipment. The deviation event of the signal equipment is determined based on the location deviation content, the dynamic tolerance parameters of the signal equipment, and the actual location coordinates. The deviation event includes the equipment ID, deviation content, actual coordinates, dynamic tolerance parameters, and frame judgment result. Based on the detection of this deviation event, the corresponding geometric deviation and functional deviation are determined. According to the geometric deviation, functional deviation and working history of the signal equipment, the corresponding multi-level decision system is determined, and the multi-level decision path of the multi-level decision system is marked. Multiple decision nodes are identified based on the multi-layer decision path identification. The corresponding decision progression relationship is determined based on the decision content of each decision node, the corresponding node position, and the deviation event of the signal device, and the corresponding decision result is marked. The decision hierarchy relationship includes identifying parent-child relationship, parallel relationship, and priority relationship. Based on the identification of the decision results, the final deviation of the corresponding signal equipment is determined. According to the final deviation of each signal equipment, the current work task of the train, and the multi-level decision-making system, the corresponding dynamic maintenance content is determined to dynamically maintain the corresponding signal system database.

2. The method for detecting position deviation of a signal device based on theoretical and actual position coordinates according to claim 1, characterized in that, The theoretical coordinates of the train's signaling equipment on the plan are determined based on the design documents, and the actual coordinates of the signaling equipment are collected. The location information is determined based on the basic information, theoretical location coordinates, and actual location coordinates of the signal equipment, including: Based on the design documents, determine the plan view of the signal equipment and obtain the theoretical coordinates of the signal equipment on the plan view; The signal equipment is tested on-site, and the corresponding actual location coordinates are marked during the on-site test. At the same time, the basic information of the signal equipment is collected, and the location information is determined based on the basic information, theoretical location coordinates and actual location coordinates of the signal equipment.

3. The method for detecting position deviation of a signal device based on theoretical and actual position coordinates according to claim 1, characterized in that, The process involves identifying the location information to determine the corresponding location deviation content, determining the corresponding dynamic tolerance parameters based on the type and function of the signal equipment, and determining the deviation event of the signal equipment based on the location deviation content, the dynamic tolerance parameters of the signal equipment, and the actual location coordinates. This includes: The location information is dynamically identified, and the corresponding deviation keywords are marked during the identification. The corresponding location deviation content is determined by tracing the deviation keywords. At this time, the location deviation content presents the sub-deviation content of the signal device in various directional dimensions. The equipment types of signal devices are collected, and the corresponding equipment functions are marked. Based on the mapping relationship between the equipment type, the corresponding equipment function, and the dynamic tolerance parameters, the corresponding dynamic tolerance parameters are determined. The dynamic tolerance parameters present the dynamic controllable range of the position deviation of the signal device. Based on the position deviation content and the dynamic tolerance parameters of the signal device, a first-level deviation framework is determined, and based on the first-level deviation framework and the actual position coordinates of the signal device, the deviation event of the signal device is determined.

4. The method for detecting position deviation of a signal device based on theoretical and actual position coordinates according to claim 1, characterized in that, The process involves determining the corresponding geometric and functional deviations based on the detection of the deviation event, establishing a multi-layered decision-making system based on the geometric and functional deviations of the signal equipment and its operational history, and marking the multi-layered decision-making paths of the multi-layered decision-making system, including: The deviation event is dynamically detected, and multiple deviation contents are marked during the detection process. The corresponding geometric deviation and functional deviation are determined based on the identification of each deviation content. The geometric deviation and functional deviation are regarded as the deviation contents of the signal device in different dimensions.

5. The method for detecting position deviation of a signal device based on theoretical and actual position coordinates according to claim 4, characterized in that, The process of determining the corresponding geometric and functional deviations based on the detection of the deviation event, determining the corresponding multi-level decision-making system based on the geometric and functional deviations of the signal equipment and the operating history of the signal equipment, and marking the multi-level decision-making paths of the multi-level decision-making system, further includes: The operational history of the acquired signal equipment is presented, which shows the multiple tasks performed by the signal equipment in its working state. The first level of decision-making content is determined based on the operational history and geometric deviation of the signal equipment, and the second level of decision-making content is determined based on the operational history and functional deviation of the signal equipment. The corresponding multi-level decision-making system is determined based on the first and second level decision-making content; the corresponding decision hierarchy relationship is determined based on the identification of the multi-level decision-making system, and the multi-level decision-making path of the multi-level decision-making system is marked along the traversal of the decision hierarchy relationship.

6. The method for detecting position deviation of a signal device based on theoretical and actual position coordinates according to claim 1, characterized in that, The process of identifying multiple decision nodes based on the multi-layered decision path, determining the corresponding decision progression relationship based on the decision content of each decision node, the corresponding node position, and the deviation event of the signal equipment, and marking the corresponding decision results includes: The system monitors the multi-layered decision-making path in real time, identifies multiple decision nodes based on the path and past decision content of the signal equipment, establishes corresponding relationships between these decision nodes, and marks the decision content of each node.

7. The method for detecting position deviation of a signal device based on theoretical and actual position coordinates according to claim 6, characterized in that, The process of identifying multiple decision nodes based on the multi-layer decision path identification, determining the corresponding decision progression relationship based on the decision content of each decision node, the corresponding node position, and the deviation event of the signal equipment, and marking the corresponding decision results, further includes: Deviation events of the acquired signal equipment are collected, and the corresponding combination of deviation content is determined based on the identification of the deviation events of the signal equipment. The first-level decision relationship is determined based on the combination of deviation content and the decision content of each decision node. The second-level decision relationship is determined based on the combination of the deviation content and the node position of each decision node. The corresponding decision progression relationship is determined based on the first-level decision relationship and the first-level decision relationship, and the corresponding decision results are marked.

8. The method for detecting position deviation of a signal device based on theoretical and actual position coordinates according to claim 1, characterized in that, The final deviation of the corresponding signaling equipment is determined based on the identification of the decision result. The corresponding dynamic maintenance content is determined based on the final deviation of each signaling device, the current work task of the train, and the multi-layered decision-making system, in order to dynamically maintain the corresponding signaling system database, including: The decision result is collected, and multiple deviation components in different dimensions are identified based on the identification of the decision result. The final deviation of the signal device is determined based on the multiple deviation components and the corresponding signal device.

9. The method for detecting position deviation of a signal device based on theoretical and actual position coordinates according to claim 8, characterized in that, The process of identifying the final deviation of the corresponding signaling equipment based on the decision result, determining the corresponding dynamic maintenance content based on the final deviation of each signaling device, the current work task of the train, and the multi-level decision-making system, and dynamically maintaining the corresponding signaling system database, also includes: The system collects the train's current work tasks, identifies multiple work items based on the identification of the train's current work tasks, determines a dynamic maintenance path based on the multiple work items and the final deviation of each signaling device, and determines the corresponding dynamic maintenance content based on the dynamic maintenance path, the multi-level decision-making system and the working status of the signaling devices. Based on the detection of the dynamic maintenance content, multiple dynamic maintenance items are determined, and dynamic maintenance of the signaling system database is triggered.

10. A position deviation detection system for a signal device based on theoretical and actual position coordinates, characterized in that, The position deviation detection system of the signal device based on theoretical position coordinates and actual position coordinates is applied to the position deviation detection method of the signal device based on theoretical position coordinates and actual position coordinates as described in any one of claims 1-9.

Images