Railway facility abnormal data intelligent alarm method and system based on GIS

Abstract

The invention relates to the technical field of railway facility monitoring, in particular to a GIS-based railway facility abnormal data intelligent alarm method and system. The method comprises the steps of obtaining multi-source detection data, determining a first abnormal area and a second abnormal area, calculating a real-time pull-out value deviation, adjusting a correlation degree threshold value, correcting a track state threshold value and generating a high-risk abnormal area alarm prompt. According to the method, multi-source data structured management and spatial correlation analysis are realized through a unified data interface and an intelligent preprocessing mechanism, abnormal distribution is presented in combination with a GIS display module, the data analysis intuition and decision support capability are improved, a hierarchical alarm strategy is designed, and the timeliness and accuracy of railway facility abnormal response are remarkably improved.

Description

Intelligent Alarm Method and System for Abnormal Railway Facility Data Based on GIS Technical Field

[0001] This invention relates to the field of railway facility monitoring technology, and more specifically, to a GIS-based intelligent alarm method and system for abnormal railway facility data. Background Technology

[0002] Currently, the safe operation of railway facilities relies heavily on the joint monitoring and analysis of multiple professional detection systems, including track inspection systems, overhead contact line inspection systems, and BeiDou positioning systems.

[0003] However, existing technical systems are mostly based on independent testing and vertical management by specialty and system, lacking unified data interfaces and sharing mechanisms between systems. This results in test data being scattered across different devices or platforms, leading to isolated information and hindering effective correlation analysis. This model not only increases the complexity of data management but also limits the ability to make cross-professional fault correlation judgments and analyze the overall operational situation. Furthermore, during high-speed rail joint commissioning and daily inspections, the formats, coordinate systems, and accuracy standards of various test data differ, lacking unified data standards and fusion processing methods. Existing anomaly data processing often relies on manual analysis, resulting in low automation and a large workload for data cleaning, coordinate transformation, and classification management, making it difficult to achieve efficient analysis and visualization of large-scale test data. In addition, the results of each test system are usually presented in tabular or list format, lacking spatial correlation and intuitive display capabilities, making it difficult for on-site personnel to quickly locate abnormal areas. Moreover, current railway facility monitoring systems generally suffer from problems such as single alarm mechanisms and delayed response. Because multi-source test data is not integrated with Geographic Information Systems (GIS), the spatial distribution and risk levels of anomalies are difficult to present intuitively, affecting the timeliness and accuracy of emergency decision-making and dispatch command.

[0004] Therefore, there is an urgent need for a system and method that can achieve multi-source abnormal data fusion processing, GIS spatial visualization, and intelligent alarm linkage to solve the problems of data dispersion, fragmented analysis, and low alarm efficiency in existing technologies. Summary of the Invention

[0005] In view of this, the present invention proposes a GIS-based intelligent alarm method and system for abnormal railway facility data, aiming to solve the problems of data dispersion, fragmented analysis and low alarm efficiency in the current technology.

[0006] This invention proposes a GIS-based intelligent alarm method for abnormal railway facility data, comprising: acquiring multi-source detection data from a track inspection system, a catenary inspection system, and a BeiDou positioning system, wherein the multi-source detection data includes track geometric state parameters, catenary operating parameters, and equipment location information; determining several first abnormal regions based on track geometric state parameters and a preset track state threshold, and determining several second abnormal regions based on track geometric state parameters, catenary operating parameters, and a preset correlation threshold for the first abnormal regions; obtaining real-time pull-out value deviations at each hard point within the second abnormal regions based on the catenary operating parameters within all second abnormal regions, and adjusting the preset correlation threshold based on the real-time pull-out value deviations within a preset adjustment period to form an adjusted correlation threshold; correcting the preset track state threshold based on the number of second abnormal regions determined based on the adjusted correlation threshold within a preset correction period to form a corrected track state threshold; determining several high-risk abnormal regions based on the real-time pull-out value deviations obtained based on the corrected track state threshold within a preset determination period, and generating alarm prompts based on the high-risk abnormal regions.

[0007] Furthermore, when determining several first abnormal regions based on track geometric state parameters and preset track state thresholds, the process includes: determining whether a track detection region is a first abnormal region based on the relationship between the track geometric state parameters of the track detection region and the preset track state thresholds; when the track geometric state parameters are greater than the preset track state thresholds, the track detection region is determined to be a first abnormal region; when the track geometric state parameters are less than or equal to the preset track state thresholds, the track detection region is determined not to be a first abnormal region.

[0008] Furthermore, when determining several second abnormal regions based on the track geometric state parameters, catenary operation parameters, and preset correlation threshold of the first abnormal region, the process includes: obtaining the standard deviation of all track geometric state parameters within a preset correlation calculation period to form track state fluctuation values; obtaining the standard deviation of all catenary operation parameters within a preset correlation calculation period to form catenary state fluctuation values; and determining several second abnormal regions based on the track state fluctuation values, catenary state fluctuation values, and preset correlation threshold.

[0009] Furthermore, when determining several second abnormal regions based on track state fluctuation values, catenary state fluctuation values, and a preset correlation threshold, the process includes: obtaining the change curve of track state fluctuation values ​​within a preset correlation calculation period and forming a track fluctuation curve; obtaining the change curve of catenary state fluctuation values ​​within a preset correlation calculation period and forming a catenary fluctuation curve; obtaining the cosine similarity between the track fluctuation curve and the catenary fluctuation curve and forming a correlation between the track fluctuation curve and the catenary fluctuation curve; and determining the first abnormal region as a second abnormal region when the correlation is less than a preset correlation threshold, thereby identifying several second abnormal regions.

[0010] Furthermore, when obtaining the real-time pull-out value deviation at each hard point in the second abnormal area based on the catenary operation parameters of all the second abnormal areas, the process includes: obtaining the standard deviation of all catenary operation parameters and forming the catenary distribution value; when the catenary distribution value is greater than the preset catenary distribution threshold, obtaining the real-time pull-out value deviation at each hard point in the second abnormal area based on the catenary operation parameters of any two adjacent second abnormal areas.

[0011] Furthermore, when obtaining the real-time pull-out value deviation at each hard point within the second abnormal region based on the catenary operation parameters of any two adjacent second abnormal regions, the process includes: obtaining the distance between the two second abnormal regions, obtaining the difference in the catenary operation parameters between the two second abnormal regions, and forming a catenary difference; generating a catenary gradient based on the ratio of the catenary difference to the distance, and determining the midpoint of the two second abnormal regions as the midpoint of the hard point when the catenary gradient is greater than a preset gradient threshold, thus forming the hard point midpoint; determining the deviation of all pull-out values ​​within a circular region centered on the hard point midpoint and with a preset hard point length as the radius, and determining the real-time pull-out value deviation based on the average of all deviations.

[0012] Furthermore, when adjusting the preset correlation threshold based on the real-time pull-out value deviation within the preset adjustment period, the process includes: determining the first deviation fluctuation value based on the standard deviation of the real-time pull-out value deviation; wherein, when the first deviation fluctuation value is greater than the preset first deviation fluctuation threshold, the preset correlation threshold is reduced based on the relative deviation between the first deviation fluctuation value and the preset first deviation fluctuation threshold and the preset adjustment coefficient to determine the adjustment correlation threshold.

[0013] Furthermore, when correcting the preset orbital state threshold based on the number of second abnormal regions determined by adjusting the correlation threshold within a preset correction period, the process includes: determining the quantity fluctuation value based on the standard deviation of the number of second abnormal regions; when the quantity fluctuation value is greater than the preset quantity fluctuation threshold, determining the quantity fluctuation deviation based on the relative deviation between the quantity fluctuation value and the preset quantity fluctuation threshold; and when the quantity fluctuation deviation is greater than the preset fluctuation deviation threshold, reducing the preset orbital state threshold based on the relative deviation between the quantity fluctuation deviation and the preset fluctuation deviation threshold, and a preset correction coefficient, to determine the corrected orbital state threshold.

[0014] Furthermore, when determining several high-risk anomaly areas based on the real-time pull-out value deviation obtained within a preset time period based on the corrected orbital state threshold, the process includes: determining a second deviation fluctuation value based on the standard deviation of the real-time pull-out value deviation; when the second deviation fluctuation value is greater than the preset second deviation fluctuation threshold, determining the corresponding circular area as a high-risk anomaly area, thereby identifying several high-risk anomaly areas.

[0015] Compared with existing technologies, the advantages of this invention are as follows: By simultaneously acquiring multi-source detection data from the track detection system, the catenary detection system, and the BeiDou positioning system, a comprehensive data system covering track geometry, catenary operating parameters, and geographical location information is constructed. This design breaks through the limitations of traditional single detection data sources, realizes the correlation analysis between track and catenary states, provides data support for multi-dimensional comprehensive judgment, and effectively improves the comprehensiveness and reliability of anomaly detection. Secondly, by setting track state thresholds and correlation thresholds, the first and second anomaly areas are identified in stages, realizing a step-by-step screening process from single-equipment anomalies to multi-system collaborative anomalies. This mechanism enables the system not only to identify local track geometric anomalies but also to determine their coupling relationship with the catenary operating state, thereby achieving higher-precision anomaly location and risk classification. Furthermore, this method introduces a dynamic monitoring mechanism for real-time pull-out value deviation within the second anomaly area and automatically adjusts the correlation threshold within a preset adjustment period based on the real-time deviation. Through this adaptive parameter correction method, the system can dynamically optimize the correlation judgment criteria according to the on-site operating status, thereby improving the sensitivity and adaptability of anomaly identification and avoiding false alarms or missed alarms caused by fixed thresholds. Finally, based on the adjusted correlation threshold and the corrected track status threshold, high-risk anomaly areas are identified in the GIS space, and alarm prompts are automatically generated. This dynamic correction and spatial visualization linkage design significantly improves the accuracy and practicality of alarm results, enabling maintenance personnel to intuitively grasp the distribution of anomalies and risk levels, and achieve rapid response and precise handling of railway facility anomalies.

[0016] On the other hand, this application also provides a GIS-based intelligent alarm system for abnormal railway facility data, comprising: a first acquisition module for acquiring multi-source detection data from a track inspection system, a catenary inspection system, and a BeiDou positioning system, wherein the multi-source detection data includes track geometric state parameters, catenary operating parameters, and equipment location information; the first acquisition module is further configured to determine several first abnormal regions based on track geometric state parameters and a preset track state threshold; a second acquisition module connected to the first acquisition module, wherein the second acquisition module is configured to determine several second abnormal regions based on track geometric state parameters, catenary operating parameters, and a preset correlation threshold of the first abnormal regions; the second acquisition module is further configured to determine several second abnormal regions based on all the first abnormal regions. The system acquires the real-time pull-out value deviation at each hard point within the second abnormal area of ​​the overhead contact line; an adjustment module, connected to the second acquisition module, adjusts a preset correlation threshold based on the real-time pull-out value deviation within a preset adjustment period to form an adjustment correlation threshold; the adjustment module also corrects a preset track status threshold based on the number of second abnormal areas determined by the adjustment correlation threshold within a preset correction period to form a corrected track status threshold; an alarm module, connected to the adjustment module, identifies several high-risk abnormal areas based on the real-time pull-out value deviation acquired within a preset time period based on the corrected track status threshold; the alarm module also generates alarm prompts based on the high-risk abnormal areas.

[0017] It is understood that the intelligent alarm method and system for abnormal railway facility data based on GIS in the above embodiments of the present invention have the same beneficial effects, and will not be described again. Attached Figure Description

[0018] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings: Figure 1 is a flowchart of a GIS-based intelligent alarm method for abnormal railway facility data provided by an embodiment of the present invention; Figure 2 is a schematic flowchart of a GIS-based intelligent alarm method for abnormal railway facility data provided by an embodiment of the present invention; Figure 3 is a functional block diagram of a GIS-based intelligent alarm system for abnormal railway facility data provided by an embodiment of the present invention. Detailed Implementation

[0019] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the disclosure to those skilled in the art. It should be noted that, unless otherwise specified, embodiments and features in the embodiments of the present invention can be combined with each other. The present invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0020] As shown in Figures 1-2, in some embodiments of this application, this embodiment provides a GIS-based intelligent alarm method for abnormal railway facility data, including: step S100, acquiring multi-source detection data from the track detection system, the catenary detection system, and the Beidou positioning system, wherein the multi-source detection data includes track geometric state parameters, catenary operating parameters, and equipment location information.

[0021] Understandably, by collaboratively collecting and fusing multi-source detection data, a comprehensive detection system covering the geometric characteristics, electrical operating status, and spatial positioning information of railway infrastructure can be constructed, thus providing high-precision data support for subsequent anomaly identification and intelligent alarms. First, the track inspection system is responsible for collecting track geometric parameters, including key indicators reflecting the health of the track structure such as gauge, elevation, level, and alignment. These parameters directly characterize the smoothness and stability of the track and are important bases for judging the safety status of the line. Through continuous monitoring of the track geometry, potential structural anomalies or deformation trends can be detected at an early stage. Second, the catenary inspection system is used to obtain the operating parameters of the catenary, such as catenary height, pull-out value, hard point location, and voltage fluctuations. These data reflect the electrical contact quality and mechanical stress characteristics during the train's power receiving process. When the track geometry deviates, the stress state of the catenary also changes accordingly; therefore, there is a close dynamic coupling relationship between track and catenary parameters. Finally, the BeiDou positioning system provides high-precision spatiotemporal positioning information for calibrating the geographical location of track inspection and catenary detection data. By mapping the detection data to a unified geographic coordinate system, the system can achieve spatial alignment and correlation analysis of track and overhead contact line anomalies. This fusion principle based on GIS spatial benchmarks enables data from different detection sources to be synchronized in both time and space, constructing a globally consistent railway facility status model.

[0022] Step S200: Determine several first abnormal regions based on track geometric state parameters and preset track state thresholds, and determine several second abnormal regions based on track geometric state parameters of the first abnormal regions, catenary operation parameters, and preset correlation thresholds.

[0023] Specifically, when determining several first abnormal regions based on track geometric state parameters and preset track state thresholds, the process includes: determining whether a track detection region is a first abnormal region based on the relationship between the track geometric state parameters of the track detection region and the preset track state thresholds; when the track geometric state parameters are greater than the preset track state thresholds, the track detection region is determined to be a first abnormal region; when the track geometric state parameters are less than or equal to the preset track state thresholds, the track detection region is determined not to be a first abnormal region.

[0024] Specifically, when determining several second abnormal regions based on the track geometric state parameters, catenary operation parameters, and preset correlation threshold of the first abnormal region, the process includes: obtaining the standard deviation of all track geometric state parameters within a preset correlation calculation period to form track state fluctuation values; obtaining the standard deviation of all catenary operation parameters within a preset correlation calculation period to form catenary state fluctuation values; and determining several second abnormal regions based on the track state fluctuation values, catenary state fluctuation values, and preset correlation threshold.

[0025] Specifically, when determining several second abnormal regions based on track state fluctuation values, catenary state fluctuation values, and a preset correlation threshold, the process includes: obtaining the change curve of track state fluctuation values ​​within a preset correlation calculation period and forming a track fluctuation curve; obtaining the change curve of catenary state fluctuation values ​​within a preset correlation calculation period and forming a catenary fluctuation curve; obtaining the cosine similarity between the track fluctuation curve and the catenary fluctuation curve and forming a correlation between the track fluctuation curve and the catenary fluctuation curve; and determining a first abnormal region as a second abnormal region when the correlation is less than a preset correlation threshold, thereby identifying several second abnormal regions.

[0026] It is understandable that by using multi-level anomaly identification and track-catenment coupling analysis, precise location and spatial correlation judgment of railway facility anomalies can be achieved, thereby improving the sensitivity and reliability of anomaly detection. First, several first-stage anomaly areas are identified by comparing track geometric parameters with preset track state thresholds. This principle is based on a threshold judgment mechanism: when track geometric parameters exceed a safety threshold, the system determines that the area has a potential anomaly, thus achieving a preliminary screening of the local structural health of the track. The core of this step lies in establishing a quantitative mapping relationship between track state parameters and thresholds, enabling automated preliminary judgment of track anomalies. Second, based on the first-stage anomaly areas, this invention introduces coupling analysis of track and catenary operating parameters to identify several second-stage anomaly areas. Specifically, by calculating the standard deviation of track geometric parameters and catenary operating parameters within a preset time period, track state fluctuation values ​​and catenary state fluctuation values ​​are formed. This fluctuation-based analysis principle can reflect the dynamic characteristics of the system in the time dimension, identifying potential correlation anomalies between the track and the catenary, rather than relying solely on single measurement values. Finally, this method quantifies the correlation between track fluctuations and catenary fluctuations by constructing track and catenary state fluctuation curves and calculating their cosine similarity. When the correlation is below a preset threshold, it indicates an inconsistency or potential risk between track anomalies and overhead contact line operation anomalies, thus further confirming the first anomaly area as the second anomaly area. The innovation of this technology lies in combining the temporal characteristics and spatial distribution of multi-source data through curve fluctuations and correlation analysis, enabling multi-dimensional anomaly identification and enhancing the system's sensitivity to complex coupled anomalies.

[0027] It can be seen that by using threshold screening for preliminary anomaly judgment and then combining it with track-overhead catenary fluctuation correlation analysis, a multi-level anomaly identification method that integrates multi-source data provides a scientific basis for dynamic monitoring and accurate early warning of railway facility anomalies.

[0028] Step S300: Obtain the real-time pull-out value deviation at each hard point in the second abnormal area based on the contact network operation parameters in all second abnormal areas, and adjust the preset correlation threshold according to the real-time pull-out value deviation within the preset adjustment time to form the adjustment correlation threshold.

[0029] Specifically, when obtaining the real-time pull-out value deviation at each hard point in the second abnormal area based on the catenary operation parameters of all the second abnormal areas, the process includes: obtaining the standard deviation of all catenary operation parameters and forming the catenary distribution value; when the catenary distribution value is greater than the preset catenary distribution threshold, obtaining the real-time pull-out value deviation at each hard point in the second abnormal area based on the catenary operation parameters of any two adjacent second abnormal areas.

[0030] Specifically, when obtaining the real-time pull-out value deviation at each hard point within the second abnormal region based on the catenary operation parameters of any two adjacent second abnormal regions, the process includes: obtaining the distance between the two second abnormal regions, obtaining the difference in the catenary operation parameters between the two second abnormal regions, and forming a catenary difference; generating a catenary gradient based on the ratio of the catenary difference to the distance, and determining the midpoint of the two second abnormal regions as the midpoint of the hard point when the catenary gradient is greater than a preset gradient threshold, thus forming the hard point midpoint; determining the deviation of all pull-out values ​​within a circular region centered on the hard point midpoint and with a preset hard point length as the radius, and determining the real-time pull-out value deviation based on the average of all deviations.

[0031] Specifically, when adjusting the preset correlation threshold based on the real-time pull-out value deviation within a preset adjustment period, the process includes: determining the first deviation fluctuation value based on the standard deviation of the real-time pull-out value deviation; wherein, when the first deviation fluctuation value is greater than the preset first deviation fluctuation threshold, the preset correlation threshold is reduced based on the relative deviation between the first deviation fluctuation value and the preset first deviation fluctuation threshold and the preset adjustment coefficient to determine the adjustment correlation threshold.

[0032] It can be seen that by refining the analysis of the overhead contact system operating parameters within the second anomaly area, identifying key hard point locations, and dynamically adjusting the correlation threshold, high-precision identification and intelligent early warning of railway facility anomalies are achieved. First, this method obtains the standard deviation of the overhead contact system operating parameters within the second anomaly area to form an overhead contact system distribution value, used to assess the state fluctuations of the overhead contact system in that area. When the overhead contact system distribution value exceeds a preset threshold, it indicates significant operational fluctuations in the area, potentially leading to localized stress concentration or abnormal hard points. The core principle of this step lies in using statistical fluctuation characteristics to pre-screen anomalies, providing fundamental data support for subsequent hard point identification. Second, during hard point identification, this method combines the difference in overhead contact system operating parameters between adjacent second anomaly areas with the distance between areas to calculate the overhead contact system gradient. When the gradient exceeds a preset threshold, the midpoint of the gradient is determined as the midpoint of the hard point. A circular area is formed with this midpoint as the center and a preset hard point length as the radius. The average deviation of all pull-out values ​​within the area is calculated to determine the real-time pull-out value deviation of the hard point. This principle, through gradient analysis and spatial aggregation, achieves precise local location of local anomalies in the overhead contact system, transforming abstract fluctuation data into quantifiable hard point indicators. Finally, this method utilizes the real-time pull-out value deviation within a preset adjustment period to calculate the standard deviation of the deviation, forming a first deviation fluctuation value. Based on the relative deviation of the fluctuation value from the threshold and a preset adjustment coefficient, the correlation threshold is dynamically adjusted. When the deviation fluctuation exceeds the safety standard, the correlation threshold is automatically lowered, making the determination of coupled anomalies more sensitive in subsequent anomaly identification. This technical principle achieves adaptive parameter adjustment, ensuring that the anomaly identification standard can be dynamically optimized according to the actual operating status, improving detection accuracy and reducing false alarms or missed alarms.

[0033] It can be seen that by statistical analysis of overhead contact line operating parameters, gradient positioning, and dynamic threshold adjustment, the local anomalies in the second anomaly area are closely integrated with the overall correlation, thereby achieving high-precision and intelligent identification and dynamic early warning of railway facility anomalies.

[0034] Step S400: Correct the preset track state threshold according to the number of second abnormal regions determined based on the adjustment correlation threshold within the preset correction time period to form a corrected track state threshold. Determine several high-risk abnormal regions based on the real-time pull-out value deviation obtained based on the corrected track state threshold within the preset time period, and generate alarm prompts based on the high-risk abnormal regions.

[0035] Specifically, when adjusting the preset orbital state threshold based on the number of second abnormal regions determined by adjusting the correlation threshold within a preset correction period, the process includes: determining the quantity fluctuation value based on the standard deviation of the number of second abnormal regions; when the quantity fluctuation value is greater than the preset quantity fluctuation threshold, determining the quantity fluctuation deviation based on the relative deviation between the quantity fluctuation value and the preset quantity fluctuation threshold; and when the quantity fluctuation deviation is greater than the preset fluctuation deviation threshold, reducing the preset orbital state threshold based on the relative deviation between the quantity fluctuation deviation and the preset fluctuation deviation threshold, and a preset correction coefficient, to determine the corrected orbital state threshold.

[0036] Specifically, when determining several high-risk anomaly areas based on the real-time pull-out value deviation obtained within a preset time period based on the corrected orbital state threshold, the process includes: determining a second deviation fluctuation value based on the standard deviation of the real-time pull-out value deviation; and when the second deviation fluctuation value is greater than a preset second deviation fluctuation threshold, determining the corresponding circular area as a high-risk anomaly area, thereby identifying several high-risk anomaly areas.

[0037] Understandably, by dynamically monitoring the number of second abnormal areas and the deviation of pull-out values, the system achieves adaptive correction of track status thresholds and accurate identification of high-risk abnormal areas, thereby improving the sensitivity and reliability of railway facility anomaly alarms. First, the system statistically analyzes the number of second abnormal areas within a preset correction period and calculates their standard deviation to form a quantity fluctuation value, used to assess the fluctuation of the number of abnormal areas over time. When the quantity fluctuation value exceeds a preset threshold, the system further calculates the quantity fluctuation deviation and dynamically corrects the track status threshold based on a preset correction coefficient. This principle is based on the idea that "abnormal quantity fluctuations reflect changes in the overall track status." By adaptively adjusting the track status threshold, anomaly identification can flexibly respond to changes in actual operating conditions, avoiding misjudgments or missed judgments due to fixed thresholds. Second, based on the corrected track status threshold, the system calculates the second deviation fluctuation value using real-time pull-out value deviations to dynamically determine high-risk abnormal areas. When the second deviation fluctuation value exceeds a preset second deviation fluctuation threshold, the system marks the corresponding circular area as a high-risk abnormal area. This principle analyzes the standard deviation of local pull-out values ​​to correlate the dynamic changes of the track and overhead contact system with spatial location, enabling precise positioning of high-risk points. Finally, by combining adaptive threshold correction and deviation fluctuation analysis, it organically integrates quantity fluctuations, track status, and pull-out value deviations to form a high-risk anomaly area identification mechanism and generate corresponding alarm prompts. Through dynamic threshold adjustment and spatial risk assessment, the system can respond to changes in railway facility status in real time, improving the accuracy and timeliness of intelligent alarms and providing a reliable basis for operation and maintenance decisions.

[0038] It can be seen that by utilizing the dynamic analysis of fluctuations in the number of abnormal areas and deviations in pull-out values, adaptive correction of track status thresholds and intelligent determination of high-risk abnormal areas can be achieved, thereby improving the accuracy and sensitivity of railway facility anomaly detection and alarm.

[0039] In the above embodiments, by simultaneously acquiring multi-source detection data from the track detection system, the catenary detection system, and the BeiDou positioning system, a comprehensive data system covering track geometry, catenary operating parameters, and geographical location information is constructed. This design breaks through the limitations of traditional single detection data sources, realizes the correlation analysis between track and catenary states, provides data support for multi-dimensional comprehensive judgment, and effectively improves the comprehensiveness and reliability of anomaly detection. Secondly, by setting track state thresholds and correlation thresholds, the first and second anomaly areas are identified in stages, realizing a step-by-step screening process from single-equipment anomalies to multi-system collaborative anomalies. This mechanism enables the system not only to identify local geometric anomalies of the track but also to determine their coupling relationship with the catenary operating state, thereby achieving higher-precision anomaly location and risk classification. Furthermore, this method introduces a dynamic monitoring mechanism for real-time pull-out value deviation within the second anomaly area and automatically adjusts the correlation threshold based on the real-time deviation within a preset adjustment period. Through this adaptive parameter correction method, the system can dynamically optimize the correlation judgment criteria according to the on-site operating status, thereby improving the sensitivity and adaptability of anomaly identification and avoiding false alarms or missed alarms caused by fixed thresholds. Finally, based on the adjusted correlation threshold and the corrected track status threshold, high-risk anomaly areas are identified in the GIS space, and alarm prompts are automatically generated. This dynamic correction and spatial visualization linkage design significantly improves the accuracy and practicality of alarm results, enabling maintenance personnel to intuitively grasp the distribution of anomalies and risk levels, and achieve rapid response and precise handling of railway facility anomalies.

[0040] In another preferred embodiment based on the above embodiments, as shown in FIG3, this embodiment provides a GIS-based intelligent alarm system for abnormal railway facility data, including: a first acquisition module, a second acquisition module, an adjustment module, and an alarm module.

[0041] Specifically, the first acquisition module is used to acquire multi-source detection data from the track detection system, the catenary detection system, and the BeiDou positioning system. This multi-source detection data includes track geometric state parameters, catenary operating parameters, and equipment location information. The first acquisition module is also used to determine several first abnormal regions based on the track geometric state parameters and a preset track state threshold. The second acquisition module is connected to the first acquisition module and is used to determine several second abnormal regions based on the track geometric state parameters of the first abnormal regions, the catenary operating parameters, and a preset correlation threshold. The second acquisition module is also used to obtain the first... The adjustment module is connected to the second acquisition module. The adjustment module is used to adjust the preset correlation threshold according to the real-time pull-out value deviation within a preset adjustment period to form an adjusted correlation threshold. The adjustment module is also used to correct the preset track status threshold according to the number of second abnormal areas determined based on the adjusted correlation threshold within a preset correction period to form a corrected track status threshold. The alarm module is connected to the adjustment module. The alarm module is used to determine several high-risk abnormal areas according to the real-time pull-out value deviation obtained based on the corrected track status threshold within a preset time period. The alarm module is also used to generate alarm prompts based on the high-risk abnormal areas.

[0042] It is understood that the intelligent alarm method and system for abnormal railway facility data based on GIS in the above embodiments of the present invention have the same beneficial effects, and will not be described again.

[0043] To enable those skilled in the art to fully understand and implement this invention, the specific implementation principle of this invention is further explained below in conjunction with a specific application scenario.

[0044] In the actual operation of railway facility monitoring, multi-source detection data from the track inspection system, catenary inspection system, and BeiDou positioning system are first acquired through the first acquisition module. This data includes track geometric parameters, catenary operating parameters, and equipment location information. The first acquisition module interfaces with the aforementioned detection systems through a unified data interface standard to ensure the real-time performance and integrity of the data. For example, in a certain inspection task, the first acquisition module obtains a track gauge deviation of +8mm from the track inspection system and a pull-out deviation of +50mm from the catenary inspection system for the same area. This data is then transmitted to the first and second judgment modules as the basis for subsequent analysis.

[0045] The first judgment module receives track geometric state parameters from the first acquisition module and determines several first abnormal regions based on preset track state thresholds. Specifically, the first judgment module first compares each track geometric state parameter. When a parameter exceeds the preset track state threshold, the detected track area is determined to be a first abnormal region. For example, if the gauge deviation of a certain track segment exceeds ±6mm, that area is marked as a first abnormal region. The first judgment module transmits information on all first abnormal regions to the second judgment module for further analysis.

[0046] The second judgment module is connected to both the first acquisition module and the first judgment module. Its main task is to determine several second abnormal regions based on the track geometric state parameters, catenary operating parameters, and a preset correlation threshold of the first abnormal region. To achieve this, the second judgment module first calculates the standard deviation of all track geometric state parameters within a preset correlation calculation period to form track state fluctuation values; simultaneously, it calculates the standard deviation of all catenary operating parameters within the same period to form catenary state fluctuation values. Then, the second judgment module plots the change curves of the track state fluctuation values ​​(track fluctuation curve) and the change curves of the catenary state fluctuation values ​​(catenary fluctuation curve). By calculating the cosine similarity between these two curves, the second judgment module obtains a correlation value. If this correlation value is less than the preset correlation threshold, the corresponding first abnormal region is determined to be a second abnormal region. For example, if the cosine similarity between the track fluctuation curve and the catenary fluctuation curve is less than 0.8, the region is considered to have a high risk of abnormality and requires further attention.

[0047] The second acquisition module is connected to the second judgment module. Its function is to obtain the real-time pull-out value deviation at each hard point within the entire second abnormal area based on the catenary operating parameters. Specifically, the second acquisition module first calculates the standard deviation of all catenary operating parameters to form the catenary distribution value. If the catenary distribution value is greater than a preset catenary distribution threshold, it further analyzes the catenary operating parameters of any two adjacent second abnormal areas. The second acquisition module obtains the distance between the two second abnormal areas and calculates the difference in their catenary operating parameters to form the catenary difference. Next, the second acquisition module calculates the ratio of the catenary difference to the distance to form the catenary gradient. If the catenary gradient is greater than a preset gradient threshold, the midpoint between the two second abnormal areas is determined as the midpoint of the hard point, forming the hard point midpoint. A circular area is delineated with the hard point midpoint as the center and a preset hard point length as the radius, and the deviation of all pull-out values ​​within this area is obtained. Finally, the second acquisition module calculates the average of all deviations to form the real-time pull-out value deviation.

[0048] The adjustment module is connected to both the second judgment module and the second acquisition module. Its function is to adjust a preset correlation threshold based on the real-time pull-out value deviation within a preset adjustment period, thus forming an adjusted correlation threshold. The adjustment module first calculates the standard deviation of the real-time pull-out value deviation to form a first deviation fluctuation value. If the first deviation fluctuation value is greater than the preset first deviation fluctuation threshold, the preset correlation threshold is reduced based on the relative deviation between the first deviation fluctuation value and the preset first deviation fluctuation threshold, as well as a preset adjustment coefficient. For example, if the first deviation fluctuation value exceeds 10% of the preset threshold, the adjustment module reduces the preset correlation threshold by 0.05, thereby improving the system's sensitivity.

[0049] The correction module is connected to the first judgment module, the adjustment module, and the second judgment module. Its task is to correct the preset track state threshold based on the number of second abnormal regions determined by the adjustment correlation threshold within a preset correction time, thus forming a corrected track state threshold. The correction module first calculates the standard deviation of the number of second abnormal regions to form a quantity fluctuation value. If the quantity fluctuation value is greater than the preset quantity fluctuation threshold, it further calculates the relative deviation between the quantity fluctuation value and the preset quantity fluctuation threshold to form a quantity fluctuation deviation. If the quantity fluctuation deviation is greater than the preset fluctuation deviation threshold, the preset track state threshold is reduced based on the relative deviation between the quantity fluctuation deviation and the preset fluctuation deviation threshold, as well as a preset correction coefficient. For example, if the quantity fluctuation of the second abnormal regions is large and exceeds the preset range, the correction module reduces the preset track state threshold by 1 mm to adapt to the current actual detection requirements.

[0050] The third judgment module is connected to both the correction module and the second acquisition module. Its function is to identify several high-risk anomaly areas based on the real-time pull-out value deviation obtained within a preset time period based on the correction orbital state threshold. The third judgment module first calculates the standard deviation of the real-time pull-out value deviation to form a second deviation fluctuation value. If the second deviation fluctuation value is greater than the preset second deviation fluctuation threshold, the corresponding circular area is determined to be a high-risk anomaly area. For example, if the real-time pull-out value deviation fluctuation within a certain circular area is significant and exceeds the preset range, then that area is marked as a high-risk anomaly area.

[0051] The alarm module connects to the third judgment module, and its function is to generate alarm prompts based on high-risk anomaly areas. The alarm module uses a GIS display module to present the spatial distribution of high-risk anomaly areas as a heat map or multi-layer overlay, allowing maintenance personnel to intuitively understand the anomaly situation. Simultaneously, the alarm module designs a tiered alarm strategy based on the anomaly level; for example, it issues a red alert for high-risk anomaly areas and a yellow alert for general anomaly areas. Furthermore, the alarm module supports a linkage notification function, which can push alarm information to the mobile terminals of relevant management personnel to ensure timely anomaly response.

[0052] In actual operation, the system of this invention achieves intelligent monitoring and alarm of abnormal data of railway facilities through the collaborative work of the above modules. For example, in a certain inspection task, the first acquisition module obtains track gauge deviation data of +8mm from the track inspection system, and pull-out value deviation data of +50mm from the catenary inspection system for the same area. The first judgment module determines the area as the first abnormal area based on the preset track state threshold and transmits the relevant information to the second judgment module. The second judgment module calculates the cosine similarity between the track fluctuation curve and the catenary fluctuation curve and finds that its correlation is less than 0.8, so it further marks the area as the second abnormal area. Subsequently, the second acquisition module analyzes the catenary operating parameters in the area and finds that the real-time pull-out value deviation at the hard point has increased significantly. The adjustment module adjusts the preset correlation threshold according to the real-time pull-out value deviation, and the correction module corrects the preset track state threshold according to the number of second abnormal areas. Finally, the third judgment module determines the area as a high-risk abnormal area, and the alarm module generates a red alarm prompt and pushes the alarm information to the mobile terminals of relevant personnel.

[0053] As can be seen from the above implementation methods, this invention achieves structured management of multi-source detection data by introducing a unified data interface standard and acquisition architecture, solving the problem of data isolation in existing technologies. The intelligent data preprocessing mechanism, including cleaning, standardization, and coordinate transformation, enables spatial correspondence between detection data from different sources, providing a foundation for subsequent spatial correlation analysis. Combining a GIS display module with heatmaps and multi-layer overlays to present the spatial distribution of abnormal data significantly enhances the intuitiveness of data analysis and decision support capabilities. Finally, an intelligent alarm strategy based on anomaly level and spatial location implements tiered alarm and linkage notification functions, improving the timeliness and accuracy of railway facility anomaly response.

[0054] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program goods. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program goods embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0055] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program goods according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, as well as combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in one or more blocks of the flowchart illustrations and / or one or more blocks of the block diagrams.

[0056] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means that implement the functions specified in one or more flowcharts and / or one or more block diagrams.

[0057] These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, such that the instructions, which execute on the computer or other programmable apparatus, provide steps for implementing the functions specified in one or more flowcharts and / or one or more block diagrams.

[0058] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A GIS-based intelligent alarm method for abnormal railway facility data, characterized in that, include: Acquire multi-source detection data from the track inspection system, the catenary inspection system, and the BeiDou positioning system. The multi-source detection data includes track geometric state parameters, catenary operating parameters, and equipment location information. Several first abnormal regions are determined based on track geometric state parameters and preset track state thresholds, and several second abnormal regions are determined based on track geometric state parameters of the first abnormal regions, catenary operation parameters, and preset correlation thresholds. The real-time pull-out value deviation at each hard point in the second abnormal area is obtained based on the overhead contact line operation parameters of all the second abnormal areas, and the preset correlation threshold is adjusted according to the real-time pull-out value deviation within the preset adjustment time to form the adjustment correlation threshold. The preset track status threshold is adjusted based on the number of second abnormal regions determined by the correlation threshold within the preset correction time period to form a corrected track status threshold. Several high-risk abnormal regions are determined based on the real-time pull-out value deviation obtained based on the corrected track status threshold within the preset time period, and alarm prompts are generated based on the high-risk abnormal regions.

2. The intelligent alarm method for abnormal railway facility data based on GIS as described in claim 1, characterized in that, When determining several first abnormal regions based on track geometric state parameters and preset track state thresholds, the process includes: determining whether a track detection region is a first abnormal region based on the relationship between the track geometric state parameters of the track detection region and the preset track state thresholds; when the track geometric state parameters are greater than the preset track state thresholds, the track detection region is determined to be a first abnormal region; when the track geometric state parameters are less than or equal to the preset track state thresholds, the track detection region is determined not to be a first abnormal region.

3. The intelligent alarm method for abnormal railway facility data based on GIS as described in claim 2, characterized in that, When determining several second abnormal regions based on the track geometric state parameters, catenary operation parameters, and preset correlation threshold of the first abnormal region, the process includes: obtaining the standard deviation of all track geometric state parameters within a preset correlation calculation period to form track state fluctuation values; obtaining the standard deviation of all catenary operation parameters within a preset correlation calculation period to form catenary state fluctuation values; and determining several second abnormal regions based on the track state fluctuation values, catenary state fluctuation values, and preset correlation threshold.

4. The intelligent alarm method for abnormal railway facility data based on GIS as described in claim 3, characterized in that, When determining several second abnormal regions based on track status fluctuation values, catenary status fluctuation values, and a preset correlation threshold, the process includes: obtaining the change curve of track status fluctuation values ​​within a preset correlation calculation period and forming a track fluctuation curve; obtaining the change curve of catenary status fluctuation values ​​within a preset correlation calculation period and forming a catenary fluctuation curve; obtaining the cosine similarity between the track fluctuation curve and the catenary fluctuation curve and forming a correlation between the track fluctuation curve and the catenary fluctuation curve; and determining a first abnormal region as a second abnormal region when the correlation is less than a preset correlation threshold, thereby identifying several second abnormal regions.

5. The intelligent alarm method for abnormal railway facility data based on GIS as described in claim 4, characterized in that, When obtaining the real-time pull-out value deviation at each hard point in the second abnormal area based on the catenary operation parameters of all the second abnormal areas, the process includes: obtaining the standard deviation of all catenary operation parameters and forming the catenary distribution value; when the catenary distribution value is greater than the preset catenary distribution threshold, obtaining the real-time pull-out value deviation at each hard point in the second abnormal area based on the catenary operation parameters of any two adjacent second abnormal areas.

6. The intelligent alarm method for abnormal railway facility data based on GIS as described in claim 5, characterized in that, When obtaining the real-time pull-out value deviation at each hard point within the second abnormal region based on the catenary operation parameters of any two adjacent second abnormal regions, the process includes: obtaining the distance between the two second abnormal regions, obtaining the difference in the catenary operation parameters between the two second abnormal regions, and forming a catenary difference; generating a catenary gradient based on the ratio of the catenary difference to the distance, and determining the midpoint of the two second abnormal regions as the midpoint of the hard point when the catenary gradient is greater than a preset gradient threshold, thus forming the hard point midpoint; determining the deviation of all pull-out values ​​within a circular region centered on the hard point midpoint and with a preset hard point length as the radius, and determining the real-time pull-out value deviation based on the average of all deviations.

7. The intelligent alarm method for abnormal railway facility data based on GIS as described in claim 6, characterized in that, When adjusting the preset correlation threshold based on the real-time pull-out value deviation within a preset adjustment period, the process includes: determining the first deviation fluctuation value based on the standard deviation of the real-time pull-out value deviation; wherein, when the first deviation fluctuation value is greater than the preset first deviation fluctuation threshold, the preset correlation threshold is reduced based on the relative deviation between the first deviation fluctuation value and the preset first deviation fluctuation threshold and the preset adjustment coefficient to determine the adjustment correlation threshold.

8. The intelligent alarm method for abnormal railway facility data based on GIS as described in claim 7, characterized in that, The process of adjusting the preset orbital state threshold based on the number of second abnormal regions determined by the correlation threshold within a preset correction period includes: determining the quantity fluctuation value based on the standard deviation of the number of second abnormal regions; determining the quantity fluctuation deviation based on the relative deviation between the quantity fluctuation value and the preset quantity fluctuation threshold when the quantity fluctuation value is greater than the preset quantity fluctuation threshold; and determining the corrected orbital state threshold by reducing the preset orbital state threshold based on the relative deviation between the quantity fluctuation deviation and the preset fluctuation deviation threshold and the preset correction coefficient when the quantity fluctuation deviation is greater than the preset fluctuation deviation threshold.

9. The intelligent alarm method for abnormal railway facility data based on GIS as described in claim 8, characterized in that, When determining several high-risk anomaly areas based on the real-time pull-out value deviation obtained within a preset time period based on the corrected orbital state threshold, the process includes: determining a second deviation fluctuation value based on the standard deviation of the real-time pull-out value deviation; when the second deviation fluctuation value is greater than the preset second deviation fluctuation threshold, determining the corresponding circular area as a high-risk anomaly area, thereby identifying several high-risk anomaly areas.

10. A GIS-based intelligent alarm system for abnormal railway facility data, based on any one of the GIS-based intelligent alarm methods for abnormal railway facility data according to claims 1 to 9, characterized in that, include: The first acquisition module is used to acquire multi-source detection data from the track detection system, the catenary detection system, and the Beidou positioning system. The multi-source detection data includes track geometric state parameters, catenary operating parameters, and equipment location information. The first acquisition module is also used to determine several first abnormal regions based on the track geometric state parameters and the preset track state threshold. The second acquisition module is connected to the first acquisition module. The second acquisition module is used to determine several second abnormal areas based on the track geometry state parameters of the first abnormal area, the catenary operation parameters, and the preset correlation threshold. The second acquisition module is also used to obtain the real-time pull-out value deviation at each hard point in the second abnormal area based on the contact network operation parameters of all the second abnormal areas; the adjustment module is connected to the second acquisition module and is used to adjust the preset correlation threshold based on the real-time pull-out value deviation within the preset adjustment time to form the adjustment correlation threshold. The adjustment module is also used to adjust the preset track state threshold according to the number of second abnormal areas determined based on the adjustment correlation threshold within the preset correction time, forming a corrected track state threshold; the alarm module is connected to the adjustment module and is used to determine several high-risk abnormal areas based on the real-time pull-out value deviation obtained based on the corrected track state threshold within the preset time. The alarm module is also used to generate alarm prompts based on high-risk abnormal areas.

Images