Railway operation environment intelligent monitoring and risk assessment system

Abstract

The invention relates to the technical field of railway transportation safety monitoring, and discloses a railway operation environment intelligent monitoring and risk assessment system, which comprises a railway environment multi-source data acquisition module, a track potential safety hazard detection module and a risk assessment and processing unit, and is also provided with a data fusion and preprocessing module. The acquisition module acquires various types of environmental data in real time, the detection module accurately identifies hidden danger track sections, and the risk assessment and processing unit analyzes hidden danger influences, assesses risk levels and formulates strategies. And the data fusion and preprocessing module improves the data quality. The beneficial effects are obvious, and hidden dangers can be comprehensively monitored in real time and accurately positioned; risks are scientifically evaluated, and coping strategies are reasonably formulated; data processing is optimized, and a reliable decision basis is provided; the operation and maintenance cost is reduced and the operation efficiency is improved; the device adapts to complex environments, guarantees safe development of railways, and meets safe operation requirements of railways.

Description

Technical Field

[0001] The present invention relates to the technical field of railway transportation safety monitoring, and more specifically to an intelligent monitoring and risk assessment system for railway operation environment. Background Art

[0002] With the increasingly prominent position of railway transportation in the modern transportation system, its safe operation has become a key factor in ensuring the stable development of the economic society. In recent years, the global railway operation mileage has been continuously increasing, and the passenger and freight volumes have been rising steadily, posing higher requirements for railway operation safety. According to the statistics of the International Union of Railways, in the past decade, the annual freight turnover of the global railway has increased by 30%, the passenger volume has increased by 25%, and the train operation density has increased significantly. In such a huge and busy transportation system, the safety monitoring and risk assessment of the railway operation environment are of vital importance.

[0003] The railway operation environment is complex and changeable, facing various potential threats. On the one hand, the influence of natural environmental factors is huge. For example, extreme temperatures can change the performance of track materials. In cold regions, low winter temperatures may cause the embrittlement of track steel, increasing the risk of fracture; in high-temperature environments, the track may experience buckling due to thermal expansion. Natural disasters such as strong winds, heavy rains, floods, and earthquakes can also directly damage railway facilities and affect the stability of the track structure. According to relevant statistics, thousands of railway operation interruption events are caused by natural disasters every year, bringing huge economic losses. On the other hand, during the long-term operation of the railway, problems will gradually occur in the track structure itself, such as track wear, fastener loosening, and ballast deformation. If these problems cannot be discovered and handled in a timely manner, serious safety accidents will be triggered. Traditional railway safety monitoring methods have many limitations. Manual inspections rely on human labor, with low efficiency and difficulty in achieving comprehensive and real-time monitoring. Manual inspections are usually carried out at fixed intervals. During the inspection intervals, it is difficult to detect sudden safety hazards in a timely manner. For example, in some remote mountain railway sections, the manual inspection cycle is long, and it is difficult to discover and handle problems with the track during the inspection gaps. Moreover, manual judgment is subjective and prone to errors, and the judgment criteria for the track safety status may vary among different inspection personnel. At the same time, manual inspections are also restricted by external conditions such as bad weather. In extreme weather such as heavy rains and blizzards, it is difficult to carry out normal manual inspections.

[0004] Although the monitoring system based on fixed sensors can achieve real-time monitoring of some parameters, its functions are relatively single, lacking the ability to comprehensively analyze various environmental data. Such systems can often only monitor one or several parameters of the track, such as only monitoring the track temperature or track stress, and cannot comprehensively understand the railway operation environment. Moreover, the data between the sensors are independent of each other, without an effective fusion mechanism, making it difficult to evaluate the risks of the railway operation environment as a whole. For example, when the track temperature rises, the surrounding wind speed and rainfall also change. The fixed sensor monitoring system cannot analyze these data comprehensively and is difficult to accurately judge the impact on track safety. Most of the existing railway safety assessment methods are based on experience or simple threshold judgments, lacking a scientific and systematic risk assessment system. This assessment method cannot accurately quantify the risk level and cannot formulate targeted treatment strategies according to different risk levels. In the face of complex track safety hazards, it is difficult to make timely and effective decisions, resulting in large loopholes in railway safety management. Summary of the Invention

[0005] The purpose of the present invention is to provide an intelligent monitoring and risk assessment system for railway operation environment to solve the problems raised in the above background technology.

[0006] To achieve the above purpose, the present invention provides the following technical solutions: An intelligent monitoring and risk assessment system for railway operation environment, the system includes:

[0007] A multi-source data acquisition module for railway environment, which is used to collect various environmental data along the railway in real time. The various environmental data include, but are not limited to, track temperature, track stress, surrounding wind speed, rainfall, and geological displacement data, and mark the corresponding areas of the collected data as each target monitoring area;

[0008] A track safety hazard detection module, which is used to determine multiple detection points of the track in each target monitoring area, and use intelligent detection equipment to obtain the real-time spatial coordinates and track structure parameter values of each detection point within the set detection period, and identify the track sections with safety hazards;

[0009] The specific identification method is: obtain the initial spatial coordinates of each detection point of the track in each target monitoring area from the system database, and calculate the displacement deviation ΔS between the real-time spatial coordinates of each detection point and the initial spatial coordinates according to the real-time spatial coordinates of each detection point xy , where x represents the target monitoring area number x = 1, 2,..., a, a is a positive integer greater than 2, y is the number of each detection point, y = 1, 2,..., b, b is a positive integer greater than 2; obtain the allowable displacement deviation threshold S0 from the system database, and calculate the displacement risk coefficient of each detection point

[0010] Statistically calculate the displacement risk coefficient of the tracks in each target monitoring area; calculate the track structure risk coefficient based on the track structure parameter values of each detection point; obtain the track structure risk coefficient threshold from the system database. If the track structure risk coefficient of the tracks in a certain target monitoring area is greater than the threshold and the total displacement risk coefficient exceeds the set comprehensive risk displacement threshold, then mark the tracks in this area as track sections with potential safety hazards;

[0011] The risk assessment and handling unit is used to analyze the impact degree of the potential hazards on the train operation for the track sections with potential safety hazards, evaluate the risk level, and formulate corresponding handling strategies.

[0012] Preferably, the specific calculation method for calculating the track structure risk coefficient of each detection point is as follows:

[0013] Obtain the initial track structure parameter value P of each detection point of the tracks in each target monitoring area from the system database xy0 ; Calculate the change rate of the track structure parameters of each detection point based on the real-time track structure parameter value P of each detection point xy

[0014] Statistically calculate the change rate of the track structure parameters of the tracks in each target monitoring area, and calculate the comprehensive coefficient of regional track structure change Based on the comprehensive coefficient C of regional track structure change x And the total displacement risk coefficient Calculate the track structure risk coefficient R gx = C x × R x .

[0015] Preferably, the specific analysis method for analyzing the impact degree of the potential hazards on the train operation is as follows:

[0016] Obtain the train speed limit value V lim , and the emergency braking distance increment ΔD corresponding to different types of track potential hazards from the system database; determine the corresponding train speed limit value and emergency braking distance increment according to the potential hazard type of the track section with potential safety hazards; combine the current train operation speed V cur , and the train braking performance parameter K b to calculate the theoretical braking distance of the train under the influence of this potential hazard Compare the theoretical braking distance D cal with the forward safety braking distance D safe . If D cal > D safe , then it is determined that the impact degree is relatively high, otherwise the impact degree is relatively low.

[0017] Preferably, the specific assessment method for evaluating the risk level is as follows:

[0018] Obtain the risk base score S corresponding to different degrees of influence from the system database base , the displacement risk coefficient weight w1, and the track structure risk coefficient weight w2; determine the risk base score S according to the degree of influence of the hidden danger on the train operation base ; combine the total displacement risk coefficient R of the track section with potential safety hazards x , and the track structure risk coefficient R gx , calculate the comprehensive risk score S = S base + w1×R x + w2×R gx , obtain the risk levels corresponding to each comprehensive risk score interval from the system database, and map to obtain the risk level of the track section with potential safety hazards

[0019] Preferably, the method for formulating the treatment strategy is as follows:

[0020] When the risk level is low risk, generate a regular recheck plan, set the recheck period T1, and arrange inspectors to recheck the hidden danger area within the recheck period; when the risk level is medium risk, send a speed limit instruction to the train dispatching system to limit the running speed of the train in the hidden danger area to V mid , and at the same time arrange maintenance personnel to arrive at the scene within T2 time for preliminary inspection and maintenance preparation; when the risk level is high risk, immediately send an emergency braking instruction to the train dispatching system to stop the train within a safe distance, and at the same time start the emergency plan and organize the emergency repair team to quickly rush to the scene for emergency repair

[0021] Preferably, in the railway environment multi-source data acquisition module, when collecting track temperature data, a distributed fiber optic temperature sensor is used for collection, and the collection principle is as follows:

[0022] Emit an optical pulse into the optical fiber. When the optical pulse travels in the optical fiber, due to the non-uniformity of the optical fiber material, backward scattered light will be generated, which contains temperature-related information; by detecting the spectral characteristics of the backward scattered light and using the relationship between the intensity ratio of Stokes light and anti-Stokes light and temperature, calculate the temperature values T at different positions along the track i , where i is the measurement point number on the optical fiber, i = 1, 2,..., c, and c is a positive integer greater than 2

[0023] Preferably, in the railway environment multi-source data acquisition module, when collecting geological displacement data, Beidou satellite positioning technology is combined with a ground displacement monitoring station for collection, and the collection principle is as follows:

[0024] The ground displacement monitoring station sets multiple monitoring marker points, and each monitoring marker point is equipped with a Beidou positioning terminal; the Beidou positioning terminal receives Beidou satellite signals to obtain the real-time three-dimensional coordinates (X of the monitoring marker pointsj , Y j , Z j ), where j is the number of monitoring landmark points, j = 1, 2, …, d, and d is a positive integer greater than 2; by comparing the real-time three-dimensional coordinates of the monitoring landmark points with the initial three-dimensional coordinates (X j0 , Y j0 , Z j0 ), the geological displacement ΔX j = X j - X j0 , ΔY j = Y j - Y j0 , ΔZ j = Z j - Z j0 are calculated, and the geological displacement data along the railway is obtained in this way.

[0025] Preferably, when the intelligent detection device obtains the real-time spatial coordinates of each detection point, it uses lidar scanning technology, and the specific implementation method is as follows:

[0026] The lidar emits laser beams to scan the track. After the laser beams hit the track surface, they are reflected back and received by the lidar; according to the flight time t of the laser and the speed of light c, the distance between the lidar and the track detection point is calculated At the same time, the angle measurement device of the lidar is used to obtain the emission angle θ and elevation angle of the laser beam Through the principle of triangulation, combined with the installation position coordinates (X0, Y0, Z0) of the lidar, the real-time spatial coordinates (X, Y, Z) of each detection point are calculated, and the calculation formula is Z = Z0 + L × cosθ.

[0027] Preferably, the system further includes a data fusion and preprocessing module, which is used to fuse and preprocess the data collected by the multi-source data acquisition module for the railway environment, specifically including:

[0028] Perform time synchronization processing on data of different types and different acquisition frequencies, and unify the data to the same time scale; use the Kalman filter algorithm to denoise the collected data, remove the noise interference in the data, and improve the accuracy of the data; perform normalization processing on the denoised data, and map the data to the interval [0, 1] for subsequent data analysis and processing.

[0029] Preferably, in the data fusion process of the intelligent monitoring and risk assessment system for the railway operating environment, for data of the same type of physical quantities such as track temperature and track stress, the weighted average method is used for fusion, and the specific calculation method is as follows:

[0030] Let the data of the same physical quantity collected by n sensors be x1, x2, …, x n , and the corresponding weights be w1, w2, …, w n , and Then the fused data The weight w i is determined according to the accuracy and reliability of the sensors. The higher the accuracy and the stronger the reliability of the sensor, the greater the weight.

[0031] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0032] Through the multi-source data acquisition module for the railway environment, the system can collect various environmental data along the railway in real time, including track temperature, track stress, surrounding wind speed, rainfall, geological displacement data, etc., and mark the target monitoring area. Compared with the limited coverage and fixed cycle of traditional manual inspections, and the one-sidedness of a single sensor monitoring system, the system realizes all-round and uninterrupted monitoring. For example, distributed fiber optic temperature sensors can accurately obtain the temperatures at different positions along the track, and the Beidou satellite positioning technology combined with ground displacement monitoring stations can real-time master the geological displacement data. The track safety hazard detection module uses intelligent detection equipment to obtain the real-time spatial coordinates of the detection points and the track structure parameter values, and through accurate calculation of the displacement deviation amount, displacement risk coefficient, and track structure risk coefficient, can accurately identify the track sections with potential safety hazards. This comprehensive and real-time monitoring and accurate hazard positioning greatly improve the early warning ability for track safety problems, timely discover potential dangers, and effectively avoid accidents.

[0033] Based on the rich data in the system database, the risk assessment and handling unit accurately assesses the risk level in combination with a scientific analysis method for the impact degree of potential hazards on train operation. For example, by obtaining the train speed limit values and emergency braking distance increments corresponding to different types of track hazards, combining the current running speed and braking performance parameters of the train to calculate the theoretical braking distance, and comparing it with the safe braking distance ahead, the impact degree is determined. Then, based on the impact degree, the basic risk score is determined, and the comprehensive risk score is calculated in combination with the displacement risk coefficient and the track structure risk coefficient, so as to map to obtain the risk level. Based on the accurate risk level, the system formulates a highly targeted handling strategy. When the risk is low, arrange for regular rechecks; when the risk is medium, speed limit in a timely manner and arrange maintenance personnel to be on standby; when the risk is high, immediately apply emergency braking and start emergency repair. This scientific and reasonable risk response mechanism can maximize the safety of train operation and reduce accident losses.

[0034] The data fusion and preprocessing module performs time synchronization, denoising, and normalization on the collected multi-source data. It also uses the weighted average method to fuse data of the same type of physical quantity. This significantly improves the data quality in the system, making data of different types and different acquisition frequencies more accurate and comparable on a unified time scale. For example, the track stress data after denoising by the Kalman filter algorithm can truly reflect the track structure state, and the normalized data is convenient for subsequent analysis and processing. The fused data, such as track temperature data, more accurately represents the actual temperature situation. The high-quality data provides a reliable basis for track safety monitoring and risk assessment, helping managers make more scientific and accurate decisions.

[0035] The intelligent monitoring and precise risk assessment functions of the system reduce the unnecessary workload of manual inspections and the number of equipment maintenance times. By promptly detecting potential hazards and taking appropriate treatment measures, it avoids situations such as train delays and suspensions caused by track failures, ensuring the continuity and efficiency of railway transportation. For example, through regular review plans and targeted maintenance arrangements, human and material resources are reasonably allocated, reducing the operation and maintenance costs. At the same time, with safety guarantees, trains can maintain a stable operating speed, improving the railway's transportation capacity and operation efficiency, bringing significant economic benefits to railway operating enterprises. In the complex and changeable railway operating environment, whether it is extreme weather or geological condition changes, this system can operate stably and play its role. It can continuously monitor the impact of environmental changes on the track, give early warnings of potential risks, and provide strong guarantees for the safe operation of railway infrastructure under various harsh conditions. With the continuous expansion of railway transportation scale and the increase in operating speed, this system can meet the growing safety needs and promote the safe and sustainable development of the railway industry. Brief Description of the Drawings

[0036] Figure 1 It is the working principle diagram of the intelligent monitoring and risk assessment system for railway operating environment described in the present invention;

[0037] Figure 2 It is the step diagram for analyzing the impact degree of potential hazards on train operation in combination with the track structure risk coefficient;

[0038] Figure 3 It is the step diagram for evaluating the risk level and formulating treatment strategies. Detailed Embodiments

[0039] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0040] Please refer to Figures 1 - 3 , the present invention provides a technical solution: an intelligent monitoring and risk assessment system for railway operation environment, the system includes:

[0041] The railway environment multi-source data acquisition module collects various environmental data along the railway in real time, such as track temperature, track stress, surrounding wind speed, rainfall, geological displacement data, etc., and marks each target monitoring area corresponding to the collected data. For example, along a 10-kilometer-long railway section, a target monitoring area is set every 100 meters, with a total of 100 target monitoring areas. Corresponding sensors are arranged in each area. For example, distributed fiber optic temperature sensors are installed on the track to collect track temperature, and anemometers are set around to collect wind speed, etc.

[0042] The track safety hazard detection module determines multiple detection points of the track in each target monitoring area, and uses intelligent detection equipment to obtain the real-time spatial coordinates and track structure parameter values of each detection point according to the set detection period, so as to identify the track sections with potential safety hazards. For example, in the above-mentioned certain target monitoring area, a detection point is set every 5 meters, with a total of 20 detection points. The real-time spatial coordinates of each detection point are obtained by lidar scanning, and the track structure parameter values are obtained by devices such as strain gauges. The specific identification method is: obtain the initial spatial coordinates of each detection point of the track in each target monitoring area from the system database, and calculate the displacement deviation ΔS between the real-time spatial coordinates and the initial spatial coordinates xy . Suppose the initial spatial coordinates of a certain detection point are (100, 200, 300) (unit: meter), and the real-time spatial coordinates become (100.05, 200.03, 300.02), and calculate the displacement deviation according to the formula. Then obtain the allowable displacement deviation threshold S0 from the system database, and calculate the displacement risk coefficient R of each detection point xy . Count the displacement risk coefficients of the tracks in each target monitoring area, and calculate the track structure risk coefficient based on the track structure parameter values of each detection point. If the track structure risk coefficient of the track in a certain target monitoring area is greater than the threshold in the system database, and the sum of the displacement risk coefficients exceeds the set comprehensive risk displacement threshold, then mark the track in this area as a track section with potential safety hazards.

[0043] The risk assessment and handling unit analyzes the impact degree of the hidden danger on the train operation, evaluates the risk level, and formulates corresponding handling strategies for the track sections with potential safety hazards. For example, when it is identified that there is a potential safety hazard in a certain track section, relevant data is obtained from the system database, combined with parameters such as the current running speed of the train, calculate the theoretical braking distance of the train under the influence of this hidden danger, compare it with the safety braking distance ahead, evaluate the impact degree, and then determine the risk level and formulate handling strategies such as regular recheck, speed limit, and emergency braking.

[0044] The present invention will be further described below in conjunction with Embodiments 1 to 5:

[0045] Embodiment 1:

[0046] This embodiment details how to calculate the track structure risk coefficients of each detection point. In practical applications, taking a specific target monitoring area of a certain railway line as an example, the area number x = 5, and the number of track detection points in the area b = 30. Obtain the initial track structure parameter values P of each detection point from the system database xy0 , for example, the initial track structure parameter value P of detection point y = 10 5,10,0 = 100 (assuming this parameter represents the stress value of a certain key component of the track, unit: MPa).

[0047] Use the track structure parameter detection equipment to obtain the real-time track structure parameter values P of each detection point xy , assuming that at a certain moment, the real-time track structure parameter value P of detection point y = 10 5,10 = 105.

[0048] Calculate the track structure parameter change rate C of each detection point xy , according to the formula

[0049] For detection point y = 10, its track structure parameter change rate

[0050] Statistically analyze the track structure parameter change rates of the tracks in the target monitoring area, and calculate the comprehensive coefficient C of the regional track structure change x , Assume that after calculation, the sum of the track structure parameter change rates of other detection points in this area is 0.8, then C5 = 0.05 + 0.8 = 0.85.

[0051] Based on the comprehensive coefficient C of the regional track structure change x and the total displacement risk coefficient R x (assuming the total displacement risk coefficient R5 of this area = 0.6), calculate the track structure risk coefficient R gx , according to the formula R gx = C x ×R x , it can be obtained that R g5 = 0.85×0.6 = 0.51.

[0052] Embodiment 2:

[0053] This embodiment clarifies how to analyze the impact degree of potential hazards on train operation, which helps to accurately judge the threat level of track potential hazards to train operation safety and is an important part of risk assessment. Taking a track section with potential hazards of track geometric dimension overrun as an example, obtain the train speed limit value V corresponding to different types of track potential hazards from the system database lim and the emergency braking distance increment ΔD. For this potential hazard of track geometric dimension overrun, V lim = 80 km / h, ΔD = 50 m.

[0054] Suppose a train's current operating speed V cur = 120 km / h, and the train braking performance parameter K b = 0.15 (this parameter is related to the performance of the train braking system and may vary for different trains).

[0055] Combining these data, calculate the theoretical braking distance D of the train under the influence of this potential hazard cal , according to the formula

[0056]

[0057] First, convert the speed unit to m / s. 120 km / h is approximately 33.33 m / s, then

[0058]

[0059] Suppose the forward safe braking distance D safe = 200 m. Compare the theoretical braking distance D cal with the forward safe braking distance D safe . Since D cal > D safe , it is determined that the impact degree of this potential hazard on train operation is relatively high.

[0060] Example 3:

[0061] This embodiment details the specific method for risk level assessment. By comprehensively considering various factors to determine the risk level. Taking a track section with potential safety hazards as an example, obtain the risk basic score S corresponding to different impact degrees base , the displacement risk coefficient weight w1, and the track structure risk coefficient weight w2 from the system database. Suppose when the impact degree is relatively high, S base = 60 points, w1 = 0.4, w2 = 0.4 (the weights can be determined according to actual experience and expert evaluation).

[0062] The total displacement risk coefficient R x of this track section = 0.7, and the track structure risk coefficient R gx = 0.6.

[0063] Combine these data to calculate the comprehensive risk score S, according to the formula

[0064] S=S base +w1×R x +w2×R gx

[0065] We can get S=60+0.4×0.7+0.4×0.6=60+0.28+0.24=60.52 points.

[0066] The risk level corresponding to each comprehensive risk score interval is obtained from the system database. Assuming that the comprehensive risk score of 60-70 is a medium risk level, the risk level of the track section with safety hazards is obtained through mapping as medium risk.

[0067] Embodiment 4:

[0068] This embodiment formulates corresponding processing strategies according to different risk levels to ensure that appropriate measures can be taken to ensure the safety of train operation when faced with track safety hazards of varying degrees.

[0069] Low-risk situation: Assume that a certain track section is assessed as low-risk, and the basis for determining the risk level is that the comprehensive risk score is in the low-risk range. At this time, the system generates a regular review plan and sets the review period T1 = 7 days (can be adjusted according to actual conditions. Generally, the review period of low-risk track sections is relatively long to balance the detection cost and safety requirements). The system automatically arranges inspection personnel to re-inspect the potential hazard area within 7 days. The inspection personnel use intelligent detection equipment to detect various parameters of the track, such as track geometry, track structure stress, etc., according to the predetermined inspection process, and upload the inspection data to the system for analysis and comparison to determine whether the hidden danger has developed or changed.

[0070] Medium risk: If a track section is assessed as medium risk, the system sends a speed limit instruction to the train dispatching system, limiting the running speed of the train in the potential risk area to V mid =60km / h (speed limit value is determined according to the type and severity of hidden danger). At the same time, arrange maintenance personnel to arrive at the site within T2 = 2 hours for preliminary inspection and maintenance preparation. After arriving at the site, the maintenance personnel will conduct a detailed survey of the track hidden danger area, record the actual condition of the track, such as the degree of track deformation, component damage, etc., and prepare the corresponding maintenance tools and materials, waiting for further maintenance instructions.

[0071] High-risk situation: When a certain track section is evaluated as high-risk, the system immediately sends an emergency braking instruction to the train dispatching system, causing the train to stop within a safe distance. Suppose the current running speed of the train is 100 km / h. According to the braking performance of the train and the safe distance ahead, the train needs to stop within 300 m. After the system sends the emergency braking instruction, the train braking system responds quickly, enabling the train to stop successfully within the safe distance. At the same time, the system activates the emergency plan and organizes the repair team to rush to the scene for emergency repair immediately. The repair team carries professional repair equipment and spare parts. After arriving at the scene, they immediately deal with the hidden dangers, such as replacing damaged track components, repairing track deformation, etc., and restore the safe operation state of the track as soon as possible.

[0072] Example 5:

[0073] The process of data fusion and preprocessing includes processing the collected data to improve data quality and provide reliable data for subsequent track safety monitoring and risk assessment. Specifically:

[0074] ① Time synchronization processing: The data types collected by the multi-source data acquisition module in the railway environment are diverse, and the acquisition frequencies are also different. For example, the acquisition frequency of track temperature data is once per minute, while the acquisition frequency of wind speed data is once every 5 minutes. In the data fusion and preprocessing module, a time synchronization algorithm is used to unify the data to the same time scale with a unified time reference (such as Coordinated Universal Time, UTC). Suppose at a certain moment, the timestamp of the data collected by the track temperature sensor is 10:00:00, and the timestamp of the data collected by the anemometer is 10:05:00. Through the time synchronization algorithm, the timestamp of the wind speed data is adjusted to the same time scale as the track temperature data for subsequent analysis and processing.

[0075] ② Denoising processing: The Kalman filtering algorithm is used to denoise the collected data. Taking track stress data as an example, due to factors such as electromagnetic interference in the field environment, the collected track stress data may contain noise. Suppose the original track stress data shows a curve with large fluctuations during a certain period. Through the Kalman filtering algorithm, using the state equation and observation equation of the system, the track stress data is estimated and predicted to remove noise interference, and a relatively smooth and accurate track stress data curve is obtained, improving the accuracy of the data.

[0076] ③ Normalization processing: The denoised data is normalized to map the data to the [0, 1] interval. Taking track temperature data as an example, suppose the collected track temperature range is 0 - 60 °C. Through the normalization formula

[0077]

[0078] where x is the original data, x minis the data minimum value, x max is the data maximum value, and the track temperature data is normalized. For example, if the track temperature at a certain moment is 30°C, the normalized value is which is convenient for subsequent data analysis and processing, enabling different types of data to be compared and analyzed on the same scale.

[0079] ④ Fusion of data of the same type of physical quantity (taking track temperature as an example): For data of various physical quantities such as track temperature and track stress, the weighted average method is used for fusion. In a certain target monitoring area, 5 track temperature sensors are set up to obtain more comprehensive and accurate track temperature information. At a certain moment, the track temperature data collected by these 5 sensors are T1 = 28°C, T2 = 27°C, T3 = 29°C, T4 = 26°C, and T5 = 28°C respectively. Weights are determined according to the accuracy and reliability of each sensor, and sensors with higher accuracy and stronger reliability have larger weights. After evaluating the performance of the sensors, it is determined that the weight w1 of sensor 1 is 0.3, the weight w2 of sensor 2 is 0.2, the weight w3 of sensor 3 is 0.2, the weight w4 of sensor 4 is 0.15, and the weight w5 of sensor 5 is 0.15. According to the weighted average method formula

[0080]

[0081] The fused track temperature data T = 0.3×28 + 0.2×27 + 0.2×29 + 0.15×26 + 0.15×28 = 8.4 + 5.4 + 5.8 + 3.9 + 4.2 = 27.7°C. Through this fusion method, the data information of multiple sensors is comprehensively considered, effectively improving the accuracy and representativeness of the track temperature data, more truly reflecting the actual temperature condition of the track in this area, and providing a more reliable data basis for track safety monitoring.

[0082] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the term "including", "comprising" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device.

[0083] Although embodiments of the present invention have been shown and described, it will be understood by those of ordinary skill in the art that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of the present invention, and the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. Railway operation environment intelligent monitoring and risk assessment system, characterized by: include: Railway environment multi-source data acquisition module, used to collect various environmental data along the railway in real time, including but not limited to track temperature, track stress, surrounding wind speed, rainfall, geological displacement data, and mark the corresponding area of ​​the collected data as each target monitoring area; The track safety hazard detection module is used to determine multiple detection points on the track in each target monitoring area, obtain the real-time spatial coordinates and track structure parameter values ​​of each detection point by using intelligent detection equipment within the set detection period, and identify the track section with safety hazards; the specific identification method is: obtain the initial spatial coordinates of each detection point on the track in each target monitoring area from the system database, calculate the displacement deviation ΔS between the real-time spatial coordinates of each detection point and the initial spatial coordinates based on the real-time spatial coordinates of each detection point xy , where x represents the target monitoring area number x=1, 2, ..., a, a is a positive integer greater than 2, and y represents the number of each detection point, y=1, 2, ..., b, b is a positive integer greater than 2; Obtain the allowable displacement deviation threshold S0 from the system database and calculate the displacement risk coefficient of each detection point Statistics are collected on the displacement risk coefficient of the track in each target monitoring area; the track structure risk coefficient is calculated based on the track structure parameter values ​​of each detection point; the track structure risk coefficient threshold is obtained from the system database; if the track structure risk coefficient of the track in a target monitoring area is greater than the threshold, and the sum of the displacement risk coefficients exceeds the set comprehensive risk displacement threshold, the track in this area is marked as a track section with safety hazards; The risk assessment and processing unit is used to analyze the impact of hidden dangers on train operation, assess the risk level, and formulate corresponding processing strategies for track sections with safety hazards.

2. The railway operation environment intelligent monitoring and risk assessment system according to claim 1 is characterized in that: The specific calculation method for calculating the track structure risk coefficient of each detection point is as follows: The initial track structure parameter value P of each detection point in each target monitoring area is obtained from the system database xy0 ; According to the real-time track structure parameter value P of each detection point xy , calculate the change rate of track structure parameters at each detection point Statistics on the change rate of track structure parameters in each target monitoring area, and calculate the comprehensive coefficient of regional track structure change Based on the comprehensive coefficient of regional track structure change C x And the sum of displacement risk factors Calculate the track structure risk factor R gx =C x ×R x .

3. The railway operation environment intelligent monitoring and risk assessment system according to claim 2 is characterized in that: The specific analysis method for analyzing the impact of hidden dangers on train operation is as follows: Obtain the train speed limit values ​​V corresponding to different types of track hazards from the system database lim , emergency braking distance increment ΔD; determine the corresponding train speed limit value and emergency braking distance increment according to the type of potential safety hazard on the track section; combined with the current train running speed V cur , Train braking performance parameters K b , calculate the theoretical braking distance of the train under the influence of this hidden danger Comparison of theoretical braking distance D cal Safe braking distance D safe , if D cal >D safe , then the impact is judged to be high, otherwise the impact is low.

4. The railway operation environment intelligent monitoring and risk assessment system according to claim 3 is characterized in that: The specific assessment method for the assessment risk level is as follows: Obtain the risk base scores S corresponding to different impact levels from the system database base , displacement risk factor weight w1, track structure risk factor weight w2; Determine the risk base score S based on the impact of hidden dangers on train operation base ; Combined with the total displacement risk coefficient R of the track section with potential safety hazards x , Track structure risk factor R gx , calculate the comprehensive risk score S = S base +w1×R x +w2×R gx ; Obtain the risk level corresponding to each comprehensive risk score interval from the system database, and map it to obtain the risk level of the track section with safety hazards.

5. The railway operation environment intelligent monitoring and risk assessment system according to claim 4 is characterized in that: The specific method for formulating the processing strategy is as follows: When the risk level is low, a regular review plan is generated, the review cycle T1 is set, and inspection personnel are arranged to re-inspect the potential hazard area within the review cycle; when the risk level is medium, a speed limit instruction is sent to the train dispatching system to limit the running speed of the train in the potential hazard area to V mid At the same time, arrange maintenance personnel to arrive at the scene within T2 time to conduct preliminary inspection and maintenance preparation; when the risk level is high, immediately send an emergency braking command to the train dispatching system to stop the train at a safe distance, and at the same time activate the emergency plan and organize a repair team to rush to the scene for emergency repairs.

6. The railway operation environment intelligent monitoring and risk assessment system according to claim 1 is characterized in that: In the railway environment multi-source data acquisition module, when collecting track temperature data, distributed optical fiber temperature sensors are used for collection. The collection principle is: A light pulse is emitted into the optical fiber. When the light pulse is transmitted in the optical fiber, backscattered light will be generated due to the inhomogeneity of the optical fiber material, which contains information related to temperature. By detecting the spectral characteristics of the backscattered light and using the relationship between the intensity ratio of Stokes light and anti-Stokes light and temperature, the temperature value T at different positions along the track is calculated. i , i is the measurement point number on the optical fiber, i = 1, 2, ..., c, c is a positive integer greater than 2.

7. The railway operation environment intelligent monitoring and risk assessment system according to claim 1 is characterized in that: In the railway environment multi-source data acquisition module, when collecting geological displacement data, Beidou satellite positioning technology is used in combination with ground displacement monitoring stations for collection. The collection principle is: The ground displacement monitoring station is equipped with multiple monitoring landmarks, each of which is equipped with a Beidou positioning terminal. The Beidou positioning terminal receives Beidou satellite signals and obtains the real-time three-dimensional coordinates (X j ,Y j ,Z j ), j is the number of the monitoring mark point, j = 1, 2, ..., d, d is a positive integer greater than 2; by comparing the real-time three-dimensional coordinates of the monitoring mark point with the initial three-dimensional coordinates (X j0 ,Y j0 ,Z j0 ), and the geological displacement ΔX is calculated j =X j -X j0 , ΔY j =Y j -Y j0 , ΔZ j =Z j -Z j0 , in order to obtain geological displacement data along the railway.

8. The intelligent monitoring and risk assessment system for rail operation environment according to claim 1 is characterized in that: When the intelligent detection device obtains the real-time spatial coordinates of each detection point, the laser radar scanning technology is used, and the specific implementation method is as follows: The laser radar emits a laser beam to scan the track. The laser beam is reflected back after encountering the track surface and is received by the laser radar. The distance between the laser radar and the track detection point is calculated based on the laser flight time t and the speed of light c. At the same time, the laser radar angle measurement device is used to obtain the laser beam emission angle θ and elevation angle Through the principle of triangulation, combined with the installation position coordinates of the laser radar (X0, Y0, Z0), the real-time spatial coordinates (X, Y, Z) of each detection point are calculated. The calculation formula is: Z=Z0+L×cosθ.

9. The intelligent monitoring and risk assessment system for rail operation environment according to claim 1 is characterized in that: The system also includes a data fusion and preprocessing module, which is used to fuse and preprocess the data collected by the railway environment multi-source data collection module, specifically including: Time synchronization is performed on data of different types and different acquisition frequencies to unify the data to the same time scale; the Kalman filter algorithm is used to denoise the collected data to remove noise interference in the data and improve the accuracy of the data; the denoised data is normalized and mapped to the [0, 1] interval to facilitate subsequent data analysis and processing.

10. According to the intelligent monitoring and risk assessment system for the rail operation environment of claim 9, in the data fusion process, the weighted average method is used to fuse the similar physical quantity data such as rail temperature and rail stress. The specific calculation method is: Assume that the same physical quantity data collected by n sensors are x1, x2, ..., x n , the corresponding weights are w1,w2,…,w n ,and The fused data Weight w i Determined according to the accuracy and reliability of the sensor, the sensor with higher accuracy and stronger reliability has a greater weight.

Images