Safety detection system for high-speed rail transit corollary equipment structure

Abstract

The invention discloses a safety detection system for a high-speed rail transit corollary equipment structure. The safety detection system comprises an excitation response module, an infrared heat source image acquisition module, a parameter monitoring module, an image preprocessing module, a heat source feature extraction module and a structure anomaly recognition module. In the train operation process, the system excites trackside equipment structure response through train body aerodynamic disturbance, thermal response images are collected through high-frame-rate infrared imaging, and image standardization processing is carried out based on disturbance intensity and the relative distance. And the system further extracts thermal response characteristics of the equipment structure area, and compares the thermal response characteristics with a normal template to realize abnormal structure identification and positioning. Under the condition that train operation is not affected, non-contact, high-precision and intelligent detection of the structure state of the trackside equipment is achieved, and the method has the advantages of being flexible in deployment, accurate in recognition, high in real-time performance and the like and is suitable for rail transit operation and maintenance scenes.

Description

Technical Field

[0001] The present invention relates to the technical field of high-speed rail transit safety detection, and in particular to a safety detection system for high-speed rail transit supporting equipment structures. Background Art

[0002] With the large-scale construction of high-speed railways and urban rail transit systems, the extensive trackside infrastructure (such as signal control boxes, communication equipment, and power cabinets) deployed along the lines has become a crucial component in ensuring train safety. This equipment often operates outdoors for extended periods, making it susceptible to various factors, including the natural environment, equipment aging, and external shocks. These issues can lead to structural loosening, shell cracking, and abnormal internal heating. If these structural defects go undetected, they can cause equipment failure. Failure and damage to fixed structures can lead to trains being drawn into the tracks during high-speed operation, causing train failures and posing a significant safety hazard.

[0003] At present, the following technical methods are mainly used for the detection and inspection of trackside equipment: At present, the following technical methods are mainly used for the detection and inspection of trackside equipment: 1. Manual visual inspection, in which operation and maintenance personnel conduct regular offline inspections, and identify whether the equipment has structural damage or abnormalities through visual inspection, knocking, or infrared handheld device detection. This type of method relies on manual experience, and the detection results are easily affected by human subjective judgment. There are problems such as missed detection, misjudgment, and low efficiency, which make it difficult to meet the operation and maintenance needs of high-density and high-speed rail lines. 2. Fixed monitoring system, video surveillance equipment is installed at specific locations to monitor key trackside equipment 24 hours a day. This method is suitable for anomaly monitoring in a small area and key points, but due to its limited coverage, it cannot conduct comprehensive inspections of trackside equipment along the entire line. In addition, the fixed camera has a single viewing angle and is difficult to adapt to the actual situation where there are many types of equipment and diverse deployment methods.

[0004] Therefore, current technology still lacks a technical means to monitor the structural safety issues of trackside equipment in a timely manner to ensure the safety of high-speed rail operation. Summary of the Invention

[0005] The purpose of the present invention is to provide a safety detection system for the structure of supporting equipment of high-speed rail transit, which has the advantages of not requiring additional excitation devices, being able to dynamically collect high-quality infrared thermal images, and having the ability to intelligently identify and locate structural anomalies.

[0006] The above technical objectives of the present invention are achieved through the following technical solutions:

[0007] A safety detection system for high-speed rail transit supporting equipment structure, comprising:

[0008] The excitation response module is used to stimulate the structural response of the trackside equipment in the passing area through the aerodynamic disturbances naturally generated by the train body during the operation of the high-speed train;

[0009] an infrared heat source image acquisition module, disposed on the side or lower area of ​​the train body, for acquiring an infrared heat source response image of the trackside equipment under aerodynamic disturbance excitation when the train passes by the trackside equipment;

[0010] A parameter monitoring module, comprising an excitation monitoring unit and a distance measurement unit. The excitation monitoring unit is used to collect information on the intensity of aerodynamic disturbances during train operation; the distance measurement unit is used to measure the relative spatial distance between the train and the trackside equipment.

[0011] An image preprocessing module, configured to perform standardization processing on the infrared heat source response image based on the aerodynamic disturbance intensity information and the relative spatial distance information to obtain a heat source response map;

[0012] a heat source feature extraction module, configured to extract thermal response features of various structural areas of the trackside equipment from the heat source response map;

[0013] The structural anomaly identification module is used to compare and analyze the thermal response characteristics with the preset normal state heat source response template, identify whether there is a structural anomaly in the trackside equipment, and output the anomaly type and positioning coordinate information.

[0014] Further configuration: the infrared heat source image acquisition module specifically includes:

[0015] A high frame rate image acquisition unit is used to continuously capture multiple frames of infrared thermal images at a frame rate not lower than a preset frame rate while the train passes the target trackside equipment;

[0016] An image window adjustment unit, configured to dynamically adjust the spatial range of image acquisition by the high-frequency image acquisition unit according to the relative spatial distance information provided by the device distance measurement module, so as to ensure the coverage integrity of the target device in the infrared thermal image;

[0017] The viewing angle offset correction unit is used to calculate the projection angle of the trackside equipment in the infrared thermal image based on the relative position relationship between the trackside equipment and the high-frequency image acquisition unit, and obtain the infrared heat source response image after geometric correction processing of the infrared thermal image.

[0018] Further configuration: the incentive monitoring unit includes:

[0019] The acceleration estimation subunit is used to obtain the acceleration change data of the train body in the lateral or vertical direction during the operation of the train, and estimate the current aerodynamic disturbance intensity around the train body based on the acceleration data;

[0020] The environmental parameter calibration subunit is used to obtain external meteorological parameters in the environment where the train is located, and to correlate the external environmental parameters with the acceleration estimation results to correct and compensate the estimated disturbance intensity to obtain gas disturbance intensity information.

[0021] Further configuration: the distance measurement unit includes:

[0022] The train positioning subunit is used to obtain the real-time position information of the current train in the track coordinate system based on the inertial navigation system, odometer sensor or on-board track positioning system carried by the train;

[0023] The equipment location information calling subunit is used to extract the standard layout position of the target trackside equipment ahead of the train from the preset track infrastructure map database;

[0024] The relative distance calculation unit is used to calculate the relative spatial distance between the train and the trackside equipment according to the real-time position information of the train and the standard layout position to obtain relative spatial distance information.

[0025] Further configuration: the image preprocessing module specifically includes:

[0026] A spatial distance correction unit is configured to adjust the scale of each frame of the infrared heat source image according to the relative spatial distance information corresponding to each frame of the infrared heat source response image to obtain a spatial correction image, so as to make the scale of the area corresponding to the trackside equipment in each frame of the infrared heat source image consistent;

[0027] The normalization unit is used to correct each pixel value representing the heat source response intensity in the spatial correction image according to the gas disturbance intensity information to obtain a heat source response map.

[0028] Further setting: the step of correcting each pixel value representing the heat source response intensity in the spatial correction image according to the gas disturbance intensity information to obtain the heat source response map specifically includes the following steps:

[0029] extracting thermal response image data of the area corresponding to the trackside equipment from the spatially corrected image, and identifying the thermal response intensity corresponding to each pixel value;

[0030] The thermal response correction parameter is calculated based on the gas disturbance intensity information and the preset disturbance-thermal response mapping model;

[0031] The standardized thermal response intensity is obtained by correcting the thermal response intensity corresponding to each pixel value according to the thermal response correction parameter;

[0032] The pixel values ​​corresponding to the normalized thermal response intensity are updated back into the spatially corrected image to generate a heat source response map.

[0033] Further configuration: the heat source feature extraction module includes:

[0034] An area division unit, used to divide the area corresponding to the trackside equipment into multiple structural areas and encode each structural area;

[0035] A time series extraction unit is used to extract a time feature of each structural region based on a time series of multiple frames of thermal response maps, wherein the time feature represents a characteristic of how the thermal response intensity of each structural region changes over time;

[0036] a distribution pattern extraction unit, configured to extract heat source pattern features of each structural region, wherein the heat source pattern features include concentration, heat source symmetry, and heat flow variability;

[0037] The intensity feature extraction unit is used to extract the intensity feature of each structural area, wherein the intensity feature includes a thermal response peak value and a thermal response fluctuation amplitude.

[0038] The feature output unit outputs the time feature, intensity feature and heat source pattern feature as thermal response features to the structural anomaly recognition module.

[0039] Further configuration: the structural anomaly identification module includes:

[0040] A comparison and analysis unit is used to calculate the similarity between the thermal response characteristics and the standard response characteristics in the normal state heat source response template through a feature vector comparison method. If any similarity is lower than a preset threshold, it is determined that there is a structural abnormality;

[0041] a type recognition unit that determines the type of anomaly based on the type of thermal response features whose similarity is lower than a preset threshold;

[0042] The abnormal position positioning unit obtains the corresponding code of the structural area determined by the comparison and analysis unit to have structural abnormality as the abnormal area position, and generates positioning coordinate information in combination with the standard layout position of the trackside equipment.

[0043] In summary, the present invention has the following beneficial effects:

[0044] The excitation process is completed based on the natural disturbances caused by train operation, without the need for additional active excitation devices or trigger mechanisms, which simplifies the system structure and reduces equipment costs. The excitation method can be adapted to different lines and environmental conditions as the train moves, and has good deployment flexibility and engineering feasibility.

[0045] Dynamic imaging is performed using an infrared heat source image acquisition module. By configuring a high-frame-rate acquisition unit, a window adjustment unit, and a perspective correction unit, the thermal imagery provides complete and stable coverage of the trackside equipment area. This ensures image clarity and structural integrity even under dynamic conditions, such as high-speed train operation and constantly changing perspectives. A dual monitoring mechanism for disturbance intensity and relative spatial distance is introduced, improving the quantification accuracy of aerodynamic disturbances through acceleration estimation and environmental calibration. Distance correction is performed by combining train positioning with trackside equipment map location data, achieving precise standardization of equipment thermal responses and providing a solid foundation for image comparison across time and equipment.

[0046] The image preprocessing module implements spatial and thermal value normalization processing, so that infrared images under different environments, different distances, and different speed conditions are unified into physically comparable heat source response maps, thereby significantly improving the accuracy and stability of subsequent feature extraction and comparison analysis. The heat source feature extraction module obtains multi-dimensional response characteristics at the structural level, including time evolution characteristics, heat flux distribution characteristics, thermal response intensity characteristics, etc., which comprehensively reflect the thermal response patterns of various structural areas of the trackside equipment under disturbance excitation, and help identify potential local anomalies or structural degradation problems.

[0047] The structural anomaly identification module has the ability to match templates and classify and locate anomalies, and can realize quantitative judgment of the structural status of the equipment. Once the thermal response characteristics are found to deviate from the normal template, it can automatically determine the type of anomaly and output the precise coordinate position, providing a structured and visual inspection basis for the back-end operation and maintenance system. The entire system can complete the equipment acquisition, processing and identification closed loop during the normal operation of the train without stopping operations or manual intervention. It has high-frequency, wide-coverage, and low-cost inspection capabilities, which will help build a full-life cycle equipment health management platform for future smart railways. The system architecture of the present invention is modular and highly scalable. It can be integrated into different types of trains such as high-speed railways and urban railways. It is also suitable for new lines and existing line reconstruction projects. It has significant engineering promotion value and industry application prospects. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 It is an overall structural block diagram of the embodiment. DETAILED DESCRIPTION

[0049] The present invention will be further described in detail below with reference to the accompanying drawings.

[0050] Example:

[0051] like Figure 1As shown, the proposed system is suitable for real-time inspection tasks during high-speed train operation. It can remotely and contactlessly identify structural defects in trackside infrastructure, such as communication equipment, signal boxes, and power control cabinets, without disrupting normal train operation. Integrated and installed on the train body, the system relies on aerodynamic disturbances generated by the train's motion to guide the equipment to generate thermal response signals. Combined with infrared thermal imaging, spatial positioning, and thermal map analysis, it forms a complete process for identifying structural anomalies.

[0052] Through standardized processing and feature extraction of infrared heat source response images, the present invention can accurately identify different types of structural defects, including but not limited to: poor box sealing, loose structure, internal overheating, etc., and can realize abnormal type judgment and spatial positioning output. It has the advantages of high detection accuracy, fast response speed, easy deployment, and applicability to high-speed operation environments. It is suitable for application scenarios such as intelligent track inspection and railway infrastructure safety monitoring. The specific plan is as follows:

[0053] A safety detection system for high-speed rail transit supporting equipment structure, comprising:

[0054] The excitation response module is used to stimulate the structural response of the trackside equipment in the passing area through the aerodynamic disturbances naturally generated by the train body during the operation of the high-speed train;

[0055] an infrared heat source image acquisition module, disposed on the side or lower area of ​​the train body, for acquiring an infrared heat source response image of the trackside equipment under aerodynamic disturbance excitation when the train passes by the trackside equipment;

[0056] A parameter monitoring module, comprising an excitation monitoring unit and a distance measurement unit. The excitation monitoring unit is used to collect information on the intensity of aerodynamic disturbances during train operation; the distance measurement unit is used to measure the relative spatial distance between the train and the trackside equipment.

[0057] An image preprocessing module, configured to perform standardization processing on the infrared heat source response image based on the aerodynamic disturbance intensity information and the relative spatial distance information to obtain a heat source response map;

[0058] a heat source feature extraction module, configured to extract thermal response features of various structural areas of the trackside equipment from the heat source response map;

[0059] The structural anomaly identification module is used to compare and analyze the thermal response characteristics with the preset normal state heat source response template, identify whether there is a structural anomaly in the trackside equipment, and output the anomaly type and positioning coordinate information.

[0060] In an embodiment of the present invention, the excitation response module does not include a specific physical structure. Specifically, it utilizes the aerodynamic disturbances naturally generated by the train during operation as an excitation source to implement contactless structural excitation on the trackside equipment in the area it passes through to guide it to respond.

[0061] When a train runs at a high speed (such as 250 km / h and above), a high-intensity aerodynamic disturbance field will be formed around the leading edge of the train and the sides of the car body due to air compression, flow effects and boundary layer disturbances. These disturbances include turbulent wakes, pressure pulsations and lateral / vertical vortex structures. Especially when the train passes close to the equipment area, the disturbance will be transmitted to the surface of the equipment in the form of shock waves or vibration waves, thereby triggering the response behavior of the equipment structure. This response mainly manifests in the following categories: microstructural vibration, such as slight deformation of the equipment housing or bracket under instantaneous pressure; low-frequency mechanical resonance of internal connecting parts (bolts, connecting plates, etc.); temporary thermal abnormal changes in surface temperature due to small deformations or stress concentration areas. Since these structural response processes are usually accompanied by subtle changes in heat conduction or radiation, combined with high-sensitivity infrared thermal imaging methods, the changing characteristics of the equipment structure state can be perceived without touching the equipment. In the present invention, the excitation response module is a purely passive structure. It does not rely on active excitation sources outside the vehicle body (such as mechanical knocking, electromagnetic pulses, etc.). It uses natural aerodynamic disturbances to replace traditional physical excitation devices, which not only reduces the system complexity and maintenance costs, but also improves the safety and detection efficiency during train operation.

[0062] In this embodiment of the present invention, the infrared heat source image acquisition module, the core data acquisition component of the entire system, is installed on the side or bottom area of ​​the high-speed train body. It is used to collect infrared heat source response image sequences generated by trackside equipment under the influence of aerodynamic disturbances when the train passes by the equipment. This module has a compact structure, strong vibration resistance, and high response speed. It mainly includes the following three functional units:

[0063] 1. High frame rate image acquisition unit

[0064] The high-frame-rate image acquisition unit uses an uncooled infrared focal plane detector (such as a microbolometer) with high temporal resolution. It supports the continuous acquisition of multiple frames of infrared thermal images at a preset frame rate (for example, 200 frames per second) during high-speed operation of the train. The optical field of view of the unit is spatially matched with the equipment layout interval to ensure that when the train passes the key positions of the trackside equipment, the thermal imaging equipment can complete high-density image acquisition in a short time. This high-frame-rate acquisition capability ensures: obtaining information on changes in thermal response before, during, and after the disturbance; effectively suppressing image blur, ghosting, or frame loss problems; and supporting subsequent dynamic analysis and trend modeling of thermal features. The thermal image acquisition data is transmitted to the back-end image processing module via a high-speed interface (such as Camera Link or GigE Vision) to maintain the overall real-time performance of the system.

[0065] 2. Image window adjustment unit

[0066] This unit is used to dynamically adjust the spatial window of image acquisition according to the real-time spatial relative distance between the trackside equipment and the infrared acquisition equipment during train operation.

[0067] The image window adjustment unit uses position information provided by the device distance measurement module to calculate the distance between the current device and the train in real time. Based on this information, it performs the following operations: automatically adjusts the infrared lens focal length or field of view to keep the device centered or fully visible in the image; controls the start and end points of the acquisition frame window to avoid early or delayed acquisition; and dynamically adjusts the region of interest (ROI) to improve image resolution utilization. For example, when the distance between the train and the device is less than a set threshold, the system automatically reduces the image window to avoid close-range imaging distortion; when the distance is greater, the window is expanded to ensure that the device is not cropped. This function allows the system to adapt to device deployment density, train speed fluctuations, and differences in device structure, ensuring image availability and integrity.

[0068] 3. Viewing angle deviation correction unit

[0069] Due to the spatial offset and projection angle between the infrared acquisition unit installed on the train and the trackside equipment, directly acquired infrared images often suffer from angular distortion, scale distortion, and contour tilt, which is not conducive to subsequent heat source feature comparison and template matching. To this end, the perspective offset correction unit uses a perspective transformation algorithm to perform geometric correction processing on the infrared image based on the relative position coordinates between the train and the equipment, the installation height, and the tilt angle. Its basic process includes:

[0070] Calculate the projection angle of the device in the image;

[0071] Use affine transformation or four-point mapping to rotate, scale, and stretch images;

[0072] Output the corrected infrared thermal image, namely the "heat source response image".

[0073] This correction process ensures that the device presents a standardized geometric structure in the image at different shooting angles and distances, ensuring the consistency of the position and distribution of heat source features in the map, and enhancing the accuracy of subsequent thermal map comparisons. In summary, the infrared heat source image acquisition module's "high-speed imaging + distance adjustment + projection correction" architecture ensures that the system can still obtain high-quality thermal response images even at high speeds, providing stable and reliable raw data support for structural defect identification.

[0074] In this embodiment of the present invention, the parameter monitoring module, a key subsystem supporting infrared image standardization processing, is primarily used to obtain two key pieces of information during train operation: the intensity of aerodynamic disturbances and the relative distance between the train and trackside equipment. This module comprises two subsystems: an excitation monitoring unit and a distance measurement unit.

[0075] The excitation monitoring unit is used to evaluate the aerodynamic disturbance intensity index generated during train operation. This index will be used to normalize and correct the thermal response intensity in subsequent images. This unit includes the following two sub-units:

[0076] The acceleration estimation subunit is deployed at multiple locations in the lateral and vertical directions of the train body (such as the front, middle and rear of the train body) to collect acceleration change information of the train body structure under high-speed operation. Specifically, the acceleration fluctuation data of the train body in the X (lateral) and Z (vertical) directions are recorded in real time through a three-axis acceleration sensor array. The acceleration time series is formed at a frequency of 500 times per second:

[0077] a x (t), a z (t)

[0078] The system then estimates the disturbance intensity based on the following empirical model:

[0079]

[0080] Here, A represents the estimated value of the current external disturbance intensity of the train body. This disturbance intensity is highly correlated with the degree of air turbulence generated outside the train. This data is used in subsequent image processing to estimate the excitation background conditions for the thermal response of trackside equipment.

[0081] Environmental parameter calibration subunit: Since the aerodynamic disturbance around the vehicle body may be affected by environmental factors (such as natural wind speed and wind direction), the system introduces an environmental parameter calibration subunit to improve the estimation accuracy. This unit obtains environmental data in the following two ways: real-time collection of wind field data by the rooftop meteorological sensor array (anemometer, wind vane); or access to the track section meteorological data interface provided by the onboard train operation management system (TMS). The parameters obtained include: real-time wind speed V wind , wind direction angle θ wind The system corrects this data with the estimated disturbance intensity A using the following calibration model (which can be linear or empirically weighted):

[0082] A′=A-k1·V wind ·cos(θ wind -θ train )

[0083] Where: A′ is the corrected disturbance intensity index; θ train is the direction of train operation; k1 is the empirical correction coefficient.

[0084] The distance measurement unit is used to obtain the spatial relative distance information between the train and the trackside equipment it is about to pass. It consists of the following three sub-units:

[0085] The train positioning subunit integrates multiple position sensing components, including: a high-precision GNSS receiver for obtaining the longitude and latitude position information of the train in the track coordinate system; an inertial navigation system (INS) for providing continuous position compensation in a short period of time to improve stability in tunnels and obstructed areas; and a wheel pulse meter or odometer sensor for providing cumulative distance traveled correction information. The system obtains the train's real-time position P through a multi-source fusion positioning algorithm (such as the extended Kalman filter). train (t), with an accuracy of up to sub-meter level.

[0086] The device location information calling subunit of the present invention presets a track infrastructure map database, which records the standard layout positions of all detection target devices, including: device code; track segment number; center coordinates (projection coordinates or longitude and latitude) P dev ,The system calls the location of the target device that is about to pass from the database based on the current position and driving direction of the train.

[0087] According to the current position of the train P train With the target device position P dev , the system calculates the spatial distance D between the two in real time, that is:

[0088] D=||P train -P dev ||

[0089] This result serves as the input parameter for image window adjustment and scale normalization, ensuring that the target device is accurately captured and standardized during image acquisition. In summary, the parameter monitoring module, through dual-channel information acquisition and real-time calculation, provides two key fundamental variables for system operation (disturbance intensity and relative distance). These form the input starting point for the image processing chain, ensuring the entire detection system's environmental adaptability and positioning accuracy.

[0090] In this embodiment of the present invention, the image preprocessing module is used to standardize the scale and heat intensity of the original infrared heat source image to eliminate image inconsistencies caused by changes in spatial distance and disturbance intensity during train operation, providing a unified heat source response map for subsequent heat source feature extraction and anomaly identification. This module mainly includes a spatial distance correction unit and a normalization unit.

[0091] The spatial distance correction unit, because the relative distance between the train and the trackside equipment continuously changes during operation, the display ratio of the same equipment in the thermal image will change in different frames, affecting the subsequent image comparison and thermal feature consistency. Therefore, this unit performs spatial scale correction on the image based on the relative spatial distance information of the equipment corresponding to each frame (provided by the distance measurement module). The correction method is as follows:

[0092] For each frame of infrared heat source response image, let the original image be I(x, y) and the corresponding distance be D. The system calculates the image scaling factor s based on the preset reference distance D0:

[0093]

[0094] Then perform a scaling transformation on the image:

[0095] I s (x′,y′)=I(s·x,s·y)

[0096] Among them, I s (x′, y′) represents the scale-corrected image, representing the actual size of the device area displayed in the image at a uniform reference distance. This unit ensures that the projected area of ​​the same device type is consistent across all images, facilitating subsequent spatial alignment and atlas synthesis.

[0097] Normalization unit: Because the thermal response intensity is directly affected by the intensity of the disturbance excitation, the thermal response value of the same device under different train disturbance conditions may shift. To this end, this unit introduces the disturbance intensity information A′ to perform intensity normalization on the thermal value of each pixel in the image, obtaining a stable and comparable heat source response map.

[0098] The normalization steps are as follows:

[0099] Step 1: Thermal response region extraction

[0100] Correct the image I from the spatial scale s In (x, y), extract the image data corresponding to the preset device area, which is recorded as:

[0101]

[0102] Where R(x, y) represents the set of pixels within the device area, and each pixel value T(x, y) represents the thermal response intensity.

[0103] Step 2: Perturbation-thermal response mapping model call

[0104] The system is based on a disturbance-thermal response mapping model constructed through experimental fitting or simulation:

[0105] T std =f(T, A′)

[0106] Where: T: original thermal response value; A′: disturbance intensity; T std : the corrected standard thermal response value; f(.): the mapping function, which can be a linear function, a piecewise function, or an empirical formula. The mapping model takes into account the nonlinear effects of disturbance intensity on the thermal response, such as delayed response under low disturbances and enhanced response under high disturbances.

[0107] Step 3: Pixel value correction

[0108] Perform mapping correction on each pixel value T(x, y)∈R to obtain a standardized pixel value:

[0109] T std (x, y) = f(T(x, y), A′)

[0110] Step 4: Heat source response map generation

[0111] The above corrected standard calorific value T std (x, y) is replaced back to the device area to form a new heat source response map:

[0112]

[0113] The final output image I std That is, the heat source response map, which has standardized characteristics of consistent scale and intensity, and meets the requirements of comparative analysis across devices, frames, and environments.

[0114] This image preprocessing module effectively solves the problem of thermal map comparability caused by equipment image changes and inconsistent excitation during train operation through dual standardization of spatial scale and thermal intensity, providing unified input for the subsequent structural anomaly recognition module.

[0115] In one embodiment of the present invention, the heat source feature extraction module is used to perform structured analysis on standardized infrared heat source response maps, extracting the thermal response behavior characteristics of trackside equipment in different structural regions, and providing basic data support for subsequent structural anomaly identification. This module primarily includes the following five functional units: a region division unit, a time series extraction unit, a distribution pattern extraction unit, an intensity feature extraction unit, and a feature output unit. Each unit processes data sequentially according to the data flow order.

[0116] The area division unit is used to identify the main structural components corresponding to the trackside equipment in the heat source response map and divide it into several functional structural areas.

[0117] The partitioning method can be based on one of the following two methods: Template matching method: using a predefined structural template (such as a distribution box partition diagram) to slice the area for the standardized equipment map; Image segmentation method: using an image segmentation algorithm based on grayscale gradient, edge detection or heat flow features to automatically identify the structural boundaries in the map. The partitioning result is a set of structural regions {R1, R2, ..., R n}, each region is given a unique code ID i , used for subsequent feature binding and position association.

[0118] The time series extraction unit uses the standardized heat source response maps obtained continuously in the previous section to extract the thermal response behavior of each structural region over time. The specific method is as follows: for each structural region RiR_iRi, the average thermal response intensity of the corresponding position in the continuous frame image is extracted to form a time series:

[0119]

[0120] Where: T i (t): average thermal response value of the i-th region in the t-th frame; Normalized atlas pixel value in frame t; |R i |: Number of pixels in the area.

[0121] Based on this sequence, the system can extract time-related features such as rise / fall rates, peak occurrence times, and duration of heating or cooling cycles. These temporal features can reveal potential defects in structural regions, such as delayed response and abnormal heat dissipation.

[0122] Distribution pattern extraction unit: This unit analyzes the spatial distribution characteristics of heat sources within each structural area and extracts its thermal field pattern characteristics, including the following three dimensions:

[0123] 1. Heat source concentration

[0124] Defined as the percentage of pixels with higher-than-average heat values ​​within a region, reflecting the degree of heat source focus:

[0125]

[0126] Among them, C i : heat source concentration of the i-th structural area; Region R i The average heat value in the area; numerator: the number of pixels with a temperature higher than the average; denominator: the total number of pixels in the area.

[0127] 2. Heat source symmetry

[0128] The symmetry of the thermal field distribution is measured by comparing the difference in pixel values ​​on both sides of the symmetry axis in the region:

[0129]

[0130] Where (x′, y′) is a pixel symmetrical to (x, y) about the center of the region, S i : The symmetry score of the i-th structural region. The closer the value is to 1, the more symmetrical it is. (x′, y′): The symmetric point of the pixel (x, y) about the central axis of the region. The absolute value represents the difference in thermal intensity between the left and right pixels.

[0131] 3. Heat flow variability

[0132] The degree of thermal field non-uniformity is calculated using the regional internal gradient change index:

[0133]

[0134] F i : The gradient change intensity of heat source distribution in region i; Transverse and longitudinal temperature gradients (can be estimated by the Sobel operator).

[0135] The above three parameters together constitute the characteristic vector of the regional heat source distribution pattern.

[0136] The intensity feature extraction unit is used to extract the thermal response intensity features of the structural area from the time series, including: thermal response peak value and thermal response fluctuation amplitude. This information can be used to determine whether the area has short-term intense heating, intermittent thermal failure and other phenomena.

[0137] Feature output unit, ultimately, the system integrates the features of the above four dimensions into a unified thermal response feature set:

[0138] F i =[T i (t), C i , S i , F i , T peak，i , ΔT i ]

[0139] F i : The complete thermal response feature vector of the i-th region, used by the anomaly recognition module.

[0140] Each structural region forms an independent feature vector, which is bound through structural coding and transmitted to the Structural Anomaly Identification Module for subsequent template comparison or classification. Through regional decomposition, multidimensional modeling, and unified feature structure, this module constructs a clear thermal response profile mechanism, providing a high-resolution data foundation for intelligent identification of the structural status of trackside equipment.

[0141] In one embodiment of the present invention, the Structural Anomaly Identification Module compares and analyzes the thermal response feature vectors output by the Heat Source Feature Extraction Module to identify structural anomalies in the trackside equipment and further output the anomaly type and location. This module includes three core functional units: a comparison and analysis unit, a type identification unit, and an anomaly location unit.

[0142] The comparison and analysis unit is used to determine whether the thermal response of the device structure area deviates from the normal state. It uses the feature vector similarity matching method to compare the real-time extracted thermal response feature vector with the preset normal template. The normal state heat source template vector corresponding to the thermal response feature vector extracted in the current frame of the i-th structure area in the system database is:

[0143]

[0144] The system uses the following similarity function for vector comparison:

[0145]

[0146] Among them, ||.||2: represents the Euclidean norm (L2 distance). The closer the similarity value is to 1, the more normal the state is, and the closer it is to 0, the greater the deviation.

[0147] The system sets a preset threshold θ∈(0,1), if: Sim(F i , F i ref )<θ, it is determined that there is structural abnormality in the i-th structural region.

[0148] The type recognition unit classifies abnormalities based on feature items whose similarity is below the threshold, identifying different types of potential defects. The recognition process is as follows:

[0149] If the main deviation occurs at ΔT i 、T peak，i : It may be "intermittent overheating";

[0150] If S iObvious decrease (symmetry destruction): may be "structural loosening or deformation";

[0151] If F i Significant increase (dramatic change in heat flow): This may be due to "uneven internal distribution or insulation damage."

[0152] The system classifies based on the following set of logical rules R:

[0153]

[0154] Assign anomalies to:

[0155] Category A: Abnormal heat source concentration; Category B: Abnormal structural geometry (such as warping); Category C: Poor heat dissipation or disordered internal heat source.

[0156] Abnormal location positioning unit, once the abnormality is confirmed in the structural area, this unit will use the unique coding ID of the area i , locate the abnormal position in the equipment, and combine it with the standard layout coordinates of the equipment provided by the distance measurement module to output the positioning results that can be used for the ground inspection system.

[0157] Abnormal coordinate expression:

[0158] Loc i =Pos device +δ i

[0159] P osdevice : the standard center position of the target device in the orbital coordinate system; δ i : Structural region R i The offset vector relative to the center of the device (can be obtained from the atlas template).

[0160] Finally, the system will output: abnormality type (such as structural looseness), abnormal area code (such as R3), and positioning coordinate information.

[0161] The present invention has the following beneficial effects:

[0162] The excitation process is completed based on the natural disturbances caused by train operation, without the need for additional active excitation devices or trigger mechanisms, which simplifies the system structure and reduces equipment costs. The excitation method can be adapted to different lines and environmental conditions as the train moves, and has good deployment flexibility and engineering feasibility.

[0163] Dynamic imaging is performed using an infrared heat source image acquisition module. By configuring a high-frame-rate acquisition unit, a window adjustment unit, and a perspective correction unit, the thermal imagery provides complete and stable coverage of the trackside equipment area. This ensures image clarity and structural integrity even under dynamic conditions, such as high-speed train operation and constantly changing perspectives. A dual monitoring mechanism for disturbance intensity and relative spatial distance is introduced, improving the quantification accuracy of aerodynamic disturbances through acceleration estimation and environmental calibration. Distance correction is performed by combining train positioning with trackside equipment map location data, achieving precise standardization of equipment thermal responses and providing a solid foundation for image comparison across time and equipment.

[0164] The image preprocessing module implements spatial and thermal value normalization processing, so that infrared images under different environments, different distances, and different speed conditions are unified into physically comparable heat source response maps, thereby significantly improving the accuracy and stability of subsequent feature extraction and comparison analysis. The heat source feature extraction module obtains multi-dimensional response characteristics at the structural level, including time evolution characteristics, heat flux distribution characteristics, thermal response intensity characteristics, etc., which comprehensively reflect the thermal response patterns of various structural areas of the trackside equipment under disturbance excitation, and help identify potential local anomalies or structural degradation problems.

[0165] The structural anomaly identification module has the ability to match templates and classify and locate anomalies, and can realize quantitative judgment of the structural status of the equipment. Once the thermal response characteristics are found to deviate from the normal template, it can automatically determine the type of anomaly and output the precise coordinate position, providing a structured and visual inspection basis for the back-end operation and maintenance system. The entire system can complete the equipment acquisition, processing and identification closed loop during the normal operation of the train without stopping operations or manual intervention. It has high-frequency, wide-coverage, and low-cost inspection capabilities, which will help build a full-life cycle equipment health management platform for future smart railways. The system architecture of the present invention is modular and highly scalable. It can be integrated into different types of trains such as high-speed railways and urban railways. It is also suitable for new lines and existing line reconstruction projects. It has significant engineering promotion value and industry application prospects.

[0166] The above-described embodiments do not constitute a limitation on the scope of protection of this technical solution. Any modifications, equivalent replacements, and improvements made within the spirit and principles of the above-described embodiments shall be included in the scope of protection of this technical solution.

Claims

1. A safety detection system for high-speed rail transit supporting equipment structure, characterized in that: include: The excitation response module is used to stimulate the structural response of the trackside equipment in the passing area through the aerodynamic disturbances naturally generated by the train body during the operation of the high-speed train; an infrared heat source image acquisition module, disposed on the side or lower area of ​​the train body, for acquiring an infrared heat source response image of the trackside equipment under aerodynamic disturbance excitation when the train passes by the trackside equipment; A parameter monitoring module, comprising an excitation monitoring unit and a distance measurement unit. The excitation monitoring unit is used to collect information on the intensity of aerodynamic disturbances during train operation; the distance measurement unit is used to measure the relative spatial distance between the train and the trackside equipment. An image preprocessing module, configured to perform standardization processing on the infrared heat source response image based on the aerodynamic disturbance intensity information and the relative spatial distance information to obtain a heat source response map; a heat source feature extraction module, configured to extract thermal response features of various structural areas of the trackside equipment from the heat source response map; The structural anomaly identification module is used to compare and analyze the thermal response characteristics with the preset normal state heat source response template, identify whether there is a structural anomaly in the trackside equipment, and output the anomaly type and positioning coordinate information.

2. A safety detection system for high-speed rail transit supporting equipment structure according to claim 1, characterized in that: The infrared heat source image acquisition module specifically includes: A high frame rate image acquisition unit is used to continuously capture multiple frames of infrared thermal images at a frame rate not lower than a preset frame rate while the train passes the target trackside equipment; An image window adjustment unit, configured to dynamically adjust the spatial range of image acquisition by the high-frequency image acquisition unit according to the relative spatial distance information provided by the device distance measurement module, so as to ensure the coverage integrity of the target device in the infrared thermal image; The viewing angle offset correction unit is used to calculate the projection angle of the trackside equipment in the infrared thermal image based on the relative position relationship between the trackside equipment and the high-frequency image acquisition unit, and obtain the infrared heat source response image after geometric correction processing of the infrared thermal image.

3. A safety detection system for high-speed rail transit supporting equipment structure according to claim 2, characterized in that: The excitation monitoring unit includes: The acceleration estimation subunit is used to obtain the acceleration change data of the train body in the lateral or vertical direction during the operation of the train, and estimate the current aerodynamic disturbance intensity around the train body based on the acceleration data; The environmental parameter calibration subunit is used to obtain external meteorological parameters in the environment where the train is located, and to correlate the external environmental parameters with the acceleration estimation results to correct and compensate the estimated disturbance intensity to obtain gas disturbance intensity information.

4. A safety detection system for high-speed rail transit supporting equipment structure according to claim 3, characterized in that: The distance measuring unit includes: The train positioning subunit is used to obtain the real-time position information of the current train in the track coordinate system based on the inertial navigation system, odometer sensor or on-board track positioning system carried by the train; The equipment location information calling subunit is used to extract the standard layout position of the target trackside equipment ahead of the train from the preset track infrastructure map database; The relative distance calculation unit is used to calculate the relative spatial distance between the train and the trackside equipment according to the real-time position information of the train and the standard layout position to obtain relative spatial distance information.

5. A safety detection system for high-speed rail transit supporting equipment structure according to claim 4, characterized in that: The image preprocessing module specifically includes: A spatial distance correction unit is configured to adjust the scale of each frame of the infrared heat source image according to the relative spatial distance information corresponding to each frame of the infrared heat source response image to obtain a spatial correction image, so as to make the scale of the area corresponding to the trackside equipment in each frame of the infrared heat source image consistent; The normalization unit is used to correct each pixel value representing the heat source response intensity in the spatial correction image according to the gas disturbance intensity information to obtain a heat source response map.

6. A safety detection system for high-speed rail transit supporting equipment structure according to claim 5, characterized in that: The step of correcting each pixel value representing the heat source response intensity in the spatial correction image according to the gas disturbance intensity information to obtain the heat source response map specifically includes the following steps: extracting thermal response image data of the area corresponding to the trackside equipment from the spatially corrected image, and identifying the thermal response intensity corresponding to each pixel value; The thermal response correction parameter is calculated based on the gas disturbance intensity information and the preset disturbance-thermal response mapping model; The standardized thermal response intensity is obtained by correcting the thermal response intensity corresponding to each pixel value according to the thermal response correction parameter; The pixel values ​​corresponding to the normalized thermal response intensity are updated back into the spatially corrected image to generate a heat source response map.

7. A safety detection system for high-speed rail transit supporting equipment structure according to claim 6, characterized in that: The heat source feature extraction module includes: An area division unit, used to divide the area corresponding to the trackside equipment into multiple structural areas and encode each structural area; A time series extraction unit is used to extract a time feature of each structural region based on a time series of multiple frames of thermal response maps, wherein the time feature represents a characteristic of how the thermal response intensity of each structural region changes over time; a distribution pattern extraction unit, configured to extract heat source pattern features of each structural region, wherein the heat source pattern features include concentration, heat source symmetry, and heat flow variability; an intensity feature extraction unit, configured to extract intensity features of each structural region, wherein the intensity features include a thermal response peak value and a thermal response fluctuation amplitude; The feature output unit outputs the time feature, intensity feature and heat source pattern feature as thermal response features to the structural anomaly recognition module.

8. A safety detection system for high-speed rail transit supporting equipment structure according to claim 7, characterized in that: The structural anomaly identification module includes: A comparison and analysis unit is used to calculate the similarity between the thermal response characteristics and the standard response characteristics in the normal state heat source response template through a feature vector comparison method. If any similarity is lower than a preset threshold, it is determined that there is a structural abnormality; a type recognition unit that determines the type of anomaly based on the type of thermal response features whose similarity is lower than a preset threshold; The abnormal position positioning unit obtains the corresponding code of the structural area determined by the comparison and analysis unit to have structural abnormality as the abnormal area position, and generates positioning coordinate information in combination with the standard layout position of the trackside equipment.

Images