Railway Sleeper Crack Detection Method and System Based on Three-Dimensional Features

Abstract

The present invention provides a method and system for detecting railway sleeper cracks based on three-dimensional feature construction, including a sleeper data acquisition step of acquiring a sleeper image and a thermal imaging map; a cracked sleeper screening step of screening the sleeper images with cracks and retrieving the thermal imaging map of the sleeper; a three-dimensional feature construction step of extracting a planar crack region, then calculating the crack depth through an inversion strategy according to the thermal imaging map, and adding the crack depth to the depth of the planar crack region to form a three-dimensional crack; a crack safety assessment step of calibrating the main crack and the branch cracks spreading from the main crack in the three-dimensional crack, analyzing the crack safety factor through an evaluation strategy with the size data of the main crack and the size data of the branch cracks, and judging whether the sleeper needs to be replaced according to the crack safety factor; the advantage of the present invention is that through the three-dimensional size analysis of the main crack and the branch cracks, a quantitative safety factor evaluation model is established, which can accurately judge the structural stability of the sleeper.

Description

Technical Field

[0001] The present invention relates to the technical field of railway sleeper detection, and more specifically, to a railway sleeper crack detection method and system based on three-dimensional feature construction. Background Art

[0002] As a core component of the track structure, railway sleepers play a key role in transmitting train loads, maintaining gauge stability, and dispersing stresses. During long-term service, sleepers are prone to cracks due to cyclic loads, environmental erosion, and construction defects.

[0003] Existing detection techniques include visual inspection and ultrasonic inspection. The defects of relying solely on visual inspection are as follows: ①. Depth blind spot: It can only detect surface opening cracks, and the missed detection rate of internal closed cracks (depth > 3mm) reaches 100%; ②. Direction dependence: Vertical cracks (such as on the side of the sleeper) are easily misjudged as defect-free due to the shadow effect, while the width measurement error of inclined cracks (angle < 30°) reaches ±40%; ③. Resolution bottleneck: The pixel limit of industrial cameras results in blurred edges of cracks at the 0.1mm level. The sub-pixel algorithm (error ±0.02mm) needs to be combined, but the computational complexity increases.

[0004] The defects of ultrasonic inspection are as follows: ①. Multi-interface scattering: The steel bar mesh inside the sleeper (spacing 150mm) causes the acoustic wave reflectivity to fluctuate by ±30%, and phased array focusing technology needs to be used (cost increases by 200%); ②. Geometric occlusion: A 10mm blind spot is formed behind the bolt hole (diameter 32mm), and multi-angle scanning (such as a 45° / 90° combination) is required, resulting in a 60% decrease in detection efficiency; ③. Mode confusion: The difference in the propagation speeds of transverse waves and longitudinal waves in concrete (3.5km / s vs 5.9km / s) causes echo overlap, and time-frequency analysis (such as wavelet transform) is needed to separate them, with a computational delay of up to 50ms.

[0005] In summary, the current sleeper crack detection is difficult to achieve the safety assessment of sleepers, there are detection bottlenecks, and it cannot meet the purposes of railway intelligent and safety detection. Summary of the Invention

[0006] Aiming at the deficiencies of the existing technology, the purpose of the present invention is to provide a railway sleeper crack detection method and system based on three-dimensional feature construction, which breaks through the limitations of traditional two-dimensional detection based on multi-modal data fusion, improves the crack recognition accuracy, and establishes a quantitative safety factor assessment model through the three-dimensional size analysis of main cracks and branch cracks, and can accurately judge the structural stability of sleepers.

[0007] To achieve the above purpose, the present invention provides the following technical solutions:

[0008] A railway sleeper crack detection method based on three-dimensional feature construction includes the following steps:

[0009] Steps for obtaining sleeper data: Obtain the sleeper images captured by the visual camera carried under the vehicle body during train operation and the thermal imaging maps captured by the infrared camera.

[0010] Steps for screening cracked sleepers: In the sleeper images, screen out the sleeper images with cracks through target detection, and retrieve the thermal imaging maps of the sleepers.

[0011] Steps for constructing three-dimensional features: Construct a two-dimensional coordinate system on the sleeper surface according to the screened sleeper images, extract the planar crack regions of the cracks in the sleeper images in the two-dimensional coordinate system, then calculate the crack depth through an inversion strategy based on the thermal imaging maps, construct the z-axis coordinate on the basis of the two-dimensional coordinate system to form a three-dimensional coordinate system, and attach the depth of the crack depth to the depth of the planar crack region in the three-dimensional coordinate system to form a three-dimensional crack.

[0012] Steps for crack safety assessment: Calibrate the main cracks and the branch cracks spreading from the main cracks in the three-dimensional cracks, analyze the crack safety factor through the evaluation strategy with the size data of the main cracks and the size data of the branch cracks, and determine whether the sleepers need to be replaced according to the crack safety factor.

[0013] Further, the crack safety assessment steps include a crack classification strategy, and the crack classification strategy includes a crack segment distinction step and a crack segment connection judgment step.

[0014] The crack segment distinction step: Enclose each continuous crack in the three-dimensional crack with a surrounding circle as a single crack.

[0015] The crack connection judgment step: Record the connection number of each single crack with other single cracks as the connection number of the single crack, and take the single crack with the most connection numbers as the main crack, and the other single cracks are all branch cracks.

[0016] Further, the crack classification strategy also includes a crack classification verification step.

[0017] The crack classification verification step: Obtain the size data of the main crack and the size data of the branch cracks output by the crack connection judgment step in the three-dimensional crack, compare the aspect ratio of the main crack with the aspect ratio of the branch cracks or compare the depth of the main crack with the depth of the branch cracks, and verify whether the main crack and the branch cracks output by the crack connection judgment step are correct according to the comparison results. If not, re-perform the crack segment distinction step.

[0018] Further, the evaluation strategy includes marking the end point of the branch crack far from the main crack as the first connection point, marking the connection point of the branch crack and the main crack as the second connection point, connecting the first connection point and the second connection point as the inclined crack of the branch crack, connecting the second connection point of the branch crack and the second connection point of the next branch crack as the straight crack of the main crack, calculating the included angle value between the inclined crack and the straight crack, and then calculating the crack safety factor through the evaluation algorithm by using the length, width and depth of the main crack, the number of branch cracks, the length, width and depth of each branch crack, and the included angle value between each branch crack and the main crack.

[0019] Further, the evaluation algorithm is configured as:

[0020] ,

[0021] ,

[0022] ,

[0023] ,

[0024] where, is the reference risk parameter of the main crack; is the position coordinate along the length of the main crack; is the length of the main crack; is the depth of the main crack; is the width of the main crack; is the length of the i-th branch crack; is the width of the i-th branch crack; is the depth of the i-th branch crack; is the included angle value between the i-th branch crack and the main crack; ; is the influence factor of the i-th branch crack; is the series order; is the factorial function; is the number of branch cracks; is the risk correction term of the main crack; is the comprehensive influence factor of branch cracks; is the crack safety factor, is the fractal series function; is the standardized logic function.

[0025] Further, in the three-dimensional feature construction step, a two-dimensional coordinate system is constructed in the sleeper image in the length direction and the width direction of the sleeper, the outer contour points of the cracks in the sleeper image are screened according to the edge detection algorithm, the outer contour points are mapped in the two-dimensional coordinate system, and the adjacent outer contour points are connected to form a planar crack region.

[0026] Furthermore, the inversion strategy includes a crack location step, a temperature data analysis step, and a heat conduction inversion step.

[0027] In the crack location step, each edge contour point of the planar crack region in the sleeper image is mapped in the thermal imaging diagram in the form of coordinate points as the crack position.

[0028] In the temperature data analysis step, multiple points are selected from the crack positions to record the temperature change curves over time, and the temperature difference between the crack positions and the normal positions of the sleepers is analyzed.

[0029] In the heat conduction inversion step, a heat conduction model is constructed, and the temperature difference is substituted into the heat conduction model for inversion calculation to obtain the crack depth.

[0030] Furthermore, the inversion strategy also includes a vibration noise filtering step, which eliminates jitter from the thermal imaging diagram to update the temperature difference between the crack position and the normal position of the sleeper, and obtains the vibration amplitude and correction coefficient to correct the heat conduction model to obtain the filtered heat diffusion rate. The crack depth is recalculated by inversion using the filtered diffusion rate and the updated temperature difference between the crack position and the normal position of the sleeper.

[0031] Furthermore, the crack safety assessment step includes a priority judgment sub-step. In the priority judgment sub-step, when there are two main cracks or two independent three-dimensional cracks in the three-dimensional feature construction step, the sleeper is directly output as a failed sleeper, and a replacement instruction is output.

[0032] A railway sleeper crack detection system based on three-dimensional feature construction, including a sleeper data acquisition module, which acquires the sleeper image captured by the visual camera carried under the vehicle body during train operation and the thermal imaging diagram captured by the infrared camera.

[0033] A cracked sleeper screening module, which screens out the sleeper images with cracks in the sleeper images through target detection and retrieves the thermal imaging diagram of the sleeper.

[0034] A three-dimensional feature construction module, which constructs a two-dimensional coordinate system on the surface of the sleeper according to the selected sleeper image, extracts the planar crack region of the crack in the sleeper image in the two-dimensional coordinate system, and then calculates the crack depth through the inversion strategy based on the thermal imaging diagram. A z-axis coordinate is constructed on the basis of the two-dimensional coordinate system to form a three-dimensional coordinate system, and the crack depth is added to the depth of the crack region in the three-dimensional coordinate system to form a three-dimensional crack.

[0035] A crack safety assessment module, which calibrates the main crack and the branch cracks spreading from the main crack in the three-dimensional crack, analyzes the crack safety factor through the evaluation strategy based on the size data of the main crack and the size data of the branch cracks, and determines whether the sleeper needs to be replaced according to the crack safety factor.

[0036] Advantages of the present invention: By combining visual images and infrared thermal imaging, multi-dimensional feature extraction of cracks is achieved, breaking through the limitations of traditional two-dimensional detection, improving the accuracy of crack recognition. Through a two-dimensional coordinate system and depth inversion strategy, a three-dimensional spatial distribution model of cracks is constructed to accurately quantify the crack depth (at the millimeter level) and spatial morphology, providing a reliable basis for safety assessment. And through the three-dimensional size analysis of main cracks and branch cracks, a quantitative safety factor assessment model is established, which can accurately judge the structural stability of the sleeper and provide scientific decision-making support for preventive maintenance. In addition, it is applicable to train driving scenarios under different working conditions, and a single analysis is carried out for different real-time train driving to ensure real-time monitoring of the sleeper and also improve the detection robustness in complex environments. Brief Description of the Drawings

[0037] Figure 1 is the overall flowchart in the present invention;

[0038] Figure 2 is the flowchart for inverting the crack depth from the thermal imaging diagram in the present invention;

[0039] Figure 3 is the flowchart for crack classification in the present invention;

[0040] Figure 4 is a partial diagram for crack recognition in the present invention;

[0041] Figure 5 is the connection diagram of the detection system module in the present invention. Detailed Embodiment

[0042] The present invention will be further described in detail below in conjunction with the drawings and embodiments. The same reference numerals are used for the same components. It should be noted that the terms "front", "rear", "left", "right", "upper" and "lower" used in the following description refer to the directions in the drawings, and the terms "bottom surface" and "top surface", "inner" and "outer" refer to the directions towards or away from the geometric center of a specific component, respectively.

[0043] At present, it is difficult to achieve the safety assessment of sleepers in the detection of sleeper cracks, there are detection bottlenecks, and it cannot meet the purpose of railway intelligent and safety detection. Therefore, the present invention designs a railway sleeper crack detection method based on three-dimensional feature construction, as Figure 1 shown, including the following steps:

[0044] Sleeper data acquisition step: Obtain the sleeper images taken by the line scan camera carried under the vehicle bottom when the train is running and the thermal imaging diagrams captured by the infrared camera. The line scan camera and the infrared camera are triggered synchronously to ensure the spatio-temporal matching of the visual and infrared images of the same sleeper. Among them, dynamic compensation technology is used to eliminate blurring, making the captured images more stable.

[0045] The steps for screening cracked sleepers are as follows Figure 4 As shown, in the sleeper image, the sleeper images with cracks are screened through object detection, and the thermal image of the sleeper is retrieved.

[0046] Among them, the steps for identifying cracks in the sleeper image include: ① Data collection and preprocessing: Collect a large number of sleeper images in different scenarios, lighting conditions, and crack types, which can be taken on-site from the railway or obtained through simulation experiments; ② Data annotation: Use annotation tools to annotate the cracks in the sleeper image, clarify the location and boundary of the cracks, and the annotation format is usually XML; ③ Data augmentation: To increase the diversity of data and the generalization ability of the model, perform data augmentation operations on the original images. Common augmentation methods include rotation, flipping, scaling, brightness adjustment, contrast adjustment, etc.; ④ Dataset division: Divide the annotated dataset into a training set, a validation set, and a test set, with a ratio usually of 7:2:1. The training set is used for model training, the validation set is used to adjust the model hyperparameters, and the test set is used to evaluate the model.

[0047] When 10 cracked sleeper images are screened out from 1000 sleeper images, the sleeper numbers will be marked. The marking method is that the train marks 1 for the first sleeper passed according to the starting point, and counts continuously when passing subsequent sleepers. And the sleepers with numbered marks and all the captured sleeper images are transmitted to the database for storage.

[0048] The three-dimensional feature construction steps: Construct a two-dimensional coordinate system on the sleeper surface according to the screened sleeper image, and extract the planar crack region of the crack in the two-dimensional coordinate system in the sleeper image. Specifically, in the sleeper image, construct a two-dimensional coordinate system along the length direction and width direction of the sleeper, screen out the outer contour points of the crack in the sleeper image according to the edge detection algorithm (object detection model), map the outer contour points in the two-dimensional coordinate system, and connect adjacent outer contour points to form a planar crack region. Then, calculate the crack depth through the inversion strategy according to the thermal image, construct the z-axis coordinate (the height direction of the sleeper) on the basis of the two-dimensional coordinate system to form a three-dimensional coordinate system, and attach the crack depth to the depth of the crack region in the three-dimensional coordinate system to form a three-dimensional crack;

[0049] Since in railway detection, applying thermal imaging technology to detect the depth of sleeper cracks has become a common method, and its principle is temperature inversion calculation, as Figure 2 shown, the inversion strategy in the present invention includes a crack location step, a temperature data analysis step, and a heat conduction inversion step.

[0050] Crack location step: Map each edge contour point of the planar crack area in the sleeper image to the thermal image as a crack position in the form of coordinate points. The purpose is to identify the crack position in the thermal image. According to the heat condition of the thermal image, the crack position can also be known. However, by combining the crack coordinates in the visual image with the thermal image, the purpose of mutual correspondence verification can be achieved, making the crack location more accurate;

[0051] Temperature data analysis step: Select multiple points at the crack position and record the temperature change curve over time, and analyze the temperature difference between the crack position and the normal position of the sleeper; Let the average temperature of the crack area be , and the average temperature of the normal area (normal position of the sleeper) be , then the temperature difference is: , the time when the train passes through the sleeper can be calculated by the train speed and the sleeper width : , the temperature difference and the time are the key input parameters for the subsequent heat conduction model;

[0052] Heat conduction inversion step: Build a heat conduction model, substitute the temperature difference into the heat conduction model for inversion calculation to obtain the crack depth. The heat conduction satisfies the one-dimensional Fourier equation: , where: is the thermal diffusivity of the sleeper material ( ), is the coordinate in the depth direction. By the method of separation of variables or Laplace transform, the relationship between the crack depth and the temperature difference can be obtained: , where, is the heat flux density per unit area ( ), is the material density ( ), is the specific heat capacity ( ). When the crack is relatively deep, , approximately . For the concrete sleeper parameters: , , , assuming , , , then .

[0053] Since vibrations occur when the wheel axle contacts the track during train operation, resulting in deviations in the thermal imaging map and the heat conduction model, an anti-inversion strategy also includes a vibration noise filtering step to eliminate jitter in the thermal imaging map to update the temperature difference between the crack position and the normal position of the sleeper. First, the vibration frequency needs to be analyzed through Fourier transform and amplitude , , , is the vibration signal acquired by the sensor, usually set on the train, but can also be set on the sleeper is the vibration period is the number of acquisition points. Motion compensation is used to estimate the inter-frame displacement through feature point matching, perform a translation transformation on the image, and use the multi-frame averaging technique to suppress vibration noise and eliminate image blurring caused by vibration. The image after anti-shake is used to improve the measurement accuracy of the temperature difference and obtain the vibration amplitude and correction coefficient to correct the heat conduction model to obtain the filtered thermal diffusivity. The filtered temperature difference is: where is the Fourier transform is the filter transfer function. Heat conduction model correction: Vibration causes changes in the diffusivity, and a predetermined correction coefficient is introduced: The crack depth is recalculated by anti-inversion through the filtered diffusivity and the updated temperature difference between the crack position and the normal position of the sleeper Assume , The filtered temperature difference The corrected diffusivity , 。

[0054] Crack safety assessment step: Calibrate the main crack and the branch cracks that spread from the main crack in the three-dimensional crack. Analyze the crack safety factor through the evaluation strategy with the size data of the main crack and the size data of the branch cracks, and determine whether the sleeper needs to be replaced according to the crack safety factor. A threshold range is set, and the threshold range includes that the safety factor between {0.5, 1} is the warning state, between {0, 0.5} is the failure state, and between {1, 2} is the safe state

[0055] Specifically, such as Figure 3As shown, the crack safety assessment steps include a crack classification strategy. The crack classification strategy includes a crack segment differentiation step. Usually, cracks are vertically cracked downward from the surface, so only a two-dimensional diagram of the crack plane area needs to be analyzed. However, for more accurate crack analysis, it is analyzed in three-dimensional cracks. Each continuous crack segment is surrounded by a surrounding circle to obtain a single crack. Assuming the crack is a long crack and many branched cracks extend from the long crack, and the long crack is cracked along the length direction of the sleeper, then taking one end point of the long crack as the starting point, the end point continuously connected to this starting point is taken as the ending point of the crack, and the crack between the starting point and the ending point is a single crack. Then, other cracks are surrounded in the same way;

[0056] Crack connection judgment step: Record the connection number of each single crack with other single cracks as the connection number of this single crack. The single crack with the largest connection number is used as the main crack, and other single cracks are all branched cracks. Usually, the branched cracks are all connected to the main crack. This method of judging the main crack and branched cracks through connection can accurately identify the main-branch relationship in the crack network, and the accuracy rate of main crack positioning reaches 95%.

[0057] In order to improve the accuracy of crack type analysis, the crack classification strategy in the present invention also includes a crack classification verification step. In three-dimensional cracks, the size data of the main crack and the size data of the branched cracks output by the crack connection judgment step are obtained. The size data mainly includes the length, brightness, and depth of the crack. By comparing the aspect ratio of the length and width of the main crack with that of the branched crack or comparing the depth of the main crack with the depth of the branched crack, according to the comparison result, it is verified whether the main crack and the branched cracks output by the crack connection judgment step are correct. If not, the crack segment differentiation step is performed again. Usually, the aspect ratio of the length and width of the main crack is greater than that of the branched crack, and the depth of the main crack is greater than that of the branched crack.

[0058] Specifically, the assessment strategy includes marking the end point of the branched crack far from the main crack as the first connection point, marking the connection point of the branched crack and the main crack as the second connection point, connecting the first connection point and the second connection point as the oblique crack (straight line segment) of this branched crack, connecting the second connection point of this branched crack and the second connection point of the next branched crack as the straight crack of the main crack, calculating the included angle value between the oblique crack and the straight crack, and then calculating the crack safety factor through the assessment algorithm with the length, width, and depth of the main crack, the number of branched cracks, the length, width, and depth of each branched crack, and the included angle value between each branched crack and the main crack. Since the width of the crack may be partially wider, the width of the crack in the assessment formula is calculated based on the value at the widest part of this crack.

[0059] The evaluation algorithm includes a main crack baseline risk calculation formula, a single-branch crack influence factor calculation formula, a branch crack comprehensive influence calculation formula, and a safety factor calculation formula. Among them, the main crack baseline risk calculation formula is configured as:

[0060] ,

[0061] Among them, is the main crack baseline risk parameter. Through the integral operation of the Gaussian kernel function and the error function ( ), the comprehensive influence of the geometric characteristics (length, width, depth) of the main crack on the structural safety is quantified. The larger the value, the more serious the threat of the main crack to the structural integrity; is the position coordinate along the length of the main crack. Taking one endpoint (the detection starting point) of the main crack as the coordinate origin ( ), it is the position parameter in a one-dimensional coordinate system established along the derivative direction of the main crack. The integration interval 0, directly corresponds to the full length range of the main crack; is the length of the main crack. The endpoint of the main crack far from the starting point is the end point, and the distance between this end point and the starting point is the length of the main crack; is the depth of the main crack, which is the deepest depth perpendicular to the sleeper surface; is the width of the main crack, which is the maximum transverse size of the crack opening. is the Gaussian error function; the integral term reflects the risk distribution in the crack length direction.

[0062] The single-branch crack influence factor calculation formula is configured as:

[0063] ,

[0064] Among them, is the length of the i-th branch crack; is the width of the i-th branch crack; is the gamma function, and the input is the depth of the branch crack . Its purpose is to amplify the threat of deep cracks. When , . When , , reflecting the characteristic of "doubling the depth, non-linear growth of risk"; is the depth of the i-th branch crack; is the hyperbolic tangent function. converts the included angle to radians, and its function is to limit the angle influence in the {0,1} interval; is the series order, which is the summation loop variable and is used to construct the polynomial influence of the branch crack length ; is the factorial function; is used to penalize wide and shallow branches ( ); is the included angle value between the i-th branch crack and the main crack, is the included angle and the absolute value of the cosine of the included angle controls the weight of the series terms; is the influence factor of the i-th branch crack. Through multi-parameter non-linear coupling, it quantifies the comprehensive influence of the geometric characteristics (length, width, depth) of a single branch crack and its included angle with the main crack on the structural safety, and the larger the value, the more significant the threat of the branch crack to the structural safety.

[0065] The calculation formula for the comprehensive influence of branch cracks is configured as:

[0066] ,

[0067] where, is the number of branch cracks; is the risk correction term of the main crack, , preventing from being zero when is zero, and taking the main crack reference risk as the normalization reference for the influence of branch cracks. When the main crack risk , then the influence of the branch crack is suppressed; is the comprehensive influence factor of branch cracks. By coupling the threats of all branch cracks through a geometric series, it reflects the synergistic effect of the multi-crack system. When (no branch cracks), the more branch cracks, that is , the smaller the value (the threat increases).

[0068] The calculation formula for the safety factor is configured as:

[0069] ,

[0070] where, is the crack safety factor, is the fractal series function, , when s = 1 / 2, this function characterizes the fractal characteristics of crack propagation, and its convergence domain is , input to reverse the main crack risk parameter into an inhibition factor ( ), reflecting the non-linear attenuation of the main crack risk on the safety factor. When , (convergence value before the divergence critical point), when When , the series converges rapidly (e.g., when ); ); is the comprehensive influence factor of the branched crack, and its square root reduces the numerical sensitivity to avoid the denominator from fluctuating violently caused by small values (high threat), reflecting the sub-linear growth of the multi-crack coupling effect. is the standardized logic function. If , weighted influence of the branched crack (the coefficient 3 is a set number, and the equivalent threat of the branched crack group is usually on the order of 1 / 3 of the main crack, and it needs to be amplified by 3 times to match the main-secondary risk balance). When the branched threat exceeds the reference risk of the main crack, a rapid decay of the safety factor is triggered.

[0071] Example of data calculation:

[0072] Main crack: , , ;

[0073] Branched crack 1: , , , ;

[0074] Branched crack 2: , , , ;

[0075] Reference risk of the main crack: ;

[0076] Integral kernel is a normal distribution curve centered at 30mm with a standard deviation of 15mm, and the integration interval is {0,60}. Through numerical integration: ;

[0077] Error function: (saturation value of the error function);

[0078] ;

[0079] Branched crack 1: ;

[0080] , , ;

[0081] Series term: ;

[0082] ; After the series term is corrected: ;

[0083] Exponential term: ;

[0084] ;

[0085] Similarly, for branch crack 2: ;

[0086] Comprehensive influence of branch cracks: ;

[0087] For : ;

[0088] For : ;

[0089] Exponential term: ;

[0090] ;

[0091] Safety factor: ;

[0092] Fractal series: ;

[0093] ;

[0094] ; ;

[0095] Analysis of key factors: 1. Dominated by the main crack: Extremely large ( ), resulting in a sharp attenuation of the fractal series term; 2. Weak branch influence: The long branch crack is strongly suppressed due to the gamma function and ; 3. Threshold trigger: Makes the denominator approach 1, but the numerator has decayed to a dangerous level.

[0096] The crack safety assessment step includes a priority judgment sub-step. In the priority judgment sub-step, when there are two main cracks or two independent three-dimensional cracks in the three-dimensional feature construction step, the sleeper is directly output as a failed sleeper, and a replacement instruction is output.

[0097] Based on the crack detection method, a railway sleeper crack detection system based on three-dimensional feature construction is configured. As Figure 5 shown, it includes:

[0098] The sleeper data acquisition module acquires the sleeper images captured by the visual camera carried under the train body during train operation and the thermal imaging maps captured by the infrared camera;

[0099] The cracked sleeper screening module screens out the sleeper images with cracks through object detection in the sleeper images and retrieves the thermal imaging maps of the sleepers;

[0100] The three-dimensional feature construction module constructs a two-dimensional coordinate system on the sleeper surface according to the screened sleeper images, extracts the planar crack regions of the cracks in the two-dimensional coordinate system in the sleeper images, then calculates the crack depth through an inversion strategy based on the thermal imaging maps, constructs the z-axis coordinate on the basis of the two-dimensional coordinate system to form a three-dimensional coordinate system, and attaches the crack depth to the depth of the crack region in the three-dimensional coordinate system to form a three-dimensional crack;

[0101] The crack safety assessment module calibrates the main crack and the branch cracks spreading from the main crack in the three-dimensional crack, analyzes the crack safety factor through an assessment strategy with the size data of the main crack and the size data of the branch cracks, and determines whether the sleeper needs to be replaced according to the crack safety factor.

[0102] The above detection method or system combines visual images and infrared thermal imaging to achieve multi-dimensional feature extraction of cracks, breaks through the limitations of traditional two-dimensional detection, improves the crack recognition accuracy, constructs a three-dimensional spatial distribution model of cracks through a two-dimensional coordinate system and a depth inversion strategy, accurately quantifies the crack depth (in millimeters) and spatial morphology, and provides a reliable basis for safety assessment; and through the three-dimensional size analysis of the main crack and the branch cracks, a quantitative safety factor assessment model is established, which can accurately judge the structural stability of the sleeper, provide scientific decision-making support for preventive maintenance, and is also applicable to train running scenarios under different working conditions, and performs a single analysis for different train runs in real time to ensure the real-time monitoring of the sleepers and also improve the detection robustness in complex environments.

[0103] In addition, the sleeper crack detection method and detection system of the present invention are not only applicable to concrete sleepers, but also applicable to traditional wooden sleepers.

[0104] The above is only the preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above embodiments. All technical solutions falling within the idea of the present invention belong to the protection scope of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and refinements should also be regarded as the protection scope of the present invention.

Claims

1. A method for detecting railway sleeper cracks based on three-dimensional feature construction, characterized in that: It includes the following steps: The sleeper data acquisition step, which acquires the sleeper images captured by the visual camera carried under the vehicle body during train operation and the thermal imaging maps captured by the infrared camera; The cracked sleeper screening step, which screens out the sleeper images with cracks in the sleeper images through target detection and retrieves the thermal imaging maps of the sleepers; The three-dimensional feature construction step, which constructs a two-dimensional coordinate system on the sleeper surface according to the screened sleeper images, extracts the planar crack regions of the cracks in the sleeper images in the two-dimensional coordinate system, then calculates the crack depth through an inversion strategy based on the thermal imaging maps, constructs the z-axis coordinate on the basis of the two-dimensional coordinate system to form a three-dimensional coordinate system, and adds the depth of the crack depth to the depth of the planar crack region in the three-dimensional coordinate system to form a three-dimensional crack; The crack safety assessment step, which calibrates the main crack and the branch cracks spreading from the main crack in the three-dimensional crack, analyzes the crack safety factor through an evaluation strategy with the size data of the main crack and the size data of the branch cracks, and determines whether the sleeper needs to be replaced according to the crack safety factor; The evaluation strategy includes calculating the main crack reference risk parameter according to the size data of the main crack, calculating the comprehensive influence factor of the branch crack according to the size data of the branch crack and the included angle value between the branch crack and the main crack, and then calculating the crack safety factor according to the main crack reference risk parameter and the comprehensive influence factor of the branch crack.

2. The method for detecting railway sleeper cracks based on three-dimensional feature construction according to claim 1, characterized in that: The crack safety assessment step includes a crack classification strategy, and the crack classification strategy includes a crack segment distinction step and a crack segment connection judgment step. The crack segment distinction step, which encloses each continuous crack in the three-dimensional crack with a surrounding circle as a single crack; The crack connection judgment step, which records the connection number of each single crack with other single cracks as the connection number of the single crack, and takes the single crack with the most connection numbers as the main crack, and other single cracks are branch cracks.

3. The railway sleeper crack detection method based on three-dimensional feature construction according to claim 2, wherein: The crack classification strategy also includes a crack classification verification step. The crack classification verification step, which acquires the size data of the main crack and the size data of the branch cracks output by the crack connection judgment step in the three-dimensional crack, compares the aspect ratio of the main crack with the aspect ratio of the branch crack or compares the depth of the main crack with the depth of the branch crack, and verifies whether the main crack and the branch cracks output by the crack connection judgment step are correct according to the comparison results. If not, the crack segment distinction step is performed again.

4. The railway sleeper crack detection method based on three-dimensional feature construction according to claim 1, characterized in that: The evaluation strategy includes marking the end point of the branch crack far from the main crack as the first connection point, marking the connection point of the branch crack and the main crack as the second connection point, connecting the first connection point and the second connection point as the oblique crack of the branch crack, connecting the second connection point of the branch crack and the second connection point of the next branch crack as the straight crack of the main crack, calculating the included angle value between the oblique crack and the straight crack, and then calculating the crack safety factor through an evaluation algorithm with the length, width and depth of the main crack, the number of branch cracks, the length, width and depth of each branch crack, and the included angle value between each branch crack and the main crack.

5. The method for detecting railway sleeper cracks based on three-dimensional feature construction according to claim 4, characterized in that: The evaluation algorithm is configured as: ， ， ， ， Among them, is the reference risk parameter of the main crack; is the position coordinate along the length of the main crack; is the length of the main crack; is the depth of the main crack; is the width of the main crack; is the length of the i-th branch crack; is the width of the i-th branch crack; is the depth of the i-th branch crack; is the included angle value between the i-th branch crack and the main crack; ; is the influence factor of the i-th branch crack; is the series order; is the factorial function; is the number of branch cracks; is the risk correction term of the main crack; is the comprehensive influence factor of branch cracks; is the crack safety factor, is the fractal series function; is the standardized logistic function.

6. The method for detecting railway sleeper cracks based on three-dimensional feature construction according to any one of claims 1-4, characterized in that: In the three-dimensional feature construction step, a two-dimensional coordinate system is constructed in the sleeper image in the length direction and width direction of the sleeper. According to the edge detection algorithm, the outer contour points of the cracks in the sleeper image are screened out, the outer contour points are mapped in the two-dimensional coordinate system, and the adjacent outer contour points are connected to form a planar crack region.

7. The method for detecting railway sleeper cracks based on three-dimensional features according to claim 6, wherein: The inversion strategy includes a crack location step, a temperature data analysis step, and a heat conduction inversion step. In the crack location step, each edge contour point of the planar crack region in the sleeper image is mapped in the thermal imaging map in the form of coordinate points as the crack location. In the temperature data analysis step, multiple points are selected at the crack location to record the temperature change curve over time, and the temperature difference between the crack location and the normal position of the sleeper is analyzed. In the heat conduction inversion step, a heat conduction model is constructed, and the temperature difference is substituted into the heat conduction model for inversion calculation to obtain the crack depth.

8. The method for detecting railway sleeper cracks based on three-dimensional features according to claim 7, wherein: The inversion strategy also includes a vibration noise filtering step, which eliminates jitter of the thermal imaging map to update the temperature difference between the crack location and the normal position of the sleeper, and obtains the vibration amplitude and correction coefficient to correct the heat conduction model to obtain the filtered heat diffusion rate. The crack depth is recalculated by inversion using the filtered diffusion rate and the updated temperature difference between the crack location and the normal position of the sleeper.

9. The method for detecting cracks in railway sleepers based on three-dimensional feature construction according to claim 1, wherein: The crack safety assessment step includes a priority judgment sub-step. In the priority judgment sub-step, when there are two main cracks or two independent three-dimensional cracks in the three-dimensional feature construction step, the sleeper is directly output as a failed sleeper, and a replacement instruction is output.

10. A railway sleeper crack detection system constructed based on three-dimensional features, characterized in that: It includes: A sleeper data acquisition module, which acquires the sleeper image captured by the visual camera carried under the vehicle body during train operation and the thermal imaging map captured by the infrared camera. A cracked sleeper screening module, which screens out the sleeper image with cracks through target detection in the sleeper image and retrieves the thermal imaging map of the sleeper. A three-dimensional feature construction module, which constructs a two-dimensional coordinate system on the surface of the sleeper according to the selected sleeper image, extracts the planar crack region of the crack in the sleeper image in the two-dimensional coordinate system, and then calculates the crack depth through the inversion strategy according to the thermal imaging map. The z-axis coordinate is constructed on the basis of the two-dimensional coordinate system to form a three-dimensional coordinate system, and the crack depth is added to the depth of the crack region in the three-dimensional coordinate system to form a three-dimensional crack. A crack safety assessment module, which calibrates the main crack and the branch cracks spreading from the main crack in the three-dimensional crack, analyzes the crack safety factor through the evaluation strategy based on the size data of the main crack and the size data of the branch cracks, and determines whether the sleeper needs to be replaced according to the crack safety factor.

Images