Nondestructive testing method for ballastless track of high-speed railway

Abstract

The invention discloses a nondestructive testing method for a ballastless track of a high-speed railway, which comprises the following steps: S1000, acquiring a track scanning image, analyzing the track scanning image, and determining whether an abnormal area exists or not; s2000, if the abnormal area exists, track filling data are obtained, the abnormal area is analyzed according to the track filling data, and the abnormal type and the abnormal reason are determined; s3000, predicting an accident state of an abnormal area in a preset time period according to the abnormal type; and S4000, according to the accident state and the abnormity type, determining a repair opportunity. By integrating the high-precision image detection technology, the data analysis method and the fault prediction model, accurate detection and early warning of track abnormity can be achieved, scientific maintenance decision support is provided, and the safety and maintenance efficiency of the ballastless track of the high-speed railway are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of high-speed railways, and particularly relates to a non-destructive detection method for ballastless tracks of high-speed railways. Background Art

[0002] The ballastless track system of high-speed railways usually consists of sleepers, rails, ballast beds, and other auxiliary facilities. Since ballastless tracks can better withstand the vibration and pressure of high-speed trains, especially showing excellent stability under harsh climate and geological conditions, they have been widely used in high-speed railway construction at home and abroad. In recent years, with the continuous increase in train speed and transportation volume, the operating conditions of tracks have become more and more stringent, making the problems of track damage and defects more prominent. Problems such as track wear, rail cracks, cracking and settlement of concrete ballast beds, and deviation of track geometry will all affect the safety and comfort of train operation.

[0003] Currently, the detection methods for ballastless tracks mainly include manual inspection, ground measurement, and non-destructive testing techniques through various detection means (such as ultrasonic, laser, infrared, etc.). These techniques can identify the faults and defects of the track system to a certain extent, but still face some limitations, such as limited detection accuracy, slow detection speed, and high cost of manual intervention. Especially when facing tiny cracks and early damage of the track, traditional detection methods often have difficulty providing real-time and comprehensive monitoring and diagnosis.

[0004] With the progress of technology, especially the rapid development of artificial intelligence, big data, sensor technology, etc., the non-destructive testing technology of railway tracks has gradually developed towards the direction of intelligence, automation, and real-time. The wide application of high-precision sensors and integrated detection equipment enables the detection of ballastless tracks not only limited to a single technical means, but through the integration of multiple detection methods and data analysis, it is possible to achieve comprehensive monitoring of the track operating state and early fault warning.

[0005] For example, through the track detection sensors mounted on high-speed trains, it is possible to collect the mechanical change data of the contact between the train and the track in real time, and through data processing and analysis, to identify the abnormal behavior of the track in a timely manner. In addition, using artificial intelligence algorithms for in-depth learning and pattern recognition of the detection data helps to improve the detection accuracy and efficiency, especially for the identification of early damages such as tiny cracks and fatigue damages.

[0006] Although current non-destructive testing technologies have made significant progress to a certain extent, the following major problems still exist: (1) The detection accuracy is not high. Existing non-destructive testing technologies still have limitations in identifying some micro-cracks or hidden damages. Especially under the dynamic load of high-speed train operation, traditional technologies often cannot reflect the actual state of the track in real time and accurately; (2) The detection speed is slow. Traditional manual or semi-automatic detection methods cannot meet the real-time monitoring requirements during the operation of high-speed railways. Existing non-destructive testing means still require a long time cycle for a comprehensive inspection under the continuous operation of high-speed railways; (3) Lack of unified standards. Different detection technologies and methods often lack unified standards and specifications, resulting in certain differences in detection data and results between different regions and companies, affecting the overall efficiency of railway maintenance and management; (4) High cost and high dependence on manual labor. Although sensors and automated detection equipment are constantly being applied, high-precision and high-stability equipment still requires a large amount of capital investment and manual operation. Summary of the Invention

[0007] The purpose of the present invention is to provide a non-destructive testing method for ballastless tracks of high-speed railways, which is used to solve at least one of the above technical problems, and can solve problems such as detection accuracy, speed, and cost in the existing technology, and improve the safety and durability of ballastless tracks.

[0008] The embodiments of the present invention are implemented as follows:

[0009] A non-destructive testing method for ballastless tracks of high-speed railways includes:

[0010] S1000, obtaining a track scan image, analyzing the track scan image, and determining whether there is an abnormal area;

[0011] S2000, if there is an abnormal area, obtaining track filling data, and analyzing the abnormal area according to the track filling data to determine the type and cause of the abnormality;

[0012] S3000, predicting the accident state of the abnormal area within a preset time period according to the type of the abnormality;

[0013] S4000, determining the repair timing according to the accident state and the type of the abnormality.

[0014] In a preferred embodiment of the present invention, in the above non-destructive testing method for ballastless tracks of high-speed railways, before analyzing the track scan image and determining whether there is an abnormal area in S1000, the following steps are further included:

[0015] S1010, based on the track scan image, retrieving a scan task, analyzing the scan task, and determining the operation direction;

[0016] S1020. Analyze the orbital scan image to determine the edge features;

[0017] S1030. Analyze the operation direction and the edge features to determine the horizon position.

[0018] Its technical effects are as follows: Ensure that the analysis work is consistent with the current scanning task, provide the latest orbital status data, and provide accurate context information for subsequent analysis. Determining the scanning direction helps to correctly identify the edge features and abnormal areas of the roadbed slab in subsequent image analysis, improving the accuracy and efficiency of the analysis. Extracting the edge features of the roadbed slab helps to identify the position of the surface layer of the roadbed slab in the radar image, provides a basis for determining the horizon position, and provides a reference for subsequent identification of abnormal areas. Determining the horizon position provides a stable reference point, which helps to judge the deformation and other structural problems shown in the radar image of the roadbed slab, and lays a foundation for subsequent identification of abnormal areas and prediction of accident states.

[0019] In a preferred embodiment of the present invention, in the above non-destructive testing method for ballastless tracks of high-speed railways, in S2000, if there is an abnormal area, then according to the orbital filling data, analyze the abnormal area to determine the type and cause of the abnormality, including:

[0020] S2010. Analyze the orbital filling data to obtain the thickness of the roadbed slab and the thickness of the supporting layer;

[0021] S2020. According to the horizon position, analyze the abnormal area to obtain the scope of the abnormal accident;

[0022] S2030. According to the thickness of the roadbed slab and the thickness of the supporting layer, analyze the scope of the abnormal accident to determine the type of abnormality;

[0023] S2040. According to the abnormal area and the type of abnormality, determine the cause of the abnormality.

[0024] Its technical effects are as follows: By analyzing the orbital filling data, key information such as the thickness of the roadbed slab and the supporting layer can be obtained. Using the horizon position as a reference benchmark, the position and scope of the abnormal area can be more accurately identified and analyzed, which is crucial for evaluating the structural defects of the roadbed slab of the track. According to the characteristics of the abnormal area and the horizon position, the scope that the abnormal accident may affect can be determined, and the degree of influence of the abnormality on the overall structure of the track can be evaluated. Combining the thickness data of the roadbed slab and the supporting layer, the influence of the scope of the abnormal accident on the track structure can be analyzed. According to the characteristics of the abnormal area, the scope of the accident and the structural thickness data, the type of abnormality can be determined. Combining the type of abnormality and the area characteristics, the possible causes of the abnormality, such as material defects, construction problems, environmental factors, etc., can be analyzed, which is crucial for preventing problems in advance and improving the efficiency and effect of track maintenance.

[0025] In a preferred embodiment of the present invention, in the above non-destructive testing method for ballastless tracks of high-speed railways, in S2040, when the abnormal type is an abnormality inside the track slab, determining the cause of the abnormality based on the abnormal area and the abnormal type includes:

[0026] S2041, obtaining and analyzing the procurement records of the track slab to obtain a record analysis result;

[0027] S2042, determining the structural data of the track slab based on the record analysis result;

[0028] S2043, determining whether the abnormality inside the track slab is a production defect based on the structural data of the track slab;

[0029] S2044, if it is not a production defect, determining that the cause of the abnormality inside the track slab is track load-bearing.

[0030] Its technical effect is that by analyzing the procurement records, information such as the source, production date, material specifications, and quality control of the track slab can be understood, and the structural data such as the design parameters and actual construction parameters of the track slab can be determined, which helps to trace the quality of the track slab and potential production problems. The record analysis result may reveal problems such as non-standard operations, material quality problems, or insufficient quality control during the production process, and the cause of the abnormality can be determined. By comparing the structural data and the analysis result, it can be judged whether the abnormality inside the track slab is caused by defects during the production process, so as to determine whether corrective measures need to be taken. If it is not a production defect, then analyze the load-bearing situation of the track, including train loads, environmental factors, etc., to determine whether the abnormality is caused by excessive load-bearing or improper use, and thus take corresponding preventive measures.

[0031] In a preferred embodiment of the present invention, in the above non-destructive testing method for ballastless tracks of high-speed railways, in S3000, predicting the accident state of the abnormal area within a preset time period based on the abnormal type includes:

[0032] S3010, when the abnormal type is an abnormality inside the track slab, analyzing the track scan image to determine the current time;

[0033] S3020, predicting the environmental changes within a preset time period based on the current time;

[0034] S3030, obtaining the track load-bearing data and determining the track load-bearing impact based on the track load-bearing data;

[0035] S3040, predicting the accident state of the abnormal area within a preset time period based on the environmental changes and the track load-bearing impact.

[0036] Its technical effects are as follows: By means of image processing and analysis technologies, the track state at the current moment is obtained to provide real-time data for subsequent prediction. Using historical environmental data and weather forecast information, the changing trend of the future environment is predicted, and the possible impacts of these changes on the abnormal areas of the track are evaluated. Train operation data, including train type, weight, operation time, etc., are collected to evaluate the load borne by the track. The load-bearing data is analyzed to evaluate the stress distribution and potential damage of the track structure, and the analysis results of the load-bearing impact are provided for predicting the accident state. Combining the load-bearing impact and the prediction of environmental changes, a machine learning model or statistical analysis method is used to predict the accident state of the abnormal area within a preset future time period, providing a basis for maintenance decisions.

[0037] In a preferred embodiment of the present invention, in the above non-destructive detection method for ballastless tracks of high-speed railways, in S4000, the determining the repair time according to the accident state and the abnormal type includes:

[0038] S4010, determining the associated diseases according to the abnormal type and the environmental changes;

[0039] S4020, analyzing the associated diseases to determine the spreading time period;

[0040] S4030, according to the preset time period and the spreading time period, determining the disease impact of the associated diseases on the abnormal area;

[0041] S4040, determining the repair time according to the accident state and the disease impact.

[0042] Its technical effects are as follows: By analyzing the influence of environmental factors on track anomalies, diseases that may be associated with specific abnormal types are identified so as to take preventive measures. The development law of the diseases is studied to predict their spreading speed and time period under different environmental conditions, so as to plan the repair work in advance. Combining the disease spreading time period and the preset time period of railway operation, the potential impact of the diseases on the abnormal area is evaluated, so as to determine the urgency and priority of the repair. Considering comprehensively the impact of the diseases and the current accident state, the possible accident risks in the future are predicted, and the best repair time is determined to ensure that the repair work is carried out before the accident is caused by the impact of the diseases.

[0043] In a preferred embodiment of the present invention, in the above non-destructive detection method for ballastless tracks of high-speed railways, in S3000, when the abnormal type is an interlayer gap, the predicting the accident state of the abnormal area within a preset time period according to the abnormal type includes:

[0044] S3050, when the abnormal type is an interlayer gap, analyze the track scan image, determine the gap characteristics of the interlayer gap, determine a newly changed area based on the gap characteristics, and predict the change direction within a preset time period based on the newly changed area;

[0045] S3060, retrieve and analyze historical scan records, and determine the development period of the newly changed area based on the historical scan analysis results;

[0046] S3070, determine the difficulty of change impact based on the gap characteristics;

[0047] S3080, predict the accident state of the abnormal area within a preset time period based on the change direction, the development period, and the difficulty of change impact.

[0048] The technical effect is as follows: Through image analysis techniques such as image segmentation and feature extraction, the position, size, shape, and other characteristics of the interlayer gap can be accurately identified, so as to be applied to evaluate the severity and potential impact of the gap. By comparing the scan images at different time points, new interlayer gaps can be identified, and the newly changed area may be the key point that needs to be concerned and processed in the future. By analyzing the characteristics of the newly changed area, the change trend of these areas within a preset time period in the future can be predicted, such as whether the gap will expand or whether new defects will form. By reviewing historical scan records and analyzing the development process of the newly changed area to determine its development period, it helps to understand the time and development speed of the gap formation. According to the position, size, shape, and other characteristics of the gap, the difficulty of repair or reinforcement can be evaluated, which helps to formulate a maintenance plan and determine the required resources. By comprehensively considering the difficulty of change impact, the development period, and the change direction, the accident state of the abnormal area within a preset time period in the future, such as track settlement, track fracture, etc., can be predicted, so as to take preventive measures in time.

[0049] In a preferred embodiment of the present invention, in the above non-destructive testing method for ballastless tracks of high-speed railways, in S3000, when the abnormal type is a crack in the roadbed slab, the predicting the accident state of the abnormal area within a preset time period according to the abnormal type includes:

[0050] S3090, when the abnormal type is a crack in the roadbed slab, determine whether there is the interlayer gap or an abnormality inside the roadbed slab according to the analysis result of the abnormal area. If so, determine the associated impact of the interlayer gap or the abnormality inside the roadbed slab according to the gap characteristics or the internal abnormality characteristics;

[0051] S3100, determine the crack characteristics according to the analysis result of the abnormal area, and determine the crack range according to the crack characteristics;

[0052] S3110, Obtain track load-bearing data, and determine the track load-bearing impact based on the track load-bearing data.

[0053] S3120, Predict the accident state of the abnormal area within a preset time period based on the associated impact, the crack range, and the track load-bearing impact.

[0054] Its technical effect is as follows: By analyzing the track scan images and detection data, the crack area of the ballastless track slab can be identified, and whether there are interlayer voids or internal abnormalities can be checked, which is used to evaluate the severity and potential impact of the cracks. Analyze the characteristics of the interlayer voids or internal abnormalities to determine their impact on the crack development, and evaluate the potential impact of the interlayer voids or internal abnormalities on the cracks, so as to better predict the development trend of the cracks. Integrate the crack range, associated impact, and track load-bearing impact, and use a prediction model to predict the accident state of the abnormal area within a preset future time period, and predict the accident risks that the cracks may cause, such as track fracture, structural instability, etc., so as to take preventive measures in a timely manner.

[0055] In a preferred embodiment of the present invention, in the above non-destructive testing method for high-speed railway ballastless tracks, in S4000, the determining the repair timing according to the accident state and the abnormal type includes:

[0056] S4050, Determine the repairable time period according to the current time.

[0057] S4060, Predict the abnormal change situation of the abnormal area within the repairable time period according to the accident state.

[0058] S4070, Analyze the abnormal change situation and determine the risk level.

[0059] S4080, Determine whether to repair within the repairable time period according to the risk level. If it is determined to repair, determine the repair method according to the abnormal type.

[0060] S4090, Determine the abnormal shape of the abnormal area according to the repair method.

[0061] S4100, Determine the abnormal state at the current time according to the abnormal accident range.

[0062] S4110, Determine the repair timing according to the abnormal shape and the abnormal state at the current time.

[0063] The technical effects are as follows: identify the time periods in the railway operation plan that will not interfere with train operation for repair work. Or avoid the problem that ballastless slab repair cannot be carried out in winter. By analyzing the current accident status and abnormal types, predict the possible changes in the abnormal area during the future repairable time periods to make preparations in advance. Evaluate the risks that may be brought by abnormal changes, determine the risk level to decide whether emergency repair is needed. According to the risk level and the feasibility of the repair time period, decide whether to carry out repair work during the repairable time period to ensure the repair effect and the long-term performance of the track. Select the most suitable repair method and technology according to the abnormal type to ensure the repair effect and the long-term performance of the track. According to the selected repair method, predict the shape and performance of the abnormal area after repair to evaluate the track status after repair. Analyze the scope of the abnormal accident, determine the current track abnormal status to understand the current abnormal status of the track. Considering comprehensively the current abnormal status, abnormal shape and the predicted effect of the repair method, determine the best repair timing to ensure that the repair work is carried out at the best timing, minimize the impact on railway operation and maximize the repair effect.

[0064] In a preferred embodiment of the present invention, in the non-destructive detection method for ballastless tracks of high-speed railways, in S4110, the determining the repair timing according to the abnormal shape and the current abnormal status includes:

[0065] S4111, determine the repair limit range according to the repair method;

[0066] S4112, analyze the current abnormal status, determine whether the abnormal status is greater than the repair limit range. If not, analyze the abnormal status to determine the abnormal difference between the abnormal status and the abnormal shape;

[0067] S4113, determine the repair timing according to the abnormal change situation and the abnormal difference.

[0068] The technical effects are as follows: by evaluating the applicability and effects of different repair methods, determine the abnormal degree and repair limit range that each repair method can handle. Use non-destructive detection technology to evaluate the severity of the current track abnormality and compare it with the limit range of the repair method to judge whether the current abnormality exceeds the capacity range of the repair method. If the current abnormal status does not exceed the repair limit range, further analyze the difference between the abnormal status and the abnormal shape, identify the specific characteristics of the abnormality, such as the depth, width, distribution of cracks, etc. Combining the change trend of the abnormality and the difference between the abnormal status and shape, predict the development of the abnormality, determine the best repair timing, and choose to carry out repair before the abnormality develops to the critical point to prevent further damage and potential safety risks.

[0069] The beneficial effects of the embodiments of the present invention are as follows:

[0070] A non-destructive testing method for ballastless tracks on high-speed railways according to the present invention obtains detailed images of the track slab through a high-precision imaging device, can capture minute changes and potential defects in the track slab, provides rich basic data, and lays a solid foundation for subsequent analysis.

[0071] By applying advanced image processing and analysis techniques, it is possible to automatically identify abnormal areas in the track images, including cracks, wear, deformation, etc., reduce the errors of manual inspection, and improve efficiency.

[0072] The present invention combines the track scan images with the track filling data (such as track slab thickness, support layer thickness, etc.) obtained from the construction archives, can not only understand the structural state of the track more deeply, but also accurately analyze the characteristics of the abnormal areas, determine the type of abnormality (such as internal defects, cracks or settlements) and its possible causes (such as material defects or excessive wear).

[0073] Based on a prediction model, the present invention can predict the accident state of the abnormal area, such as whether the abnormality will further deteriorate, whether it will affect the safety of railway operation, etc., so as to achieve early warning of faults. According to the predicted accident state and the type of abnormality, the best repair time is recommended to help railway operation units optimize the maintenance plan, avoid over-maintenance or delayed repair, effectively reduce the maintenance cost. By taking preventive measures in advance, the potential accident risks caused by track abnormalities are reduced, ensuring the safe operation of the railway. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required to be used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention, and therefore should not be regarded as limiting the scope. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts.

[0075] Figure 1 is a flowchart of the non-destructive testing method for ballastless tracks on high-speed railways according to the present invention;

[0076] Figure 2 is a schematic diagram of an application scenario of an embodiment of the non-destructive testing method for ballastless tracks on high-speed railways according to the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0077] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0078] As the ballastless track is used for a longer time, it will inevitably face various potential damages or defects. Especially during high-intensity train operation, track wear, deformation and other structural problems may pose a major threat to the safety of railway transportation.

[0079] Therefore, how to effectively monitor and non-destructively test high-speed railway ballastless tracks and promptly detect and eliminate potential faults or anomalies has become a technical problem that needs to be urgently solved in modern railway maintenance.

[0080] Based on this, the present application provides a non-destructive testing method for high-speed railway ballastless track, such as Figure 1 As shown, it includes: S1000, acquiring a track scanning image, analyzing the track scanning image, and determining whether there is an abnormal area; S2000, if there is an abnormal area, acquiring track filling data, analyzing the abnormal area according to the track filling data, and determining the abnormal type and the cause of the abnormality; S3000, predicting the accident state of the abnormal area within a preset time period according to the abnormal type; S4000, determining the repair time according to the accident state and the abnormal type.

[0081] Figure 2A schematic diagram of an application scenario provided by the present application. When performing non-destructive detection of diseases on the track slab of the ballastless track of high-speed railways, the method provided by the present application is applied. Specifically, the method provided by the present application is applied to any server, and the server interacts with a geological radar and a construction archive system. By using the high-precision geological radar to obtain the track scan image of the ballast slab, it can reflect the minute changes and potential defects of the ballast slab. The acquisition of the image provides the basic data for subsequent identification and analysis of abnormal areas. Through image processing and analysis techniques, abnormal areas in the track image, such as cracks, wear, and deformation, can be automatically identified. The track filling data obtained from the construction archive system, such as the thickness of the ballast slab and the thickness of the supporting layer, helps to understand the structural state of the track more deeply. By combining the track scan image and the filling data, the characteristics of the abnormal area can be analyzed, the type of abnormality (such as internal defects, cracks, settlement, etc.) can be determined, and the causes of these abnormalities (such as material defects, excessive wear, etc.) can be inferred. Through the prediction model, the accident state that the abnormal area may reach within a preset time period can be predicted, such as whether it will deteriorate further, whether it will affect the safety of railway operation, etc. This helps to take preventive measures in advance to avoid accidents. Based on the predicted accident state and the determined type of abnormality, the best repair time is recommended; the maintenance plan is optimized to improve the maintenance efficiency while ensuring the safety of railway operation. The specific implementation method can refer to the following embodiments.

[0082] S1000. Obtain the track scan image, analyze the track scan image, and determine whether there is an abnormal area.

[0083] The track scan image can be the radar image information of the ballast slab and its deep layer obtained by the geological radar; the abnormal area can be the area shown in the track scan image that is inconsistent with the normal track state.

[0084] Specifically, use the geological radar to scan the ballastless track of high-speed railways to obtain a high-resolution track scan image. During the acquisition process, it is necessary to ensure the clarity and error-free of the image to ensure the high quality of the data. Analyze the track scan image through image processing algorithms (such as edge detection, morphological analysis, deep learning models), extract the edge features, texture features and other key indicators of the ballast slab, and identify whether there is an abnormal area.

[0085] S2000. If there is an abnormal area, obtain the track filling data, and analyze the abnormal area according to the track filling data to determine the type of abnormality and the cause of the abnormality.

[0086] The track filling data can be the relevant data of the ballast slab and the filling layer obtained through sensors, measuring devices, or construction archives; the abnormal types can be the results of classifying the detected abnormal areas, such as internal abnormalities of the ballast slab, cracks, settlements, damage to the supporting layer, etc.; the abnormal causes can be the root factors leading to track abnormalities analyzed from the detected abnormal areas, such as material defects, improper construction, excessive wear, environmental factor impacts, etc.

[0087] Specifically, if there is an abnormal area, the filling data of the ballast slab is obtained through the construction archives of the previous construction, including the thickness of the ballast slab, the height of the supporting layer, the load-bearing condition of the track, etc. The track scan image is fused and analyzed with the filling data to form a complete ballast slab condition model. Based on the analysis results, the specific types and causes of the abnormal area are further determined.

[0088] S3000, predict the accident state of the abnormal area within a preset time period according to the abnormal type; S4000, determine the repair timing according to the accident state and the abnormal type.

[0089] The preset time period can be a pre-set time period for predicting and evaluating possible accidents in the abnormal area, stored in a preset database; the accident state can be the dangerous state that the track abnormal area may reach under certain conditions; the repair timing can be the time point most suitable for repair determined according to the condition and development trend of the abnormal area.

[0090] Specifically, a prediction model for track abnormalities is established using machine learning algorithms (such as regression models, support vector machines, etc.). When training the model, the input parameters include the characteristics of the abnormal area, historical scan records, track filling data, and environmental change data, etc. Since the operating environment of the track may affect the track state, environmental changes (such as temperature, humidity, precipitation, etc.) are obtained and analyzed in real time, and these factors are incorporated into the accident prediction model. According to the predicted accident state and abnormal type, it can be automatically judged whether the abnormal area needs to be repaired and the repair timing is determined. Based on the current abnormal state and the predicted abnormal change situation of the abnormal area, a risk assessment of the repair timing is carried out. If the risk level of the abnormal area exceeds the set threshold, it is determined as an area that needs to be repaired immediately. Repair plans are automatically recommended according to the abnormal type, such as replacing the ballast slab, repairing cracks, strengthening the supporting layer, etc.

[0091] In a preferred embodiment of the present invention, in the above non-destructive testing method for ballastless tracks of high-speed railways, before analyzing the track scanning image in S1000 to determine whether there is an abnormal area, it further includes: S1010, based on the track scanning image, retrieving the scanning task, analyzing the scanning task, and determining the operation direction; S1020, analyzing the track scanning image to determine the edge features; S1030, analyzing the operation direction and the edge features to determine the ground level position.

[0092] The scanning task can be a series of operations and plans for scanning and detecting the track, including the time, location, equipment used, scanning range, and parameters, etc.; the operation direction can be the direction when scanning along the track, that is, whether the scanning is from one end of the track to the other end or along a specific direction of the track; the edge features can be the edges or contours shown in the radar image of the track bed slab; the ground level position can be the ground level reference line in the radar image of the track bed slab.

[0093] Specifically, retrieve the current scanning task information from the database or the scanning task management system, including the scanning time, location, equipment parameters, scanning range, etc. According to the information of the scanning task, analyze the scanning direction along the track, that is, determine whether the scanning is from one end of the track to the other end or along a specific direction of the track. Use image processing techniques, such as edge detection algorithms (such as Sobel operator, Canny operator, etc.), to analyze the track bed slab scanning image and extract the edge features of the radar image of the track bed slab. Combine the edge features and the operation direction, and use geometric analysis and pattern recognition techniques to determine the ground level position in the track bed slab image, that is, the ground level reference line of the track bed slab.

[0094] In a preferred embodiment of the present invention, in the above non-destructive testing method for ballastless tracks of high-speed railways, in S2000, if there is an abnormal area, then according to the track filling data, analyze the abnormal area to determine the abnormal type and the cause of the abnormality, including: S2010, analyzing the track filling data to obtain the thickness of the track bed slab and the thickness of the supporting layer; S2020, according to the ground level position, analyze the abnormal area to obtain the scope of the abnormal accident; S2030, according to the thickness of the track bed slab and the thickness of the supporting layer, analyze the scope of the abnormal accident to determine the abnormal type; S2040, according to the abnormal area and the abnormal type, determine the cause of the abnormality.

[0095] The thickness of the track bed slab can be the thickness of the concrete slab in the ballastless track for bearing the sleepers and rails; the thickness of the supporting layer can be the thickness of the material layer (such as sand cushion layer, crushed stone layer, etc.) below the track bed slab for dispersing the load and providing stability; the scope of the abnormal accident can be the area range that the abnormal area detected in the radar image of the track bed slab of the track may affect, including the directly affected track part and the adjacent areas that may be indirectly affected.

[0096] Specifically, the thickness information of the track slab and the supporting layer is extracted from the track filling data. Using image processing technology and combining with the horizon position information, the abnormal areas in the track scan image are analyzed. According to the characteristics of the abnormal areas and the horizon position, the possible affected range of the abnormal accident is determined. Combining the thickness data of the track slab and the supporting layer, the influence of the abnormal accident range on the track structure is analyzed. According to the characteristics of the abnormal areas, the accident range and the structural thickness data, the type of the abnormality is determined. Combining the type of the abnormality and the area characteristics, the possible causes of the abnormality are analyzed, such as material defects, construction problems, environmental factors, etc.

[0097] In a preferred embodiment of the present invention, in the above non-destructive testing method for ballastless tracks of high-speed railways, in S2040, when the type of the abnormality is an abnormality inside the track slab, the determination of the cause of the abnormality according to the abnormal area and the type of the abnormality includes: S2041, obtaining and analyzing the procurement record of the track slab to obtain a record analysis result; S2042, determining the track slab structure data according to the record analysis result; S2043, determining whether the abnormality inside the track slab is a production defect according to the track slab structure data; S2044, if it is not a production defect, determining that the cause of the abnormality inside the track slab is track load-bearing.

[0098] The abnormality inside the track slab can be any abnormal situation existing inside the track slab of the ballastless track, such as cracks, cavities, material separation, etc.; the procurement record of the track slab can be a document or database recording information such as the procurement process of the track slab, supplier information, production batch, quality inspection report, etc.; the record analysis result can be a conclusion or problem found after analyzing the procurement record of the track slab; the track slab structure data can be detailed data describing information such as the design parameters, construction parameters, material specifications, etc. of the track slab; the production defect can be a problem occurring during the production process of the track slab, such as unqualified materials, improper manufacturing process, insufficient quality control, etc.; the track load-bearing can be external forces such as train loads and environmental loads borne by the track, and these loads may cause structural damage or abnormalities of the track.

[0099] Specifically, through image analysis and data fusion technologies, the abnormal area is identified and determined to be an abnormality inside the ballast slab. Retrieve the procurement records of the ballast slab from the database, including the manufacturer, production date, material specifications, quality control reports, etc. Analyze the procurement records to find possible causes of abnormalities, such as production defects, material problems, etc. Combine the procurement records and track filling data to determine the structural data of the ballast slab, including design parameters, actual construction parameters, etc. By comparing the structural data and the analysis results, judge whether the abnormality inside the ballast slab is caused by defects during the production process. If it is not a production defect, then analyze the load-bearing situation of the track, including train loads, environmental factors, etc., to determine whether the abnormality is caused by overloading or improper use.

[0100] In a preferred embodiment of the present invention, in the above non-destructive testing method for ballastless tracks of high-speed railways, in S3000, predicting the accident state of the abnormal area within a preset time period according to the abnormal type includes: S3010, when the abnormal type is an abnormality inside the ballast slab, analyze the track scan image to determine the current time; S3020, according to the current time, predict the environmental changes within a preset time period; S3030, obtain the track load-bearing data, and according to the track load-bearing data, determine the track load-bearing impact; S3040, according to the environmental changes and the track load-bearing impact, predict the accident state of the abnormal area within a preset time period.

[0101] The current time can be a specific time point for track scanning or data collection; environmental changes can be changes in the surrounding environmental factors that affect the track state, such as temperature, humidity, rainfall, wind force, etc.; the track load-bearing data can be a numerical value recording the load situation when trains are running on the track, such as train type, weight, running time, etc.; the track load-bearing impact can be the physical impact of the train load on the track structure, such as stress, deformation, fatigue, etc.

[0102] Specifically, if the abnormal type is an abnormality inside the ballast slab, then through image processing technology, analyze the scan image of the ballast slab of the track to determine the track state at the scan time. Use historical environmental data and weather forecast data, combined with the information at the current time, to predict the environmental change trend within a preset time period. Collect the track load-bearing data, including the train operation schedule, train type, train weight, etc., to evaluate the load situation borne by the track. Analyze the track load-bearing data to determine the impact of the load on the track structure, including stress distribution, fatigue damage, etc. Combine the track load-bearing impact and the environmental change prediction results, and use machine learning models or statistical analysis methods to predict the accident state of the abnormal area within a preset time period.

[0103] In a preferred embodiment of the present invention, in the non-destructive testing method for ballastless tracks of high-speed railways, in S4000, determining the repair timing according to the accident state and the abnormal type includes: S4010, determining the diseases that can be associated according to the abnormal type and the environmental changes; S4020, analyzing the diseases that can be associated to determine the spreading period; S4030, determining the disease impact of the diseases that can be associated on the abnormal area according to the preset period and the spreading period; S4040, determining the repair timing according to the accident state and the disease impact.

[0104] The diseases that can be associated can be diseases that may be related to the abnormal type of the track, and these diseases may be aggravated due to environmental changes or the development of the abnormal type; the spreading period can be the period when the disease develops from the initial stage to significantly affect the track performance and safety; the disease impact can be the negative impact that the disease may have on the track performance, railway operation and passenger safety.

[0105] Specifically, analyze the impact of environmental changes (such as temperature, humidity, rainfall, etc.) on the track abnormality, and the diseases that may be caused by different abnormal types. Study the development law of the diseases that can be associated, and predict its spreading speed and period under different environmental conditions. Combine the spreading period and the preset period of railway operation to evaluate the potential impact of the disease on the abnormal area. Comprehensively consider the impact of the disease and the current accident state, predict the possible accident risks in the future, and determine the best repair timing.

[0106] In a preferred embodiment of the present invention, in the non-destructive testing method for ballastless tracks of high-speed railways, in S3000, when the abnormal type is interlayer void, predicting the accident state of the abnormal area within the preset period according to the abnormal type includes: S3050, when the abnormal type is interlayer void, analyze the track scan image, determine the void characteristics of the interlayer void, determine the newly generated change area according to the void characteristics, and predict the change direction within the preset period according to the newly generated change area; S3060, retrieve and analyze the historical scan records, and determine the development period of the newly generated change area according to the historical scan analysis results; S3070, determine the difficulty of change impact according to the void characteristics; S3080, predict the accident state of the abnormal area within the preset period according to the change direction, the development period and the difficulty of change impact.

[0107] The interlayer void can be the void that appears between different layers in the ballastless track, usually appearing between the track slab and the supporting layer; the void characteristics can be the physical properties describing the interlayer void, such as the position, size, shape, distribution, etc. of the void; the newly emerging change area can be the newly emerging interlayer void or the area where the original void has changed; the change direction can be the development trend of the interlayer void over time, for example, whether the void will expand or whether new defects will form, etc.; the historical scan record can be the data and images recorded from the scanning and detection of the track over a past period of time; the development period can be the time period from the emergence of the interlayer void to its development to the current state; the difficulty of change impact can be the degree of difficulty in repairing or strengthening the interlayer void.

[0108] Specifically, use image processing techniques, such as edge detection, image segmentation, etc., to analyze the track scan image, identify and extract the characteristics of the interlayer void. By comparing the scan images at different time points, identify the newly emerging change area of the interlayer void. Utilize the characteristics of the newly emerging change area and combine with the track structure knowledge to predict the change trend of these areas within a preset future time period. Review the historical scan record, analyze the development process of the newly emerging change area, and determine its development period. According to the characteristics of the void, such as position, size, shape, etc., evaluate the difficulty of repair or strengthening. Synthesize the difficulty of change impact, the development period, and the change direction, and use the prediction model to predict the accident state of the abnormal area within a preset future time period.

[0109] In a preferred embodiment of the present invention, in the non-destructive detection method for the ballastless track of high-speed railway, in S3000, when the abnormal type is a crack in the track slab, the predicting the accident state of the abnormal area within a preset time period according to the abnormal type includes: S3090, when the abnormal type is a crack in the track slab, according to the analysis result of the abnormal area, determine whether there is the interlayer void or the abnormality inside the track slab. If so, according to the void characteristics or the internal abnormality characteristics, determine the associated influence of the interlayer void or the abnormality inside the track slab; S3100, according to the analysis result of the abnormal area, determine the crack characteristics, and according to the crack characteristics, determine the crack range; S3110, obtain the track load-bearing data, and according to the track load-bearing data, determine the track load-bearing influence; S3120, according to the associated influence, the crack range, and the track load-bearing influence, predict the accident state of the abnormal area within a preset time period.

[0110] The associated influence can be the mutual influence between different abnormal areas or defects in the track, such as the relationship between the crack in the track slab and the interlayer void, and the influence of these abnormalities on the overall performance of the track; the crack characteristics can be the physical properties describing the crack, such as the position, length, width, depth, trend, shape, etc. of the crack; the crack range can be the area affected by the crack, including the crack itself and the stress concentration area that may be caused by it.

[0111] Specifically, by analyzing the track scanning images and detection data, the crack areas of the ballastless slab are identified, and whether there are interlayer voids or internal anomalies is checked. If any exist, the characteristics of the interlayer voids or internal anomalies, such as location, size, shape, etc., are analyzed to determine their impact on crack development. Through image processing and analysis techniques, the characteristics of the cracks, such as location, length, width, depth, orientation, etc., are determined. Based on the characteristics of the cracks, such as length, width, depth, orientation, etc., the influence range of the cracks is determined. Combining the crack range, associated influence, and track load-bearing influence, a prediction model is used to predict the accident state of the abnormal area within a preset future time period.

[0112] In a preferred embodiment of the present invention, in the non-destructive detection method for ballastless tracks of high-speed railways, in S4000, determining the repair timing according to the accident state and the abnormal type includes: S4050, determining the repairable time period according to the current time; S4060, predicting the abnormal change situation of the abnormal area within the repairable time period according to the accident state; S4070, analyzing the abnormal change situation to determine the risk level; S4080, determining whether to perform repair within the repairable time period according to the risk level. If it is determined to perform repair, the repair method is determined according to the abnormal type; S4090, determining the abnormal form of the abnormal area according to the repair method; S4100, determining the abnormal state at the current time according to the abnormal accident range; S4110, determining the repair timing according to the abnormal form and the abnormal state at the current time.

[0113] The repairable time period can be the time period during which track repair work can be safely carried out without affecting the normal operation of the railway; the abnormal change situation can be the changes that may occur in the abnormal area of the track over time, such as crack expansion, increased wear, deepened corrosion, etc.; the risk level can be the level for classifying the track safety risk according to the change situation and potential impact of the abnormality; the repair method can be the specific methods and techniques for repairing track abnormalities; the abnormal form can be the shape and state of the track abnormal area before and after repair.

[0114] Specifically, using a prediction model, based on the current accident state and abnormal type, the changes that may occur in the abnormal area within the repairable time period are predicted. According to the predicted abnormal change situation, the possible risks are evaluated to determine the risk level. According to the risk level and the feasibility of the repair time period, it is decided whether to carry out repair work within the repairable time period. According to the abnormal type (such as cracks, wear, corrosion, etc.), appropriate repair methods and techniques are selected. According to the selected repair method, the form and performance of the abnormal area after repair are predicted. The scope of the abnormal accident is analyzed to determine the abnormal state of the track at the current time. Considering comprehensively the abnormal state at the current time, the abnormal form, and the prediction effect of the repair method, the optimal repair timing is determined.

[0115] In a preferred embodiment of the present invention, in the non-destructive testing method for ballastless tracks of high-speed railways, in S4110, determining the repair timing according to the abnormal form and the abnormal state at the current moment includes: S4111, determining the repair limit range according to the repair method; S4112, analyzing the abnormal state at the current moment to determine whether the abnormal state is greater than the repair limit range. If it is not greater, analyze the abnormal state to determine the abnormal difference between the abnormal state and the abnormal form; S4113, determining the repair timing according to the abnormal change situation and the abnormal difference.

[0116] The repair limit range can be the maximum degree or range of abnormalities that the repair method can effectively handle; the abnormal difference can refer to the differences between different abnormal states or forms.

[0117] Specifically, analyze the degree of abnormalities that different repair methods can handle, and determine the repair limit range for each repair method. Evaluate the severity of the current track abnormality and compare it with the limit range of the repair method. If the current abnormal state does not exceed the repair limit range, further analyze the difference between the abnormal state and the abnormal form. Combine the change trend of the abnormality and the difference between the abnormal state and form to predict the development of the abnormality and determine the best repair timing.

[0118] It should be understood that the above specific embodiments of the present invention are only used for exemplary illustration or explanation of the principle of the present invention, and do not constitute a limitation to the present invention. Therefore, any modifications, equivalent replacements, improvements, etc. made without departing from the spirit and scope of the present invention shall be included within the protection scope of the present invention. In addition, the appended claims of the present invention are intended to cover all changes and modifications that fall within the scope and boundary of the appended claims, or equivalent forms of such scope and boundary.

Claims

1. A non-destructive testing method for ballastless tracks of high-speed railways, characterized in that, Including: S1000, acquiring an orbital scan image, analyzing the orbital scan image, and determining whether there is an abnormal area; S2000, if there is an abnormal area, acquiring orbital filling data, analyzing the abnormal area according to the orbital filling data, and determining the type and cause of the abnormality; S3000, predicting the accident state of the abnormal area within a preset time period according to the type of the abnormality; S4000, determining the repair timing according to the accident state and the type of the abnormality.

2. The non-destructive testing method for ballastless tracks of high-speed railways according to claim 1, wherein, In S1000, before analyzing the orbital scan image and determining whether there is an abnormal area, it further includes: S1010, based on the orbital scan image, retrieving a scan task, analyzing the scan task, and determining the operation direction; S1020, analyzing the orbital scan image and determining the edge feature; S1030, analyzing the operation direction and the edge feature, and determining the horizon position.

3. The non-destructive testing method for ballastless track of high-speed railway according to claim 2, wherein In S2000, if there is an abnormal area, then analyzing the abnormal area according to the orbital filling data and determining the type and cause of the abnormality includes: S2010, analyzing the orbital filling data to obtain the thickness of the roadbed slab and the thickness of the supporting layer; S2020, analyzing the abnormal area according to the horizon position to obtain the abnormal accident range; S2030, analyzing the abnormal accident range according to the thickness of the roadbed slab and the thickness of the supporting layer, and determining the type of the abnormality; S2040, determining the cause of the abnormality according to the abnormal area and the type of the abnormality.

4. The non-destructive testing method for ballastless tracks of high-speed railways according to claim 3, characterized in that, In S2040, when the type of the abnormality is an abnormality inside the roadbed slab, determining the cause of the abnormality according to the abnormal area and the type of the abnormality includes: S2041, acquiring and analyzing the procurement record of the roadbed slab to obtain a record analysis result; S2042, determining the structural data of the roadbed slab according to the record analysis result; S2043, determining whether the abnormality inside the roadbed slab is a production defect according to the structural data of the roadbed slab; S2044, if it is not a production defect, determining that the cause of the abnormality inside the roadbed slab is track load-bearing.

5. The non-destructive testing method for ballastless tracks of high-speed railways according to claim 4, characterized in that, In S3000, predicting the accident state of the abnormal area within a preset time period according to the type of the abnormality includes: S3010, when the type of the abnormality is an abnormality inside the roadbed slab, analyzing the orbital scan image to determine the current time; S3020, predicting the environmental change within a preset time period according to the current time; S3030, acquiring track load-bearing data, and determining the influence of track load-bearing according to the track load-bearing data; S3040, predicting the accident state of the abnormal area within a preset time period according to the environmental change and the influence of track load-bearing.

6. The non-destructive testing method for ballastless tracks of high-speed railways according to claim 5, characterized in that, In S4000, determining the repair timing according to the accident state and the type of the abnormality includes: S4010, determining the associated diseases according to the type of the abnormality and the environmental change; S4020, analyzing the associated diseases and determining the spread time period; S4030, determining the disease influence of the associated diseases on the abnormal area according to the preset time period and the spread time period; S4040, determining the repair timing according to the accident state and the disease influence.

7. The non-destructive testing method for ballastless track of high-speed railway according to claim 1, characterized in that, In S3000, when the abnormal type is interlayer void, predicting the accident state of the abnormal area within a preset time period according to the abnormal type includes: S3050, when the abnormal type is interlayer void, analyzing the track scan image, determining the void characteristics of the interlayer void, determining the newly changed area according to the void characteristics, and predicting the change direction within a preset time period according to the newly changed area; S3060, retrieving and analyzing the historical scan records, and determining the development time period of the newly changed area according to the historical scan analysis results; S3070, determining the difficulty of change influence according to the void characteristics; S3080, predicting the accident state of the abnormal area within a preset time period according to the change direction, the development time period, and the difficulty of change influence.

8. The non-destructive testing method for ballastless track of high-speed railway according to claim 7, wherein, In S3000, when the abnormal type is a crack in the track bed slab, predicting the accident state of the abnormal area within a preset time period according to the abnormal type includes: S3090, when the abnormal type is a crack in the track bed slab, determining whether there is an interlayer void or an internal abnormality in the track bed slab according to the analysis result of the abnormal area. If so, determining the associated influence of the interlayer void or the internal abnormality in the track bed slab according to the void characteristics or the internal abnormality characteristics; S3100, determining the crack characteristics according to the analysis result of the abnormal area, and determining the crack range according to the crack characteristics; S3110, obtaining the track load data, and determining the track load influence according to the track load data; S3120, predicting the accident state of the abnormal area within a preset time period according to the associated influence, the crack range, and the track load influence.

9. The non-destructive testing method for ballastless tracks of high-speed railways according to claim 3, characterized in that, In S4000, determining the repair time according to the accident state and the abnormal type includes: S4050, determining the repairable time period according to the current time; S4060, predicting the abnormal change situation of the abnormal area within the repairable time period according to the accident state; S4070, analyzing the abnormal change situation and determining the risk level; S4080, determining whether to repair within the repairable time period according to the risk level. If it is determined to repair, determining the repair method according to the abnormal type; S4090, determining the abnormal form of the abnormal area according to the repair method; S4100, determining the abnormal state at the current time according to the abnormal accident range; S4110, determining the repair time according to the abnormal form and the abnormal state at the current time.

10. The non-destructive testing method for ballastless track of high-speed railway according to claim 9, characterized in that, In S4110, determining the repair time according to the abnormal form and the abnormal state at the current time includes: S4111, determining the repair limit range according to the repair method; S4112, analyzing the abnormal state at the current time, and determining whether the abnormal state is greater than the repair limit range. If it is not greater than, analyzing the abnormal state and determining the abnormal difference between the abnormal state and the abnormal form; S4113, determining the repair time according to the abnormal change situation and the abnormal difference.

Images