A nondestructive testing method for high-speed railway ballastless track

Abstract

The present invention discloses a nondestructive testing method for high-speed railway ballastless track, comprising: S1000, acquiring a track scan image, analyzing the track scan image, and determining whether an abnormal area exists; S2000, if an abnormal area exists, acquiring track filling data, analyzing the abnormal area based on the track filling data, and determining the abnormality type and cause; S3000, predicting the accident state of the abnormal area within a preset time period based on the abnormality type; S4000, determining the repair opportunity based on the accident state and the abnormality type. By integrating high-precision image detection technology, data analysis methods, and fault prediction models, the present invention can achieve accurate detection and early warning of track anomalies, provide scientific maintenance decision support, and significantly improve the safety and maintenance efficiency of high-speed railway ballastless track.

Description

Technical Field

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

[0002] The ballastless track system of a high-speed railway typically consists of sleepers, rails, a roadbed, and other ancillary facilities. Because ballastless track can effectively withstand the vibration and pressure of high-speed trains, and exhibits excellent stability, especially in harsh climatic and geological conditions, it has been widely used in high-speed railway construction both domestically and internationally. In recent years, with the continuous increase in train speeds and transportation volumes, track operating conditions have become increasingly stringent, making track damage and defects more prominent. Track wear, rail cracks, cracking and settlement of the concrete roadbed, and deviations in track geometry all affect the safety and comfort of train operation.

[0003] Currently, ballastless track inspection methods primarily include manual inspection, ground measurement, and nondestructive testing (NDT) using various detection methods (such as ultrasonic, laser, and infrared). While these technologies can identify faults and defects in track systems to a certain extent, they still face limitations, such as limited accuracy, slow inspection speed, and high manual intervention costs. Traditional inspection methods often struggle to provide real-time, comprehensive monitoring and diagnosis of microcracks and early-stage damage, especially when it comes to detecting minor track cracks and early-stage damage.

[0004] With advances in science and technology, particularly the rapid development of artificial intelligence, big data, and sensor technology, nondestructive testing (NDT) for railway tracks is gradually moving towards intelligent, automated, and real-time capabilities. The widespread use of high-precision sensors and integrated testing equipment has expanded ballastless track testing beyond a single technical approach. By integrating multiple testing methods and conducting data analysis, comprehensive monitoring of track operating conditions and early warning of faults are now possible.

[0005] For example, track detection sensors installed on high-speed trains can collect real-time data on the mechanical changes in contact between the train and the track. Through data processing and analysis, abnormal track behavior can be promptly identified. Furthermore, deep learning and pattern recognition using artificial intelligence algorithms on detection data can help improve detection accuracy and efficiency, particularly in identifying early-stage damage such as fine cracks and fatigue damage.

[0006] Although current non-destructive testing technology has made significant progress to a certain extent, the following major problems still exist: (1) Low detection accuracy. Existing non-destructive testing technology is still limited in identifying some small cracks or hidden damages, especially under the dynamic load of high-speed train operation. Traditional technology often cannot reflect the actual status of the track in real time and accurately; (2) Slow detection speed. Traditional manual or semi-automatic detection methods cannot meet the real-time monitoring needs of high-speed railway operation. Existing non-destructive testing methods still require a long time period for 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 across regions and companies, affecting the overall efficiency of railway maintenance and management; (4) High cost and high dependence on labor. Although sensors and automated detection equipment are constantly being used, high-precision and high-stability equipment still requires a lot of capital investment and manual operation. Summary of the Invention

[0007] The object of the present invention is to provide a non-destructive testing method for high-speed railway ballastless track, which is used to solve at least one of the above technical problems. It can solve the problems of detection accuracy, speed and cost existing in the prior art and improve the safety and durability of ballastless track.

[0008] The embodiment of the present invention is achieved as follows:

[0009] A nondestructive testing method for high-speed railway ballastless track, comprising:

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

[0011] S2000: If an abnormal area exists, obtain track filling data, analyze the abnormal area based on the track filling data, and determine the abnormality type and cause of the abnormality;

[0012] S3000, predicting the accident status of the abnormal area within a preset time period based on the abnormality type;

[0013] S4000: Determine a repair opportunity based on the accident status and the abnormality type.

[0014] In a preferred embodiment of the present invention, in the above-mentioned nondestructive testing method for high-speed railway ballastless track, in S1000, before analyzing the track scanning image to determine whether there is an abnormal area, the method further includes:

[0015] S1010, based on the track scanning image, retrieve a scanning task, analyze the scanning task, and determine an operation direction;

[0016] S1020, analyzing the track scanning image to determine edge features;

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

[0018] Its technical benefits include ensuring that analysis work is consistent with the current scanning task, providing the latest track status data, and providing accurate context for subsequent analysis. Determining the scanning direction helps accurately identify the edge features and abnormal areas of the trackbed slab in subsequent image analysis, improving the accuracy and efficiency of the analysis. Extracting the edge features of the trackbed slab helps identify the location of the surface layer of the trackbed slab in the radar image, providing a basis for determining the horizontal position and a reference for subsequent abnormal area identification. Determining the horizontal position provides a stable reference point, helping to determine deformation and other structural issues revealed by radar images of the trackbed slab, laying the foundation for subsequent abnormal area identification and accident status prediction.

[0019] In a preferred embodiment of the present invention, in the above-mentioned high-speed railway ballastless track nondestructive testing method, in S2000, if an abnormal area exists, analyzing the abnormal area based on the track filling data to determine the abnormality type and abnormality cause includes:

[0020] S2010, analyzing the track filling data to obtain the track bed plate thickness and the supporting layer thickness;

[0021] S2020: Analyze the abnormal area based on the horizontal position to obtain the abnormal accident range;

[0022] S2030, analyzing the abnormal accident range and determining the abnormality type based on the thickness of the roadbed slab and the thickness of the supporting layer;

[0023] S2040: Determine the cause of the abnormality according to the abnormal area and the abnormality type.

[0024] Its technical effect is that by analyzing the track filling data, key information such as the thickness of the track bed and supporting layer can be obtained. By using the horizontal 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 track bed. According to the characteristics and horizontal position of the abnormal area, the scope of the possible impact of the abnormal accident can be determined, and the degree of impact of the abnormality on the overall structure of the track can be evaluated. Combined with the thickness data of the track bed and supporting layer, the impact of the abnormal accident scope on the track structure can be analyzed. According to the characteristics of the abnormal area, the accident scope and structural thickness data, the type of abnormality can be determined. Combined with the abnormality type and regional characteristics, the possible causes of the abnormality can be analyzed, such as material defects, construction problems, environmental factors, etc., which can prevent the occurrence of problems in advance, and it is crucial to improve the efficiency and effectiveness of track maintenance.

[0025] In a preferred embodiment of the present invention, in the above-mentioned high-speed railway ballastless track nondestructive testing method, in S2040, when the abnormality type is an internal abnormality of the trackbed plate, determining the cause of the abnormality based on the abnormal area and the abnormality type includes:

[0026] S2041, obtaining and analyzing the track bed plate procurement records to obtain record analysis results;

[0027] S2042, determining the track bed plate structure data according to the record analysis results;

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

[0029] S2044: If it is not a production defect, determine that the cause of the abnormality inside the track bed plate is the track load-bearing.

[0030] Its technical effect is that by analyzing procurement records, we can understand the source, production date, material specifications, quality control and other information of the track bed slab, and determine the structural data such as the design parameters and actual construction parameters of the track bed slab, which helps to trace the quality of the track bed slab and potential production problems. The record analysis results may reveal problems such as irregular operations, material quality problems or insufficient quality control in the production process, and the cause of the abnormality can be determined. By comparing the structural data and analysis results, it can be determined whether the internal abnormality of the track bed slab is caused by defects in the production process, and thus determine whether corrective measures need to be taken. If it is not a production defect, the load-bearing conditions of the track are analyzed, including train loads, environmental factors, etc., to determine whether the abnormality is caused by excessive load or improper use, so that corresponding preventive measures can be taken.

[0031] In a preferred embodiment of the present invention, in the above-mentioned high-speed railway ballastless track nondestructive testing method, in S3000, predicting the accident state of the abnormal area within a preset time period based on the abnormality type includes:

[0032] S3010, when the abnormality type is an internal abnormality of the track bed plate, analyzing the track scanning image to determine the current time;

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

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

[0035] S3040: Predicting the accident status of the abnormal area within a preset time period based on the environmental changes and the impact of the track load-bearing capacity.

[0036] Its technical effects are: through image processing and analysis technology, the current track status is obtained to provide real-time data for subsequent predictions. Historical environmental data and weather forecast information are used to predict future environmental change trends and evaluate the possible impact of these changes on abnormal track areas. Train operation data, including train type, weight, operating time, etc., are collected to evaluate the load conditions borne by the track. Load-bearing data is analyzed to evaluate the stress distribution and potential damage of the track structure, and provide load-bearing impact analysis results for predicting accident conditions. Combining load-bearing impact and environmental change predictions, machine learning models or statistical analysis methods are used to predict the accident status of abnormal areas within a preset time period in the future, providing a basis for maintenance decisions.

[0037] In a preferred embodiment of the present invention, in the above-mentioned high-speed railway ballastless track nondestructive testing method, in S4000, determining the repair timing according to the accident state and the abnormality type includes:

[0038] S4010, determining a related disease based on the abnormality type and the environmental change;

[0039] S4020, analyzing the associated diseases and determining the spreading period;

[0040] S4030: Determine the impact of the associated disease on the abnormal area based on the preset time period and the spreading time period;

[0041] S4040: Determine a repair timing based on the accident status and the impact of the disease.

[0042] Its technical benefits include: analyzing the impact of environmental factors on track anomalies to identify defects likely associated with specific anomaly types, enabling preventive measures to be taken. It also studies the development patterns of defects and predicts their spread rate and duration under different environmental conditions, allowing for pre-planned repair work. By combining the duration of the defect's spread with the pre-set operating hours of the railway, it assesses the potential impact of the defect on the anomaly area to determine the urgency and priority of repairs. By comprehensively considering the impact of the defect and the current accident status, it predicts the risk of future accidents, determines the optimal timing for repairs, and ensures that repairs are carried out before the damage causes an accident.

[0043] In a preferred embodiment of the present invention, in the above-mentioned high-speed railway ballastless track nondestructive testing method, in S3000, when the abnormality type is interlayer gap, predicting the accident state of the abnormal area within a preset time period based on the abnormality type includes:

[0044] S3050: When the anomaly type is an interlayer gap, analyze the track scanning image to 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, retrieving and analyzing historical scan records, and determining the development period of the newly changed area based on the historical scan analysis results;

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

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

[0048] The technical benefits of this technology include: using image analysis techniques such as image segmentation and feature extraction, the location, size, and shape of interlayer voids can be accurately identified, enabling assessment of their severity and potential impact. By comparing scanned images at different time points, new interlayer voids can be identified; emerging areas of change may represent areas requiring future attention and treatment. By analyzing the characteristics of these emerging areas of change, it is possible to predict their future trends over a predetermined period of time, such as whether the voids will expand or form new defects. By reviewing historical scan records and analyzing the development of these areas of change and determining their development timeframe, it is possible to understand the timing and rate of void formation. Based on the location, size, and shape of the voids, the difficulty of repair or reinforcement can be assessed, assisting in developing repair plans and determining the required resources. By integrating the impact difficulty, development timeframe, and direction of the change, it is possible to predict potential accidents in these areas of abnormality over a predetermined period of time, such as track subsidence or fracture, enabling timely preventive measures.

[0049] In a preferred embodiment of the present invention, in the above-mentioned high-speed railway ballastless track nondestructive testing method, in S3000, when the abnormality type is a trackbed slab crack, predicting the accident state of the abnormal area within a preset time period based on the abnormality type includes:

[0050] S3090, when the abnormality type is a track bed slab crack, determining whether there is an interlayer gap or an internal abnormality of the track bed slab based on the analysis result of the abnormal area; if so, determining the associated impact of the interlayer gap or the internal abnormality of the track bed slab based on the characteristics of the gap or the characteristics of the internal abnormality;

[0051] S3100, determining crack characteristics based on the analysis results of the abnormal area, and determining the crack range based on the crack characteristics;

[0052] S3110, obtaining track load-bearing data, and determining the track load-bearing impact based on the track load-bearing data;

[0053] S3120: Predict the accident status 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 benefits are as follows: By analyzing track scanning images and inspection data, it is possible to identify cracked areas in the trackbed slab and check for interlayer voids or internal anomalies, thereby assessing the severity and potential impact of the cracks. The characteristics of interlayer voids or internal anomalies are analyzed to determine their impact on crack development, and the potential impact of interlayer voids or internal anomalies on cracks is assessed to better predict crack development trends. By comprehensively considering the crack scope, associated impacts, and track load-bearing effects, a predictive model is used to predict the accident status of abnormal areas within a preset future time period. This predicts the accident risks that may result from cracks, such as track fracture and structural instability, so that timely preventive measures can be taken.

[0055] In a preferred embodiment of the present invention, in the above-mentioned high-speed railway ballastless track nondestructive testing method, in S4000, determining the repair timing according to the accident state and the abnormality type includes:

[0056] S4050, determining a repairable period based on the current time;

[0057] S4060: predicting abnormal changes in the abnormal area within the repairable period based on the accident status;

[0058] S4070, analyzing the abnormal changes and determining the risk level;

[0059] S4080, determining whether to perform repair within the repairable period based on the risk level, and if repair is determined, determining a repair method based on the anomaly type;

[0060] S4090, determining the abnormal shape of the abnormal area according to the repair method;

[0061] S4100, determining the abnormal state at the current moment according to the abnormal accident range;

[0062] S4110: Determine a repair opportunity based on the abnormal form and the abnormal state at the current moment.

[0063] Its technical benefits include identifying time periods within the railway operation plan that will not disrupt train operations, allowing for repair work to be carried out. This can also help mitigate the issue of track slab repairs being unable to be performed in winter. By analyzing the current accident status and anomaly type, the system predicts potential changes in the anomaly area during the future repairable period, allowing for proactive preparation. The system assesses the risks associated with these changes and determines the risk level to determine whether urgent repairs are necessary. Based on the risk level and the feasibility of the repair window, the system determines whether to carry out repairs within the repairable period to ensure effective repairs and long-term track performance. The system selects the most appropriate repair method and technology based on the anomaly type to ensure effective repairs and long-term track performance. Based on the selected repair method, the system predicts the morphology and performance of the repaired anomaly area to assess the track's post-repair condition. The system analyzes the scope of the anomaly incident and determines the current track anomaly status to understand the current anomaly. By comprehensively considering the current anomaly status, anomaly morphology, and the predicted effect of the repair method, the system determines the optimal repair timing to ensure that repairs are carried out at the optimal time, minimizing the impact on railway operations and maximizing the effectiveness of the repair.

[0064] In a preferred embodiment of the present invention, in the above-mentioned high-speed railway ballastless track nondestructive testing method, in S4110, determining the repair timing based on the abnormal form and the abnormal state at the current moment includes:

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

[0066] S4112, analyzing the abnormal state at the current moment to determine whether the abnormal state exceeds the repair limit range; if not, analyzing the abnormal state to determine the abnormal difference between the abnormal state and the abnormal form;

[0067] S4113: Determine a repair opportunity based on the abnormal change and the abnormal difference.

[0068] Its technical effect is to determine the degree of abnormality and repair limit range that each repair method can handle by evaluating the applicability and effectiveness of different repair methods. Non-destructive testing technology is used to assess the severity of the current track abnormality and compare it with the repair method's limit range to determine whether the current abnormality exceeds the repair method's capabilities. If the current abnormal state does not exceed the repair limit range, further analysis is conducted on the difference between the abnormal state and the abnormal morphology to identify the specific characteristics of the abnormality, such as the depth, width, and distribution of the cracks. Combining the abnormal change trend and the difference between the abnormal state and morphology, the development of the abnormality is predicted, the optimal repair time is determined, and repair is performed before the abnormality develops to a critical point to prevent further damage and potential safety risks.

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

[0070] The present invention provides a non-destructive testing method for high-speed railway ballastless track. By acquiring detailed images of the roadbed slab using high-precision imaging equipment, the method can capture subtle changes and potential defects in the roadbed slab, provide rich basic data, and lay a solid foundation for subsequent analysis.

[0071] By applying advanced image processing and analysis technologies, it is possible to automatically identify abnormal areas in track images, including cracks, wear, deformation, etc., reducing errors in manual detection and improving efficiency.

[0072] The present invention combines track scanning images with track filling data (such as roadbed slab thickness, supporting layer thickness, etc.) obtained from construction archives. This not only enables a deeper understanding of the structural status of the track, but also accurately analyzes the characteristics of abnormal areas, determines the type of abnormality (such as internal defects, cracks or settlement) and its possible cause (such as material defects or excessive wear).

[0073] Based on a predictive model, this invention can predict the accident status of an anomaly area, such as whether the anomaly will worsen or impact railway operational safety, thereby providing early warning of faults. Based on the predicted accident status and anomaly type, it recommends the optimal repair timing, helping railway operators optimize maintenance plans, avoid excessive maintenance or delayed repairs, and effectively reduce maintenance costs. By taking preventive measures in advance, the potential risk of accidents caused by track anomalies is reduced, ensuring safe railway operations. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without paying any creative work.

[0075] Figure 1 This is a flow chart of the nondestructive testing method for high-speed railway ballastless track of the present invention;

[0076] Figure 2 The figure is a schematic diagram of an application scenario of an embodiment of the nondestructive testing method for high-speed railway ballastless track of the present invention. DETAILED DESCRIPTION

[0077] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions of the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only 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 herein can be arranged and designed in various different configurations.

[0078] As the use time of ballastless track increases, 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, obtaining a track scanning image, analyzing the track scanning image, and determining whether there is an abnormal area; S2000, if there is an abnormal area, obtaining track filling data, analyzing the abnormal area according to the track filling data, and determining the abnormality type and the cause of the abnormality; S3000, predicting the accident status of the abnormal area within a preset time period according to the abnormality type; S4000, determining the repair opportunity according to the accident status and the abnormality type.

[0081] Figure 2This application provides a schematic diagram of an application scenario, employing the method provided herein for non-destructive inspection of track slab defects on high-speed railway ballastless tracks. Specifically, the method provided herein is applied to any server, interacting with the server, geological radar, and construction archive system. High-precision geological radar captures track scan images of the track slab, revealing subtle changes and potential defects. These images provide foundational data for subsequent identification and analysis of abnormal areas. Image processing and analysis techniques automatically identify abnormal areas in track images, such as cracks, wear, and deformation. Track fill data obtained from the construction archive system, such as track slab thickness and supporting layer thickness, provides a deeper understanding of the track's structural condition. Combining track scan images with fill data allows for analysis of abnormal area characteristics, determining the type of anomaly (e.g., internal defects, cracks, settlement), and inferring the cause of these anomalies (e.g., material defects, excessive wear). Predictive models can be used to predict the potential accident conditions within a preset timeframe, including potential deterioration and impact on railway operational safety. This helps preventive measures be taken in advance to avoid accidents. Based on the predicted accident status and the identified abnormality type, the optimal repair time is recommended; the maintenance plan is optimized, maintenance efficiency is improved, and the safety of railway operations is ensured. The specific implementation method can be referred to in the following examples.

[0082] S1000 , obtaining a track scanning image, analyzing the track scanning image, and determining whether there is an abnormal area.

[0083] The track scanning image may be radar image information of the track bed and its deep layer obtained by geological radar; the abnormal area may be an area displayed in the track scanning image that is inconsistent with the normal track state.

[0084] Specifically, geological radar is used to scan high-speed railway ballastless tracks, acquiring high-resolution track scan images. The acquisition process requires ensuring image clarity and error-free quality to ensure high data quality. Image processing algorithms (such as edge detection, morphological analysis, and deep learning models) are used to analyze the track scan images, extracting edge features, texture characteristics, and other key indicators of the trackbed, and identifying any abnormal areas.

[0085] S2000: If an abnormal area exists, track filling data is obtained, and the abnormal area is analyzed based on the track filling data to determine the abnormality type and cause.

[0086] Track filling data can be relevant data of the track bed and filling layer obtained through sensors or measuring equipment or construction files; the abnormality type can be the result of classifying the detected abnormal area, such as internal abnormality of the track bed, cracks, settlement, damage to the supporting layer, etc.; the abnormality cause can be the fundamental factor leading to the track abnormality obtained by analyzing the detected abnormal area, such as material defects, improper construction, excessive wear, influence of environmental factors, etc.

[0087] Specifically, if an abnormal area is found, the trackbed slab filling data, including the thickness of the slab, the height of the supporting layer, and the load-bearing capacity of the track, is obtained from the construction archives of previous construction. The track scan images and the filling data are integrated and analyzed to form a complete model of the trackbed slab condition. Based on the analysis results, the specific type and cause of the abnormal area are further determined.

[0088] S3000, predicting the accident status of the abnormal area within a preset time period according to the abnormality type; S4000, determining a repair opportunity according to the accident status and the abnormality type.

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

[0090] Specifically, a track anomaly prediction model is established using machine learning algorithms (such as regression models and support vector machines). Input parameters for model training include the characteristics of the anomaly area, historical scan records, track filling data, and environmental change data. Since the operating environment of the track may affect its condition, environmental changes (such as temperature, humidity, and precipitation) are acquired and analyzed in real time and incorporated into the accident prediction model. Based on the predicted accident status and anomaly type, the need for repair of the anomaly area and the timing of repair are automatically determined. A risk assessment is performed on the repair timing based on the current anomaly status and predicted anomaly changes. If the risk level of an anomaly area exceeds a set threshold, it is determined to require immediate repair. Repair solutions are automatically recommended based on the anomaly type, such as replacing the trackbed, repairing cracks, or reinforcing the supporting layer.

[0091] In a preferred embodiment of the present invention, in the above-mentioned high-speed railway ballastless track non-destructive testing method, in S1000, before analyzing the track scanning image to determine whether there is an abnormal area, it also includes: S1010, based on the track scanning image, calling the scanning task, analyzing the scanning task, and determining the working direction; S1020, analyzing the track scanning image to determine the edge features; S1030, analyzing the working direction and the edge features to determine the horizontal position.

[0092] A scanning task may be a series of operations and plans for scanning and inspecting the track, including the time, location, equipment used, scope and parameters of the scan, etc.; an operation direction may be the direction of scanning along the track, that is, whether the scan is performed from one end of the track to the other end, or along a specific direction of the track; an edge feature may be an edge or contour displayed in a radar image of the track bed; and a horizontal position may be a horizontal reference line in a radar image of the track bed.

[0093] Specifically, the current scanning task information, including the scanning time, location, equipment parameters, and scanning range, is retrieved from a database or scanning task management system. Based on this scanning task information, the scanning direction along the track is analyzed to determine whether the scan is from one end of the track to the other or along a specific direction. Image processing techniques, such as edge detection algorithms (e.g., Sobel operator, Canny operator, etc.), are used to analyze the scanned images of the trackbed slab and extract edge features from the radar image of the trackbed slab. Combining these edge features with the scanning direction, geometric analysis and pattern recognition techniques are used to determine the horizontal position in the trackbed slab image, namely, the trackbed slab's horizontal reference line.

[0094] In a preferred embodiment of the present invention, in the above-mentioned high-speed railway ballastless track non-destructive testing method, in S2000, if there is an abnormal area, then according to the track filling data, the abnormal area is analyzed to determine the abnormality type and the abnormality cause, including: S2010, analyzing the track filling data to obtain the roadbed plate thickness and the supporting layer thickness; S2020, according to the horizontal position, analyzing the abnormal area to obtain the abnormal accident range; S2030, according to the roadbed plate thickness and the supporting layer thickness, analyzing the abnormal accident range to determine the abnormality type; S2040, according to the abnormal area and the abnormality type, determining the abnormality cause.

[0095] The roadbed slab thickness can be the thickness of the concrete slab used to support sleepers and rails in a ballastless track; the supporting layer thickness can be the thickness of the material layer (such as a sand cushion layer, a gravel layer, etc.) under the roadbed slab used to disperse the load and provide stability; the abnormal accident range can be the area that may be affected by the abnormal area detected in the radar image of the track bed slab, including the directly affected track section and the adjacent areas that may be indirectly affected.

[0096] Specifically, the thickness information of the trackbed and supporting layer is extracted from the track filling data. Image processing techniques, combined with ground position information, are used to analyze abnormal areas in the track scan images. Based on the characteristics and ground position of the abnormal area, the potential impact range of the abnormal accident is determined. Combined with the thickness data of the trackbed and supporting layer, the impact of the abnormal accident range on the track structure is analyzed. The type of abnormality is determined based on the characteristics of the abnormal area, the accident range, and the structural thickness data. Combining the abnormality type and regional characteristics, the possible causes of the abnormality are analyzed, such as material defects, construction problems, and environmental factors.

[0097] In a preferred embodiment of the present invention, in the above-mentioned high-speed railway ballastless track non-destructive testing method, in S2040, when the abnormality type is an internal abnormality of the roadbed plate, determining the cause of the abnormality based on the abnormal area and the abnormality type includes: S2041, obtaining and analyzing the roadbed plate procurement records to obtain record analysis results; S2042, determining the roadbed plate structural data based on the record analysis results; S2043, determining whether the internal abnormality of the roadbed plate is a production defect based on the roadbed plate structural data; S2044, if it is not a production defect, determining that the abnormal cause of the internal abnormality of the roadbed plate is the track bearing.

[0098] Internal abnormalities of the track bed slab may be any abnormal conditions existing inside the track bed slab of the ballastless track, such as cracks, voids, material separation, etc.; track bed slab procurement records may be documents or databases that record the procurement process of the track bed slab, supplier information, production batches, quality inspection reports and other information; record analysis results may be conclusions or problems found after analyzing the track bed slab procurement records; track bed slab structural data may be detailed data describing information such as the track bed slab design parameters, construction parameters, material specifications, etc.; production defects may be problems that arise during the production process of the track bed slab, such as unqualified materials, improper manufacturing processes, insufficient quality control, etc.; track load bearing may be external forces such as train loads and environmental loads that the track bears, which may cause structural damage or abnormalities to the track.

[0099] Specifically, through image analysis and data fusion technology, the abnormal area is identified and determined to be an internal abnormality of the track bed slab. The procurement records of the track bed slab are retrieved from the database, including the manufacturer, production date, material specifications, quality control reports, etc. The procurement records are analyzed to find out the possible causes of the abnormality, such as production defects, material problems, etc. Combining the procurement records and track filling data, the structural data of the track bed slab is determined, including design parameters, actual construction parameters, etc. By comparing the structural data and analysis results, it is determined whether the internal abnormality of the track bed slab is caused by defects in the production process. If it is not a production defect, the load-bearing conditions of the track are analyzed, including train loads, environmental factors, etc., to determine whether the abnormality is caused by excessive load or improper use.

[0100] In a preferred embodiment of the present invention, in the above-mentioned non-destructive testing method for high-speed railway ballastless track, in S3000, the accident status of the abnormal area within a preset time period is predicted based on the abnormality type, including: S3010, when the abnormality type is an internal abnormality of the track bed plate, analyzing the track scanning image to determine the current time; S3020, predicting the environmental changes within a preset time period based on the current time; S3030, obtaining track bearing data, and determining the track bearing impact based on the track bearing data; S3040, predicting the accident status of the abnormal area within a preset time period based on the environmental changes and the track bearing impact.

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

[0102] Specifically, if the abnormality type is an internal abnormality of the trackbed, the scanned image of the trackbed is analyzed through image processing technology to determine the track status at the time of scanning. Historical environmental data and weather forecast data are used in combination with the information at the current moment to predict the trend of environmental changes within a preset time period. Track load-bearing data is collected, including train schedules, train types, train weights, etc., to evaluate the load conditions borne by the track. Track load-bearing data is analyzed to determine the impact of load on the track structure, including stress distribution, fatigue damage, etc. Combining the track load-bearing impact and environmental change prediction results, machine learning models or statistical analysis methods are used to predict the accident status of abnormal areas within a preset time period.

[0103] In a preferred embodiment of the present invention, in the above-mentioned non-destructive testing method for high-speed railway ballastless track, in S4000, determining the repair timing according to the accident status and the abnormality type includes: S4010, determining the associated defects according to the abnormality type and the environmental changes; S4020, analyzing the associated defects and determining the propagation period; S4030, determining the impact of the associated defects on the abnormal area according to the preset period and the propagation period; S4040, determining the repair timing according to the accident status and the impact of the defects.

[0104] Associable defects can be defects that may be related to track anomaly types, which may be exacerbated by environmental changes or the development of anomaly types; the spread period can be the period from the initial stage of the defect to the time when it significantly affects track performance and safety; the impact of the defect can be the negative impact that the defect may have on track performance, railway operations and passenger safety.

[0105] Specifically, we analyze the impact of environmental changes (such as temperature, humidity, and rainfall) on track anomalies, as well as the potential damage caused by different anomaly types. We study the development patterns of related damage and predict its spread rate and duration under different environmental conditions. We assess the potential impact of damage on the anomaly area, combining the spread period with the pre-set railway operation period. By comprehensively considering the impact of the damage and the current accident status, we predict the risk of future accidents and determine the optimal repair timing.

[0106] In a preferred embodiment of the present invention, in the above-mentioned non-destructive testing method for high-speed railway ballastless track, in S3000, when the abnormality type is an interlayer gap, the predicting of the accident state of the abnormal area within a preset time period based on the abnormality type includes: S3050, when the abnormality type is an interlayer gap, analyzing the track scanning image, determining the gap characteristics of the interlayer gap, determining the new change area based on the gap characteristics, and predicting the change direction within a preset time period based on the new change area; S3060, retrieving and analyzing historical scanning records, and determining the development period of the new change area based on the historical scanning analysis results; S3070, determining the difficulty of the change impact based on the gap characteristics; S3080, predicting the accident state of the abnormal area within a preset time period based on the change direction, the development period and the difficulty of the change impact.

[0107] Interlayer voids can be voids that appear between different layers in ballastless track, usually between the trackbed and the supporting layer; void characteristics can be physical properties that describe the interlayer voids, such as the location, size, shape, distribution, etc. of the voids; emerging change areas can be newly appeared interlayer voids or areas where existing voids have changed; the direction of change can be the development trend of the interlayer voids over time, such as whether the voids will expand or whether new defects will form; historical scanning records can be data and images recorded by scanning and detecting the track over a period of time in the past; the development period can be the time period from the appearance of the interlayer voids to their development to the current state; the difficulty of the change impact can be the difficulty of repairing or reinforcing the interlayer voids.

[0108] Specifically, image processing techniques, such as edge detection and image segmentation, are used to analyze track scan images and identify and extract the characteristics of interlayer gaps. Newly changed areas of interlayer gaps are identified by comparing scan images at different time points. The characteristics of these newly changed areas, combined with track structure knowledge, are used to predict the changing trends of these areas within a preset future time period. Historical scan records are reviewed to analyze the development process of newly changed areas and determine their development period. The difficulty of repair or reinforcement is assessed based on the location, size, shape, and other characteristics of the gaps. Taking into account the difficulty of the change impact, the development period, and the direction of change, a prediction model is used to predict the accident status of abnormal areas within a preset future time period.

[0109] In a preferred embodiment of the present invention, in the above-mentioned non-destructive testing method for high-speed railway ballastless track, in S3000, when the abnormality type is a crack in the track bed slab, predicting the accident state of the abnormal area within a preset time period based on the abnormality type includes: S3090, when the abnormality type is a crack in the track bed slab, determining whether the interlayer gap or the internal abnormality of the track bed slab exists based on the analysis result of the abnormal area, and if so, determining the associated influence of the interlayer gap or the internal abnormality of the track bed slab based on the gap characteristics or the internal abnormality characteristics; S3100, determining the crack characteristics based on the analysis result of the abnormal area, and determining the crack range based on the crack characteristics; S3110, obtaining track bearing data, and determining the track bearing influence based on the track bearing data; S3120, predicting the accident state of the abnormal area within a preset time period based on the associated influence, the crack range and the track bearing influence.

[0110] The associated impact can be the mutual influence between different abnormal areas or defects in the track, such as the relationship between cracks in the trackbed and interlayer gaps, and the impact of these anomalies on the overall performance of the track; crack characteristics can be the physical properties that describe the cracks, such as the location, length, width, depth, direction, and shape of the cracks; crack range can be the area affected by the cracks, including the cracks themselves and the stress concentration areas that may be caused by them.

[0111] Specifically, by analyzing track scanning images and inspection data, the cracked areas of the trackbed slab are identified and the presence of interlayer voids or internal anomalies is checked. If present, the characteristics of the interlayer voids or internal anomalies, such as location, size, and shape, are analyzed to determine their impact on crack development. Image processing and analysis techniques are used to determine the location, length, width, depth, and direction of the cracks. Based on the crack characteristics, such as length, width, depth, and direction, the impact range of the cracks is determined. A prediction model is used to predict the accident status of the abnormal area within a preset future time period, taking into account the crack range, associated impacts, and the impact of track load.

[0112] In a preferred embodiment of the present invention, in the above-mentioned non-destructive testing method for high-speed railway ballastless track, in S4000, the determination of the repair opportunity based on the accident status and the abnormality type includes: S4050, determining the repairable time period based on the current time; S4060, predicting the abnormal changes of the abnormal area within the repairable time period based on the accident status; S4070, analyzing the abnormal changes to determine the risk level; S4080, determining whether to repair within the repairable time period based on the risk level, and if repair is determined, determining the repair method based on the abnormality type; S4090, determining the abnormal form of the abnormal area based on the repair method; S4100, determining the abnormal state at the current time based on the abnormal accident range; S4110, determining the repair opportunity based on the abnormal form and the abnormal state at the current time.

[0113] The repairable period can be the time period when track repair work can be carried out safely 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 the expansion of cracks, increased wear, deepening corrosion, etc.; the risk level can be the level of classification of track safety risks based on the abnormal changes and potential impact; the repair method can be the specific method and technology used to repair the track anomaly; the abnormal morphology can be the shape and state of the abnormal area of ​​the track before and after repair.

[0114] Specifically, a prediction model is used to predict possible changes in the abnormal area within the repairable period based on the current accident status and abnormality type. Based on the predicted abnormal changes, the potential risks are assessed and the risk level is determined. Based on the risk level and the feasibility of the repair period, a decision is made as to whether to perform repair work within the repairable period. Based on the abnormality type (such as cracks, wear, corrosion, etc.), appropriate repair methods and techniques are selected. Based on the selected repair method, the morphology and performance of the repaired abnormal area are predicted. The scope of the abnormal accident is analyzed to determine the current abnormal state of the track. The optimal repair time is determined by comprehensively considering the current abnormal state, abnormal morphology, and the predicted effect of the repair method.

[0115] In a preferred embodiment of the present invention, in the above-mentioned non-destructive testing method for high-speed railway ballastless track, in S4110, the determining of the repair timing based on the abnormal form and the abnormal state at the current moment includes: S4111, determining the repair limit range based on 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, and if not, analyzing the abnormal state to determine the abnormal difference between the abnormal state and the abnormal form; S4113, determining the repair timing based on the abnormal change and the abnormal difference.

[0116] The repair limit range may be the maximum degree or range of an abnormality that can be effectively handled by the repair method; and the abnormality difference may refer to the difference between different abnormal states or forms.

[0117] Specifically, analyze the severity of the anomaly that different repair methods can address and determine the repair limits for each method. Assess the severity of the current track anomaly and compare it to the repair limits of the repair method. If the current anomaly does not exceed the repair limits, further analyze the difference between the anomaly state and its morphology. Combining the anomaly's changing trends and the differences between the anomaly state and morphology, predict the anomaly's development and determine the optimal repair timing.

[0118] It should be understood that the above-described specific embodiments of the present invention are merely illustrative or illustrative of the principles of the present invention and do not constitute limitations of the present invention. Therefore, any modifications, equivalent substitutions, improvements, etc. made without departing from the spirit and scope of the present invention should be included within the scope of protection of the present invention. In addition, the appended claims are intended to cover all variations and modifications that fall within the scope and metes and bounds of the appended claims, or equivalents thereof.

Claims

1. A nondestructive testing method for high-speed railway ballastless track, characterized in that: include: S1000, acquiring a track scan image, analyzing the track scan image, and determining whether there is an abnormal area. In S1000, before analyzing the track scan image to determine whether there is an abnormal area, the process further includes: S1010, retrieving a scan task based on the track scan image, analyzing the scan task, and determining an operation direction; S1020, analyzing the track scan image to determine edge features; S1030, analyzing the operation direction and the edge features to determine a horizontal position; S2000, if an abnormal area exists, obtain track filling data, analyze the abnormal area based on the track filling data, and determine the abnormality type and abnormality cause. In S2000, if an abnormal area exists, analyze the abnormal area based on the track filling data to determine the abnormality type and abnormality cause, including: S2010, analyze the track filling data to obtain the roadbed slab thickness and the supporting layer thickness; S2020, analyze the abnormal area based on the ground position to obtain the abnormal accident range; S2030, analyze the abnormal accident range based on the roadbed slab thickness and the supporting layer thickness to determine the abnormality type; S2040, determine the abnormality cause based on the abnormal area and the abnormality type; S3000, predicting the accident status of the abnormal area within a preset time period based on the abnormality type; S4000: Determine a repair opportunity based on the accident status and the abnormality type.

2. The nondestructive testing method for high-speed railway ballastless track according to claim 1, characterized in that: In S2040, when the abnormality type is an internal abnormality of the track bed plate, determining the cause of the abnormality based on the abnormal area and the abnormality type includes: S2041, obtaining and analyzing the track bed plate procurement records to obtain record analysis results; S2042, determining the track bed plate structure data according to the record analysis results; S2043, determining whether the internal abnormality of the track bed plate is a production defect based on the track bed plate structural data; S2044: If it is not a production defect, determine that the cause of the abnormality inside the track bed plate is the track load-bearing.

3. The nondestructive testing method for high-speed railway ballastless track according to claim 2, characterized in that: In S3000, predicting the accident status of the abnormal area within a preset time period based on the abnormality type includes: S3010, when the abnormality type is an internal abnormality of the track bed plate, analyzing the track scanning image to determine the current time; S3020, predicting environmental changes within a preset time period based on the current moment; S3030, obtaining track load-bearing data, and determining the track load-bearing impact based on the track load-bearing data; S3040: Predicting the accident status of the abnormal area within a preset time period based on the environmental changes and the impact of the track load-bearing capacity.

4. The nondestructive testing method for high-speed railway ballastless track according to claim 3, characterized in that: In S4000, determining a repair opportunity based on the accident state and the abnormality type includes: S4010, determining a related disease based on the abnormality type and the environmental change; S4020, analyzing the associated diseases and determining the spreading period; S4030: Determine the impact of the associated disease on the abnormal area based on the preset time period and the spreading time period; S4040: Determine a repair timing based on the accident status and the impact of the disease.

5. The nondestructive testing method for high-speed railway ballastless track according to claim 1, characterized in that: In S3000, when the abnormality type is interlayer gap, predicting the accident state of the abnormal area within a preset time period according to the abnormality type includes: S3050: When the anomaly type is an interlayer gap, analyze the track scanning image to 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; S3060, retrieving and analyzing historical scan records, and determining the development period of the newly changed area based on the historical scan analysis results; S3070, determining the difficulty of the change impact based on the gap characteristics; S3080: Predicting the accident status of the abnormal area within a preset time period based on the change direction, the development time period, and the difficulty of the change impact.

6. The nondestructive testing method for high-speed railway ballastless track according to claim 5, characterized in that: In S3000, when the abnormality type is a crack in the trackbed slab, predicting the accident state of the abnormal area within a preset time period based on the abnormality type includes: S3090, when the abnormality type is a track bed slab crack, determining whether there is an interlayer gap or an internal abnormality of the track bed slab based on the analysis result of the abnormal area; if so, determining the associated impact of the interlayer gap or the internal abnormality of the track bed slab based on the characteristics of the gap or the characteristics of the internal abnormality; S3100, determining crack characteristics based on the analysis results of the abnormal area, and determining the crack range based on the crack characteristics; S3110, obtaining track load-bearing data, and determining the track load-bearing impact based on the track load-bearing data; S3120: Predict the accident status of the abnormal area within a preset time period based on the associated impact, the crack range and the track load-bearing impact.

7. The nondestructive testing method for high-speed railway ballastless track according to claim 1, characterized in that: In S4000, determining a repair opportunity based on the accident state and the abnormality type includes: S4050, determining a repairable period based on the current time; S4060: predicting abnormal changes in the abnormal area within the repairable period based on the accident status; S4070, analyzing the abnormal changes and determining the risk level; S4080, determining whether to perform repair within the repairable period based on the risk level, and if repair is determined, determining a repair method based on the anomaly type; S4090, determining the abnormal shape of the abnormal area according to the repair method; S4100, determining the abnormal state at the current moment according to the abnormal accident range; S4110: Determine a repair opportunity based on the abnormal form and the abnormal state at the current moment.

8. The nondestructive testing method for high-speed railway ballastless track according to claim 7, characterized in that: In S4110, determining a repair opportunity based on the abnormal form and the abnormal state at the current moment includes: S4111, determining a repair limit range according to the repair method; S4112, analyzing the abnormal state at the current moment to determine whether the abnormal state exceeds the repair limit range; if not, analyzing the abnormal state to determine the abnormal difference between the abnormal state and the abnormal form; S4113: Determine a repair opportunity based on the abnormal change and the abnormal difference.

Images