A rail flaw detection data processing method, device and equipment and a storage medium

Abstract

This application relates to a method, apparatus, device, and storage medium for processing rail flaw detection data. The method includes processing received feedback signals based on the detected object in a position sequence to detect abnormal signals; determining the position interval to which the abnormal signals belong based on the abnormal signals; acquiring a set of planar images and a set of cross-sectional images for the position interval; establishing the spatial positional relationship between the abnormal signals in the planar image set and the cross-sectional image set and determining the feature positions based on the spatial positional relationship; analyzing the expression of the feature positions and determining the type of the position interval based on the expression of the feature positions. The rail flaw detection data processing method, apparatus, device, and storage medium disclosed in this application determines the authenticity of the data by verifying the data in three-dimensional space, and simultaneously provides type suggestions based on the expression of feature positions. This method can provide a more accurate reference for personnel judgment.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to a method, apparatus, equipment and storage medium for processing rail flaw detection data. Background Technology

[0002] Rail flaw detection is a key method for identifying internal / surface defects in rails using non-destructive testing (NDT) technology. Its core objective is "early detection, early warning, and early intervention" to ensure the safety and service life of rail operations. Currently, rail flaw detection is based on a combination of methods, such as surface analysis using image processing and internal analysis using ultrasonic testing, magnetic particle testing, and penetrant testing.

[0003] Currently, ultrasonic testing is the most commonly used method for internal flaw detection. The main problem is that different flaw detection personnel have subjective differences in their understanding of defect signals and interpretation of image features. For example, novices may misjudge clutter as defects, while experienced personnel may ignore atypical defect signals due to their own experience. These problems can be summarized as the lack of a unified image analysis standard.

[0004] In addition, there is a problem with spurious data (environmental interference, processing interference, processing accuracy, etc.) in the display of two-dimensional images, and how to deal with it requires further research. Summary of the Invention

[0005] This application provides a method, apparatus, equipment, and storage medium for processing rail flaw detection data. The method determines the authenticity of the data by verifying the data in three-dimensional space, and provides type suggestions by combining the expression of feature locations. This method can provide a more accurate reference for personnel to make judgments.

[0006] The above-mentioned objective of this application is achieved through the following technical solution:

[0007] Firstly, this application provides a method for processing rail flaw detection data, including:

[0008] The received feedback signals based on the detected object are processed on the location sequence to detect abnormal signals in the feedback signals;

[0009] Determine the location range to which the abnormal signal belongs based on the abnormal signal;

[0010] Obtain the set of planar images and the set of cross-sectional images for the location range;

[0011] Establish the spatial positional relationship between the abnormal signals in the planar image set and the cross-sectional image set, and determine the feature locations based on the spatial positional relationship;

[0012] Analyze the representation of feature positions and determine the type of position interval based on the representation of feature positions;

[0013] The received feedback signal is an ultrasonic signal;

[0014] A cross-sectional image of a location range is generated based on a set of feedback images of the detected object;

[0015] The area where the object is located is divided into an ignored area and a detection area. The feedback signal, planar image, and cross-sectional image are all generated based on the detection area.

[0016] In one possible implementation of the first aspect, determining the location range to which the abnormal signal belongs based on the abnormal signal includes:

[0017] Spatial location reference points are established using abnormal signals in the feedback signals; the number of spatial location reference points is multiple.

[0018] A bounded area is established in three-dimensional space using spatial location reference points. The bounded area represents the location range to which the abnormal signal belongs.

[0019] In one possible implementation of the first aspect, when establishing a spatial location reference point using an anomalous signal in the feedback signal, it further includes:

[0020] The abnormal signals in the feedback signal are checked using the set of cross-sectional images of the location interval to determine whether the abnormal signals in the feedback signal exist in the set of cross-sectional images of the location interval.

[0021] The abnormal signals in the feedback signal are verified using a set of planar images within the location interval, confirming that the abnormal signals in the feedback signal exist within the set of planar images within the location interval.

[0022] In one possible implementation of the first aspect, verifying the abnormal signal in the feedback signal using a set of cross-sectional images of the location interval includes:

[0023] The cross-sectional image is preprocessed, including noise removal and filtering.

[0024] The region of interest is obtained by using threshold segmentation to extract the cross-sectional image;

[0025] Calculate the correlation of regions of interest and integrate them. Use the integrated regions of interest to obtain vertices. There are multiple vertices.

[0026] Among them, the spatial location reference point established by the abnormal signal in the feedback signal coincides with the position of one of the vertices.

[0027] In one possible implementation of the first aspect, calculating the correlation of the region of interest and performing integration processing on the region of interest includes:

[0028] Regions of interest are classified into feature regions of interest and non-feature regions of interest, with feature regions of interest exhibiting curvature characteristics;

[0029] The non-feature regions of interest are merged into the feature regions of interest or merged with adjacent non-feature regions of interest using a traversal method, thus integrating the non-feature regions of interest into the feature regions of interest or generating new feature regions of interest.

[0030] In one possible implementation of the first aspect, verifying the abnormal signal in the feedback signal using a set of planar images of the location interval includes:

[0031] Thresholding segmentation is used to segment the planar image to obtain bright areas;

[0032] Determine the spatial relationship between the reference point established by the abnormal signal in the feedback signal and the bright area. The reference point established by the abnormal signal in the feedback signal is located inside or outside the bright area.

[0033] In one possible implementation of the first aspect, when the spatial position reference point established by the abnormal signal in the feedback signal is located outside the bright area, the method further includes adjusting the height of the planar image and repeating the verification process, wherein each time the height of the planar image is adjusted, the positional relationship between the spatial position reference point established by the abnormal signal in the feedback signal and the bright area is determined.

[0034] Secondly, this application provides a rail flaw detection data processing device, comprising:

[0035] The signal processing unit is used to process the received feedback signals based on the detected object on the position sequence and detect abnormal signals in the feedback signals;

[0036] A location determination unit is used to determine the location range to which an abnormal signal belongs based on the abnormal signal.

[0037] The image acquisition unit is used to acquire a set of planar images and a set of cross-sectional images of the location range;

[0038] The position processing unit is used to establish the spatial positional relationship between the abnormal signal in the planar image set and the cross-sectional image set, and to determine the feature position based on the spatial positional relationship.

[0039] The analysis unit is used to analyze the representation of feature positions and determine the type of position interval based on the representation of feature positions;

[0040] The received feedback signal is an ultrasonic signal;

[0041] A cross-sectional image of a location range is generated based on a set of feedback images of the detected object;

[0042] The area where the object is located is divided into an ignored area and a detection area. The feedback signal, planar image, and cross-sectional image are all generated based on the detection area.

[0043] Thirdly, this application provides a rail flaw detection data processing device, the device comprising:

[0044] One or more memories for storing instructions; and

[0045] One or more processors are configured to call and execute the instructions from the memory to perform the methods described in the first aspect and any possible implementation thereof.

[0046] Fourthly, this application provides a computer-readable storage medium, the computer-readable storage medium comprising:

[0047] The program, when run by a processor, is executed as described in the first aspect and any possible implementation thereof.

[0048] Fifthly, this application provides a computer program product, including program instructions that, when run by a computing device, execute the method described in the first aspect and any possible implementation thereof.

[0049] Sixthly, this application provides a chip system including a processor for implementing the functions involved in the foregoing aspects, such as generating, receiving, transmitting, or processing the data and / or information involved in the foregoing methods.

[0050] This chip system can consist of chips or include chips and other discrete components.

[0051] In one possible design, the chip system also includes a memory for storing necessary program instructions and data. The processor and the memory can be decoupled and located on different devices, connected via wired or wireless means, or the processor and the memory can be coupled to the same device. Attached Figure Description

[0052] Figure 1 This is a flowchart illustrating the steps of a rail flaw detection data processing method provided in this application.

[0053] Figure 2 This is a schematic diagram illustrating the principle of an ultrasonic flaw detection device provided in this application.

[0054] Figure 3 This is a schematic diagram of a set of cross-sectional images provided in this application.

[0055] Figure 4 This is a schematic diagram of a set of planar images provided in this application.

[0056] Figure 5 This is a schematic diagram illustrating the division between the ignored region and the detection region provided in this application.

[0057] Figure 6 This is a schematic diagram of obtaining the region of interest after preprocessing a cross-sectional image, as provided in this application.

[0058] Figure 7 This is a schematic diagram of the position of a vertex provided in this application.

[0059] Figure 8 This is a schematic diagram of an extraction operator provided in this application. Detailed Implementation

[0060] The technical solutions in this application will be further described in detail below with reference to the accompanying drawings.

[0061] This application discloses a method for processing rail flaw detection data. Please refer to [link / reference]. Figure 1 In some examples, the rail flaw detection data processing method disclosed in this application includes the following steps:

[0062] S101, Process the received feedback signal based on the detected object in the position sequence to detect abnormal signals in the feedback signal;

[0063] S102, Determine the location range to which the abnormal signal belongs based on the abnormal signal;

[0064] S103, Obtain the set of planar images and the set of cross-sectional images of the location range;

[0065] S104, Establish the spatial positional relationship of the abnormal signal in the planar image set and the cross-sectional image set, and determine the feature position based on the spatial positional relationship;

[0066] S105, Analyze the expression of feature positions and determine the type of position interval based on the expression of feature positions;

[0067] The received feedback signal is an ultrasonic signal;

[0068] A cross-sectional image of a location range is generated based on a set of feedback images of the detected object;

[0069] The area where the object is located is divided into an ignored area and a detection area. The feedback signal, planar image, and cross-sectional image are all generated based on the detection area.

[0070] The technical solution disclosed in this application uses an ultrasonic flaw detector to perform flaw detection analysis on the rail. During the flaw detection process, the ultrasonic flaw detector moves along the length of the rail, which is referred to as lateral movement. At the same time, the ultrasonic flaw detector moves longitudinally at each position to achieve full coverage of the rail.

[0071] In step S101, the received feedback signal based on the detected object is first processed on the position sequence to find abnormal signals in the feedback signal. When an abnormal signal appears in the feedback signal, step S102 is executed. In this step, the position interval to which the abnormal signal belongs is determined based on the abnormal signal.

[0072] The specific analysis process for abnormal signals in the feedback signal is as follows:

[0073] Please see Figure 2 The position between the signal transmitter and the signal receiver of the ultrasonic flaw detection equipment is determined. When the height of the rail is a certain value, the maximum signal reception time is a certain value (bottom surface reflection). If the signal reception time during the flaw detection process is less than this certain value, it indicates that the ultrasonic path of the signal has changed during propagation. This is mainly manifested in the generation of diffraction waves and scattered waves. By capturing diffraction waves and scattered waves, defects inside the rail can be determined.

[0074] In some possible implementations, TOFD technology is used for flaw detection. TOFD technology employs a dual-probe mode, where one probe is responsible for emitting ultrasonic waves and the other probe is responsible for receiving them. The received feedback signal is an ultrasonic signal.

[0075] In a defect-free area, the receiving probe sequentially receives the through wave propagating near the surface and the bottom wave reflected back from the bottom surface. Once the sound wave encounters a defect such as a crack, it will generate diffraction waves from its upper and lower ends. By precisely calculating the propagation time difference between the through wave and the diffraction wave at the lower end of the defect, the depth and height of the defect can be calculated.

[0076] In some possible implementations, the common approach to acquiring abnormal signals is the matching tracking algorithm.

[0077] The specific method for determining the location range to which an abnormal signal belongs based on the abnormal signal is as follows:

[0078] Spatial location reference points are established using abnormal signals in the feedback signals; the number of spatial location reference points is multiple.

[0079] A bounded area is established in three-dimensional space using spatial location reference points. The bounded area represents the location range to which the abnormal signal belongs.

[0080] Specifically, it involves determining an enclosed area by using a spatial location point, and this enclosed area corresponds to the defects inside the rail.

[0081] In step S103, a set of planar images and a set of cross-sectional images of the position range are obtained. The set of planar images refers to the set of planar images obtained by the C-scan method, and the set of cross-sectional images refers to the set of planar images obtained by the B-scan method.

[0082] Here, a cross-sectional image of a location range is generated based on a set of feedback images of the object being inspected. As mentioned earlier, ultrasonic flaw detection equipment needs to move during operation to cover a surface. This means that a cross-sectional image of a location range is generated based on a set of feedback images of the object being inspected, rather than being generated all at once.

[0083] If the spatial coordinates of the spatial location reference point can be determined, then the B-scan image associated with the spatial location reference point ( Figure 3 (as shown) and C-scan image ( Figure 4 (As shown) can also be determined synchronously.

[0084] In step S104, the spatial positional relationship between the abnormal signal in the planar image set and the cross-sectional image set is established, and the feature position is determined based on the spatial positional relationship.

[0085] Specifically, as mentioned above, a spatial location point should appear in both the planar image set and the cross-sectional image set. If it only appears in either the planar image set or the cross-sectional image set, then in this application, this spatial location point will be discarded.

[0086] Finally, in step S105, the expression of the feature position is analyzed and the type of the position interval is determined based on the expression of the feature position. Here, the expression of the feature position refers to some features of the feature position. The type of the position interval is determined based on the expression of the feature position. Here, the type refers to the type of defect inside the rail. The specific implementation method is as follows: a rule-based expert system, for example, establishing a set of if-then rules, such as: IF aspect ratio > 10 AND area < 10 pixels → crack; IF roundness > 0.9 → porosity.

[0087] The reason for using an expert system here is based on the current level of data accumulation and technology. While machine learning can directly process and analyze the collected data, it requires a massive amount of data and a long period of rule training, which is quite difficult to implement given the current level of accumulation. Furthermore, a core problem with machine learning is the black box nature of the processing, meaning that only the result is known, but the process is unknown, making it impossible to provide a reference for determining and reviewing the final result.

[0088] It should be noted here that the area where the object to be detected is divided into an ignored area and a detected area. The feedback signal, planar image and cross-sectional image are all generated based on the detected area. The ignored area here refers to the surface area of ​​the rail, because the direct wave and feedback wave are mixed here, making it difficult to distinguish. Therefore, this application requires that the feedback signal, planar image and cross-sectional image are all generated based on the detected area.

[0089] The surface of the ignored area (rail surface) is analyzed using image processing methods, while the interior is analyzed using methods such as magnetic testing. This also demonstrates the comprehensive use of multiple testing methods for rail flaw detection. Figure 5 As shown.

[0090] In some cases, when establishing spatial location reference points using anomalous signals from the feedback signal, the following steps are added:

[0091] The abnormal signals in the feedback signal are checked using the set of cross-sectional images of the location interval to determine whether the abnormal signals in the feedback signal exist in the set of cross-sectional images of the location interval.

[0092] The abnormal signals in the feedback signal are verified using a set of planar images within the location interval, confirming that the abnormal signals in the feedback signal exist within the set of planar images within the location interval.

[0093] Specifically, it is necessary to simultaneously identify the abnormal signals in the feedback signals from both the cross-sectional image set and the planar image set, requiring the abnormal signals in the feedback signals to exist simultaneously in both the cross-sectional image set and the planar image set.

[0094] Abnormal signals in the feedback signal can be represented by spatial location reference points. Thus, this can be described as determining that the spatial location reference points appear simultaneously in both the cross-sectional image set and the planar image set.

[0095] The specific method for verifying abnormal signals in the feedback signal using a set of cross-sectional images of the location interval is as follows:

[0096] The cross-sectional image is preprocessed, including noise removal and filtering.

[0097] The region of interest is obtained by using threshold segmentation to extract the cross-sectional image;

[0098] Calculate the correlation of regions of interest and integrate them. Use the integrated regions of interest to obtain vertices. There are multiple vertices.

[0099] Among them, the spatial location reference point established by the abnormal signal in the feedback signal coincides with the position of one of the vertices.

[0100] Specifically, the cross-sectional image is the B-scan image mentioned earlier, and the relevant content is as follows:

[0101] When ultrasound waves encounter rough surfaces, coarse-grained structures, or complex defect clusters, they are scattered. These scattered and diffracted waves from different directions are received by the probe, and their propagation times vary. When connected on a B-scan image, they form a curve. This is particularly common in TOFD (Time-of-Flight Diffraction) inspection, where the upper and lower ends of the image typically exhibit a natural curvature.

[0102] Even with ideal flat-bottomed or transverse holes, the highest echo point of the reflector is not a strict point in its depth direction, but rather a region, because the ultrasonic sound field itself has a certain width and diffusion angle.

[0103] When the probe scans, the trajectory of the highest echo point may appear as a smooth curve rather than an absolute straight line, which reflects the spatial distribution of the point with the highest sound pressure.

[0104] In this section, the cross-sectional image needs to be preprocessed first, and the result is as follows: Figure 6 As shown above, preprocessing includes noise removal and filtering. Noise removal methods include median filtering, etc. Filtering refers to retaining data of a specific frequency. For example, the frequency range of ultrasonic waves in rail flaw detection is generally 2-5 MHz. The operating frequency of the specific equipment used (assuming 3-3.5 MHz) is generally also within this range. Retaining data of a specific frequency means only retaining waveforms of the 3-3.5 MHz frequency.

[0105] Next, threshold segmentation is used to extract the region of interest from the cross-sectional image, such as... Figure 6 As shown below, the threshold segmentation method here generally uses a binarized threshold segmentation method. However, the region of interest obtained after threshold segmentation is discrete, with some regions of interest being complete and others being incomplete.

[0106] Therefore, it is necessary to calculate the correlation of the region of interest, integrate the regions of interest, and use the integrated regions of interest to obtain the vertices, such as... Figure 7 As shown, there are multiple vertices.

[0107] After obtaining the vertex, the spatial position reference point established by the abnormal signal in the feedback signal needs to coincide with the position of one of the vertexes. The coincidence indicates that the spatial position reference point appears in the set of cross-sectional images of the position interval.

[0108] In some possible implementations, the specific methods for calculating the correlation of regions of interest and integrating them are as follows:

[0109] Regions of interest are classified into feature regions of interest and non-feature regions of interest, with feature regions of interest exhibiting curvature characteristics;

[0110] The non-feature regions of interest are merged into the feature regions of interest or merged with adjacent non-feature regions of interest using a traversal method, thus integrating the non-feature regions of interest into the feature regions of interest or generating new feature regions of interest.

[0111] For the traversal method, the specific steps are as follows:

[0112] The region of interest has a curved feature. The orientation of the curve can be determined based on the curved feature. To make it clearer, the curve can be simplified into two straight line segments and one curved segment. The region of interest has a curved feature, which is the curved segment.

[0113] Merging non-feature regions of interest into feature regions of interest using a traversal approach means that non-feature regions of interest are sequentially added to each feature region of interest. The criterion here is that the influence of non-feature regions of interest on feature regions of interest is to complete the function, specifically, the slope of the line segment does not change.

[0114] Merging non-feature regions of interest with adjacent non-feature regions of interest using a traversal method means connecting any two non-feature regions of interest. If a line segment can be obtained, and the slope of the line segment is similar to the slope existing in the B-scan image (e.g., the angle between the segments must be less than or equal to 2°), then the two non-feature regions of interest are considered to be able to be connected; otherwise, they cannot be connected.

[0115] In the two processing steps described above, if the non-feature region of interest has a length direction, the slope of the connected line segment needs to be parallel to the length direction of the non-feature region of interest.

[0116] The existence of a length direction in a non-feature region of interest refers to the size of the non-feature region of interest in multiple directions. If the size in one direction is significantly larger than the size in other directions, then the direction in which this size is located is the length direction of the non-feature region of interest.

[0117] Of course, at this point, it's possible that only line segments can be obtained, in which case the extraction operator needs to be used. Figure 8 As shown, the white area is filled with 0 and the black area is filled with numbers. Extraction is performed in the area near the straight line segment (in the cross-sectional image). If a curved area can be extracted, the straight line segment is retained, and the position coordinates of the curved area are recorded.

[0118] In some cases, the specific method for verifying anomalous signals in the feedback signal using a set of planar images of location intervals is as follows:

[0119] Thresholding segmentation is used to segment the planar image to obtain bright areas;

[0120] Determine the spatial relationship between the reference point established by the abnormal signal in the feedback signal and the bright area. The reference point established by the abnormal signal in the feedback signal is located inside or outside the bright area.

[0121] The planar image is the C-scan image mentioned above. A significant feature of the C-scan image is its brightness and darkness. Therefore, in this application, a threshold segmentation method is used to segment the planar image to obtain the bright area. Then, the spatial position reference point established by the abnormal signal in the feedback signal is determined to determine the positional relationship between the bright area and the spatial position reference point.

[0122] Specifically, it refers to whether the spatial location reference point established by the abnormal signal in the feedback signal is located inside or outside the bright area.

[0123] In some possible implementations, when the spatial location reference point established by the abnormal signal in the feedback signal is located outside the bright area, the method further includes adjusting the height of the planar image (changing to an adjacent planar image) and repeating the verification process. Each time the height of the planar image is adjusted, the positional relationship between the spatial location reference point established by the abnormal signal in the feedback signal and the bright area is determined.

[0124] This application also provides a rail flaw detection data processing device, including:

[0125] The signal processing unit is used to process the received feedback signals based on the detected object on the position sequence and detect abnormal signals in the feedback signals;

[0126] A location determination unit is used to determine the location range to which an abnormal signal belongs based on the abnormal signal.

[0127] The image acquisition unit is used to acquire a set of planar images and a set of cross-sectional images of the location range;

[0128] The position processing unit is used to establish the spatial positional relationship between the abnormal signal in the planar image set and the cross-sectional image set, and to determine the feature position based on the spatial positional relationship.

[0129] The analysis unit is used to analyze the representation of feature positions and determine the type of position interval based on the representation of feature positions;

[0130] The received feedback signal is an ultrasonic signal;

[0131] A cross-sectional image of a location range is generated based on a set of feedback images of the detected object;

[0132] The area where the object is located is divided into an ignored area and a detection area. The feedback signal, planar image, and cross-sectional image are all generated based on the detection area.

[0133] Furthermore, determining the location range to which an abnormal signal belongs based on the abnormal signal includes:

[0134] Spatial location reference points are established using abnormal signals in the feedback signals; the number of spatial location reference points is multiple.

[0135] A bounded area is established in three-dimensional space using spatial location reference points. The bounded area represents the location range to which the abnormal signal belongs.

[0136] Furthermore, when establishing spatial location reference points using anomalous signals from the feedback signal, the following is also included:

[0137] The abnormal signals in the feedback signal are checked using the set of cross-sectional images of the location interval to determine whether the abnormal signals in the feedback signal exist in the set of cross-sectional images of the location interval.

[0138] The abnormal signals in the feedback signal are verified using a set of planar images within the location interval, confirming that the abnormal signals in the feedback signal exist within the set of planar images within the location interval.

[0139] Furthermore, the verification of anomalous signals in the feedback signal using a set of cross-sectional images of the location range includes:

[0140] The cross-sectional image is preprocessed, including noise removal and filtering.

[0141] The region of interest is obtained by using threshold segmentation to extract the cross-sectional image;

[0142] Calculate the correlation of regions of interest and integrate them. Use the integrated regions of interest to obtain vertices. There are multiple vertices.

[0143] Among them, the spatial location reference point established by the abnormal signal in the feedback signal coincides with the position of one of the vertices.

[0144] Furthermore, calculating the correlation of regions of interest and performing integration processing on these regions includes:

[0145] Regions of interest are classified into feature regions of interest and non-feature regions of interest, with feature regions of interest exhibiting curvature characteristics;

[0146] The non-feature regions of interest are merged into the feature regions of interest or merged with adjacent non-feature regions of interest using a traversal method, thus integrating the non-feature regions of interest into the feature regions of interest or generating new feature regions of interest.

[0147] Furthermore, the verification of anomalous signals in the feedback signal using a set of planar images within the location range includes:

[0148] Thresholding segmentation is used to segment the planar image to obtain bright areas;

[0149] Determine the spatial relationship between the reference point established by the abnormal signal in the feedback signal and the bright area. The reference point established by the abnormal signal in the feedback signal is located inside or outside the bright area.

[0150] Furthermore, when the spatial location reference point established by the abnormal signal in the feedback signal is located outside the bright area, the process also includes adjusting the height of the planar image and repeating the verification process. Each time the height of the planar image is adjusted, the positional relationship between the spatial location reference point established by the abnormal signal in the feedback signal and the bright area is determined.

[0151] In one example, the unit in any of the above devices may be one or more integrated circuits configured to implement the above methods, such as one or more application-specific integrated circuits (ASICs), or one or more digital signal processors (DSPs), or one or more field-programmable gate arrays (FPGAs), or a combination of at least two of these integrated circuit forms.

[0152] For example, when the units in the device can be implemented through a processing element scheduler, the processing element can be a general-purpose processor, such as a central processing unit (CPU) or other processor capable of calling programs. Alternatively, these units can be integrated together to form a system-on-a-chip (SOC).

[0153] In this application, various objects such as messages / information / devices / network elements / systems / apparatus / actions / operations / processes / concepts may be named. It is understood that these specific names do not constitute a limitation on the relevant objects. The names may be changed depending on the scenario, context, or usage habits. The understanding of the technical meaning of the technical terms in this application should be mainly determined from their functions and technical effects embodied / performed in the technical solution.

[0154] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0155] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0156] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0157] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0158] It should also be understood that in the various embodiments of this application, the terms "first," "second," etc., are merely to indicate that multiple objects are different. For example, a first time window and a second time window are only to indicate different time windows. They should not have any effect on the time windows themselves, and the aforementioned terms "first," "second," etc., should not impose any limitations on the embodiments of this application.

[0159] It should also be understood that, in the various embodiments of this application, unless otherwise specified or in case of logical conflict, the terms and / or descriptions between different embodiments are consistent and can be referenced by each other, and the technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationships.

[0160] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a computer-readable storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned computer-readable storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0161] This application also provides a rail flaw detection data processing device, the device comprising:

[0162] One or more memories for storing instructions; and

[0163] One or more processors are configured to retrieve and execute the instructions from the memory, performing the methods described above.

[0164] This application also provides a computer program product including instructions that, when executed, cause the terminal device and the network device to perform operations corresponding to the methods described above.

[0165] This application also provides a chip system including a processor for implementing the functions involved in the above description, such as generating, receiving, transmitting, or processing the data and / or information involved in the above methods.

[0166] This chip system can consist of chips or include chips and other discrete components.

[0167] The processor mentioned above can be a CPU, a microprocessor, an ASIC, or one or more integrated circuits that execute a program to control the method of transmitting the feedback information described above.

[0168] In one possible design, the chip system also includes a memory for storing necessary program instructions and data. The processor and the memory can be decoupled and located on different devices, connected via wired or wireless means to support the chip system in implementing the various functions described in the above embodiments. Alternatively, the processor and the memory can also be coupled to the same device.

[0169] Optionally, the computer instructions are stored in memory.

[0170] Optionally, the memory can be a storage unit within the chip, such as a register or cache. Alternatively, the memory can be a storage unit located outside the chip within the terminal, such as a ROM or other types of static storage devices that can store static information and instructions, such as RAM.

[0171] It is understood that the memory in this application may be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory.

[0172] Non-volatile memory can be ROM, programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory.

[0173] Volatile memory can be RAM, which is used as an external cache. There are many different types of RAM, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct memory bus random access memory.

[0174] The embodiments described in this specific implementation are preferred embodiments of this application and are not intended to limit the scope of protection of this application. Therefore, all equivalent changes made in accordance with the structure, shape and principle of this application should be covered within the scope of protection of this application.

Claims

1. A method for processing rail flaw detection data, characterized in that, include: The received feedback signals based on the detected object are processed on the location sequence to detect abnormal signals in the feedback signals; Determine the location range to which the abnormal signal belongs based on the abnormal signal; Obtain the set of planar images and the set of cross-sectional images for the location range; Establish the spatial positional relationship between the abnormal signals in the planar image set and the cross-sectional image set, and determine the feature locations based on the spatial positional relationship; Analyze the representation of feature positions and determine the type of position interval based on the representation of feature positions; The received feedback signal is an ultrasonic signal; A cross-sectional image of a location range is generated based on a set of feedback images of the detected object; The area where the object is located is divided into an ignored area and a detection area. The feedback signal, planar image, and cross-sectional image are all generated based on the detection area. The location range for determining the anomalous signal's location based on the anomalous signal includes: Spatial location reference points are established using abnormal signals in the feedback signals; the number of spatial location reference points is multiple. A bounded area is established in three-dimensional space using spatial location reference points. The bounded area is the location range to which the abnormal signal belongs. When establishing spatial location reference points using anomalous signals from feedback signals, the following is also included: The abnormal signals in the feedback signal are checked using the set of cross-sectional images of the location interval to determine whether the abnormal signals in the feedback signal exist in the set of cross-sectional images of the location interval. The abnormal signals in the feedback signal are checked using a set of planar images of the location interval to determine whether the abnormal signals in the feedback signal exist in the set of planar images of the location interval. Verification of anomalous signals in the feedback signal using a set of cross-sectional images within a location range includes: The cross-sectional image is preprocessed, including noise removal and filtering. The region of interest is obtained by using threshold segmentation to extract the cross-sectional image; Calculate the correlation of regions of interest and integrate them. Use the integrated regions of interest to obtain vertices. There are multiple vertices. Among them, the spatial location reference point established by the abnormal signal in the feedback signal coincides with the position of one of the vertexes; Calculating the correlation of regions of interest and integrating them includes: Regions of interest are classified into feature regions of interest and non-feature regions of interest, with feature regions of interest exhibiting curvature characteristics; The non-feature regions of interest are merged into the feature regions of interest or merged with adjacent non-feature regions of interest using a traversal method, thus integrating the non-feature regions of interest into the feature regions of interest or generating new feature regions of interest. Verification of anomalous signals in the feedback signal using a set of planar images within a location range includes: Thresholding segmentation is used to segment the planar image to obtain bright areas; Determine the spatial position reference point established by the abnormal signal in the feedback signal and the positional relationship between the two areas. The spatial position reference point established by the abnormal signal in the feedback signal may be located inside or outside the bright area. When the spatial location reference point established by the abnormal signal in the feedback signal is located outside the bright area, the process also includes adjusting the height of the planar image and repeating the verification process. Each time the height of the planar image is adjusted, the positional relationship between the spatial location reference point established by the abnormal signal in the feedback signal and the bright area is determined.

2. A rail flaw detection data processing device, characterized in that, include: The signal processing unit is used to process the received feedback signals based on the detected object on the position sequence and detect abnormal signals in the feedback signals; A location determination unit is used to determine the location range to which an abnormal signal belongs based on the abnormal signal. The image acquisition unit is used to acquire a set of planar images and a set of cross-sectional images of the location range; The position processing unit is used to establish the spatial positional relationship between the abnormal signal in the planar image set and the cross-sectional image set, and to determine the feature position based on the spatial positional relationship. The analysis unit is used to analyze the representation of feature positions and determine the type of position interval based on the representation of feature positions; The received feedback signal is an ultrasonic signal; A cross-sectional image of a location range is generated based on a set of feedback images of the detected object; The area where the object is located is divided into an ignored area and a detection area. The feedback signal, planar image, and cross-sectional image are all generated based on the detection area. The location range for determining the anomalous signal's location based on the anomalous signal includes: Spatial location reference points are established using abnormal signals in the feedback signals; the number of spatial location reference points is multiple. A bounded area is established in three-dimensional space using spatial location reference points. The bounded area is the location range to which the abnormal signal belongs. When establishing spatial location reference points using anomalous signals from feedback signals, the following is also included: The abnormal signals in the feedback signal are checked using the set of cross-sectional images of the location interval to determine whether the abnormal signals in the feedback signal exist in the set of cross-sectional images of the location interval. The abnormal signals in the feedback signal are checked using a set of planar images of the location interval to determine whether the abnormal signals in the feedback signal exist in the set of planar images of the location interval. Verification of anomalous signals in the feedback signal using a set of cross-sectional images within a location range includes: The cross-sectional image is preprocessed, including noise removal and filtering. The region of interest is obtained by using threshold segmentation to extract the cross-sectional image; Calculate the correlation of regions of interest and integrate them. Use the integrated regions of interest to obtain vertices. There are multiple vertices. Among them, the spatial location reference point established by the abnormal signal in the feedback signal coincides with the position of one of the vertexes; Calculating the correlation of regions of interest and integrating them includes: Regions of interest are classified into feature regions of interest and non-feature regions of interest, with feature regions of interest exhibiting curvature characteristics; The non-feature regions of interest are merged into the feature regions of interest or merged with adjacent non-feature regions of interest using a traversal method, thus integrating the non-feature regions of interest into the feature regions of interest or generating new feature regions of interest. Verification of anomalous signals in the feedback signal using a set of planar images within a location range includes: Thresholding segmentation is used to segment the planar image to obtain bright areas; Determine the spatial position reference point established by the abnormal signal in the feedback signal and the positional relationship between the two areas. The spatial position reference point established by the abnormal signal in the feedback signal may be located inside or outside the bright area. When the spatial location reference point established by the abnormal signal in the feedback signal is located outside the bright area, the process also includes adjusting the height of the planar image and repeating the verification process. Each time the height of the planar image is adjusted, the positional relationship between the spatial location reference point established by the abnormal signal in the feedback signal and the bright area is determined.

3. A rail flaw detection data processing device, characterized in that, The device includes: One or more memories for storing instructions; and One or more processors are configured to retrieve and execute the instructions from the memory, performing the method as described in claim 1.

4. A computer-readable storage medium for a rail flaw detection data processing method, characterized in that, The computer-readable storage medium includes: The program, when run by the processor, executes the method as described in claim 1.

Images