Steel rail welding seam damage detection method and device, computer equipment, readable storage medium and program product

Abstract

The invention relates to a steel rail welding seam damage detection method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: respectively carrying out ultrasonic detection on a to-be-detected weld zone and a non-weld zone of a steel rail to obtain respective corresponding response signals of the to-be-detected weld zone and the non-weld zone; performing multi-scale analysis on each response signal to obtain a fluctuation complexity index of each response signal; obtaining a difference correction factor according to the energy amplitude difference between the response signals corresponding to the weld zone to be detected and the non-weld zone; and according to the difference between the fluctuation complexity indexes of the response signals corresponding to the to-be-detected weld zone and the non-weld zone and the difference correction factor, obtaining a damage detection result of the to-be-detected weld zone. By adopting the method, the damage of the steel rail welding seam can be accurately detected.

Description

Technical Field

[0001] The present application relates to the field of railway engineering technology, and in particular to a rail weld damage detection method, device, computer equipment, computer-readable storage medium, and computer program product. Background Art

[0002] In railway transportation systems, rails are often joined by welding due to the limited length of track for rail changes. However, welds, as the weakest point in the rails, are prone to stress concentration, subjecting the weld area to high stress loads. Therefore, the quality of rail welds is directly related to the smoothness and safety of train operation, and their inspection and maintenance are of great significance to railway infrastructure.

[0003] In related technologies, ultrasonic testing, eddy current testing, and magnetic particle testing are commonly used to detect damage in rail welds. However, these methods have a low success rate for detecting minor defects such as microcracks in rail welds, making it difficult to achieve high-precision detection of weld damage. Summary of the Invention

[0004] Based on this, it is necessary to provide a rail weld damage detection method, device, computer equipment, computer readable storage medium and computer program product to address the above technical problems.

[0005] In a first aspect, the present application provides a rail weld damage detection method, comprising:

[0006] Performing ultrasonic testing on the weld area to be tested and the non-weld area of the rail respectively, to obtain response signals corresponding to the weld area to be tested and the non-weld area respectively;

[0007] Performing multi-scale analysis on each of the response signals to obtain a fluctuation complexity index of each of the response signals;

[0008] Obtaining a difference correction factor according to an energy amplitude difference between the response signals corresponding to the weld area to be measured and the non-weld area;

[0009] A damage detection result of the weld area to be measured is obtained according to the difference between the fluctuation complexity index of the response signals corresponding to the weld area to be measured and the non-weld area and the difference correction factor.

[0010] In one embodiment, a multi-scale analysis is performed on each of the response signals to obtain a fluctuation complexity index of each of the response signals, including: for each analysis scale, dividing the response signal according to the analysis scale to obtain multiple sub-signal segments corresponding to the analysis scale; obtaining an amplitude fluctuation index of each sub-signal segment according to the signal amplitude of each sampling point in each sub-signal segment; for each analysis scale, fusing the amplitude fluctuation index of each sub-signal segment corresponding to the analysis scale to obtain a cumulative fluctuation index of the analysis scale; and fitting the relationship between each analysis scale and each cumulative fluctuation index to obtain a fluctuation complexity index of the response signal.

[0011] In one embodiment, the amplitude fluctuation index of each sub-signal segment is obtained according to the signal amplitude of each sampling point in each sub-signal segment, including: obtaining the maximum signal amplitude, minimum signal amplitude and average signal amplitude of the sub-signal segment according to the signal amplitude of each sampling point in the sub-signal segment; and obtaining the amplitude fluctuation index according to the difference between the maximum signal amplitude and the average signal amplitude, and the difference between the maximum signal amplitude and the minimum signal amplitude.

[0012] In one embodiment, the difference correction factor is obtained according to the energy amplitude difference between the response signals corresponding to the weld area to be measured and the non-weld area, including: for each response signal, obtaining the cumulative energy amplitude of the response signal according to the energy amplitude of each sampling point in the response signal; obtaining the unit energy amplitude of each response signal according to the cumulative energy amplitude and detection distance of each response signal; and obtaining the difference correction factor according to the difference in the unit energy amplitude of the response signals corresponding to the weld area to be measured and the non-weld area.

[0013] In one embodiment, the damage detection result of the weld area to be measured is obtained based on the difference between the fluctuation complexity index of the response signal corresponding to the weld area to be measured and the non-weld area and the difference correction factor, including: obtaining a complex difference factor based on the relative deviation between the fluctuation complexity index of the response signal corresponding to the weld area to be measured and the non-weld area; correcting the complex difference factor using the difference correction factor to obtain the damage factor of the weld area to be measured; and obtaining the damage detection result of the weld area to be measured based on the damage level numerical range of the damage factor.

[0014] In one embodiment, the response signal corresponding to the weld area to be measured includes multiple detection response signals collected from multiple weld positions, and the response signal corresponding to the non-weld area includes multiple reference response signals collected from multiple non-weld positions; the difference correction factor is obtained according to the energy amplitude difference between the response signals corresponding to the weld area to be measured and the non-weld area, including: for each of the detection response signals, according to the energy amplitude difference between the detection response signal and the multiple reference response signals, obtaining the difference correction factor corresponding to the detection response signal; the relative deviation between the fluctuation complexity indexes of the response signals corresponding to the weld area to be measured and the non-weld area, obtaining the complex difference factor, including: for each of the detection response signals, according to the the relative deviation between the fluctuation complexity index of the detection response signal and the fluctuation complexity index of multiple reference response signals is obtained to obtain the complex difference factor corresponding to each detection response signal; the using the difference correction factor to correct the complex difference factor to obtain the damage factor of the weld area to be measured includes: for each detection response signal, correcting the complex difference factor according to the difference correction factor corresponding to the detection response signal to obtain the damage factor of the weld position corresponding to the detection response signal; the obtaining the damage detection result of the weld area to be measured according to the damage level numerical range where the damage factor is located includes: obtaining the damage detection result of the weld area to be measured according to the damage level numerical range where the damage factor is located at each weld position.

[0015] In a second aspect, the present application further provides a rail weld damage detection device, comprising:

[0016] A signal acquisition module is used to perform ultrasonic testing on the weld area to be tested and the non-weld area of the rail respectively, and obtain response signals corresponding to the weld area to be tested and the non-weld area respectively;

[0017] a fluctuation analysis module, configured to perform multi-scale analysis on each of the response signals to obtain a fluctuation complexity index of each of the response signals;

[0018] a difference analysis module, configured to obtain a difference correction factor based on the energy amplitude difference between the response signals corresponding to the weld area to be measured and the non-weld area;

[0019] The result acquisition module is used to obtain the damage detection result of the weld area to be tested based on the difference between the fluctuation complexity index of the response signal corresponding to the weld area to be tested and the non-weld area and the difference correction factor.

[0020] In a third aspect, the present application further provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0021] Performing ultrasonic testing on the weld area to be tested and the non-weld area of the rail respectively, to obtain response signals corresponding to the weld area to be tested and the non-weld area respectively;

[0022] Performing multi-scale analysis on each of the response signals to obtain a fluctuation complexity index of each of the response signals;

[0023] Obtaining a difference correction factor according to an energy amplitude difference between the response signals corresponding to the weld area to be measured and the non-weld area;

[0024] A damage detection result of the weld area to be measured is obtained according to the difference between the fluctuation complexity index of the response signals corresponding to the weld area to be measured and the non-weld area and the difference correction factor.

[0025] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0026] Performing ultrasonic testing on the weld area to be tested and the non-weld area of the rail respectively, to obtain response signals corresponding to the weld area to be tested and the non-weld area respectively;

[0027] Performing multi-scale analysis on each of the response signals to obtain a fluctuation complexity index of each of the response signals;

[0028] Obtaining a difference correction factor according to an energy amplitude difference between the response signals corresponding to the weld area to be measured and the non-weld area;

[0029] A damage detection result of the weld area to be measured is obtained according to the difference between the fluctuation complexity index of the response signals corresponding to the weld area to be measured and the non-weld area and the difference correction factor.

[0030] In a fifth aspect, the present application further provides a computer program product, comprising a computer program, which, when executed by a processor, implements the following steps:

[0031] Performing ultrasonic testing on the weld area to be tested and the non-weld area of the rail respectively, to obtain response signals corresponding to the weld area to be tested and the non-weld area respectively;

[0032] Performing multi-scale analysis on each of the response signals to obtain a fluctuation complexity index of each of the response signals;

[0033] Obtaining a difference correction factor according to an energy amplitude difference between the response signals corresponding to the weld area to be measured and the non-weld area;

[0034] A damage detection result of the weld area to be measured is obtained according to the difference between the fluctuation complexity index of the response signals corresponding to the weld area to be measured and the non-weld area and the difference correction factor.

[0035] The rail weld damage detection method, apparatus, computer device, computer-readable storage medium, and computer program product described above first perform ultrasonic testing on the weld and non-weld areas of the rail to be tested, obtaining response signals corresponding to the weld and non-weld areas. Multi-scale analysis is then performed on each response signal to obtain a fluctuation complexity index for each response signal, and a difference correction factor is obtained based on the energy amplitude difference between the response signals corresponding to the weld and non-weld areas to be tested. Finally, damage detection results for the weld area to be tested are obtained based on the difference between the fluctuation complexity indexes of the response signals corresponding to the weld and non-weld areas to be tested and the difference correction factor. This solution, through multi-scale analysis of the response signals, can comprehensively analyze the amplitude fluctuations of the response signals at different time scales to obtain a fluctuation complexity index that reflects the overall amplitude fluctuation complexity of the response signals. This allows for sensitive identification of subtle structural differences between the weld and non-weld areas by differentially analyzing the fluctuation complexity indexes corresponding to the weld and non-weld areas to be tested. By calculating the difference correction factor based on the energy amplitude difference between the response signals corresponding to the weld area to be tested and the non-weld area, and combining the difference correction factor with the difference between the fluctuation complexity index corresponding to the weld area to be tested and the non-weld area to be tested to determine the damage detection result, the interference of the amplitude difference can be effectively eliminated, and more accurate damage detection results can be obtained. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following briefly introduces the drawings required for use in the embodiments of the present application or related technical descriptions. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying any creative work.

[0037] Figure 1 Schematic diagram of a flow chart of a rail weld damage detection method according to an embodiment;

[0038] Figure 2 A schematic diagram of a process for obtaining a fluctuation complexity index in one embodiment;

[0039] Figure 3 Schematic diagram of ultrasonic testing position of rails in one embodiment;

[0040] Figure 4 for Figure 3 Cross-sectional view of the rail along line AA;

[0041] Figure 5 A schematic flow chart of a rail weld damage detection method in another embodiment;

[0042] Figure 6 1 is a structural block diagram of a rail weld damage detection device according to an embodiment;

[0043] Figure 7 FIG. 1 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0044] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0045] In one embodiment, Figure 1 As shown, a rail weld damage detection method is provided. This embodiment uses the method applied to a terminal as an example for illustration. It is understandable that the method can also be applied to a server, or to a system including a terminal and a server, and implemented through interaction between the terminal and the server. In this embodiment, the method includes the following steps:

[0046] Step S101 , ultrasonic testing is performed on the weld area and non-weld area of the rail to be tested, respectively, to obtain response signals corresponding to the weld area and non-weld area to be tested.

[0047] Specifically, a rail may include at least one weld zone, which may be a weld formed by welding on the rail, and a non-weld zone, which may be an area on the rail that has not been welded. The weld on the rail that requires defect detection may be the weld zone to be tested.

[0048] In this step, ultrasonic signals may be transmitted to the weld region to be tested and the non-weld region of the rail, respectively. A detection response signal is obtained after the ultrasonic signal passes through the weld region to be tested, and a reference response signal is obtained after the ultrasonic signal passes through the non-weld region. For example, in this step, ultrasonic testing may be performed using an ultrasonic detector equipped with at least two probes, one of which may serve as an ultrasonic signal transmitter and the other as a response signal receiver.

[0049] Optionally, multiple groups of detection points at different positions may be selected in the weld area and non-weld area to be tested for ultrasonic testing to obtain multiple response signals corresponding to the weld area and non-weld area to be tested.

[0050] Step S102 : performing multi-scale analysis on each response signal to obtain a fluctuation complexity index of each response signal.

[0051] The multi-scale analysis may be performed by statistically analyzing the fluctuations of the response signal amplitude at multiple preset analysis scales, and then combining the statistical results at multiple analysis scales to obtain a fluctuation complexity index of the response signal. Different analysis scales may correspond to different time scales.

[0052] For example, in this step, the response signal can be subjected to multi-scale analysis by calculating fractal dimensions, for example, to obtain a fluctuation complexity index that reflects the complexity of the response signal's amplitude fluctuations at different analysis scales. A larger value of the fluctuation complexity index indicates a higher fluctuation complexity of the response signal, while a smaller value of the fluctuation complexity index indicates a lower fluctuation complexity of the response signal.

[0053] Step S103 , obtaining a difference correction factor according to the energy amplitude difference between the response signals corresponding to the weld area to be measured and the non-weld area.

[0054] For each response signal, its energy amplitude can be statistically analyzed to obtain an energy statistic that reflects the overall energy of the response signal. Then, based on the difference between the energy statistic corresponding to the detection response signal of the weld region to be tested and the reference response signal corresponding to the non-weld region, a difference correction factor between the detection response signal and the reference response signal can be calculated. For example, the difference correction factor can be the ratio of the energy statistic corresponding to the detection response signal to the energy statistic corresponding to the reference response signal, which can reflect the overall energy difference between the detection response signal and the reference response signal.

[0055] Step S104 , obtaining a damage detection result of the weld area to be tested based on the difference between the fluctuation complexity indexes of the response signals corresponding to the weld area to be tested and the non-weld area and the difference correction factor.

[0056] In this step, the difference between the fluctuation complexity indexes corresponding to the detection response signal corresponding to the weld area to be tested and the reference response signal corresponding to the non-weld area can be analyzed to obtain a complex difference factor between the detection response signal and the reference response signal, which can reflect the difference in fluctuation complexity of the detection response signal relative to the reference response signal. It can be understood that since the response signal is the signal obtained after the ultrasonic signal passes through the weld area to be tested or the non-weld area to be tested, the fluctuation complexity of the response signal can reflect the structural complexity of the area passed by the ultrasonic signal, and thus the size of the complex difference factor between the detection response signal and the reference response signal can reflect the size of the difference in structural complexity between the weld area to be tested and the non-weld area. A larger complex difference factor indicates that the weld area to be tested has a higher structural complexity than the non-weld area.

[0057] Among them, since the size of the complex difference factor can be affected by the energy amplitude of the response signal, the complex difference factor can be corrected using a difference correction factor in this step to eliminate the influence of the overall energy difference between the detection response signal and the reference response signal on the complex difference factor. Therefore, after the correction is completed, a unified evaluation standard can be applied to analyze the complex difference factor to achieve an assessment of the damage condition of the weld area to be tested and obtain a damage detection result of the weld area to be tested. Exemplarily, the evaluation standard can include a threshold value for measuring the damage condition. When the complex difference factor is not greater than the threshold value, a damage detection result indicating that the weld area to be tested is not damaged can be obtained; when the complex difference factor is greater than the threshold value, a damage detection result indicating that the weld area to be tested is damaged can be obtained.

[0058] In the above-mentioned rail weld damage detection method, multi-scale analysis of the response signal is performed to comprehensively analyze the amplitude fluctuations of the response signal at different time scales to obtain a fluctuation complexity index that reflects the overall amplitude fluctuation complexity of the response signal. This allows for differential analysis of the fluctuation complexity indexes corresponding to the weld and non-weld areas to facilitate the sensitive identification of subtle structural differences between the weld and non-weld areas. Calculating a difference correction factor based on the energy amplitude difference between the response signals corresponding to the weld and non-weld areas, and combining this difference correction factor with the difference between the fluctuation complexity indexes corresponding to the weld and non-weld areas to determine the damage detection result, effectively eliminates interference from amplitude differences and achieves more accurate damage detection results.

[0059] In an exemplary embodiment, Figure 2 As shown, multi-scale analysis is performed on each response signal to obtain the fluctuation complexity index of each response signal, which may include:

[0060] Step S201 : for each analysis scale, dividing the response signal according to the analysis scale to obtain a plurality of sub-signal segments corresponding to the analysis scale.

[0061] Specifically, the multiple analysis scales may correspond to different time scales, wherein each analysis scale may correspond to a different partitioning parameter. In this step, for each analysis scale, the response signal may be partitioned using an equal division method according to the partitioning parameter corresponding to the analysis scale to obtain multiple sub-signal segments corresponding to the analysis scale.

[0062] For example, different analysis scales can be set in a bisection manner. Assuming that the signal length of the response signal is (i.e., including uniformly distributed sampling points), then the partitioning parameters corresponding to each analysis scale It can be 2, 4, 8, ..., . Which corresponds to each partition parameter , the response signal can be divided into sub-signal segments, and the signal length of each sub-signal segment is (i.e., including uniformly distributed sampling points).

[0063] Step S202 : obtaining an amplitude fluctuation index of each sub-signal segment according to the signal amplitude of each sampling point in each sub-signal segment.

[0064] For each of the multiple sub-signal segments obtained at each analysis scale, an amplitude fluctuation index can be calculated for each sub-signal segment. For each sub-signal segment, the signal amplitudes of each sampling point can be extracted, and the maximum, minimum, and average signal amplitudes within the sub-signal segment can be calculated. Finally, an amplitude fluctuation index for the sub-signal segment can be calculated. The amplitude fluctuation index can reflect the overall fluctuation range of the sub-signal segment and the degree of maximum amplitude deviation.

[0065] In an exemplary embodiment, obtaining the amplitude fluctuation index of each sub-signal segment based on the signal amplitude of each sampling point in each sub-signal segment may include: obtaining the maximum signal amplitude, minimum signal amplitude and average signal amplitude of the sub-signal segment based on the signal amplitude of each sampling point in the sub-signal segment; obtaining the amplitude fluctuation index based on the difference between the maximum signal amplitude and the average signal amplitude, and the difference between the maximum signal amplitude and the minimum signal amplitude.

[0066] For example, when calculating the partition parameter The first When the amplitude fluctuation index of a sub-signal segment is calculated, the difference between the maximum signal amplitude and the average signal amplitude in the sub-signal segment can be calculated respectively. and the difference between the maximum and minimum signal amplitudes , and then calculate the average of the two to get the Amplitude fluctuation index of sub-signal segments .

[0067] Step S203 : for each analysis scale, the amplitude fluctuation indexes of the sub-signal segments corresponding to the analysis scale are fused to obtain a cumulative fluctuation index of the analysis scale.

[0068] For each analysis scale, the amplitude fluctuation indexes of the sub-signal segments obtained by dividing the scale can be fused in an accumulation manner to obtain the cumulative fluctuation index of the analysis scale.

[0069] For example, for the partition parameter The analysis scale of , its cumulative fluctuation index can be expressed as ,in The first Amplitude fluctuation indicator of a sub-signal segment.

[0070] Step S204 , fitting the relationship between each analysis scale and each cumulative fluctuation index to obtain a fluctuation complexity index of the response signal.

[0071] In this step, for multiple analysis scales, the division parameters corresponding to each analysis scale can be and the cumulative volatility index The relationship between them is fitted to obtain a fluctuation complexity index that can reflect the complexity changes of the response signal at multiple scales.

[0072] For example, the least square method can be used in this step to and Fitting is performed to obtain the fluctuation complexity index The calculation process can be expressed as:

[0073]

[0074] Where, is the volatility complexity index of the response signal, is the partition parameter corresponding to each analysis scale, The partition parameter is The cumulative volatility index corresponding to the analysis scale is is the signal length of the response signal, Represents the mean of the cumulative volatility indicators corresponding to multiple analysis scales, Represents the mean of the partitioning parameters corresponding to multiple analysis scales.

[0075] In this embodiment, the response signal is divided according to different analysis scales, and the cumulative fluctuation index of the corresponding analysis scale is obtained by fusing the amplitude fluctuation index of each sub-signal segment at the same analysis scale. Then, by fitting the relationship between the analysis scale and the cumulative fluctuation index, a fluctuation complexity index that can comprehensively reflect the multi-scale fluctuation characteristics of the response signal can be obtained. The fluctuation complexity index can sensitively and accurately characterize the fluctuation complexity of the response signal under the influence of the microstructure of the area through which the ultrasonic signal passes, which is conducive to more accurate detection of minor defects in the weld area to be tested in the future.

[0076] In an exemplary embodiment, obtaining a difference correction factor based on the energy amplitude difference between the response signals corresponding to the weld area to be measured and the non-weld area can include: for each response signal, obtaining the cumulative energy amplitude of the response signal based on the energy amplitude of each sampling point in the response signal; obtaining the unit energy amplitude of each response signal based on the cumulative energy amplitude and detection distance of each response signal; and obtaining the difference correction factor based on the difference in the unit energy amplitude of the response signals corresponding to the weld area to be measured and the non-weld area.

[0077] Specifically, in this embodiment, the difference correction factor can be calculated based on the difference between the unit energy amplitude of the detection response signal corresponding to the weld area to be tested and the unit energy amplitude of the reference response signal corresponding to the non-weld area.

[0078] For each response signal, the cumulative energy amplitude of the response signal can be calculated based on the signal amplitude at each sampling point. Then, the unit energy amplitude of the response signal can be obtained based on the ratio of the cumulative energy amplitude to the detection distance. The detection distance corresponding to the response signal can be the distance between the ultrasonic signal transmitting end and the response signal receiving end in ultrasonic detection, that is, the propagation path length of the ultrasonic signal.

[0079] For example, for the response signal , its unit energy amplitude can be expressed as:

[0080]

[0081] Where, In response to the signal The unit energy amplitude, In response to the signal The detection distance, In response to the signal The signal amplitude at each sampling point.

[0082] After obtaining the unit energy amplitude of each response signal, the difference correction factor can be calculated based on the ratio between the unit energy amplitude of the detection response signal corresponding to the weld area to be tested and the reference response signal corresponding to the non-weld area. and reference response signal , its difference correction factor It can be expressed as , where To detect the response signal The unit energy amplitude, is the reference response signal The unit energy amplitude.

[0083] In this embodiment, by counting the cumulative energy amplitudes of each response signal and calculating the unit energy amplitude in combination with the detection distance, and then calculating the difference correction factor, the influence of the detection distance on the signal energy amplitude can be eliminated in the process of analyzing the energy amplitude difference between the response signals corresponding to the weld area and the non-weld area to be measured, which is conducive to obtaining a more accurate difference correction factor.

[0084] In an exemplary embodiment, obtaining a damage detection result of the weld area to be measured based on the difference between the fluctuation complexity indicators of the response signals corresponding to the weld area to be measured and the non-weld area and the difference correction factor can include: obtaining a complex difference factor based on the relative deviation between the fluctuation complexity indicators of the response signals corresponding to the weld area to be measured and the non-weld area; correcting the complex difference factor using the difference correction factor to obtain a damage factor of the weld area to be measured; and obtaining a damage detection result of the weld area to be measured based on the damage level numerical range of the damage factor.

[0085] Specifically, in this embodiment, the relative deviation between the fluctuation complexity indexes of the response signals corresponding to the weld area to be tested and the non-weld area can be calculated first to obtain a complex difference factor that can reflect the difference in fluctuation complexity between the two. and reference response signal , and its complex difference factor can be expressed as .

[0086] Then, the complex difference factor can be corrected using the difference correction factor between the detection response signal and the reference response signal to obtain the damage factor of the weld area to be tested. and reference response signal , and its damage factor can be expressed as , where To detect the response signal and reference response signal Correction factor for the difference between .

[0087] Among them, the damage factor Afterwards, the damage factor The damage condition of the weld area to be tested is graded based on the value of to obtain the damage detection result of the weld area to be tested.

[0088] For example, the damage level value range corresponding to each weld damage level can be pre-divided according to different weld damage levels. For example, the weld damage level can be divided into no damage, small range damage, medium range damage, and large range damage, and the damage factor can be The values are divided into 4 damage level ranges from small to large, including: , corresponding to no damage to the weld; , corresponding to small-scale damage in the weld; , corresponding to the range damage in the weld; , corresponding to extensive damage in the weld.

[0089] Therefore, the damage factor can be calculated based on The specific damage level numerical range that the weld area to be tested falls into is determined to determine the weld damage level corresponding to the weld area to be tested, thereby obtaining the damage detection result of the weld area to be tested.

[0090] In this embodiment, by calculating the complex difference factor between the response signals corresponding to the weld area under test and the non-weld area, it is possible to quantify the difference in fluctuation complexity between the two response signals. By correcting the complex difference factor using the difference correction factor between the two, the damage factor is obtained. This eliminates the influence of the overall energy difference between the test response signal and the reference response signal on the complex difference factor. Thus, by evaluating the damage factor using a preset damage grade range, a standardized classification of damage grades in the weld area under test is achieved, resulting in accurate damage detection results.

[0091] In an exemplary embodiment, the response signal corresponding to the weld area to be tested includes multiple detection response signals collected from multiple weld positions, and the response signal corresponding to the non-weld area includes multiple reference response signals collected from multiple non-weld positions.

[0092] Specifically, when performing ultrasonic testing on the rails, ultrasonic testing can be performed on multiple weld positions in the weld area to be tested to collect multiple detection response signals corresponding to the multiple weld positions respectively; similarly, ultrasonic testing can also be performed on multiple non-weld positions in the non-weld area to collect multiple reference response signals corresponding to the multiple non-weld positions respectively.

[0093] Among them, please refer to Figure 3 , which is an exemplary setting method of the ultrasonic detection position in this embodiment. Figure 3 As shown, the rail 300 may include a weld zone 310 to be tested and a non-weld zone 320, and multiple sets of probes of an ultrasonic detector may be provided on the rail. Figure 4 The weld zone 310 to be tested may be provided with four sets of probes, including a first set of probes 411 and 412 provided on the rail head (for collecting the detection response signal ), the second set of probes 421 and 422 set on the rail waist (for collecting detection response signals ), the third set of probes 431 and 432 set at the bottom of the rail (for collecting detection response signals ), and a fourth set of probes 441 and 442 (for collecting detection response signals) arranged at the rail head portion on both sides of the weld area 310 to be tested The non-weld area 320 may be provided with two sets of probes, including a fifth set of probes 451 and 452 (used to collect reference response signals) provided at the rail head portion of the non-weld area on one side of the weld area 310 to be tested. ), and a sixth set of probes 461 and 462 (for collecting reference response signals) arranged at the rail head portion of the non-weld area on the other side of the weld area 310 to be tested ). Thus, the detection response signals corresponding to the four different weld positions in the weld area to be tested can be collected. , and the reference response signals corresponding to two different non-weld positions in the non-weld area .

[0094] Among them, the difference correction factor is obtained according to the energy amplitude difference between the response signals corresponding to the weld area to be tested and the non-weld area, including: for each detection response signal, according to the energy amplitude difference between the detection response signal and multiple reference response signals, obtaining the difference correction factor corresponding to the detection response signal.

[0095] Specifically, for each detection response signal, a difference correction factor can be calculated based on the overall energy amplitude difference between it and multiple reference response signals. Specifically, the unit energy amplitude of each detection response signal and each reference response signal can be calculated based on the signal amplitude of each sampling point in each detection response signal and reference response signal and the detection distance (i.e., the distance between the two probes used to collect the response signal). Taking the aforementioned ultrasonic detection position setting method as an example, the detection response signals can be calculated separately. The corresponding unit energy amplitude , and calculate the reference response signal The corresponding unit energy amplitude .

[0096] Then, the unit energy amplitudes of the reference response signals can be fused to obtain a reference energy amplitude that can reflect the overall energy intensity of multiple reference response signals. .

[0097] Then, the difference correction factor corresponding to each detection response signal can be obtained according to the difference between the unit energy amplitude of each detection response signal and the reference energy amplitude. The corresponding difference correction factor can be expressed as , similarly, the detection response signal can be obtained The corresponding difference correction factors .

[0098] Among them, the complex difference factor is obtained according to the relative deviation between the fluctuation complexity indexes of the response signals corresponding to the weld area to be tested and the non-weld area, including: for each detection response signal, according to the relative deviation between the fluctuation complexity index of the detection response signal and the fluctuation complexity indexes of multiple reference response signals, obtaining the complex difference factor corresponding to each detection response signal.

[0099] Specifically, for each detection response signal, the complexity difference factor can be calculated based on the overall difference between the fluctuation complexity index corresponding to the detection response signal and the fluctuation complexity index corresponding to multiple reference response signals. The corresponding volatility complexity index is , reference response signal The corresponding volatility complexity index is , we can first calculate the reference response signal Volatility Complexity Index Fusion is performed to obtain a reference complexity index that can reflect the overall fluctuation complexity of multiple reference response signals. , then the deviation between the fluctuation complexity index corresponding to each detection response signal and the reference complexity index can be calculated respectively to obtain the complexity difference factor corresponding to each detection response signal. The corresponding complex difference factor can be expressed as , similarly, the detection response signal can be obtained The corresponding complex difference factors .

[0100] Among them, the complex difference factor is corrected by using the difference correction factor to obtain the damage factor of the weld area to be tested, including: for each detection response signal, the complex difference factor is corrected according to the difference correction factor corresponding to the detection response signal to obtain the damage factor of the weld position corresponding to the detection response signal.

[0101] Specifically, for each detection response signal, its corresponding difference correction factor can be used to correct the complex difference factor corresponding to the detection response signal to obtain the damage factor of the weld position corresponding to the detection response signal. The corresponding damage factor can be expressed as Similarly, the detection response signal can be obtained The corresponding damage factors .

[0102] Among them, the damage detection result of the weld area to be tested is obtained according to the damage level numerical range of the damage factor, including: obtaining the damage detection result of the weld area to be tested according to the damage level numerical range of the damage factor at each weld position.

[0103] After obtaining the damage factor for each weld position, the damage detection result of the weld area to be tested can be comprehensively determined based on the damage level numerical range of each damage factor. For example, the weld damage levels of the corresponding weld positions in the weld area to be tested can be divided according to the value of each damage factor based on the preset damage level numerical range, and the highest weld damage level among them can be used as the damage detection result of the weld area to be tested.

[0104] In this embodiment, by performing ultrasonic testing at multiple locations in the weld area and non-weld area to be tested, multiple detection response signals corresponding to the multiple weld locations and multiple reference response signals corresponding to the multiple non-weld locations can be obtained. By fusing the relevant indices of the multiple reference response signals, the index characteristics of the non-weld area of the rail can be more accurately reflected. Furthermore, by performing a differential analysis between the indices of the different detection response signals and the corresponding indices after fusing the multiple reference response signals, multiple damage factors can be obtained that can respectively reflect weld damage at different locations and in different directions in the weld area to be tested. Furthermore, by combining the damage level numerical ranges of the multiple damage factors, a damage detection result that can reflect the overall damage level of the weld area to be tested can be obtained, thereby achieving high-precision detection of weld damage.

[0105] In an exemplary embodiment, Figure 5 As shown, a rail weld damage detection method is provided, which can specifically include the following steps:

[0106] Step S1 : ultrasonically inspect the weld area and non-weld area of the rail to be tested, and obtain corresponding response signals of the weld area and non-weld area to be tested.

[0107] Step S2: Perform multi-scale analysis on each response signal to obtain a fluctuation complexity index of each response signal.

[0108] Step S3, obtaining a difference correction factor according to the energy amplitude difference between the response signals corresponding to the weld area to be measured and the non-weld area.

[0109] Step S4, obtaining the damage factor of the weld area to be measured according to the difference between the fluctuation complexity indexes of the response signals corresponding to the weld area to be measured and the non-weld area and the difference correction factor.

[0110] Step S5: constructing a weld damage evaluation system, wherein the weld damage evaluation system may include damage level value ranges corresponding to different weld damage levels.

[0111] Step S6: obtaining damage detection results of the weld area to be tested according to the damage level value range of the damage factor.

[0112] It should be understood that, although the steps in the flowcharts of the above embodiments are shown in sequence as indicated by the arrows, these steps are not necessarily performed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be performed in other orders. Moreover, at least a portion of the steps in the flowcharts of the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily performed at the same time, but can be performed at different times. The execution order of these steps or stages is not necessarily to be performed in sequence, but can be performed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0113] Based on the same inventive concept, embodiments of the present application also provide a rail weld damage detection device for implementing the aforementioned rail weld damage detection method. The solution provided by this device is similar to the solution described in the aforementioned method. Therefore, the specific limitations of one or more embodiments of the rail weld damage detection device provided below can be found in the aforementioned limitations of the rail weld damage detection method and will not be further elaborated here.

[0114] In an exemplary embodiment, Figure 6 As shown, a rail weld damage detection device 600 is provided, comprising:

[0115] The signal acquisition module 601 is used to perform ultrasonic testing on the weld area to be tested and the non-weld area of the rail respectively, and obtain response signals corresponding to the weld area to be tested and the non-weld area respectively.

[0116] The fluctuation analysis module 602 is configured to perform multi-scale analysis on each of the response signals to obtain a fluctuation complexity index of each of the response signals.

[0117] The difference analysis module 603 is configured to obtain a difference correction factor according to the energy amplitude difference between the response signals corresponding to the weld area to be measured and the non-weld area.

[0118] The result acquisition module 604 is configured to obtain a damage detection result of the weld area to be tested based on the difference between the fluctuation complexity index of the response signals corresponding to the weld area to be tested and the non-weld area and the difference correction factor.

[0119] In an exemplary embodiment, the fluctuation analysis module 602 is used to: for each analysis scale, divide the response signal according to the analysis scale to obtain multiple sub-signal segments corresponding to the analysis scale; obtain the amplitude fluctuation index of each sub-signal segment according to the signal amplitude of each sampling point in each sub-signal segment; for each analysis scale, fuse the amplitude fluctuation index of each sub-signal segment corresponding to the analysis scale to obtain the cumulative fluctuation index of the analysis scale; fit the relationship between each analysis scale and each cumulative fluctuation index to obtain the fluctuation complexity index of the response signal.

[0120] In an exemplary embodiment, the fluctuation analysis module 602 is used to: obtain the maximum signal amplitude, minimum signal amplitude and average signal amplitude of the sub-signal segment based on the signal amplitude of each sampling point in the sub-signal segment; and obtain the amplitude fluctuation index based on the difference between the maximum signal amplitude and the average signal amplitude, and the difference between the maximum signal amplitude and the minimum signal amplitude.

[0121] In an exemplary embodiment, the difference analysis module 603 is used to: for each of the response signals, obtain the cumulative energy amplitude of the response signal based on the energy amplitude of each sampling point in the response signal; obtain the unit energy amplitude of each response signal based on the cumulative energy amplitude and the detection distance of each response signal; and obtain the difference correction factor based on the difference between the unit energy amplitudes of the response signals corresponding to the weld area to be measured and the non-weld area.

[0122] In an exemplary embodiment, the result acquisition module 604 is used to: obtain a complex difference factor based on the relative deviation between the fluctuation complexity index of the response signal corresponding to the weld area to be tested and the non-weld area; correct the complex difference factor using the difference correction factor to obtain the damage factor of the weld area to be tested; and obtain the damage detection result of the weld area to be tested based on the damage level numerical range of the damage factor.

[0123] In an exemplary embodiment, the response signal corresponding to the weld area to be tested includes multiple detection response signals collected from multiple weld positions, and the response signal corresponding to the non-weld area includes multiple reference response signals collected from multiple non-weld positions; the difference analysis module 603 is used to: for each of the detection response signals, obtain a complex difference factor corresponding to each of the detection response signals according to the relative deviation between the fluctuation complexity index of the detection response signal and the fluctuation complexity index of the multiple reference response signals; for each of the detection response signals, correct the complex difference factor according to the difference correction factor corresponding to the detection response signal to obtain the damage factor of the weld position corresponding to the detection response signal; and obtain the damage detection result of the weld area to be tested according to the damage level numerical range of the damage factor at each of the weld positions.

[0124] Each module in the aforementioned rail weld damage detection device can be implemented in whole or in part through software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in hardware form, or stored in a computer device memory in software form, so that the processor can call and execute the corresponding operations of each module.

[0125] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Figure 7 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O) and a communication interface. The processor, memory and input / output interface are connected via a system bus, and the communication interface is connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to store data such as response signals, analysis scales, and damage level numerical ranges obtained by ultrasonic testing. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a method for detecting damage to a rail weld is implemented.

[0126] Those skilled in the art will understand that Figure 7The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0127] In one embodiment, a computer device is further provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps in the above method embodiments when executing the computer program.

[0128] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0129] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0130] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0131] Those skilled in the art will understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, database or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The databases involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the various embodiments provided herein may be, but are not limited to, general-purpose processors, central processing units (CPUs), graphics processing units (GPUs), digital signal processors (DSPs), programmable logic devices (PLDs), quantum computing-based data processing logic devices, artificial intelligence (AI) processors, and the like.

[0132] The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0133] The above embodiments merely illustrate several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art may make various modifications and improvements without departing from the spirit of the present invention, all of which fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A rail weld damage detection method, characterized in that: The method comprises: Performing ultrasonic testing on the weld area to be tested and the non-weld area of the rail respectively, to obtain response signals corresponding to the weld area to be tested and the non-weld area respectively; Performing multi-scale analysis on each of the response signals to obtain a fluctuation complexity index of each of the response signals; Obtaining a difference correction factor according to an energy amplitude difference between the response signals corresponding to the weld area to be measured and the non-weld area; A damage detection result of the weld area to be measured is obtained according to the difference between the fluctuation complexity index of the response signals corresponding to the weld area to be measured and the non-weld area and the difference correction factor.

2. The method according to claim 1, characterized in that The multi-scale analysis is performed on each of the response signals to obtain a fluctuation complexity index of each of the response signals, including: For each analysis scale, dividing the response signal according to the analysis scale to obtain a plurality of sub-signal segments corresponding to the analysis scale; Obtaining an amplitude fluctuation index of each of the sub-signal segments according to the signal amplitude of each sampling point in each of the sub-signal segments; For each analysis scale, the amplitude fluctuation indexes of the sub-signal segments corresponding to the analysis scale are fused to obtain a cumulative fluctuation index of the analysis scale; The relationship between each of the analysis scales and each of the cumulative fluctuation indices is fitted to obtain a fluctuation complexity index of the response signal.

3. The method according to claim 2, characterized in that Obtaining the amplitude fluctuation index of each sub-signal segment according to the signal amplitude of each sampling point in each sub-signal segment includes: Obtaining a maximum signal amplitude, a minimum signal amplitude, and an average signal amplitude of the sub-signal segment according to the signal amplitude of each sampling point in the sub-signal segment; The amplitude fluctuation index is obtained according to a difference between the maximum signal amplitude and the average signal amplitude, and a difference between the maximum signal amplitude and the minimum signal amplitude.

4. The method according to claim 1, wherein The obtaining of a difference correction factor according to the energy amplitude difference between the response signals corresponding to the weld area to be measured and the non-weld area includes: For each of the response signals, obtaining a cumulative energy amplitude of the response signal according to the energy amplitude of each sampling point in the response signal; Obtaining a unit energy amplitude of each response signal according to the cumulative energy amplitude of each response signal and the detection distance; The difference correction factor is obtained according to the difference in the unit energy amplitude of the response signal corresponding to the weld area to be measured and the non-weld area.

5. The method according to any one of claims 1 to 4, characterized in that Obtaining a damage detection result of the weld area to be measured based on a difference between the fluctuation complexity index of the response signals corresponding to the weld area to be measured and the non-weld area and the difference correction factor includes: Obtaining a complexity difference factor according to a relative deviation between the fluctuation complexity indexes of the response signals corresponding to the weld area to be measured and the non-weld area; Correcting the complex difference factor using the difference correction factor to obtain the damage factor of the weld area to be measured; The damage detection result of the weld area to be tested is obtained according to the damage level value range of the damage factor.

6. The method according to claim 5, characterized in that The response signal corresponding to the weld area to be tested includes a plurality of detection response signals collected from a plurality of weld positions, and the response signal corresponding to the non-weld area includes a plurality of reference response signals collected from a plurality of non-weld positions; Obtaining a difference correction factor based on an energy amplitude difference between the response signals corresponding to the weld area to be tested and the non-weld area includes: for each detection response signal, obtaining a difference correction factor corresponding to the detection response signal based on an energy amplitude difference between the detection response signal and a plurality of reference response signals; Obtaining a complex difference factor according to a relative deviation between the fluctuation complexity indices of the response signals corresponding to the weld area to be tested and the non-weld area includes: for each detection response signal, obtaining a complex difference factor corresponding to each detection response signal according to a relative deviation between the fluctuation complexity indices of the detection response signal and the fluctuation complexity indices of a plurality of reference response signals; The method of correcting the complex difference factor using the difference correction factor to obtain the damage factor of the weld area to be tested includes: for each detection response signal, correcting the complex difference factor according to the difference correction factor corresponding to the detection response signal to obtain the damage factor of the weld position corresponding to the detection response signal; Obtaining the damage detection result of the weld area to be tested according to the damage level numerical range of the damage factor includes: obtaining the damage detection result of the weld area to be tested according to the damage level numerical range of the damage factor at each weld position.

7. A rail weld damage detection device, characterized in that: The device comprises: A signal acquisition module is used to perform ultrasonic testing on the weld area to be tested and the non-weld area of the rail respectively, and obtain response signals corresponding to the weld area to be tested and the non-weld area respectively; a fluctuation analysis module, configured to perform multi-scale analysis on each of the response signals to obtain a fluctuation complexity index of each of the response signals; a difference analysis module, configured to obtain a difference correction factor based on the energy amplitude difference between the response signals corresponding to the weld area to be measured and the non-weld area; The result acquisition module is used to obtain the damage detection result of the weld area to be tested based on the difference between the fluctuation complexity index of the response signal corresponding to the weld area to be tested and the non-weld area and the difference correction factor.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images