Defect detection method and device for live working insulation tool

Abstract

The embodiment of the invention provides a defect detection method and device for a live working insulation tool. The method comprises the following steps: acquiring A scanning signal display waveform data of an ultrasonic detection system on an insulation tool as sampling data; preprocessing the sampling data to obtain candidate samples; carrying out recall processing on high echo samples and head and tail echo samples in the candidate samples, and taking the samples subjected to recall processing as a training set; constructing a defect judgment model, training the defect judgment model by utilizing the training set, and taking the defect judgment model meeting the sorting loss as a trained defect judgment model; and inputting the sampling data of the target insulation tool into the trained defect judgment model, and outputting a defect result. Through the insulation tool defect detection algorithm, small defects in the insulation tool can be stably detected, the flaw detection quality of the insulation tool is guaranteed, and maximization of economic benefits is guaranteed.

Description

Technical Field

[0001] The present invention generally relates to the field of non-destructive testing, and more particularly, to a method and apparatus for defect detection of insulating tools for live working. Background Art

[0002] Insulated tools for live working are generally made of hollow tubes and solid rods processed from glass fiber reinforced epoxy resin composite materials. They have good mechanical and insulating properties and are widely used in the power and grid industries.

[0003] Since insulating tools are subjected to the combined effects of high voltage electricity and mechanical stress during long-term use, microscopic defects such as delamination, air gaps, and impurities are easily formed inside them, resulting in the degradation of their mechanical and insulation properties, which ultimately endangers the safety of power workers and maintenance equipment. Ultrasonic testing technology can effectively diagnose internal defects of materials and ensure the safety of workers. Traditional non-destructive testing methods use manual hand probes and ordinary piezoelectric ultrasonic probes to detect insulating rods.

[0004] The existing technology has technical problems that the detection of insulating rods relies on the experience, operating techniques and professionalism of the flaw detectors, the data cannot be recorded and traced in real time, and the reliability and credibility of the flaw detection are not high. Summary of the invention

[0005] According to an embodiment of the present invention, a defect detection scheme for live working insulating tools is provided. This scheme manually attaches an ultrasonic probe to the surface of an insulating rod, and then uses hand pushing or mechanical power to push the ultrasonic probe to move on the surface of the insulating rod, collects a large amount of ultrasonic data from different directions, and uses a defect detection algorithm based on machine learning to identify abnormal waveforms, thereby screening damage defects in the insulating rod to be detected, solving the technical problem of relying on the experience of flaw detectors in the prior art, and having low reliability and credibility.

[0006] In a first aspect of the present invention, a method for detecting defects of insulating tools for live working is provided. The method comprises:

[0007] The A-scan signal display waveform data of the ultrasonic detection system for the insulating tool is obtained as sampling data.

[0008] Preprocess the sampled data to obtain candidate samples.

[0009] The high echo samples and the first and last echo samples in the candidate samples are recalled, and the recalled samples are used as training sets.

[0010] Construct a defect judgment model, use the training set to train the defect judgment model, and use the defect judgment model that meets the sorting loss as the trained defect judgment model.

[0011] The sampling data of the target insulation tool is input into the trained defect judgment model and the defect results are output.

[0012] The preprocessing of the sampled data comprises:

[0013] Fill missing values ​​in the sampled data using linear interpolation. And / or

[0014] Identify the abnormal sampling points in the sampled data, and replace the data of the abnormal sampling points with the data of the linear interpolation of the sampling points before and after the abnormal sampling points. And / or

[0015] Expand the sample-level and window-level statistical and morphological features of the sampled data. And / or

[0016] Normalize the sampled data.

[0017] The method of filling missing values ​​in the sampled data by using linear interpolation includes:

[0018]

[0019] Among them, X k is the missing value to be filled; X i is a missing value; X i-1 For missing values ​​X i The previous non-missing value of X j is the non-missing value after the last missing value; p is the set of missing values; i is the subscript corresponding to the first missing value; j is the subscript corresponding to the next value of the last missing value.

[0020] The identifying of abnormal sampling points in the sampled data includes:

[0021] If two consecutive sampling points in the sampled data meet the abnormal sampling point judgment condition, the latter of the two sampling points is the abnormal sampling point.

[0022] The abnormal sampling point judgment condition is:

[0023] |X a -X a-1 |>kσ

[0024] Among them, σ is the standard deviation of the sampled data; k is a constant; X a With X a-1 are two consecutive sampling points.

[0025] Recall the high echo samples in the candidate samples, including:

[0026] A set of intervals whose sample values ​​are greater than a first threshold is obtained from the candidate samples.

[0027] Merge consecutive points in an interval set into an interval to obtain several sub-intervals.

[0028] If there is at least one subinterval whose length is greater than the second threshold, the sample corresponding to the subinterval is a high echo sample, and the high echo sample is recalled.

[0029] The first and last echo samples in the candidate samples are recalled, including:

[0030] If there are candidate samples that meet the first condition or the second condition of the high echo interval, the high echo samples that meet the conditions are recalled.

[0031] The first condition is:

[0032] max(t ai ,t bi ) <M left

[0033] The second condition is:

[0034] max(t ai ,t bi )>M right

[0035] Among them, max(t ai ,t bi ) is t ai and t bi The larger value; t ai ,t bi are the left and right boundaries of the ith high echo interval respectively; M left is the left endpoint of the recall interval, M right is the right endpoint of the recall interval.

[0036] The defect judgment model includes a scoring layer and a first fully connected neural network layer connected in sequence, as well as a convolutional layer, a multi-head self-attention network layer, a second fully connected neural network layer and an average pooling layer connected in sequence; it also includes a splicing layer and a third fully connected neural network layer.

[0037] The scoring layer, as an input layer of the defect judgment model, is used to obtain sample-level features and perform table lookup embedding. The output of the scoring layer is input to the first fully connected neural network layer. The first fully connected neural network layer interacts and assigns weights to the input sliding window features and the original sequence, and outputs a first hidden vector.

[0038] The convolution layer, as another input layer of the defect judgment model, is used to obtain window-level features and the sampled data, map the data, and output the mapping results to the multi-head self-attention network layer for feature crossover. The crossover results are sequentially passed through the second fully connected neural network layer and the average pooling layer to output the second hidden vector.

[0039] A concatenation layer is used to concatenate the first hidden vector and the second hidden vector.

[0040] The third fully connected neural network layer takes the output result of the concatenation layer as input, and outputs a defect score result, and uses the defect score result as the output result of the defect judgment model.

[0041] The defect judgment model is trained using the training set, and the defect judgment model that satisfies the sorting loss is used as the trained defect judgment model, including:

[0042] A defect waveform is selected from the training set as a label sample, and the DTW distance between all samples in the training set and the label sample is calculated.

[0043] All samples in the training set are sorted in ascending order according to their DTW distance to the label samples to obtain a reference sequence.

[0044] The defect score results of each sample output by the defect judgment model are sorted from large to small according to the reference sequence to obtain a predicted sequence.

[0045] The pairwise ranking loss function is calculated based on the reference sequence and the predicted sequence.

[0046] The pairwise ranking loss is calculated as follows:

[0047]

[0048] where s i and j is the model's score for the i-th and j-th samples, and there is

[0049]

[0050] The step of inputting the sampled data of the target insulation tool into the trained defect judgment model and outputting the defect result comprises:

[0051] If the output scores of the trained defect judgment model are all less than the preset third threshold or there are no samples that have been recalled, the target insulating tool is considered to be free of defects.

[0052] If there is a sample whose output score of the trained defect judgment model is greater than the preset third threshold, the waveform with the highest score is output as the defect result.

[0053] In a second aspect of the present invention, a defect detection device for an insulating tool for live working is provided. The device comprises:

[0054] The data acquisition module is used to acquire the A-scan signal display waveform data of the ultrasonic detection system for the insulating tool as sampling data.

[0055] The preprocessing module is used to preprocess the sampled data to obtain candidate samples.

[0056] The recall processing module is used to perform recall processing on high echo samples and first and last echo samples in the candidate samples, and use the recalled samples as training sets.

[0057] The model training module is used to build a defect judgment model, use the training set to train the defect judgment model, and use the defect judgment model that meets the sorting loss as the trained defect judgment model.

[0058] The defect judgment module is used to judge the defect results of the sampling data of the target insulation tool using the trained defect judgment model.

[0059] It should be understood that the contents described in the summary of the invention are not intended to limit the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] The above and other features, advantages and aspects of the embodiments of the present invention will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, wherein:

[0061] Figure 1 A flow chart of a defect detection method for an insulating tool for live working according to an embodiment of the present invention is shown.

[0062] Figure 2 A flow chart of a defect judgment model according to an embodiment of the present invention is shown.

[0063] Figure 3 A block diagram of a defect detection device for an insulating tool for live working according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0064] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0065] In addition, the term "and / or" in this article is only a description of the association relationship between the associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0066] In this embodiment, Figure 1 , Figure 2 The method comprises:

[0067] S101, obtaining waveform data displayed by an A-scan signal of an ultrasonic detection system for an insulating tool as sampling data.

[0068] In this embodiment, the A-scan signal display waveform data is a kind of ultrasonic detection display mode, which uses rectangular coordinates to display the amplitude and propagation time of ultrasonic echoes.

[0069] S102: Preprocess the sampled data to obtain candidate samples.

[0070] In this embodiment, because the A-scan signal display waveform data may have large differences due to different sampling methods, the sampled data needs to be preprocessed into the same distribution.

[0071] In this embodiment, after the sample data is acquired, when it is found that there are missing segments in the sample data, the missing values ​​in the sample data are filled by using a linear interpolation operation.

[0072] The method of filling missing values ​​in the sampled data by using linear interpolation includes:

[0073]

[0074] Among them, X k is the missing value to be filled; X i is a missing value; X i-1 For missing values ​​X i The previous non-missing value of X j is the non-missing value after the last missing value; p is the set of missing values; i is the subscript corresponding to the first missing value; j is the subscript corresponding to the next value of the last missing value.

[0075] In this embodiment, when there is noise or machine failure in the process of acquiring sampling data, the data of the sampling points will greatly deviate from the normal value, and the sampling points that greatly deviate from the normal value are further screened and set as abnormal sampling points.

[0076] Furthermore, the abnormal sampling points in the sampled data are identified, and the data of the abnormal sampling points are replaced by the data of the linear interpolation of the sampling points before and after the abnormal sampling points.

[0077] Identify abnormal sampling points in the sampled data, including:

[0078] If two consecutive sampling points in the sampled data meet the abnormal sampling point judgment condition, the latter of the two sampling points is the abnormal sampling point.

[0079] The abnormal sampling point judgment condition is:

[0080] |X a -X a-1 |>kσ

[0081] Among them, σ is the standard deviation of the sampled data; k is a constant; X a With X a-1 are two consecutive sampling points.

[0082] In this embodiment, in order to facilitate the machine learning model to identify waveform features and patterns, it is necessary to extract and expand features of sample-level data and window-level data in the collected data, including: expansion of sample-level statistical features and morphological features and expansion of window-level statistical features and morphological features.

[0083] Among them, the statistical features and morphological features at the sample level and window level in the sampled data are expanded, including:

[0084] Statistical and morphological characteristics at the sample level.

[0085] Mean and standard deviation.

[0086] Minimum value, maximum value.

[0087] Median, quartiles, and interquartile range.

[0088] Deflection, torsion, central moment, second-order moment.

[0089] Statistical and morphological features at the window level.

[0090] The mean and standard deviation of the 10-step sliding window.

[0091] Minimum and maximum values ​​for the 10-step sliding window.

[0092] · Deflection and torsion of 10-step sliding window.

[0093] The mean and standard deviation of the 30-step sliding window.

[0094] Minimum and maximum values ​​for the 30-step sliding window.

[0095] Deflection and torsion of 30-step sliding window.

[0096] For the statistical features and morphological features at the window level, the tails of the statistical features and morphological features are filled with 0 and superimposed with the sampling data in the form of a vector matrix to obtain the expanded sample data.

[0097] In this embodiment, the sampled data needs to be further normalized to ensure that the feature space of each piece of sampled data is unified.

[0098] In this embodiment, normalizing the sampled data includes:

[0099] Perform MinMax normalization operation to normalize the samples in the dimension of the original data using the known maximum and minimum values ​​of all data.

[0100] The MinMax normalization operation is:

[0101]

[0102] Among them, x is the original data dimension, x i,norm is the sample value after normalization operation, x i is the current value of the normalization operation, x min is the minimum value in the sample data, x max is the maximum value in the sample data.

[0103] In this embodiment, when the sampled data acquired in step S101 is preprocessed, analysis may be performed according to the real-time situation of the sampled data, and one or more data preprocessing methods of step S102 may be used to process the data to obtain candidate samples.

[0104] S103: recall the high echo samples and the first and last echo samples in the candidate samples, and use the recalled samples as training sets.

[0105] In this embodiment, since the number of candidate samples returned by the defect detection system is huge, directly using the machine learning model is inefficient, and the noisy sampling data will interfere with the machine learning model. Therefore, it is necessary to recall the candidate samples and perform initial screening of the candidate samples to obtain smaller-scale candidate samples.

[0106] In this embodiment, there are two ways to perform recall processing on candidate samples, including performing recall processing on high echo samples in the candidate samples and performing recall processing on the first and last echo samples in the candidate samples.

[0107] Furthermore, because the waveform of the defect candidate sample has a high echo characteristic, it is necessary to perform recall processing on the high echo samples in the candidate samples.

[0108] Recall the high echo samples in the candidate samples, including:

[0109] A set of intervals whose sample values ​​are greater than a first threshold is obtained from the candidate samples.

[0110] Merge consecutive points in an interval set into an interval to obtain several sub-intervals.

[0111] If there is at least one subinterval whose length is greater than the second threshold, the sample corresponding to the subinterval is a high echo sample, and the high echo sample is recalled.

[0112] In this embodiment, the second threshold is generally set to 5.

[0113] Furthermore, since the high echo of the defect candidate sample only appears in the middle of the waveform, it is necessary to use the first and last echo samples in the candidate sample for recall processing to filter out the high echoes caused by noise interference at the first and last of the candidate sample.

[0114] The first and last echo samples in the candidate samples are recalled, including:

[0115] If there are candidate samples that meet the first condition or the second condition of the high echo interval, the high echo samples that meet the conditions are recalled.

[0116] The first condition is:

[0117] max(t ai ,t bi ) <M left

[0118] The second condition is:

[0119] max(t ai ,t bi )>M right

[0120] Among them, max(t ai ,t bi ) is t ai and t bi The larger value; t ai ,t bi are the left and right boundaries of the ith high echo interval respectively; M left is the left endpoint of the recall interval, M right is the right endpoint of the recall interval.

[0121] Among them, M left Generally, it is set to 0.15 times the length of a single waveform sample. right It is usually set to 0.85 times the length of a single waveform sample.

[0122] S104, constructing a defect judgment model, using the training set to train the defect judgment model, and using the defect judgment model that satisfies the sorting loss as the trained defect judgment model.

[0123] In this embodiment, after obtaining the training set obtained in step S103, a defect judgment model is constructed, and the defect judgment model is trained using the training set, such as Figure 2 As shown:

[0124] In this embodiment, the defect judgment model includes a scoring layer and a first fully connected neural network layer connected in sequence, as well as a convolutional layer, a multi-head self-attention network layer, a second fully connected neural network layer and an average pooling layer connected in sequence; it also includes a splicing layer and a third fully connected neural network layer.

[0125] The scoring layer, as an input layer of the defect judgment model, is used to obtain sample-level features and perform table lookup embedding. The output of the scoring layer is input to the first fully connected neural network layer. The first fully connected neural network layer interacts and assigns weights to the input sliding window features and the original sequence, and outputs a first hidden vector.

[0126] After obtaining the sample-level features, the defect judgment model divides the sample-level features into discrete features with equal frequency, then performs table lookup embedding and inputs them into the first fully connected neural network layer.

[0127] The convolution layer, as another input layer of the defect judgment model, is used to obtain window-level features and the sampled data, map the data, and output the mapping results to the multi-head self-attention network layer for feature crossover. The crossover results are sequentially passed through the second fully connected neural network layer and the average pooling layer to output the second hidden vector.

[0128] Among them, for the sliding window features and the original sequence, the data is first mapped through a 1x1 convolutional network, then passed through a layer of multi-head attention network for window-level feature crossover, and finally output after passing through the second fully connected network layer and the average pooling layer.

[0129] A concatenation layer is used to concatenate the first hidden vector and the second hidden vector.

[0130] The third fully connected neural network layer takes the output result of the concatenation layer as input, and outputs a defect score result, and uses the defect score result as the output result of the defect judgment model.

[0131] Among them, the third fully connected neural network layer can scale the feature dimension to 1 and output the defect score.

[0132] Furthermore, the defect judgment model is trained using the training set, and the defect judgment model that satisfies the ranking loss is used as the trained defect judgment model.

[0133] In this embodiment, because there is a deviation in the distribution of different insulating tool candidate samples, in order to avoid the influence of the deviation, the DTW distance is not directly used as the label training model, and the ranking loss is used instead.

[0134] A defect waveform is selected from the training set as a label sample, and the DTW distance between all samples in the training set and the label sample is calculated.

[0135] All samples in the training set are sorted in ascending order according to their DTW distance to the label samples to obtain a reference sequence.

[0136] The defect score results of each sample output by the defect judgment model are sorted from large to small according to the reference sequence to obtain a predicted sequence.

[0137] The pairwise ranking loss function is calculated based on the reference sequence and the predicted sequence.

[0138] The pairwise ranking loss is calculated as follows:

[0139]

[0140] where s i and j is the model's score for the i-th and j-th samples, and there is

[0141]

[0142] In this embodiment, the loss function is used to calculate gradient back propagation in deep learning training and then update parameters.

[0143] S105, input the sampling data of the target insulation tool into the trained defect judgment model, and output the defect result.

[0144] In this embodiment, the step of inputting the sampled data of the target insulating tool into the trained defect judgment model and outputting the defect result includes:

[0145] If the output scores of the trained defect judgment model are all less than the preset third threshold or there are no samples that have been recalled, the target insulating tool is considered to be free of defects.

[0146] The third threshold is preset as the score of the critical defect ultrasonic sample obtained by the defect judgment model.

[0147] If there is a sample whose output score of the trained defect judgment model is greater than the preset third threshold, the waveform with the highest score is output as the defect result.

[0148] By using the insulating tool defect detection algorithm, the large-scale A-scan waveform data collected by the ultrasonic detection system from different directions of the detected target is used to determine whether the detected target has defects. If there are defects, the corresponding abnormal waveform is returned at the same time. Through the insulating tool defect detection algorithm of this application, small defects in insulating tools can be stably detected, which ensures the quality of insulating tool flaw detection and maximizes economic benefits.

[0149] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should know that the present invention is not limited by the described order of actions, because according to the present invention, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required by the present invention.

[0150] The above is an introduction to a method embodiment. The following is a further explanation of the scheme of the present invention through a device embodiment having the same inventive concept as the method in the aforementioned embodiment.

[0151] like Figure 3 As shown, the device 300 includes:

[0152] The data acquisition module 310 is used to acquire the A-scan signal display waveform data of the ultrasonic detection system for the insulating tool as sampling data.

[0153] The preprocessing module 320 is used to preprocess the sampled data to obtain candidate samples.

[0154] The recall processing module 330 is used to perform recall processing on the high echo samples and the first and last echo samples in the candidate samples, and use the recalled samples as training sets.

[0155] The model training module 340 is used to construct a defect judgment model, train the defect judgment model using a training set, and use the defect judgment model that meets the sorting loss as the trained defect judgment model.

[0156] The defect judgment module 350 is used to judge the defect results of the sampling data of the target insulation tool using the trained defect judgment model.

[0157] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the described module can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0158] In the technical solution of the present invention, the acquisition, storage and application of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0159] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0160] The program code for implementing the method of the present invention can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code can be executed entirely on the machine, partially on the machine, partially on the machine as a stand-alone software package and partially on a remote machine, or entirely on a remote machine or server.

[0161] In the context of the present invention, a machine-readable medium may be a tangible medium that may contain or store a program for use by an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0162] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0163] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0164] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0165] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0166] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A defect detection method for insulating tools for live working, characterized in that: include: Acquire the A-scan signal display waveform data of the ultrasonic detection system for the insulating tool as sampling data; Preprocess the sampled data to obtain candidate samples; Recall the high echo samples and the first and last echo samples in the candidate samples, and use the recalled samples as training sets; Construct a defect judgment model, use the training set to train the defect judgment model, and use the defect judgment model that satisfies the sorting loss as the trained defect judgment model; The sampling data of the target insulation tool is input into the trained defect judgment model and the defect results are output.

2. The method according to claim 1, characterized in that The preprocessing of the sampled data comprises: Fill missing values ​​in the sampled data using linear interpolation; and / or Identify abnormal sampling points in the sampled data, and replace the data of the abnormal sampling points with data of linear interpolation of sampling points before and after the abnormal sampling points; and / or Expanding sample-level and window-level statistical and morphological features in the sampled data; and / or Normalize the sampled data.

3. The method according to claim 2, characterized in that The method of filling missing values ​​in the sampled data by using linear interpolation includes: Among them, X k is the missing value to be filled; X i is a missing value; X i-1 For missing values ​​X i The previous non-missing value of X j is the non-missing value after the last missing value; p is the set of missing values; i is the subscript corresponding to the first missing value; j is the subscript corresponding to the next value of the last missing value.

4. The method according to claim 2, characterized in that: The identifying of abnormal sampling points in the sampled data includes: If two consecutive sampling points in the sampling data meet the abnormal sampling point judgment condition, the latter of the two sampling points is the abnormal sampling point; The abnormal sampling point judgment condition is: |X a -X a-1 |>kσ Among them, σ is the standard deviation of the sampled data; k is a constant; X a With X a-1 are two consecutive sampling points.

5. The method according to claim 1, characterized in that: Recall the high echo samples in the candidate samples, including: Obtaining, from the candidate samples, a set of intervals whose sample values ​​are greater than a first threshold; Merge consecutive points in the interval set into intervals to obtain several sub-intervals; If there is at least one subinterval whose length is greater than the second threshold, the sample corresponding to the subinterval is a high echo sample, and the high echo sample is recalled.

6. The method according to claim 1, characterized in that The first and last echo samples in the candidate samples are recalled, including: If there are candidate samples that meet the first condition or the second condition of the high echo interval, the high echo samples that meet the conditions are recalled; The first condition is: max(t ai ,t bi )<M left The second condition is: max(t ai ,t bi )>M right Among them, max(t ai ,t bi ) is t ai and t bi The larger value; t ai ,t bi are the left and right boundaries of the ith high echo interval respectively; M left is the left endpoint of the recall interval, M right is the right endpoint of the recall interval.

7. The method according to claim 1, characterized in that The defect judgment model includes a scoring layer and a first fully connected neural network layer connected in sequence, and a convolutional layer, a multi-head self-attention network layer, a second fully connected neural network layer and an average pooling layer connected in sequence; and also includes a splicing layer and a third fully connected neural network layer; The scoring layer, as an input layer of the defect judgment model, is used to obtain sample-level features and perform table lookup embedding. The output of the scoring layer is input to the first fully connected neural network layer. The first fully connected neural network layer interacts and weights the input sliding window features and the original sequence, and outputs a first hidden vector. The convolution layer, as another input layer of the defect judgment model, is used to obtain the window level features and the sampled data, map the data, and output the mapping results to the multi-head self-attention network layer for feature crossover. The crossover results are sequentially passed through the second fully connected neural network layer and the average pooling layer to output the second hidden vector; A concatenation layer, used for concatenating the first hidden vector and the second hidden vector; The third fully connected neural network layer takes the output result of the concatenation layer as input, and outputs a defect score result, and uses the defect score result as the output result of the defect judgment model.

8. The method according to claim 1, characterized in that The defect judgment model is trained by using the training set, and the defect judgment model that satisfies the sorting loss is used as the trained defect judgment model, including: Select a defect waveform from the training set as a label sample, and calculate the DTW distance between all samples in the training set and the label sample; Sort all samples in the training set by their DTW distance to the label samples from small to large to obtain a reference sequence; The defect score results of each sample output by the defect judgment model are sorted from large to small according to the reference sequence to obtain a prediction sequence; Calculating a pairwise ranking loss function based on the reference sequence and the predicted sequence; The pairwise ranking loss is calculated as follows: where s i and j is the model's score for the i-th and j-th samples, and there is 9. The method according to claim 1, characterized in that: The step of inputting the sampled data of the target insulation tool into the trained defect judgment model and outputting the defect result comprises: If the output scores of the trained defect judgment model are all less than the preset third threshold or there is no sample for recall processing, the target insulating tool is considered to be free of defects; If there is a sample whose output score of the trained defect judgment model is greater than the preset third threshold, the waveform with the highest score is output as the defect result.

10. A defect detection device for insulating tools for live working, characterized in that: include: A data acquisition module is used to acquire the A-scan signal display waveform data of the ultrasonic detection system for the insulation tool as sampling data; A preprocessing module is used to preprocess the sampled data to obtain candidate samples; A recall processing module is used to perform recall processing on high echo samples and first and last echo samples in candidate samples, and use the recalled samples as training sets; The model training module is used to build a defect judgment model, train the defect judgment model using the training set, and use the defect judgment model that meets the sorting loss as the trained defect judgment model; The defect judgment module is used to judge the defect results of the sampling data of the target insulation tool using the trained defect judgment model.

Images