Defect detection method, device and equipment of composite insulator, storage medium and product

Abstract

The invention relates to a defect detection method, device and equipment for a composite insulator, a storage medium and a product. The method comprises the following steps: acquiring defect feature information of the composite insulator; according to the defect feature information, detecting a first defect probability of candidate defects generated by the composite insulator, the candidate defects being selected from a plurality of expected defects generated by the composite insulator; and performing defect detection on the composite insulator according to the first defect probability. By adopting the method, the detection effect of composite insulator defect detection is improved.

Description

Technical Field

[0001] The present application relates to the technical field of power systems, and in particular to a composite insulator defect detection method, device, computer equipment, computer-readable storage medium, and computer program product. Background Art

[0002] With the development of science and technology, composite insulator detection technology has been widely used in overhead power lines. However, since composite insulators are exposed to the natural environment for a long time, defects are inevitable due to material aging, mechanical damage or environmental factors. Therefore, in order to ensure the safe and reliable operation of the power system, defect detection of composite insulators is essential.

[0003] At present, in the process of defect detection of composite insulators, workers usually use handheld ultrasonic flaw detectors to perform detection, and detect the defect type through the reflected signal. However, since the manual detection process is affected by human subjective consciousness, the final defect identification and judgment of the composite insulator cannot match the actual defect situation of the composite insulator, and manual detection is time-consuming, which makes it easy for the defect detection of composite insulators to make mistakes or have low detection efficiency. Therefore, the current detection effect of composite insulator defect detection is poor. Summary of the invention

[0004] Based on this, it is necessary to provide a composite insulator defect detection method, device, computer equipment, computer readable storage medium and computer program product to improve the composite insulator defect detection effect in response to the above technical problems.

[0005] In a first aspect, the present application provides a composite insulator defect detection method, comprising:

[0006] Obtain defect characteristic information of composite insulators;

[0007] Detecting a first defect probability of a candidate defect occurring in the composite insulator according to the defect characteristic information, wherein the candidate defect is selected from a plurality of expected defects occurring in the composite insulator;

[0008] Defect detection is performed on the composite insulator according to the first defect probability.

[0009] In one embodiment, the obtaining defect characteristic information of the composite insulator includes:

[0010] Acquiring a defect detection signal of the composite insulator;

[0011] Defect feature information of the composite insulator is extracted from the defect detection signal.

[0012] In one embodiment, extracting defect feature information of the composite insulator from the defect detection signal includes:

[0013] Performing time domain feature extraction on the defect detection signal to obtain a defect detection time domain signal, and extracting first defect feature information of the composite insulator from the defect detection time domain signal;

[0014] Performing frequency domain feature extraction on the defect detection signal to obtain a defect detection frequency domain signal, and extracting second defect feature information of the composite insulator from the defect detection frequency domain signal;

[0015] The first defect characteristic information and the second defect characteristic information are collectively used as the defect characteristic information.

[0016] In one embodiment, detecting the first defect probability of the composite insulator generating a candidate defect according to the defect characteristic information includes:

[0017] By inputting the defect feature information into a preset defect recognition model, the second defect probability corresponding to each of the plurality of expected defects of the composite insulator is identified;

[0018] By comparing the sizes of a plurality of second defect probabilities, the first defect probability is selected from the plurality of second defect probabilities.

[0019] In one embodiment, the identifying the second defect probabilities corresponding to each of the plurality of expected defects of the composite insulator includes:

[0020] Determine the probability density corresponding to each of the plurality of expected defects;

[0021] According to the multiple probability densities and the respective corresponding probability density weights, the second defect probabilities corresponding to the multiple expected defects occurring in the composite insulator are identified.

[0022] In one embodiment, the performing defect detection on the composite insulator according to the first defect probability includes:

[0023] If it is detected that the first defect probability is greater than a preset defect probability threshold, determining that the composite insulator has the candidate defect;

[0024] If it is detected that the first defect probability is less than or equal to the preset defect probability threshold, it is determined that the composite insulator does not have the candidate defect.

[0025] In a second aspect, the present application also provides a composite insulator defect detection method and device, comprising:

[0026] An acquisition module, used for acquiring defect characteristic information of the composite insulator;

[0027] A probability detection module, configured to detect a first defect probability of a candidate defect occurring in the composite insulator according to the defect characteristic information, wherein the candidate defect is selected from a plurality of expected defects occurring in the composite insulator;

[0028] A defect detection module is used to perform defect detection on the composite insulator according to the first defect probability.

[0029] In one embodiment, the acquisition module is further used for:

[0030] Acquire a defect detection signal of the composite insulator; and extract defect feature information of the composite insulator from the defect detection signal.

[0031] In one embodiment, the processing module is further configured to:

[0032] Perform time domain feature extraction on the defect detection signal to obtain a defect detection time domain signal, and extract first defect feature information of the composite insulator from the defect detection time domain signal; perform frequency domain feature extraction on the defect detection signal to obtain a defect detection frequency domain signal, and extract second defect feature information of the composite insulator from the defect detection frequency domain signal; and use the first defect feature information and the second defect feature information together as the defect feature information.

[0033] In one embodiment, the probability detection module is further used to:

[0034] By inputting the defect characteristic information into a preset defect recognition model, the second defect probabilities corresponding to each of the multiple expected defects of the composite insulator are identified; by comparing the sizes of the multiple second defect probabilities, the first defect probability is selected from the multiple second defect probabilities.

[0035] In one embodiment, the probability detection module is further used to:

[0036] Determine the probability density corresponding to each of the multiple expected defects; and identify the second defect probability corresponding to each of the multiple expected defects in the composite insulator based on the multiple probability densities and the corresponding probability density weights.

[0037] In one embodiment, the defect detection module is further used to:

[0038] If it is detected that the first defect probability is greater than a preset defect probability threshold, it is determined that the composite insulator has the candidate defect; if it is detected that the first defect probability is less than or equal to the preset defect probability threshold, it is determined that the composite insulator does not have the candidate defect.

[0039] In a third aspect, the present application further provides a computer device, including 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:

[0040] Obtain defect characteristic information of a composite insulator; detect a first defect probability of a candidate defect generated by the composite insulator based on the defect characteristic information, wherein the candidate defect is selected from a plurality of expected defects generated by the composite insulator; and perform defect detection on the composite insulator based on the first defect probability.

[0041] 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:

[0042] Obtain defect characteristic information of a composite insulator; detect a first defect probability of a candidate defect generated by the composite insulator based on the defect characteristic information, wherein the candidate defect is selected from a plurality of expected defects generated by the composite insulator; and perform defect detection on the composite insulator based on the first defect probability.

[0043] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0044] Obtain defect characteristic information of a composite insulator; detect a first defect probability of a candidate defect generated by the composite insulator based on the defect characteristic information, wherein the candidate defect is selected from a plurality of expected defects generated by the composite insulator; and perform defect detection on the composite insulator based on the first defect probability.

[0045] The above-mentioned composite insulator defect detection method, device, computer equipment, computer-readable storage medium and computer program product first extract defect feature information of the composite insulator, and then detect the first defect probability of the composite insulator generating a candidate defect through the defect feature information, wherein the candidate defect is selected from a plurality of expected defects generated by the composite insulator, that is, based on the defect preferential total energy information, the first defect probability of the candidate defect selected from a plurality of expected defects generated by the composite insulator can be detected, and finally the composite insulator is defect-detected through the first defect probability. Since the first defect probability is a quantitative evaluation, the first defect probability is further The defect probability can be used to detect defects of composite insulators from an objective perspective, that is, the purpose of automatically detecting defects of composite insulators is achieved through the quantitative first defect probability, rather than relying on manual experience to detect defects of composite insulators through a combination of man and machine. Therefore, the manual inspection process is affected by human subjective consciousness, resulting in the final defect identification and judgment of the composite insulator being unable to match the actual defect situation of the composite insulator, and manual inspection is time-consuming, which makes it easy for the defect detection of composite insulators to make mistakes or have low detection efficiency. Therefore, the detection effect of composite insulator defect detection is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0047] Figure 1 A schematic diagram of a process of a composite insulator defect detection method according to an embodiment;

[0048] Figure 2 is a schematic flow chart of a defect detection method for a composite insulator in another embodiment;

[0049] Figure 3 It is an overall implementation flow chart of the defect detection probability of a composite insulator of a defect detection method of a composite insulator in one embodiment;

[0050] Figure 4 is a structural block diagram of a defect detection device for a composite insulator in one embodiment;

[0051] Figure 5 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0052] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0053] First of all, it should be understood that composite insulators are key components in overhead power systems. Composite insulators can support high-voltage conductors and provide necessary insulation functions to ensure that the power system can operate safely and reliably. That is, with the development of power systems, the reliability and safety requirements of power equipment are getting higher and higher. Composite insulators are important insulating components in overhead power lines, and their performance is directly related to the stability and safety of the power system. At present, defect detection of composite insulators is usually carried out by staff using handheld ultrasonic flaw detectors. It can be understood that ultrasonic flaw detectors are defect detection achieved through ultrasonic detection technology. As a non-destructive detection method, ultrasonic detection technology has become particularly important because it can detect defects inside the material. Ultrasonic detection technology can Effectively identifying defects such as cracks, bubbles and inclusions inside composite insulators is of great significance for preventing power system failures and extending equipment life. Among them, defect detection of composite insulators is performed by an ultrasonic flaw detector, specifically by emitting ultrasonic waves and receiving their reflected signals to detect defects inside the composite insulator material. However, the above method mainly relies on the experience and skills of the operator to identify and judge the defects. Since the manual inspection process is affected by human subjective consciousness, the final defect identification and judgment of the composite insulator cannot match the actual defect situation of the composite insulator, and manual inspection is time-consuming, which makes it easy for the defect detection of the composite insulator to make mistakes or have low detection efficiency. Therefore, there is an urgent need for a defect detection method for composite insulators that improves the detection effect of composite insulator defect detection.

[0054] In one embodiment, Figure 1As shown, a defect detection method for a composite insulator is provided. This embodiment takes the method applied to a terminal as an example. The terminal includes but is not limited to a personal computer, a laptop computer, a smart phone, and a tablet computer. The terminal includes an acquisition module, a probability detection module, and a defect detection module. The acquisition module is used to acquire defect feature information of the composite insulator. The probability detection module is used to detect a first defect probability of a candidate defect generated by the composite insulator according to the defect feature information, wherein the candidate defect is selected from multiple expected defects generated by the composite insulator. The defect detection module is used to perform defect detection on the composite insulator according to the first defect probability. This embodiment performs information exchange among the acquisition module, the probability detection module, and the defect detection module to detect defects in the composite insulator. In the process of defect detection, the defect characteristic information of the composite insulator is first obtained, and then the first defect probability of the composite insulator generating a candidate defect is detected through the defect characteristic information, wherein the candidate defect is selected from multiple expected defects generated by the composite insulator, and finally the composite insulator is subjected to defect detection through the first defect probability, thereby achieving the purpose of automatically performing defect detection on the composite insulator through the quantitative first defect probability, rather than relying on manual experience to perform defect detection on the composite insulator through a human-machine combination. Therefore, the detection effect of composite insulator defect detection is improved. It can be understood that the method can also be applied to a server, and can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. In this embodiment, the method includes the following steps 202 to 206. Among them:

[0055] Step 202: Obtain defect characteristic information of the composite insulator.

[0056] It should be noted that the composite insulator is a special insulating control component, which is mainly a multiple insulation structure composed of continuous layers of different insulating materials, usually including a structural layer, an intermediate insulating layer and a surface insulating layer. Specifically, it can be used as an insulating component in an overhead power line. The defect characteristic information is used to reflect the defect characteristics of the composite insulator. The method for obtaining the defect characteristic information of the composite insulator may specifically be infrared imaging, hydrophobicity detection, ultrasonic detector detection or leakage current detection, etc. It can be understood that the defect characteristic information obtained by the above-mentioned acquisition method may be indicators or information at different angles, which are feedback on the defect characteristics of the composite insulator.

[0057] As an example, step 202 includes: obtaining defect characteristic information of the composite insulator.

[0058] Step 204: Detect a first defect probability of a candidate defect occurring in the composite insulator based on the defect characteristic information, wherein the candidate defect is selected from a plurality of expected defects occurring in the composite insulator.

[0059] It should be noted that composite insulators may produce different types of defects during operation, wherein expected defects refer to defects that may occur in composite insulators. It can be understood that there may be multiple expected defects in composite insulators, specifically cracks, bubbles, inclusions, etc. Candidate defects are selected from multiple expected defects in composite insulators. For example, in one feasible method, candidate defects refer to defects that are most likely to occur in composite insulators. Assume that multiple expected defects are A1, A2, A3 and A4, wherein the defect probabilities of the multiple expected defects are a1, a2, a3 and a4, and a1>a2>a3>a4, then A1 is selected as the candidate defect among the multiple expected defects, and a1 is taken as the first defect probability.

[0060] It should be noted that after obtaining the defect characteristic information, the first defect probability of each expected defect can be predicted based on the defect characteristic information. For example, in one feasible method, the first defect probability b1 of the composite insulator producing expected defect 1 is predicted by the first model, the expected defect probability b2 of the composite insulator producing expected defect 2 is predicted by the second model, the expected defect probability b3 of the composite insulator producing expected defect 3 is predicted by the third model, and the expected defect probability b4 of the composite insulator producing expected defect 4 is predicted by the fourth model. Then, the first defect probabilities b1, b2, b3 and b4 are compared to obtain the expected defect with the largest expected defect probability as the candidate defect.

[0061] As an example, step 204 includes: inputting the defect feature information into multiple preset recognition models respectively, obtaining the expected defect probabilities corresponding to multiple expected defects through the multiple preset recognition models, and by comparing the probability sizes between the multiple expected defect probabilities, taking the expected defect corresponding to the expected defect probability with the largest probability value as a candidate defect, and taking the expected defect probability with the largest probability value as the first defect probability.

[0062] Step 206: Perform defect detection on the composite insulator according to the first defect probability.

[0063] It should be noted that after the first defect probability is obtained, that is, an index for quantifying the defect situation of the composite insulation is obtained, the first defect probability can be directly used as the detection result of defect detection on the composite insulator.

[0064] As an example, step 206 includes: using the first defect probability as a detection result of defect detection on the composite insulator.

[0065] The defect detection method of the composite insulator first extracts the defect feature information of the composite insulator, and then detects the first defect probability of the composite insulator generating a candidate defect through the defect feature information, wherein the candidate defect is selected from a plurality of expected defects generated by the composite insulator, that is, based on the defect preferential total energy information, the first defect probability of the candidate defect selected from a plurality of expected defects generated by the composite insulator can be detected, and finally the composite insulator is defect-detected through the first defect probability. Since the first defect probability is a quantitative evaluation, the defect detection of the composite insulator can be performed from an objective perspective through the first defect probability, that is, the purpose of automatically performing defect detection on the composite insulator through the quantitative first defect probability is achieved, rather than relying on manual experience to perform defect detection on the composite insulator through a human-machine combination method. Therefore, the technical defects that the manual detection process is affected by human subjective consciousness, resulting in the final defect identification and judgment of the composite insulator cannot match the actual defect situation of the composite insulator, and the manual detection is time-consuming, which makes it easy to make errors in the defect detection of the composite insulator or low detection efficiency, are overcome, so the detection effect of the composite insulator defect detection is improved.

[0066] In one embodiment, Figure 2 As shown, defect characteristic information of composite insulators is obtained, including:

[0067] Step 302: Acquire a defect detection signal of a composite insulator.

[0068] It should be noted that the extraction of defect characteristics of composite insulators can be obtained based on the defect detection signal obtained by measurement, and specifically, the defect detection signal can be obtained by an ultrasonic flaw detector. For example, in an implementable manner, the system for executing the detection method of composite insulators can specifically deploy an ultrasonic signal transmitting module and a receiving module, a receiving signal and a signal processing module, wherein the ultrasonic signal transmitting module is used to transmit an ultrasonic signal, the ultrasonic signal receiving module is used to receive the reflected ultrasonic signal, and the signal processing module is used to perform signal processing on the reflected ultrasonic signal to obtain the defect characteristic information of the composite insulator. In the process of using an ultrasonic flaw detector to detect composite insulators, it is usually necessary to select a suitable ultrasonic frequency and transmission power to ensure that the defects inside the composite insulator can be detected. For example, the frequency is usually selected between 0.5MHz and 5MHz, and the transmission power is adjusted according to the material properties and thickness of the insulator, generally between 5W and 20W. The ultrasonic flaw detector forms a signal sample of the defect detection signal by transmitting ultrasonic waves and receiving the reflected signals.

[0069] As an example, step 302 includes: sending an ultrasonic signal to the composite insulator, and receiving a defect detection signal fed back by the composite insulator based on the ultrasonic detection signal.

[0070] Step 304, extracting defect feature information of the composite insulator from the defect detection signal;

[0071] It should be noted that by preprocessing and extracting features from the defect detection signal of the composite insulator through the signal processing module, the defect feature information of the composite insulator can be extracted from the defect detection signal. For example, in one feasible method, after obtaining the defect detection signal, the received defect detection signal needs to be filtered and denoised to extract information that can reflect the defect characteristics of the composite insulator. The preprocessing process may specifically include using a low-pass filter to remove high-frequency noise.

[0072] As an example, step 304 includes: filtering the defect detection signal with a low-pass filter to obtain a defect detection filter signal, and extracting features from the defect detection filter signal to obtain defect feature information of the composite insulator.

[0073] In this embodiment, in the process of obtaining the defect characteristic information of the composite insulator, the defect detection signal of the composite insulator can be first collected by reflecting and receiving the ultrasonic signal, and then the defect characteristic information reflecting the defect characteristics of the composite insulator can be obtained by preprocessing and extracting the features of the defect detection signal. Thus, the purpose of accurately capturing the defect characteristic information of the composite insulator can be achieved through the above method, thus laying a foundation for improving the detection effect of composite insulator defect detection.

[0074] In one embodiment, extracting defect feature information of a composite insulator from a defect detection signal includes:

[0075] Perform time domain feature extraction on the defect detection signal to obtain a defect detection time domain signal, and extract first defect feature information of the composite insulator from the defect detection time domain signal; perform frequency domain feature extraction on the defect detection signal to obtain a defect detection frequency domain signal, and extract second defect feature information of the composite insulator from the defect detection frequency domain signal; and use the first defect feature information and the second defect feature information together as the defect feature information.

[0076] It should be noted that in order to improve the accurate feedback of defect characteristics of composite insulators, after filtering the defect detection signal with a low-pass filter to obtain a defect detection filter signal, useful information can be extracted by calculating the time domain and frequency characteristics of the signal, where the time domain characteristics include peak value, mean value, and standard deviation, and the frequency characteristics can be the spectrum distribution calculated by algorithms such as Fourier transform.

[0077] As an example, the defect detection signal is filtered to obtain a defect detection filter signal, time domain feature extraction is performed on the defect detection filter signal to obtain a defect detection time domain signal, and first defect feature information of the composite insulator is extracted from the defect detection time domain signal; the defect detection signal is filtered to obtain a defect detection filter signal, frequency domain feature extraction is performed on the defect detection filter signal to obtain a defect detection frequency domain signal, and second defect feature information of the composite insulator is extracted from the defect detection frequency domain signal; the first defect feature information and the second defect feature information are used together as the defect feature information.

[0078] In this embodiment, by extracting the time domain and frequency domain features of the defect detection signal respectively, the defect characteristics of the composite insulator are fed back from two different aspects, so that the defect characteristic information can more accurately reflect the defect characteristics of the composite insulator. Therefore, while improving the detection effect of composite insulator defect detection, the detection accuracy of composite insulator defect detection is also improved.

[0079] In one embodiment, detecting a first defect probability of a composite insulator generating a candidate defect according to defect characteristic information includes:

[0080] By inputting defect feature information into a preset defect recognition model, the second defect probabilities corresponding to each of the multiple expected defects of the composite insulator are identified; by comparing the sizes of the multiple second defect probabilities, the first defect probability is selected from the multiple second defect probabilities.

[0081] It should be noted that after obtaining the defect feature information, the defect feature information can also be input into a specified preset defect recognition model, so as to be classified and identified by the preset defect recognition model. For example, in an implementable manner, the preset defect recognition model can be specifically a Gaussian mixture model, and the step of "detecting the first defect probability of the composite insulator generating a candidate defect according to the defect feature information" can be specifically performed by the Gaussian mixture model to classify and identify the defect feature information to distinguish different types of defects, wherein the formula of the Gaussian mixture model can be specifically:

[0082]

[0083] in, represents the feature vector, represents the parameters of the model, K represents the number of Gaussian distributions, is the weight of the i-th Gaussian distribution, It means the mean , the variance is It can be understood that the Gaussian mixture model is a trained model. During the training phase of the Gaussian mixture model, it is necessary to use sample data optimization methods of known defect types to estimate model parameters. The trained Gaussian mixture model can classify and identify feature information to distinguish different types of defects.

[0084] As an example, by inputting defect feature information into a preset defect recognition model, the second defect probability corresponding to each of a plurality of expected defects of the composite insulator is identified; and the maximum second defect probability is used as the first defect probability.

[0085] In this embodiment, the second defect probabilities corresponding to multiple expected defects of the composite insulator are uniformly identified through the trained preset recognition model, so as to uniformly predict the second defect probabilities of different expected defects of the composite insulator. Therefore, while improving the detection effect of defect detection on the composite insulator, the detection efficiency of defect detection on the composite insulator is also improved.

[0086] In one embodiment, identifying second defect probabilities corresponding to a plurality of expected defects of the composite insulator, respectively, includes:

[0087] Determine the probability density corresponding to each of the multiple expected defects; and identify the second defect probability corresponding to each of the multiple expected defects of the composite insulator based on the multiple probability densities and the corresponding probability density weights.

[0088] It should be noted that in the process of identifying the probability of different expected defects in composite insulators through a preset defect recognition model, it can be identified based on probability density and probability density weight. For example, in one feasible method, the probability that a given defect detection signal belongs to a certain type of defect can be calculated based on the output of a Gaussian mixture model. Specifically, the extracted defect feature information is input into the trained Gaussian mixture model, the probability density of each Gaussian distribution is calculated, and the weighted average is performed according to the weight to obtain the second defect probability of composite insulators producing different categories of expected defects. Then, by comparing the probabilities of different categories, it is possible to determine the expected defect to which the sample is most likely to belong, thereby finally obtaining the first defect probability of the candidate defect.

[0089] As an example, the defect feature information is input into a preset defect recognition model, and the probability density of each Gaussian distribution is obtained through the preset defect recognition model; multiple probability densities and their corresponding probability density weights are weighted averaged to obtain the second defect probability corresponding to each of the multiple expected defects of the composite insulator.

[0090] For example, in one practicable manner, it is assumed that a trained Gaussian mixture model has been obtained, and the model is used to identify two types of defects: Class A and Class B. The model parameters are as follows:

[0091] For the Gaussian distribution model of type A defects: K=3 (using 3 Gaussian distributions), =[0.2,0.5,0.3] (weights of each Gaussian distribution), =[[1.2,2.5],[3.1,4.6],[5.3,6.7]] (mean vector of each Gaussian distribution), =[[0.1,0.1],[0.2,0.2],[0.3,0.3]] (variance matrix of each Gaussian distribution); for GMM of Class B defects: K=2 (using 2 Gaussian distributions), =[0.6,0.4] (weights of each Gaussian distribution, =[[2.3,3.4],[4.5,5.6]]] (mean vector of each Gaussian distribution), =[[0.15,0.15],[0.25,0.25]] (variance matrix of each Gaussian distribution) If the feature vector x=[2.4,3.5] (defect feature information) of the defect detection signal is extracted and input into the above-trained Gaussian mixture model for classification and recognition; then for Class A defects, the calculated probability density is:

[0092] P 1 = 0 . 2 ⋅ N ( [ 2 . 4 , 3 . 5 ] | [ 1 . 2 , 2 . 5 ] ， [ 0 . 1 , 0 . 1 ] ) P 2 = 0 . 5 ⋅ N ( [ 2 . 4 , 3 . 5 ] | [ 3 . 1 , 4 . 6 ] ， [ 0 . 2 , 0 . 2 ] ) P 3 = 0 . 3 ⋅ N ( [ 2 . 4 , 3 . 5 ] | [ 5 . 3 , 6 . 7 ] ， [ 0 . 3 , 0 . 3 ] )

[0093] For Class B defects, the calculated probability density is:

[0094] P 1 = 0 . 6 ⋅ N ( [ 2 . 4 , 3 . 5 ] | [ 2 . 3 , 3 . 4 ] ， [ 0 . 15 , 0 . 15 ] ) P 2 = 0 . 4 ⋅ N ( [ 2 . 4 , 3 . 5 ] | [ 4 . 5 , 5 . 6 ] ， [ 0 . 25 , 0 . 25 ] )

[0095] ; Set the threshold value to T=0.05. Calculate the probability that the sample belongs to class A and class B defects respectively and ,in,

[0096]

[0097] ; Assume that the calculation result is and ,because and , it is determined that there are candidate defects in the composite insulator.

[0098] In this embodiment, the second defect probabilities corresponding to the multiple expected defects can be identified through the probability densities corresponding to the multiple expected defects and the probability density weights corresponding to the multiple expected defects, thereby achieving the purpose of accurately identifying the second defect probabilities of different expected defects. Therefore, it lays a foundation for improving the detection effect of composite insulators.

[0099] In one embodiment, defect detection is performed on a composite insulator according to a first defect probability, including:

[0100] If the detected first defect probability is greater than the preset defect probability threshold, it is determined that there is a candidate defect in the composite insulator; if the detected first defect probability is less than or equal to the preset defect probability threshold, it is determined that there is no candidate defect in the composite insulator.

[0101] It should be noted that after obtaining the first defect probability, a preset defect probability threshold can be set to determine whether the composite insulator has a candidate defect, wherein the preset defect probability threshold can specifically be 0.04, 0.05 or 0.06, etc.

[0102] As an example, if the detected first defect probability is greater than a preset defect probability threshold, it is determined that a candidate defect exists in the composite insulator; if the detected first defect probability is less than or equal to the preset defect probability threshold, it is determined that no candidate defect exists in the composite insulator.

[0103] In this embodiment, by comparing the first defect probability with the preset defect probability threshold, it is possible to accurately distinguish and predict whether the composite insulator has a candidate defect, thereby achieving the purpose of converting a quantitative indicator into a qualitative assessment of whether the composite insulator has a defect. Therefore, the detection effect of defect detection on the composite insulator is further improved.

[0104] After the defect detection of the composite insulator, the corresponding treatment suggestions are given according to the test results; according to the type and severity of the test results, the corresponding treatment suggestions are given; if serious defects such as cracks or fractures are detected, it is recommended to replace the composite insulator; if the defects are minor, repair or enhanced monitoring measures can be considered; it can be understood that according to the output of the Gaussian mixture model, the defect type (such as Class A or Class B) is determined, and then the severity of the defect is evaluated, which requires the combination of characteristic information such as the size, location, and shape of the defect, which can be obtained through the characteristic vector of the signal sample. If a Class A defect is detected, for example, Class A defects represent serious defects such as cracks or fractures. In this case, it is recommended to replace the composite insulator immediately to avoid potential power system failures; if a Class B defect is detected, for example, Class B defects represent lighter defects such as small bubbles or slight inclusions; according to the specific characteristics and location of the defect, repair or enhanced monitoring can be considered.

[0105] Reference Figure 3 , Figure 3 The present invention is an overall implementation flow chart of the defect detection probability of composite insulators. Since the first defect probability is a quantitative evaluation, the defect detection of composite insulators can be performed from an objective perspective through the first defect probability, that is, the purpose of automatically performing defect detection on composite insulators through the quantitative first defect probability is achieved, rather than relying on manual experience to perform defect detection on composite insulators through a human-machine combination. Therefore, the technical defects that the manual detection process is affected by human subjective consciousness, resulting in the final defect identification and judgment of the composite insulator being unable to match the actual defect situation of the composite insulator, and the manual detection is time-consuming, which makes it easy for the defect detection of composite insulators to make mistakes or have low detection efficiency are overcome. Therefore, the detection effect of composite insulator defect detection is improved.

[0106] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0107] Based on the same inventive concept, the embodiment of the present application also provides a composite insulator defect detection device for implementing the composite insulator defect detection method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in the embodiments of one or more composite insulator defect detection devices provided below can refer to the limitations of the composite insulator defect detection method above, and will not be repeated here.

[0108] In an exemplary embodiment, Figure 4 As shown, a defect detection device for a composite insulator is provided, comprising: an acquisition module 401, a probability detection module 402 and a defect detection module 403, wherein:

[0109] An acquisition module 401 is used to acquire defect characteristic information of a composite insulator;

[0110] A probability detection module 402 is used to detect a first defect probability of a candidate defect occurring in the composite insulator according to the defect characteristic information, wherein the candidate defect is selected from a plurality of expected defects occurring in the composite insulator;

[0111] The defect detection module 403 is used to perform defect detection on the composite insulator according to the first defect probability.

[0112] In one embodiment, the acquisition module 401 is further used for:

[0113] Acquire a defect detection signal of the composite insulator; and extract defect feature information of the composite insulator from the defect detection signal.

[0114] In one embodiment, the processing module 402 is further configured to:

[0115] Perform time domain feature extraction on the defect detection signal to obtain a defect detection time domain signal, and extract first defect feature information of the composite insulator from the defect detection time domain signal; perform frequency domain feature extraction on the defect detection signal to obtain a defect detection frequency domain signal, and extract second defect feature information of the composite insulator from the defect detection frequency domain signal; and use the first defect feature information and the second defect feature information together as the defect feature information.

[0116] In one embodiment, the probability detection module 402 is further configured to:

[0117] By inputting the defect characteristic information into a preset defect recognition model, the second defect probabilities corresponding to each of the multiple expected defects of the composite insulator are identified; by comparing the sizes of the multiple second defect probabilities, the first defect probability is selected from the multiple second defect probabilities.

[0118] In one embodiment, the probability detection module 402 is further configured to:

[0119] Determine the probability density corresponding to each of the multiple expected defects; and identify the second defect probability corresponding to each of the multiple expected defects in the composite insulator based on the multiple probability densities and the corresponding probability density weights.

[0120] In one embodiment, the defect detection module 403 is further used to:

[0121] If it is detected that the first defect probability is greater than a preset defect probability threshold, it is determined that the composite insulator has the candidate defect; if it is detected that the first defect probability is less than or equal to the preset defect probability threshold, it is determined that the composite insulator does not have the candidate defect.

[0122] Each module in the defect detection device for composite insulators can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0123] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 5 As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected via a system bus, and the communication interface, the display unit and the input device are 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 and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a defect detection method for a composite insulator is implemented. Those skilled in the art can understand that Figure 5 The 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 those shown in the figure, or combine certain components, or have a different arrangement of components.

[0124] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0125] 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.

[0126] 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.

[0127] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and 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 the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile 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), magnetoresistive 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. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0128] The technical features of the above embodiments may be combined arbitrarily. 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 specification.

[0129] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A defect detection method for a composite insulator, characterized in that: The method comprises: Obtain defect characteristic information of composite insulators; Detecting a first defect probability of a candidate defect occurring in the composite insulator according to the defect characteristic information, wherein the candidate defect is selected from a plurality of expected defects occurring in the composite insulator; Defect detection is performed on the composite insulator according to the first defect probability.

2. The method according to claim 1, characterized in that The obtaining of defect characteristic information of the composite insulator includes: Acquiring a defect detection signal of the composite insulator; Defect feature information of the composite insulator is extracted from the defect detection signal.

3. The method according to claim 2, characterized in that Extracting defect feature information of the composite insulator from the defect detection signal includes: Performing time domain feature extraction on the defect detection signal to obtain a defect detection time domain signal, and extracting first defect feature information of the composite insulator from the defect detection time domain signal; Performing frequency domain feature extraction on the defect detection signal to obtain a defect detection frequency domain signal, and extracting second defect feature information of the composite insulator from the defect detection frequency domain signal; The first defect characteristic information and the second defect characteristic information are collectively used as the defect characteristic information.

4. The method according to claim 1, characterized in that: The step of detecting the first defect probability of the composite insulator generating a candidate defect according to the defect characteristic information includes: By inputting the defect feature information into a preset defect recognition model, the second defect probability corresponding to each of the plurality of expected defects of the composite insulator is identified; By comparing the sizes of a plurality of second defect probabilities, the first defect probability is selected from the plurality of second defect probabilities.

5. The method according to claim 4, characterized in that The identifying of the second defect probabilities corresponding to the plurality of expected defects of the composite insulator respectively comprises: Determine the probability density corresponding to each of the plurality of expected defects; According to the multiple probability densities and the respective corresponding probability density weights, the second defect probabilities corresponding to the multiple expected defects occurring in the composite insulator are identified.

6. The method according to claim 1, characterized in that The performing defect detection on the composite insulator according to the first defect probability includes: If it is detected that the first defect probability is greater than a preset defect probability threshold, determining that the composite insulator has the candidate defect; If it is detected that the first defect probability is less than or equal to the preset defect probability threshold, it is determined that the composite insulator does not have the candidate defect.

7. A defect detection device for a composite insulator, characterized in that: The device comprises: An acquisition module, used for acquiring defect characteristic information of the composite insulator; A probability detection module, configured to detect a first defect probability of a candidate defect occurring in the composite insulator according to the defect characteristic information, wherein the candidate defect is selected from a plurality of expected defects occurring in the composite insulator; A defect detection module is used to perform defect detection on the composite insulator according to the first defect probability.

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