Insulator maintenance device control method and device, electronic device and medium

Abstract

Embodiments of the present disclosure disclose insulator maintenance device control methods, devices, electronic devices, and media. A specific embodiment of the method includes: obtaining an image of a target insulator as an insulator image; generating a blur angle according to the insulator image; generating a blur length according to the insulator image and the blur angle; determining a degradation function matrix according to the blur length and the blur angle; generating a restored image according to the insulator image, the degradation function matrix, and a preset matrix; generating fault identification result information according to the restored image and a pre-trained image fault identification model; and controlling an associated insulator maintenance device to perform a fault maintenance operation according to the fault identification result information. This embodiment improves the accuracy of insulator fault identification and the correctness of fault maintenance, thereby prolonging the service life of the power line and reducing the frequency of power accidents.

Description

TECHNICAL FIELD

[0001] Embodiments of the present disclosure relate to the technical field of computer technology, and specifically to an insulator maintenance device control method and apparatus, electronic device, and medium. BACKGROUND

[0002] With the development of computer technology and the improvement of automation level, an unmanned aerial vehicle can be used to take aerial photos of insulators in a power line for fault detection. Currently, when performing maintenance operations on insulator faults, the commonly used method is to obtain a motion blurred image through aerial photography, perform insulator fault identification on the aerial motion blurred image based on a general recognition model, and perform maintenance operations on the fault according to the fault identification result.

[0003] However, the inventors have found that when the above method is used to perform maintenance operations on insulator faults, the following technical problems often occur:

[0004] First, the image is not restored before the target image is identified, resulting in low accuracy of insulator fault identification, which in turn leads to low accuracy of fault maintenance, shortens the service life of the power line, and causes frequent power accidents.

[0005] Second, the general recognition model does not use jump layer connection technology, and the model degradation problem is prominent. The classified data is not processed by the last global average pooling, and the model is prone to overfitting, resulting in low accuracy of insulator fault identification, which in turn leads to low accuracy of fault maintenance, shortens the service life of the power line, and causes frequent power accidents.

[0006] The above information disclosed in this BACKGROUND section is only for the purpose of enhancing the understanding of the background of the present inventive concepts, and therefore, it can contain information that does not form the prior art that is already known in this country to those ordinary skilled in the art. SUMMARY

[0007] The summary section of the present disclosure is used to introduce the concepts in a brief manner, which will be described in detail in the following detailed description section. The summary section of the present disclosure is not intended to identify key or essential features of the claimed technical solutions, nor is it intended to limit the scope of the claimed technical solutions.

[0008] Some embodiments of the present disclosure propose an insulator maintenance device control method and apparatus, electronic device, and computer readable medium to solve one or more of the technical problems mentioned in the BACKGROUND section.

[0009] In a first aspect, some embodiments of the present disclosure provide a method for controlling an insulator maintenance device, the method comprising: obtaining an image of a target insulator as an insulator image; generating a blur angle according to the insulator image; generating a blur length according to the insulator image and the blur angle; determining a degradation function matrix according to the blur length and the blur angle; generating a restored image according to the insulator image, the degradation function matrix, and a preset matrix; generating fault identification result information according to the restored image and a pre-trained image fault identification model; and controlling an associated insulator maintenance device to perform a fault maintenance operation according to the fault identification result information.

[0010] In a second aspect, some embodiments of the present disclosure provide a device for controlling an insulator maintenance device, the device comprising: an obtaining unit configured to obtain an image of a target insulator as an insulator image; a first generating unit configured to generate a blur angle according to the insulator image; a second generating unit configured to generate a blur length according to the insulator image and the blur angle; a determining unit configured to determine a degradation function matrix according to the blur length and the blur angle; a third generating unit configured to generate a restored image according to the insulator image, the degradation function matrix, and a preset matrix; a fourth generating unit configured to generate fault identification result information according to the restored image and a pre-trained image fault identification model; and a control unit configured to control an associated insulator maintenance device to perform a fault maintenance operation according to the fault identification result information.

[0011] In a third aspect, some embodiments of the present disclosure provide an electronic device, comprising: one or more processors; and a storage storing one or more programs, wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method described in any implementation manner of the first aspect.

[0012] In a fourth aspect, some embodiments of the present disclosure provide a computer-readable medium having stored thereon a computer program, wherein the computer program, when executed by a processor, implements the method described in any implementation manner of the first aspect.

[0013] The above various embodiments of the present disclosure have the following beneficial effects: through the insulator maintenance device control method of some embodiments of the present disclosure, the accuracy of insulator fault identification is improved, thereby improving the correctness of fault maintenance, and further prolonging the service life of the power line and reducing the frequency of power accidents. Specifically, the reasons for the low accuracy of insulator fault identification, the low correctness of fault maintenance, the short service life of the power line, and the frequent occurrence of power accidents are that the image is not restored before the target image is identified, which leads to low accuracy of insulator fault identification, thereby leading to low correctness of fault maintenance, shortening the service life of the power line, and causing frequent power accidents. Based on this, the insulator maintenance device control method of some embodiments of the present disclosure first acquires an image of a target insulator as an insulator image. In this way, the insulator image can be obtained, so that the insulator image can be used for image restoration to improve the clarity of the insulator image. Then, according to the above insulator image, a blur angle is generated. In this way, the blur angle parameter affecting image restoration can be obtained, so that the clarity of the insulator image can be improved. Subsequently, according to the above insulator image and the above blur angle, a blur length is generated. In this way, the blur length parameter affecting image restoration can be obtained, so that the clarity of the insulator image can be improved. Secondly, according to the above blur length and the above blur angle, a degradation function matrix is determined. In this way, the degradation function matrix capable of improving the clarity of the restored image under different blur conditions can be determined. Then, according to the above insulator image, the above degradation function matrix, and a preset matrix, a restored image is generated. In this way, the restored image with high clarity can be obtained, so that the accuracy of insulator fault identification can be improved. Subsequently, according to the above restored image and a pre-trained image fault identification model, fault identification result information is generated. In this way, the fault identification result information with high recognition accuracy can be obtained. Thus, the correctness of fault maintenance can be improved. Finally, according to the above fault identification result information, the associated insulator maintenance device is controlled to perform fault maintenance operation. In this way, the insulator fault can be repaired. Because the insulator image is restored, the clarity of the insulator image can be improved. Because the image fault identification model with high recognition accuracy is used to identify the restored image with high clarity, the accuracy of insulator fault identification can be improved. Thus, the correctness of fault maintenance is improved. Further, the service life of the power line is prolonged, and the frequency of power accidents is reduced. BRIEF DESCRIPTION OF DRAWINGS

[0014] The above and other features, advantages, and aspects of the embodiments of the present disclosure will become more apparent upon consideration of the following detailed description, taken in conjunction with the accompanying drawings. In the drawings, like reference numerals refer to like elements throughout. It should be understood that the drawings are schematic and elements and features are not necessarily to scale.

[0015] Figure 1 is a flowchart of some embodiments of the insulator maintenance equipment control method according to the present disclosure;

[0016] Figure 2 is a structural schematic diagram of some embodiments of the insulator maintenance equipment control apparatus according to the present disclosure;

[0017] Figure 3 is a structural schematic diagram of an electronic device suitable for use to implement some embodiments of the present disclosure. DETAILED DESCRIPTION

[0018] Embodiments of the present disclosure will be described below in greater detail with reference to the accompanying drawings. While certain embodiments of the present disclosure are shown in the drawings, it is understood that the present disclosure can be embodied in various forms and should not be interpreted as being limited to the embodiments set forth herein. Rather, these embodiments are provided so that the present disclosure will be more thoroughly and completely understood. It should be understood that the drawings of the present disclosure are only for illustrative purposes and should not be used to limit the scope of protection of the present disclosure.

[0019] It should also be noted that, for the sake of brevity, only the portions of the drawings that are relevant to the present disclosure are shown. The embodiments in the present disclosure and the features in the embodiments can be combined with each other in the case of no conflict.

[0020] It should be noted that the terms “first”, “second”, and the like in the present disclosure are only used to distinguish different devices, modules, or units, and are not intended to limit the order or interdependence of the functions performed by these devices, modules, or units.

[0021] It should be noted that the terms “one”, “multiple” in the present disclosure are illustrative and not limiting, and those skilled in the art should understand that, unless otherwise explicitly stated in the context, it should be understood as “one or more”.

[0022] The names of the messages or information exchanged between the devices in the embodiments of the present disclosure are only for illustrative purposes, and are not intended to limit the scope of the messages or information.

[0023] The present disclosure will be described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.

[0024] Figure 1 A flowchart 100 of some embodiments of the insulator maintenance equipment control method according to the present disclosure is shown. The insulator maintenance equipment control method comprises the following steps:

[0025] In step 101, an image of a target insulator is acquired as an insulator image.

[0026] In some embodiments, the execution subject (e.g., a computing device) of the insulator maintenance device control method can obtain the image of the target insulator from the image acquisition device as the insulator image through wired connection or wireless connection. The image acquisition device can be a device with a shooting function. For example, the image acquisition device can be a UAV. The image can be the image of the target insulator. The target insulator can be the insulator mounted on either end of a high-voltage tower. The high-voltage tower is not limited herein. It should be noted that the wireless connection can include, but is not limited to, 3G / 4G connection, WiFi connection, Bluetooth connection, WiMAX connection, Zigbee connection, UWB (ultra wideband) connection, and other now known or future developed wireless connection methods.

[0027] In step 102, the blur angle is generated according to the insulator image.

[0028] In some embodiments, the execution subject can generate the blur angle according to the insulator image. The blur angle can be the angle between the motion direction of the insulator image and the horizontal direction.

[0029] In some optional implementations of some embodiments, the execution subject can generate the blur angle according to the insulator image by the following steps:

[0030] Firstly, the insulator image is transformed to obtain a frequency spectrum image. In practice, the execution subject can perform Fourier transform on the insulator image to obtain a frequency spectrum image. The frequency spectrum image can be an image showing the frequency spectrum fringe characteristics of the insulator image in a wave pattern of the horizontal axis and the vertical axis.

[0031] Secondly, the frequency spectrum image is enhanced to obtain an enhanced image. In practice, firstly, the execution subject can perform histogram equalization on the frequency spectrum image to obtain a histogram equalization image. Then, the histogram equalization image can be binarized to obtain an enhanced image.

[0032] Thirdly, the enhanced image is morphologically transformed to obtain a morphologically transformed image. In practice, the execution subject can perform morphological opening operation on the enhanced image to obtain a morphologically transformed image.

[0033] Fourthly, the morphologically transformed image is edge detected to obtain an edge-detected image as a fringe edge image. In practice, the execution subject can perform edge detection on the morphologically transformed image by the following steps to obtain an edge-detected image as a fringe edge image:

[0034] In a first step, the morphological transformation image is dilated to obtain a dilated image as a dilated image.

[0035] In a second step, the morphological transformation image is eroded to obtain an eroded image as an eroded image.

[0036] In a third step, the dilated image and the eroded image are subtracted to obtain a fringe edge image.

[0037] In a fifth step, a blur angle is generated according to the fringe edge image. In practice, first, the execution body can perform Radon transformation on the fringe edge image to obtain a fringe inclination angle. Then, the blur angle can be obtained by the following formula:

[0038]

[0039] wherein, The fringe inclination angle can be represented by θ. The blur angle can be represented by θ. M can represent the image width. N can represent the image length. The tangent of the blur angle can be represented by tan θ. The tangent of the fringe inclination angle can be represented by tan θ.

[0040] In step 103, a blur length is generated according to the insulator image and the blur angle.

[0041] In some embodiments, the execution body can generate a blur length according to the insulator image and the blur angle. The blur length can be the number of interval pixels of movement.

[0042] In some optional implementations of some embodiments, the execution body can generate a blur length according to the insulator image and the blur angle by the following steps:

[0043] In a first step, a spectrum image vertical projection image is determined according to the spectrum image and the blur angle. In practice, first, the execution body can rotate the spectrum image in the clockwise direction of the blur angle to obtain a rotated spectrum image as a rotated image. Then, the rotated image can be vertically projected to obtain a vertically projected rotated image as a spectrum image vertical projection image.

[0044] In a second step, a fringe spacing is determined according to the spectrum image vertical projection image. In practice, the execution body can determine the pixel distance between adjacent negative peak points in the spectrum image vertical projection image as the fringe spacing. The negative peak point can be the difference between the minimum value and the average value in a period. The average value can be the average value corresponding to each signal value in the period.

[0045] In the third step, an image length and an image width of the insulator image are determined. The image length can be a number of vertical pixels of the insulator image. The image width can be a number of horizontal pixels of the insulator image. In practice, the execution subject can first determine the number of vertical pixels of the insulator image as the image length. Then, the number of horizontal pixels of the insulator image can be determined as the image width.

[0046] In the fourth step, a blur length is generated according to the stripe interval, the blur angle, the image length, and the image width. In practice, the execution subject can generate the blur length according to the stripe interval, the blur angle, the image length, and the image width by the following steps:

[0047] In the first sub-step, a square of a cosine value corresponding to the blur angle is determined as a first value.

[0048] In the second sub-step, a square of a ratio of the image width to the image length is determined as a second value.

[0049] In the third sub-step, a square of a sine value corresponding to the blur angle is determined as a third value.

[0050] In the fourth sub-step, a product of the second value and the third value is determined as a fourth value.

[0051] In the fifth sub-step, a sum of the first value and the fourth value is determined as a fifth value.

[0052] In the sixth sub-step, a product of one-half of the fifth value and the stripe interval is determined as a sixth value.

[0053] In the seventh sub-step, a ratio of the image width to the sixth value is determined as the blur length.

[0054] In step 104, a degradation function matrix is determined according to the blur length and the blur angle.

[0055] In some embodiments, the execution subject can determine the degradation function matrix according to the blur length and the blur angle. The degradation function matrix can be a function matrix for blurring weighting of an original image. The original image can be a clear image corresponding to the insulator image.

[0056] In some optional implementations of some embodiments, the execution subject can determine the degradation function matrix according to the blur length and the blur angle by the following steps:

[0057] In a first step, in response to determining that the angle value corresponding to the above-mentioned blur angle satisfies a first preset condition, a preset linear degradation function matrix is determined as the degradation function matrix. The angle value corresponding to the above-mentioned blur angle can be a value from 0 degrees to 180 degrees. The first preset condition can be that the angle value is equal to a preset angle value. The preset angle value can be 0 degrees or 180 degrees. The preset linear degradation function matrix can be a linear function matrix preset for blurring and weighting the original image.

[0058] In a second step, in response to determining that the angle value corresponding to the above-mentioned blur angle does not satisfy the first preset condition, a preset rotation degradation function matrix is determined as the degradation function matrix. The preset rotation degradation function matrix can be a rotation function matrix preset for blurring and weighting the original image.

[0059] In step 105, a restored image is generated according to the insulator image, the degradation function matrix, and a preset matrix.

[0060] In some embodiments, the execution subject can generate a restored image according to the above-mentioned insulator image, the above-mentioned degradation function matrix, and a preset matrix. The preset matrix can be a matrix preset in advance. The preset matrix can be a Laplacian operator.

[0061] In some optional implementations of some embodiments, the execution subject can generate a restored image according to the above-mentioned insulator image, the above-mentioned degradation function matrix, and a preset matrix by the following steps:

[0062] In a first step, a matrix corresponding to the above-mentioned insulator image is determined as an image function matrix. The matrix corresponding to the insulator image can be a two-dimensional matrix.

[0063] In a second step, the image function matrix is subjected to a transformation process to obtain a transformed image function matrix as a transformed image function matrix. In practice, the execution subject can perform Fourier transformation on the image function matrix to obtain a Fourier-transformed image function matrix as a transformed image function matrix.

[0064] In a third step, the degradation function matrix is subjected to a transformation process to obtain a transformed degradation function matrix as a transformed degradation function matrix. In practice, the execution subject can perform Fourier transformation on the degradation function matrix to obtain a Fourier-transformed degradation function matrix as a transformed degradation function matrix.

[0065] Fourthly, a conjugate complex matrix corresponding to the transform degenerate function matrix is determined as a conjugate degenerate function matrix. The conjugate complex matrix can be a matrix composed of elements equal to the real part of the corresponding element in the transform degenerate function matrix and opposite to the imaginary part of the corresponding element in the transform degenerate function matrix.

[0066] Fifthly, a preset matrix is transformed to obtain a transformed preset matrix as a transform preset matrix. In practice, the execution subject can perform Fourier transform on the preset matrix to obtain a Fourier transformed preset matrix as the transform preset matrix.

[0067] Sixthly, a product of a square of the transform preset matrix and a preset coefficient is determined as a first preset matrix. The preset coefficient can be a coefficient preset to optimize the clarity of the recovered image. For example, the preset coefficient can be 0.001.

[0068] Seventhly, a sum of a square of the transform degenerate function matrix and the first preset matrix is determined as a transform parameter.

[0069] Eighthly, a ratio of the conjugate degenerate function matrix and the transform parameter is determined as a transform parameter matrix.

[0070] Ninthly, a product of the transform parameter matrix and the image function matrix is determined as a transform recovered function matrix.

[0071] Tenthly, the transform recovered function matrix is inverse transformed to obtain an inverse transformed transform recovered function matrix as a recovered image matrix. In practice, the execution subject can perform inverse Fourier transform on the transform recovered function matrix to obtain an inverse Fourier transformed transform recovered function matrix as the recovered image matrix.

[0072] Eleventhly, an image corresponding to the recovered image matrix is determined as a recovered image. The recovered image can be a clear image obtained by recovering the insulator image.

[0073] Step 106, generating fault identification result information according to the recovered image and the pre-trained image fault identification model.

[0074] In some embodiments, the execution subject can generate fault identification result information according to the restored image and the pre-trained image fault identification model. The fault identification result information can be information of a fault type of the insulator corresponding to the insulator image. The fault type can include, but is not limited to, insulator normal, insulator damage, insulator crack, and insulator contamination. The image fault identification model can be a neural network model taking the restored image as input and outputting the fault identification result information. The image fault identification model can include a convolution layer, a pooling layer, a skip-connection residual layer, a global average pooling layer, and a classification layer.

[0075] In some optional implementations of some embodiments, the execution subject can generate the fault identification result information according to the restored image and the pre-trained image fault identification model by the following steps:

[0076] In the first step, the restored image is input into the convolution layer to obtain a convolution vector. The convolution layer can be a network layer for feature extraction of input data using a convolution kernel. The convolution layer can be a network layer for feature extraction of the restored image using a convolution kernel to obtain a convolution vector.

[0077] In the second step, the convolution vector is input into the pooling layer to obtain a pooling vector. The pooling layer can be a network layer for maximum pooling processing of an input vector to reduce the size of a parameter matrix. The pooling layer can be a network layer for maximum pooling processing of the convolution vector to reduce the size of a parameter matrix of the convolution vector.

[0078] In the third step, the pooling vector is input into the skip-connection residual layer to obtain an optimized vector. The skip-connection residual layer can be a network layer for increasing the reusability of a feature vector and solving a model degradation problem in a residual layer to obtain an optimized vector. The reusability can represent that a feature vector can be reused. The model degradation problem can be a problem that the performance of a model decreases with the increase of the architecture depth during the training process. The skip-connection residual layer can be a network layer for increasing the reusability of a feature of the pooling vector and solving a model degradation problem of the image fault identification model by adding a skip-connection in the residual layer of the image fault identification model.

[0079] In the fourth step, the optimized vector is input into the global average pooling layer to obtain a global pooling vector. The global average pooling layer can be a network layer that performs average pooling on the input vector to reduce the number of parameters, speed up the model training, and reduce the model overfitting. Here, the global average pooling layer can be a network layer that performs average pooling on the optimized vector to reduce the number of parameters, speed up the model training, and reduce the model overfitting.

[0080] In the fifth step, the global pooling vector is input into the classification layer to obtain fault recognition result information. The classification layer can be a network layer that classifies the input data through a Softmax multi-classification function. Here, the classification layer can be a network layer that classifies the global pooling vector through a Softmax multi-classification function to obtain fault recognition result information.

[0081] The first to fifth steps and the related content thereof are an application point of one embodiment of the present disclosure, and solve the second technical problem mentioned in the background art, i.e., the general recognition model does not use the jump layer connection technology, and the model degradation problem is prominent; the classified data is not subjected to the last global average pooling processing, and the model is prone to overfitting, thereby causing the insulator fault recognition accuracy to be low, the fault maintenance correctness to be low, the service life of the power line to be shortened, and power accidents to occur frequently. The factors that cause the model degradation problem to be prominent and the model to be prone to overfitting, thereby causing the insulator fault recognition accuracy to be low, the fault maintenance correctness to be low, the service life of the power line to be shortened, and power accidents to occur frequently are often as follows: the general recognition model does not use the jump layer connection technology, and the model degradation problem is prominent; the classified data is not subjected to the last global average pooling processing, and the model is prone to overfitting, thereby causing the insulator fault recognition accuracy to be low, the fault maintenance correctness to be low, the service life of the power line to be shortened, and power accidents to occur frequently. If the above factors are solved, the insulator fault recognition accuracy can be improved, the fault maintenance correctness can be improved, thereby the service life of the power line is prolonged, and the frequency of power accidents is reduced. In order to achieve this effect, first, the restored image is input into the convolution layer to obtain a convolution vector. In this way, the convolution vector after feature extraction of the restored image can be obtained. Second, the convolution vector is input into the pooling layer to obtain a pooling vector. In this way, the pooling vector after maximum pooling processing can be obtained, and the size of the parameter matrix of the convolution vector can be reduced, thereby the convergence speed of the model can be improved. Then, the pooling vector is input into the jump layer connection residual layer to obtain an optimization vector. In this way, the jump layer connection is added to the residual layer, the reusability of the features of the pooling vector can be improved, and the model degradation problem of the image fault recognition model can be solved. After that, the optimization vector is input into the global average pooling layer to obtain a global pooling vector. In this way, the global pooling vector after global average pooling processing can be obtained, thereby the number of parameters can be reduced as a whole, the risk of overfitting of the model can be reduced, and the classification ability of the model can be improved. Finally, the global pooling vector is input into the classification layer to obtain fault recognition result information. In this way, the fault recognition result information can be obtained, and can be used for insulator fault maintenance operation. Also, by adding the jump layer connection to the residual layer, the model degradation problem of the image fault recognition model can be solved. Moreover, by performing the global average pooling processing on the optimization vector, the number of parameters of the model can be reduced as a whole, the risk of overfitting of the model can be reduced, and the classification ability of the model can be improved. Therefore, the insulator fault recognition accuracy can be improved, the fault maintenance correctness can be improved, thereby the service life of the power line is prolonged, and the frequency of power accidents is reduced.

[0082] In some optional implementations of some embodiments, the image fault identification model described above can be trained in the following way:

[0083] First, a sample set is obtained. The samples in the sample set include sample recovered images and sample fault identification result information corresponding to the sample recovered images. The sample recovered images can be images used for training the image fault identification model. The sample fault identification result information can be sample labels corresponding to the recovered images. It should be noted that the execution subject for training the image fault identification model can be the execution subject described above or other computing devices.

[0084] Second, the following training steps are performed based on the sample set:

[0085] The first training step is to input the sample recovered images of at least one sample in the sample set into an initial image fault identification model respectively to obtain fault identification result information corresponding to each sample in the at least one sample. The initial image fault identification model is an initial neural network that can obtain fault identification result information according to a recovered image. The initial neural network can be a neural network to be trained. As an example, the initial neural network can be a network including a convolutional layer, a pooling layer, a jump connection residual layer, a global average pooling layer, and a classification layer.

[0086] The second training step is to compare the fault identification result information corresponding to each sample in the at least one sample with the corresponding sample fault identification result information. The comparison can be whether the fault identification result information corresponding to each sample in the at least one sample is the same as the corresponding sample fault identification result information.

[0087] The third training step is to determine whether the initial image fault identification model reaches a preset optimization target according to the comparison result.

[0088] The fourth training step is to determine the initial image fault identification model as a trained image fault identification model in response to determining that the initial image fault identification model reaches the optimization target. The optimization target can be whether the accuracy of the initial image fault identification model prediction reaches a preset threshold. Here, the preset threshold can be 0.9.

[0089] Optionally, the step of training the image fault identification model described above can further include:

[0090] In the fifth training step, in response to determining that the initial image fault identification model does not achieve the optimization target, the network parameters of the initial image fault identification model are adjusted, and the unused sample set is used to constitute a sample set, and the initial image fault identification model after adjustment is used as the initial image fault identification model, and the above training steps are executed again. As an example, the network parameters of the initial image fault identification model can be adjusted by using a back propagation algorithm (BP algorithm) and a gradient descent method (for example, a small batch gradient descent algorithm).

[0091] In step 107, according to the fault identification result information, the associated insulator maintenance device is controlled to perform fault maintenance operation.

[0092] In some embodiments, according to the above fault identification result information, the above execution subject can control the associated insulator maintenance device to perform fault maintenance operation. The insulator maintenance device can be a device for maintaining the insulator fault. For example, the insulator maintenance device can be a power maintenance robot.

[0093] In practice, according to the above fault identification result information, the above execution subject can control the associated insulator maintenance device to perform fault maintenance operation. For example, the fault identification result information can be that the insulator is contaminated. The execution subject can control the power maintenance robot to perform contamination cleaning operation on the insulator.

[0094] The above various embodiments of the present disclosure have the following beneficial effects: through the insulator maintenance device control method of some embodiments of the present disclosure, the accuracy of insulator fault identification is improved, thereby improving the correctness of fault maintenance, further prolonging the service life of the power line, and reducing the frequency of power accidents. Specifically, the reasons for the low accuracy of insulator fault identification, the low correctness of fault maintenance, the short service life of the power line, and the frequent occurrence of power accidents are that the image is not restored before the target image is identified, which leads to low accuracy of insulator fault identification, thereby leading to low correctness of fault maintenance, shortening the service life of the power line, and causing frequent power accidents. Based on this, the insulator maintenance device control method of some embodiments of the present disclosure first acquires an image of a target insulator as an insulator image. Thereby, the insulator image can be obtained, so that the insulator image can be used for image restoration to improve the clarity of the insulator image. Then, according to the above insulator image, a blur angle is generated. Thereby, the blur angle parameter affecting image restoration can be obtained, so that the clarity of the insulator image can be improved. Subsequently, according to the above insulator image and the above blur angle, a blur length is generated. Thereby, the blur length parameter affecting image restoration can be obtained, so that the clarity of the insulator image can be improved. Secondly, according to the above blur length and the above blur angle, a degradation function matrix is determined. Thereby, the degradation function matrix capable of improving the clarity of the restored image under different blur conditions can be determined. Then, according to the above insulator image, the above degradation function matrix, and a preset matrix, a restored image is generated. Thereby, the restored image with high clarity can be obtained, so that the accuracy of insulator fault identification can be improved. Subsequently, according to the above restored image and a pre-trained image fault identification model, fault identification result information is generated. Thereby, the fault identification result information with high identification accuracy can be obtained. So that the correctness of fault maintenance can be improved. Finally, according to the above fault identification result information, the associated insulator maintenance device is controlled to perform fault maintenance operation. Thereby, the insulator fault can be repaired. Because the insulator image is restored, the clarity of the insulator image can be improved. Because the image fault identification model with high identification accuracy is used to identify the restored image with high clarity, the accuracy of insulator fault identification can be improved. So that the correctness of fault maintenance is improved. Further prolong the service life of the power line, and reduce the frequency of power accidents.

[0095] Further reference Figure 2 , as an implementation of the method shown in the above figures, the present disclosure provides some embodiments of an insulator maintenance device control apparatus, which apparatus embodiments correspond to those method embodiments shown in Figure 1 , which apparatus can be applied in various electronic devices.

[0096] AsFigure 2 As shown, the insulator maintenance device control apparatus 200 of some embodiments includes an acquisition unit 201, a first generation unit 202, a second generation unit 203, a determination unit 204, a third generation unit 205, a fourth generation unit 206, and a control unit 207. The acquisition unit 201 is configured to acquire an image of a target insulator as an insulator image. The first generation unit 202 is configured to generate a blur angle according to the insulator image. The second generation unit 203 is configured to generate a blur length according to the insulator image and the blur angle. The determination unit 204 is configured to determine a degradation function matrix according to the blur length and the blur angle. The third generation unit 205 is configured to generate a restored image according to the insulator image, the degradation function matrix, and a preset matrix. The fourth generation unit 206 is configured to generate fault recognition result information according to the restored image and a pre-trained image fault recognition model. The control unit 207 is configured to control an associated insulator maintenance device to perform a fault maintenance operation according to the fault recognition result information.

[0097] It can be understood that the units described in the insulator maintenance device control apparatus 200 correspond to the respective steps in the method described above with reference to FIG. 2. Therefore, the operations, features, and advantages described above with reference to the method also apply to the apparatus 200 and the units included therein, and will not be described again here. Figure 1 It can be understood that the units described in the insulator maintenance device control apparatus 200 correspond to the respective steps in the method described above with reference to FIG. 2. Therefore, the operations, features, and advantages described above with reference to the method also apply to the apparatus 200 and the units included therein, and will not be described again here.

[0098] Reference is made below to FIG. 3, Figure 3 which shows a structural schematic diagram of an electronic device 300 (e.g., a computing device) suitable for use in implementing some embodiments of the present disclosure. The electronic device in some embodiments of the present disclosure can include, but is not limited to, a mobile terminal such as a mobile phone, a notebook computer, a digital broadcast receiver, a PDA (Personal Digital Assistant), a PAD (Tablet Personal Computer), a PMP (Portable Multimedia Player), a car terminal (e.g., a car navigation terminal), and the like, as well as a stationary terminal such as a digital TV, a desktop computer, and the like. Figure 3 The electronic device shown is merely an example and should not impose any limitation on the functions and scope of use of embodiments of the present disclosure.

[0099] As Figure 3As shown, the electronic device 300 can include a processing device 301 (e.g., a central processing unit, a graphics processing unit, etc.) that can perform various appropriate actions and processes according to programs stored in a read-only memory (ROM) 302 or loaded into a random access memory (RAM) 303 from a storage device 308. Various programs and data required for the operation of the electronic device 300 are also stored in the RAM 303. The processing device 301, the ROM 302, and the RAM 303 are connected to each other through a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0100] Generally, the following devices can be connected to the I / O interface 305: input devices 306 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 307 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 308 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 309. The communication devices 309 can allow the electronic device 300 to communicate wirelessly or wired with other devices to exchange data. Although Figure 3 The electronic device 300 is shown with various devices, but it should be understood that all of the illustrated devices are not required, and more or fewer devices can alternatively be implemented. Figure 3 Each block shown in the flowcharts can represent a device, or multiple devices, as necessary.

[0101] In particular, processes described above with reference to the flowcharts can be implemented as a computer software program according to some embodiments of the present disclosure. For example, some embodiments of the present disclosure include a computer program product including a computer program carried on a computer readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In some such embodiments, the computer program can be downloaded and installed from a network through the communication devices 309, or installed from the storage devices 308, or installed from the ROM 302. When the computer program is executed by the processing device 301, the above-described functions defined in the methods of some embodiments of the present disclosure are performed.

[0102] Note that the computer readable medium in some embodiments of the present disclosure can be a computer readable signal medium or a computer readable storage medium or any combination thereof. The computer readable storage medium can be, for example but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus or device, or any suitable combination of the foregoing. More specific examples of the computer readable storage medium can include, but are not limited to, an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In some embodiments of the present disclosure, the computer readable storage medium can be any tangible medium that contains or stores a program used by an instruction execution system, apparatus or device, or that can be used by or in connection with an instruction execution system, apparatus or device. In some embodiments of the present disclosure, the computer readable signal medium can include a computer readable program code propagated in or on a carrier medium, in which the computer readable program code is embodied. Such propagated computer readable program code can take many forms, including but not limited to, an electromagnetic signal, an optical signal or any suitable combination of the foregoing. The computer readable signal medium can also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate or transport a program for use by or in connection with an instruction execution system, apparatus or device. Program code embodied on a computer readable medium can be transmitted using any suitable medium, including but not limited to, wire, cable, wireless, RF, infrared or any suitable combination of the foregoing.

[0103] In some embodiments, the client, server, or both can communicate using any current known or future developed network protocol, such as HTTP (Hyper Text Transfer Protocol), and can be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include local area networks ("LAN"), wide area networks ("WAN"), the Internet, and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any current known or future developed networks.

[0104] The computer readable medium can be included in the electronic device, or can exist separately from the electronic device. The computer readable medium bears one or more programs, which, when executed by the electronic device, cause the electronic device to: acquire an image of a target insulator as an insulator image; generate a blur angle according to the insulator image; generate a blur length according to the insulator image and the blur angle; determine a degradation function matrix according to the blur length and the blur angle; generate a restored image according to the insulator image, the degradation function matrix, and a preset matrix; generate fault identification result information according to the restored image and a pre-trained image fault identification model; and control an associated insulator maintenance device to perform a fault maintenance operation according to the fault identification result information.

[0105] Computer program code for carrying out operations of some embodiments of the disclosure can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C++ or the like, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0106] The flow diagrams and the block diagrams in the drawings are illustrations of architectures, functionalities, and operations of possible implementations of systems, methods, and computer program products according to various embodiments of present disclosure. In this regard, each block in the flow diagrams or block diagrams can represent a module, a procedure, or a part of code, which comprises one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions noted in the blocks can occur in a different order than that noted in the figures. For example, two blocks noted in succession can in fact be executed substantially concurrently or in the opposite order, depending on the functionality involved. It is also noted that each block in the block diagrams and / or flow diagrams, and combinations of blocks in the block diagrams and / or flow diagrams, can be implemented by dedicated hardware-based systems that perform the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0107] The units described in some embodiments of the present disclosure can be implemented in the form of software, or can be implemented in the form of hardware. The described units can also be arranged in a processor, for example, can be described as: a processor includes an acquisition unit, a first generation unit, a second generation unit, a determination unit, a third generation unit, a fourth generation unit and a control unit. Among them, the name of these units does not constitute a limitation to the unit itself in some cases, for example, the acquisition unit can also be described as: a unit for acquiring the image of the target insulator as the insulator image.

[0108] The functions described above herein can be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that can be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system on a chip (SOCs), complex programmable logic devices (CPLDs), etc.

[0109] The above description is merely some preferred embodiments of the present disclosure and a description of the principles of the technology used. Those skilled in the art should understand that the scope of the application involved in the embodiments of the present disclosure is not limited to the technical solutions formed by the specific combinations of the above technical features, and should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above inventive concept. For example, the above features are replaced with each other to form a technical solution with similar functions to the technical features disclosed in the embodiments of the present disclosure (but not limited to).

Claims

1. An insulator maintenance device control method, comprising: acquiring an image of a target insulator as an insulator image; generating a blur angle according to the insulator image; generating a blur length according to the insulator image and the blur angle; determining a degradation function matrix according to the blur length and the blur angle; generating a restored image according to the insulator image, the degradation function matrix, and a preset matrix, wherein the preset matrix is a matrix preset, and the generating a restored image according to the insulator image, the degradation function matrix, and a preset matrix comprises: determining a matrix corresponding to the insulator image as an image function matrix; performing transformation processing on the image function matrix to obtain a transformed image function matrix as a transformed image function matrix; performing transformation processing on the degradation function matrix to obtain a transformed degradation function matrix as a transformed degradation function matrix; determining a conjugate complex matrix corresponding to the transformed degradation function matrix as a conjugate degradation function matrix, wherein the conjugate complex matrix is a matrix composed of elements equal to the real part of the corresponding elements in the transformed degradation function matrix and having opposite imaginary parts; performing transformation processing on the preset matrix to obtain a transformed preset matrix as a transformed preset matrix; determining a product of a square of the transformed preset matrix and a preset coefficient as a first preset matrix, wherein the preset coefficient is a coefficient preset to optimize the clarity of the restored image; determining a sum of a square of the transformed degradation function matrix and the first preset matrix as a transformed parameter; determining a ratio of the conjugate degradation function matrix to the transformed parameter as a transformed parameter matrix; determining a product of the transformed parameter matrix and the image function matrix as a transformed restoration function matrix; performing inverse transformation processing on the transformed restoration function matrix to obtain an inverse transformed transformed restoration function matrix as a restored image matrix; determining an image corresponding to the restored image matrix as a restored image, wherein the restored image is a clear image obtained by restoring the insulator image; generating fault identification result information according to the restored image and a pre-trained image fault identification model; controlling an associated insulator maintenance device to perform fault maintenance operations according to the fault identification result information.

2. The method of claim 1, wherein, The generating a blur angle according to the insulator image comprises: performing transformation processing on the insulator image to obtain a frequency spectrum image; performing enhancement processing on the frequency spectrum image to obtain an enhanced image; performing morphological transformation on the enhanced image to obtain a morphologically transformed image; performing edge detection on the morphologically transformed image to obtain an edge-detected image as a fringe edge image; generating a blur angle according to the fringe edge image.

3. The method of claim 2, wherein, The generating a blur length according to the insulator image and the blur angle comprises: determining a frequency spectrum image vertical projection according to the frequency spectrum image and the blur angle; determining a fringe spacing according to the frequency spectrum image vertical projection; determine an image length and an image width of the insulator image, wherein the image length is a number of longitudinal pixels of the insulator image, and the image width is a number of transverse pixels of the insulator image; generate a blur length according to the stripe interval, the blur angle, the image length, and the image width.

4. The method of claim 3, wherein, The determining of the degradation function matrix according to the blur length and the blur angle comprises: in response to determining that the angle value corresponding to the blur angle satisfies a first preset condition, determining a preset linear degradation function matrix as the degradation function matrix, wherein the blur angle corresponds to an angle value; in response to determining that the angle value corresponding to the blur angle does not satisfy the first preset condition, determining a preset rotation degradation function matrix as the degradation function matrix.

5. The method of claim 1, wherein, The image fault recognition model is trained in the following manner: obtain a sample set, wherein a sample in the sample set includes a sample restored image and sample fault recognition result information corresponding to the sample restored image; based on the sample set, perform the following training steps: input the sample restored image of at least one sample in the sample set into an initial image fault recognition model respectively to obtain fault recognition result information corresponding to each sample in the at least one sample; compare the fault recognition result information corresponding to each sample in the at least one sample with the corresponding sample fault recognition result information; determine whether the initial image fault recognition model reaches a preset optimization target according to the comparison result; in response to determining that the initial image fault recognition model reaches the optimization target, determine the initial image fault recognition model as the image fault recognition model trained.

6. The method of claim 5, wherein, The step of training the image fault recognition model further comprises: in response to determining that the initial image fault recognition model does not reach the optimization target, adjust the network parameters of the initial image fault recognition model, and use a sample set composed of unused samples to use the adjusted initial image fault recognition model as the initial image fault recognition model to perform the training steps again.

7. An insulator maintenance device control apparatus, comprising: an acquisition unit configured to acquire an image of a target insulator as an insulator image; a first generation unit configured to generate a blur angle according to the insulator image; a second generation unit configured to generate a blur length according to the insulator image and the blur angle; a determination unit configured to determine a degradation function matrix according to the blur length and the blur angle; a third generation unit configured to generate a restored image according to the insulator image, the degradation function matrix, and a preset matrix, wherein the preset matrix is a matrix preset in advance, and the generation of the restored image according to the insulator image, the degradation function matrix, and the preset matrix comprises: determining a matrix corresponding to the insulator image as an image function matrix; performing transformation processing on the image function matrix to obtain a transformed image function matrix as a transformed image function matrix; performing transformation processing on the degradation function matrix to obtain a transformed degradation function matrix as a transformed degradation function matrix; The conjugate complex matrix corresponding to the transformation degenerate function matrix is determined as a conjugate degenerate function matrix, and the conjugate complex matrix is a matrix composed of elements equal to the real part of the corresponding element in the transformation degenerate function matrix and having opposite imaginary parts; The preset matrix is subjected to transformation processing to obtain a transformed preset matrix as a transformation preset matrix; A product of a square of the transformation preset matrix and a preset coefficient is determined as a first preset matrix, wherein the preset coefficient is a coefficient that is previously set to optimize the clarity of the restored image; A sum of a square of the transformation degenerate function matrix and the first preset matrix is determined as a transformation parameter; A ratio of the conjugate degenerate function matrix and the transformation parameter is determined as a transformation parameter matrix; A product of the transformation parameter matrix and the image function matrix is determined as a transformation restored function matrix; The transformation restored function matrix is subjected to inverse transformation processing to obtain an inverse transformation processed transformation restored function matrix as a restored image matrix; An image corresponding to the restored image matrix is determined as a restored image, wherein the restored image is a clear image obtained by performing restoration processing on the insulator image; A fourth generation unit is configured to generate fault identification result information according to the restored image and a pre-trained image fault identification model; A control unit is configured to control an associated insulator maintenance device to perform fault maintenance operation according to the fault identification result information. 8.An electronic device, comprising: one or more processors; a storage having one or more programs stored thereon, when the one or more programs are executed by the one or more processors, the one or more processors implement the method of any one of claims 1-6.

9. A computer readable medium having stored thereon a computer program, wherein, The computer program is executed by the processor to implement the method of any one of claims 1-6.

Images