Partial discharge defect type identification method, device, equipment and storage medium

Abstract

The present invention discloses a method, device, equipment and storage medium for identifying the type of partial discharge defects. The method includes: collecting partial discharge signals of target defective objects; converting partial discharge signals into pulse sequence phase distribution images; establishing an image enhancement model, and determining target α parameters and target β parameters in the image enhancement model based on a fitness function; performing adaptive image enhancement on the pulse sequence phase distribution image based on the image enhancement model to obtain an enhanced pulse sequence phase distribution image; and determining the type of partial discharge defects based on the enhanced pulse sequence phase distribution image. Through the technical solution of the present invention, it is possible to perform adaptive image enhancement on PRPS images, improve the contrast of PRPS images, make images clearer, facilitate further extraction of more differentiated image features, determine the type of partial discharge defects, and thus improve the recognition accuracy of faults, and has a strong engineering application value.

Description

Technical Field

[0001] The embodiments of the present invention relate to the technical field of power equipment status monitoring, and in particular to a partial discharge defect type identification method, device, equipment and storage medium. Background Art

[0002] Gas Insulated Switchgear (GIS) is widely used in power systems due to its advantages such as small footprint, compact structure, high operational reliability, and easy maintenance. However, due to some human factors in the equipment manufacturing, transportation, installation, and operation process, there may be certain insulation defects and potential faults in GIS equipment. Since GIS is a fully enclosed device, general monitoring technology cannot effectively monitor its internal insulation status. Partial discharge, as an important indicator of the insulation status of high-voltage power equipment, is closely related to the degree of deterioration of the insulating medium. Therefore, studying the severity of GIS partial discharge has important engineering significance.

[0003] At present, due to the complex operating environment of GIS equipment and the presence of various noise interferences, the acquisition of GIS equipment fault signals is affected and is not conducive to subsequent processing. On the other hand, the current GIS fault identification method based on UHF technology does not adequately process fault maps, resulting in problems such as insufficient image clarity, low color contrast, and blurred map edges, which is not conducive to subsequent map feature extraction and further fault type identification. Summary of the invention

[0004] The embodiments of the present invention provide a method, device, equipment and storage medium for identifying the type of partial discharge defect, so as to realize adaptive image enhancement of PRPS images, improve the contrast of partial discharge pulse signal spectrum (Phase Resolved Pulse Sequence, PRPS) images, make the images clearer, facilitate further extraction of more differentiated image features, determine the type of partial discharge defect, and thus improve the recognition accuracy of faults, which has strong engineering application value.

[0005] In a first aspect, an embodiment of the present invention provides a method for identifying a partial discharge defect type, wherein a voltage is passed into a GIS experimental chamber to cause a target defect object in the GIS experimental chamber to undergo partial discharge, comprising:

[0006] Collect partial discharge signals of target defective objects;

[0007] Convert the partial discharge signal into a pulse sequence phase distribution image;

[0008] Establish an image enhancement model, and determine the target α parameter and the target β parameter in the image enhancement model based on the fitness function;

[0009] Based on the image enhancement model, the pulse sequence phase distribution image is adaptively enhanced to obtain an enhanced pulse sequence phase distribution image;

[0010] The type of partial discharge defect is determined based on the enhanced pulse sequence phase distribution image.

[0011] Optionally, performing adaptive image enhancement on the pulse sequence phase distribution image based on an image enhancement model to obtain an enhanced pulse sequence phase distribution image includes:

[0012] Convert the pulse sequence phase distribution image into double format to obtain a first image;

[0013] Adaptive image enhancement is performed on the first image based on the image enhancement model to obtain an enhanced pulse sequence phase distribution image.

[0014] Optionally, the image enhancement model is a non-complete Beta function.

[0015] Optionally, determining a target α parameter and a target β parameter in the image enhancement model based on a fitness function includes:

[0016] Acquire a parameter pair set, wherein the parameter pair set includes at least two parameter pairs, and the parameter pairs include: an α parameter and a β parameter;

[0017] Determine the fitness corresponding to each parameter pair in the parameter pair set based on the fitness function;

[0018] The parameter pair with the maximum fitness is determined as the target α parameter and the target β parameter.

[0019] Optionally, determining the fitness corresponding to each parameter pair in the parameter pair set based on the fitness function includes:

[0020] Obtain the structural similarity between the enhanced image and the image before enhancement corresponding to the parameter pair;

[0021] Obtain the entropy value and grayscale standard deviation of the enhanced image corresponding to the parameter pair;

[0022] The fitness of the parameter pair is determined according to the entropy value of the enhanced image, the grayscale standard deviation and the structural similarity between the enhanced image and the image before enhancement.

[0023] Optionally, determining a target α parameter and a target β parameter based on a fitness function includes:

[0024] Get initial α parameters and initial β parameters;

[0025] Determine the initial position of the moth according to the initial α parameter and the initial β parameter;

[0026] Generate a moth matrix based on the initial positions of the moths;

[0027] Determine the fitness corresponding to each moth in the moth matrix based on the fitness function;

[0028] The target α parameter and the target β parameter are determined according to the position corresponding to the moth with the largest fitness.

[0029] Optionally, the type of partial discharge defect is determined based on the enhanced pulse sequence phase distribution image, including:

[0030] Determine the local discharge characteristic parameters based on the enhanced pulse sequence phase distribution image;

[0031] The local discharge characteristic parameters are input into the target model to obtain the local discharge defect type.

[0032] In a second aspect, an embodiment of the present invention provides a partial discharge defect type identification device, which passes a voltage into a GIS experimental chamber to cause a target defect object in the GIS experimental chamber to partially discharge, including:

[0033] An acquisition module, used for acquiring partial discharge signals of target defective objects;

[0034] A conversion module, used for converting a partial discharge signal into a pulse sequence phase distribution image;

[0035] A model building module is used to build an image enhancement model and determine a target α parameter and a target β parameter in the image enhancement model based on a fitness function;

[0036] An image enhancement module, used for performing adaptive image enhancement on the pulse sequence phase distribution image based on an image enhancement model to obtain an enhanced pulse sequence phase distribution image;

[0037] The type determination module is used to determine the type of partial discharge defect based on the enhanced pulse sequence phase distribution image.

[0038] Optional, image enhancement module, including:

[0039] A conversion unit, used for converting the pulse sequence phase distribution image into a double format to obtain a first image;

[0040] The image enhancement unit is used to perform adaptive image enhancement on the first image based on the image enhancement model to obtain an enhanced pulse sequence phase distribution image.

[0041] Optionally, the image enhancement model is a non-complete Beta function.

[0042] Optional, model building module, including:

[0043] A first acquisition unit is used to acquire a parameter pair set, wherein the parameter pair set includes at least two parameter pairs, and the parameter pairs include: an α parameter and a β parameter;

[0044] A first determining unit, configured to determine the fitness corresponding to each parameter pair in the parameter pair set based on the fitness function;

[0045] The second determining unit is used to determine the parameter pair with the maximum fitness as the target α parameter and the target β parameter.

[0046] Optionally, the first determining unit is specifically configured to:

[0047] Obtain the structural similarity between the enhanced image and the image before enhancement corresponding to the parameter pair;

[0048] Obtain the entropy value and grayscale standard deviation of the enhanced image corresponding to the parameter pair;

[0049] The fitness of the parameter pair is determined according to the entropy value of the enhanced image, the grayscale standard deviation and the structural similarity between the enhanced image and the image before enhancement.

[0050] Optionally, the model building module also includes:

[0051] A second acquisition unit is used to acquire an initial α parameter and an initial β parameter;

[0052] A third determining unit is used to determine the initial position of the moth according to the initial α parameter and the initial β parameter;

[0053] A generating unit, used for generating a moth matrix according to an initial position of the moth;

[0054] A fourth determining unit, used for determining the fitness corresponding to each moth in the moth matrix based on the fitness function;

[0055] The fifth determining unit is used to determine the target α parameter and the target β parameter according to the position corresponding to the moth with the largest fitness.

[0056] Optional, type determination module, specifically used to:

[0057] Determine the local discharge characteristic parameters based on the enhanced pulse sequence phase distribution image;

[0058] The local discharge characteristic parameters are input into the target model to obtain the local discharge defect type.

[0059] In a third aspect, an embodiment of the present invention provides an electronic device, the electronic device comprising:

[0060] at least one processor; and

[0061] a memory communicatively connected to the at least one processor; wherein,

[0062] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the partial discharge defect type identification method described in any embodiment of the present invention.

[0063] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the partial discharge defect type identification method described in any embodiment of the present invention when executed.

[0064] The embodiment of the present invention passes voltage into a GIS experimental cavity to make a target defective object in the GIS experimental cavity perform partial discharge; collects partial discharge signals of the target defective object; converts the partial discharge signals into a pulse sequence phase distribution image; establishes an image enhancement model, and determines target α parameters and target β parameters in the image enhancement model based on a fitness function; performs adaptive image enhancement on the pulse sequence phase distribution image based on the image enhancement model to obtain an enhanced pulse sequence phase distribution image; determines the type of partial discharge defect based on the enhanced pulse sequence phase distribution image; solves the problem in the prior art that the local discharge image has insufficient clarity and low color contrast, which is not conducive to feature extraction and fault type identification, realizes adaptive image enhancement of the PRPS image, improves the contrast of the PRPS image, makes the image clearer, and facilitates further extraction of more differentiated image features, determines the type of partial discharge defect, and thus improves the fault identification accuracy, and has strong engineering application value.

[0065] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0067] Figure 1 A flow chart of a method for identifying partial discharge defect types provided in Embodiment 1 of the present invention;

[0068] Figure 2A flow chart of a method for identifying partial discharge defect types provided in Embodiment 2 of the present invention;

[0069] Figure 3 A flowchart of an MFO optimization algorithm for a non-complete Beta function provided in Embodiment 2 of the present invention;

[0070] Figure 4 A schematic diagram of the structure of a partial discharge defect type identification device provided in Embodiment 3 of the present invention;

[0071] Figure 5 A schematic diagram of the structure of an electronic device that can be used to implement an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0072] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0073] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0074] It is understandable that before using the technical solutions disclosed in the embodiments of the present disclosure, the types, scope of use, usage scenarios, etc. of the personal information involved in the present disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0075] Embodiment 1

[0076] Figure 1This is a flow chart of a method for identifying a partial discharge defect type provided in the first embodiment of the present invention. This embodiment is applicable to the case of identifying a partial discharge defect type. A voltage is passed into a GIS experimental chamber to cause a target defect object in the GIS experimental chamber to undergo partial discharge. This method can be performed by a partial discharge defect type identification device in the embodiment of the present invention. The device can be implemented in software and / or hardware, such as Figure 1 As shown, the method specifically comprises the following steps:

[0077] S110, collecting partial discharge signals of the target defective object.

[0078] The target defect object may refer to metal particles, spikes, air gaps, suspended electrodes, etc. Specifically, a voltage is passed into the GIS experimental cavity to cause partial discharge of the target defect object in the GIS experimental cavity. The voltage can be divided into high voltage and low voltage; the GIS experimental cavity may refer to a typical model of partial discharge of GIS equipment. The partial discharge signal of the target defect object may be collected by a sensor, the sensor may refer to an ultra-high frequency sensor, and the ultra-high frequency electrical signal may refer to an electrical signal of 300MHZ to 3GHZ.

[0079] In this embodiment, typical partial discharge models of four defects of GIS equipment, namely metal particles, spikes, air gaps, and suspended electrodes, can be pre-constructed. For example, metal particle defects can be simulated by placing a 0.5mm metal ball in the GIS cavity; the suspended electrode defect can be simulated by placing a copper block with a side length of 10mm in a cylindrical epoxy resin with a height of 30mm, and the epoxy resin is sandwiched between the high-voltage electrode and the ground electrode; the metal spike defect can be simulated by grinding one end of a 20mm long and 5mm long copper wire into a needle tip with a curvature radius of about 0.1mm and placing it in the GIS cavity, and the tip is 10mm away from the ground electrode; the air gap defect can be simulated by sealing a cylindrical air gap with a radius of 3mm in the epoxy resin, and the size and placement of the epoxy resin are the same as those of the suspended electrode defect. By applying high voltage to the four defect partial discharge models, the metal particles, spikes, air gaps, and suspended electrodes in the GIS experimental cavity are partially discharged, and the partial discharge signals of different types of target defect objects are collected by ultra-high frequency sensors.

[0080] S120, converting the local discharge signal into a pulse sequence phase distribution image.

[0081] The pulse sequence phase distribution image may refer to a local discharge pulse signal image, which displays the phased pulse signal generated by the local discharge in a three-dimensional coordinate system in chronological order.

[0082] S130, establishing an image enhancement model, and determining a target α parameter and a target β parameter in the image enhancement model based on a fitness function;

[0083] The image enhancement model may refer to a non-complete Beta function, the α parameter and the β parameter are two parameters in the non-complete function, and the target α parameter and the target β parameter may refer to the optimal α parameter and the β parameter; specifically, the non-complete Beta function F(u) is defined as:

[0084]

[0085] Among them, B (α, β) is the Beta function, and the mathematical expression is:

[0086]

[0087] Since the α parameter and the β parameter have a great influence on image enhancement, the Moth-Flame Optimization (MFO) algorithm can be used to optimize the α parameter and the β parameter. Specifically, the MFO optimization algorithm can be used to optimize the α parameter and the β parameter, and the fitness value can be calculated through the fitness function to determine the optimal α parameter and the optimal β parameter.

[0088] Specifically, the fitness function can refer to:

[0089] fitness=a1H+a2S+a3logV

[0090] Wherein, H is the entropy value of the test image, S is the structural similarity; V is the grayscale standard deviation of the test image. a1, a2, and a3 are constants, which can be preset, for example, a1, a2, and a3 can be set equal, that is, a1=a2=a3=1; or they can be determined according to actual conditions, which is not limited in this embodiment.

[0091] In one embodiment, the fitness corresponding to the α parameter and the β parameter can be determined by a fitness function, and then the optimal α parameter and the optimal β parameter can be determined from multiple α parameters and β parameters, and the incomplete Beta function can be determined according to the optimal α parameter and the optimal β parameter.

[0092] In this embodiment, the MFO optimization algorithm can be used to optimize the α parameter and β parameter in the image enhancement model, and the fitness value can be calculated through the fitness function to determine the target α parameter and the target β parameter. The image enhancement model is established according to the target α parameter and the target β parameter; the pulse sequence phase distribution image is enhanced based on the image enhancement model to obtain an enhanced PRPS image, which is convenient for further extracting more differentiated image features and improving the fault recognition accuracy.

[0093] S140, performing adaptive image enhancement on the pulse sequence phase distribution image based on an image enhancement model to obtain an enhanced pulse sequence phase distribution image.

[0094] The adaptive image enhancement may refer to adaptive image enhancement of the PRPS image by using an adaptive algorithm.

[0095] In this embodiment, the PRPS image is adaptively enhanced based on the image enhancement model through an adaptive algorithm, so that the discharge characteristics in the PRPS image are strengthened, thereby enhancing the visual characteristics of the PRPS image, providing a good foundation for further improving the recognition of different types of partial discharge of GIS equipment.

[0096] S150, determining the local discharge defect type based on the enhanced pulse sequence phase distribution image.

[0097] Among them, the types of partial discharge defects may include: the presence of freely moving metal particles in the GIS air chamber, the presence of needle-like protrusions on the GIS shell or high-voltage conductor, the presence of fixed metal particles on the surface of the insulator in the GIS air chamber, the presence of suspended potential bodies near the high-voltage conductor in the GIS air chamber or poor contact between the connection points between conductors, the presence of bubbles and / or cracks inside or on the surface of the insulator of the GIS air chamber during manufacturing, non-metallic contaminant defects on the insulator surface, ground electrode fault defects, interface defects, etc.

[0098] In this embodiment, the type of partial discharge defect can be determined through the enhanced PRPS image, which is not only easy to implement but also improves the recognition accuracy of the type of partial discharge defect.

[0099] In this embodiment, voltage is passed into the GIS experimental cavity to cause local discharge of the target defective object in the GIS experimental cavity; local discharge signals of the target defective object are collected by sensors; the local discharge signals are converted into PRPS images; an image enhancement model is established, and the target α parameter and the target β parameter in the image enhancement model are determined based on the fitness function; the PRPS image is adaptively enhanced based on the image enhancement model to obtain an enhanced PRPS image; the type of local discharge defect is determined based on the enhanced PRPS image; the problem of insufficient clarity and low color contrast of local discharge images in the prior art, which is not conducive to feature extraction and fault type identification, is solved, adaptive image enhancement of PRPS images is achieved, the contrast of PRPS images is improved, the image is clearer, and it is convenient to further extract more differentiated image features, determine the type of local discharge defects, and thus improve the fault identification accuracy, which has a strong engineering application value.

[0100] Optionally, the type of partial discharge defect is determined based on the enhanced pulse sequence phase distribution image, including:

[0101] Determine the local discharge characteristic parameters based on the enhanced pulse sequence phase distribution image;

[0102] The local discharge characteristic parameters are input into the target model to obtain the local discharge defect type.

[0103] The local discharge characteristic parameters may refer to two-dimensional pixel parameters and RGB channel parameters in the PRPD image. The target model may refer to a pre-trained model that can determine the local discharge defect type according to the local discharge characteristic parameters. Specifically, the target model can be obtained by training a training sample set. The training sample set may include local discharge characteristic parameters and local discharge defect types corresponding to the local discharge characteristic parameters.

[0104] In this embodiment, the local discharge characteristic parameters can be determined based on the enhanced PRPS image by pre-training the target model; the local discharge characteristic parameters are input into the trained target model to obtain the local discharge defect type, which is not only easy to implement but also improves the recognition accuracy of the local discharge defect type.

[0105] Optionally, after collecting the partial discharge signal of the target defective object through the sensor, the SG filter can be used to filter and denoise the partial discharge signal. Among them, the SG smoothing filter can cope with different application scenarios by setting the minimum number of variables (i.e., the setting of the window width). The SG smoothing filter can filter out the noise while still ensuring that the shape and width of the initial spectrum of the signal remain unchanged.

[0106] In this embodiment, the SG filter is used to perform denoising on the partial discharge signal, thereby improving the signal-to-noise ratio of the signal, which can effectively help improve the smoothing characteristics of the signal and reduce the interference of environmental noise on the UHF signal.

[0107] Embodiment 2

[0108] Figure 2 This is a flow chart of a method for identifying partial discharge defect types provided in the second embodiment of the present invention. The technical solution of this embodiment is further refined on the basis of the above embodiment. Figure 2 As shown, the method includes:

[0109] S210, collecting partial discharge signals of the target defective object.

[0110] S220, converting the local discharge signal into a pulse sequence phase distribution image.

[0111] S230, establishing an image enhancement model, and determining a target α parameter and a target β parameter in the image enhancement model based on a fitness function;

[0112] S240, converting the pulse sequence phase distribution image into a double format to obtain a first image.

[0113] The double format may refer to a double-type output format, and the first image may refer to an image obtained by converting the PRPS image into a double format and normalizing the image.

[0114] In this embodiment, the PRPS image is preprocessed, converted into a double format and normalized, so that the obtained first image is clearer and more accurate.

[0115] S250, performing adaptive image enhancement on the first image based on the image enhancement model to obtain an enhanced pulse sequence phase distribution image.

[0116] In this embodiment, the enhanced PRPS image obtained by adaptively enhancing the first image based on the image enhancement model strengthens the discharge features in the image, thereby enhancing the visual features of the PRPS image and effectively improving the contrast of the image.

[0117] S260, determining the local discharge defect type based on the enhanced pulse sequence phase distribution image.

[0118] In this embodiment, the PRPS image is preprocessed, converted into a double format and normalized, so that the obtained first image is clearer and more accurate; then the first image is adaptively enhanced based on the image enhancement model to obtain an enhanced PRPS image, which strengthens the discharge features in the image, thereby enhancing the visual features of the PRPS image and effectively improving the image contrast; the local discharge defect type is determined based on the enhanced PRPS image, thereby improving the recognition accuracy of the local discharge defect type.

[0119] Optionally, determining a target α parameter and a target β parameter in the image enhancement model based on a fitness function includes:

[0120] Acquire a parameter pair set, wherein the parameter pair set includes at least two parameter pairs, and the parameter pairs include: an α parameter and a β parameter;

[0121] Determine the fitness corresponding to each parameter pair in the parameter pair set based on the fitness function;

[0122] The parameter pair with the maximum fitness is determined as the target α parameter and the target β parameter.

[0123] In this embodiment, parameter pairs can be randomly obtained, and the parameter pairs include: α parameters and β parameters, and at least two pairs of parameter pairs constitute a parameter pair set; the fitness value corresponding to each parameter pair in the parameter pair set can be determined by fitness function calculation; each parameter pair in the set is sorted according to the size of the fitness value; the parameter pair with the largest fitness is determined as the target α parameter and the target β parameter; the image enhancement model is determined according to the obtained optimal α parameter and β parameter, and the first image is adaptively enhanced based on the image enhancement model to obtain an enhanced PRPS image; the contrast of the PRPS image is effectively improved, making the image clearer, and facilitating further extraction of more differentiated image features, determining the type of local discharge defects, and thereby improving the fault recognition accuracy, which has a strong engineering application value.

[0124] Optionally, determining the fitness corresponding to each parameter pair in the parameter pair set based on the fitness function includes:

[0125] Obtain the structural similarity between the enhanced image and the image before enhancement corresponding to the parameter pair;

[0126] Obtain the entropy value and grayscale standard deviation of the enhanced image corresponding to the parameter pair;

[0127] The fitness of the parameter pair is determined according to the entropy value of the enhanced image, the grayscale standard deviation and the structural similarity between the enhanced image and the image before enhancement.

[0128] Specifically, the entropy value, grayscale standard deviation, and structural similarity between the enhanced image and the image before enhancement corresponding to the parameter pair can be calculated by the following formula:

[0129]

[0130]

[0131]

[0132] Among them, p(i) is the probability of the i-th gray value appearing in the image; μ and σ represent the mean and variance of the pixels, and σ xy represents the covariance between pixel x in the original image and pixel y in the enhanced image. C1 and C2 are constants, which can generally be set to 0. N is the total number of pixels in the image. The larger V is, the clearer the image texture is.

[0133] In this embodiment, the entropy value, grayscale standard deviation and structural similarity between the enhanced image and the image before enhancement of the parameter pair are obtained, and the fitness value corresponding to the parameter pair is determined according to the fitness function; each parameter pair in the set is sorted according to the fitness value; the parameter pair with the largest fitness is determined as the target α parameter and the target β parameter; the image enhancement model is determined according to the target α parameter and the target β parameter; the first image is adaptively enhanced based on the image enhancement model to obtain an enhanced PRPS image; the contrast of the PRPS image is improved to make the image clearer, which is convenient for further extracting more differentiated image features, determining the type of local discharge defects, and thereby improving the fault recognition accuracy, which has a strong engineering application value.

[0134] Optionally, determining a target α parameter and a target β parameter based on a fitness function includes:

[0135] Get initial α parameters and initial β parameters;

[0136] Determine the initial position of the moth according to the initial α parameter and the initial β parameter;

[0137] Generate a moth matrix based on the initial positions of the moths;

[0138] Determine the fitness corresponding to each moth in the moth matrix based on the fitness function;

[0139] The target α parameter and the target β parameter are determined according to the position corresponding to the moth with the largest fitness.

[0140] Specifically, Figure 3 A flowchart of an MFO optimization algorithm for a non-complete Beta function provided in Embodiment 2 of the present invention is shown in FIG. Figure 3 As shown, after inputting the PRPS image, the initial α parameter and the initial β parameter are randomly obtained, the number of moth populations can be initialized to M, the number of flames to N, the parameter search range, the search space dimension D (D = 2), and the maximum number of iterations I are set. The initial position of the moth is determined by obtaining the initial α parameter and the initial β parameter, the fitness is calculated, and the moth matrix is ​​generated according to the initial position of the moth, where each moth position in the moth matrix corresponds to an α parameter and a β parameter.

[0141] Define the flame as the historical optimal solution and update the number of flames according to the following formula:

[0142]

[0143] Flame nThe number of flames under the current iteration number, round() is the rounding down operation function, the number N is defined as the initial number of flames, I is defined as the total number of iterations, and L is defined as the current number of iterations. Based on the fitness function, the fitness value of each moth individual in the moth matrix is ​​calculated, the moths are sorted according to the size of the fitness value, the position information is given to the flame, the flame position is updated, and the flame with a better fitness value is retained.

[0144] Update the moth position as follows:

[0145] S(M i ,F j )=D i ·e bθ ·cos(2πθ)+F j

[0146] D i =|F j -M i |

[0147] Among them, M i is the i-th moth, F j is the jth flame, θ is a random number in [-1,1], D i is the distance from moth M to flame F, and b is the grayscale value of each pixel. After updating, it is determined whether the maximum number of iterations has been reached or the preset fitness threshold has been met. If the maximum number of iterations has not been reached or the preset threshold has not been met, the fitness values ​​of the moth and flame are calculated again until the maximum number of iterations has been reached or the preset threshold has been met. Then the iteration is stopped and the optimal α parameter and β parameter are output. The image enhancement model is determined based on the obtained optimal α parameter and β parameter; the first image is adaptively enhanced based on the image enhancement model to obtain an enhanced PRPS image, improve the contrast of the PRPS image, make the image clearer, and facilitate further extraction of more differentiated image features, determine the type of partial discharge defects, and thus improve the recognition accuracy of faults, which has strong engineering application value.

[0148] Embodiment 3

[0149] Figure 4 A schematic diagram of a partial discharge defect type identification device provided in the third embodiment of the present invention is shown. A voltage is passed into the GIS experimental chamber to cause a target defect object in the GIS experimental chamber to undergo partial discharge, such as Figure 4 As shown, the device comprises:

[0150] The acquisition module 310 is used to acquire the partial discharge signal of the target defective object;

[0151] A conversion module 320, for converting a partial discharge signal into a pulse sequence phase distribution image;

[0152] A model building module 330 is used to build an image enhancement model and determine a target α parameter and a target β parameter in the image enhancement model based on a fitness function;

[0153] An image enhancement module 340 is used to perform adaptive image enhancement on the pulse sequence phase distribution image based on an image enhancement model to obtain an enhanced pulse sequence phase distribution image;

[0154] The type determination module 350 is used to determine the type of partial discharge defect based on the enhanced pulse sequence phase distribution image.

[0155] Optionally, the image enhancement module 340 includes:

[0156] A conversion unit, used for converting the pulse sequence phase distribution image into a double format to obtain a first image;

[0157] The image enhancement unit is used to perform adaptive image enhancement on the first image based on the image enhancement model to obtain an enhanced pulse sequence phase distribution image.

[0158] Optionally, the image enhancement model is a non-complete Beta function.

[0159] Optionally, the model building module 330 includes:

[0160] A first acquisition unit is used to acquire a parameter pair set, wherein the parameter pair set includes at least two parameter pairs, and the parameter pairs include: an α parameter and a β parameter;

[0161] A first determining unit, configured to determine the fitness corresponding to each parameter pair in the parameter pair set based on the fitness function;

[0162] The second determining unit is used to determine the parameter pair with the maximum fitness as the target α parameter and the target β parameter.

[0163] Optionally, the first determining unit is specifically configured to:

[0164] Obtain the structural similarity between the enhanced image and the image before enhancement corresponding to the parameter pair;

[0165] Obtain the entropy value and grayscale standard deviation of the enhanced image corresponding to the parameter pair;

[0166] The fitness of the parameter pair is determined according to the entropy value of the enhanced image, the grayscale standard deviation and the structural similarity between the enhanced image and the image before enhancement.

[0167] Optionally, the model building module 330 further includes:

[0168] A second acquisition unit is used to acquire an initial α parameter and an initial β parameter;

[0169] A third determining unit is used to determine the initial position of the moth according to the initial α parameter and the initial β parameter;

[0170] A generating unit, used for generating a moth matrix according to an initial position of the moth;

[0171] A fourth determining unit, used for determining the fitness corresponding to each moth in the moth matrix based on the fitness function;

[0172] The fifth determining unit is used to determine the target α parameter and the target β parameter according to the position corresponding to the moth with the largest fitness.

[0173] Optionally, the type determination module 350 is specifically configured to:

[0174] Determine the local discharge characteristic parameters based on the enhanced pulse sequence phase distribution image;

[0175] The local discharge characteristic parameters are input into the target model to obtain the local discharge defect type.

[0176] The partial discharge defect type identification device provided in the embodiment of the present invention can execute the partial discharge defect type identification method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0177] Embodiment 4

[0178] Figure 5 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0179] like Figure 5As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0180] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0181] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a partial discharge defect type identification method.

[0182] In some embodiments, the partial discharge defect type identification method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the partial discharge defect type identification method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the partial discharge defect type identification method in any other appropriate manner (e.g., by means of firmware).

[0183] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0184] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0185] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0186] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0187] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0188] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0189] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0190] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for identifying partial discharge defect types, wherein voltage is passed into a GIS experimental cavity to cause a target defect object in the GIS experimental cavity to undergo partial discharge, characterized in that: include: Collect partial discharge signals of target defective objects; Convert the partial discharge signal into a pulse sequence phase distribution image; Establish an image enhancement model, and determine the target α parameter and the target β parameter in the image enhancement model based on the fitness function; Based on the image enhancement model, the pulse sequence phase distribution image is adaptively enhanced to obtain an enhanced pulse sequence phase distribution image; Determine the type of partial discharge defect based on the enhanced pulse sequence phase distribution image; The image enhancement model is a non-complete Beta function; Determining the target α parameter and the target β parameter in the image enhancement model based on the fitness function includes: Acquire a parameter pair set, wherein the parameter pair set includes at least two parameter pairs, and the parameter pairs include: an α parameter and a β parameter; Determine the fitness corresponding to each parameter pair in the parameter pair set based on the fitness function; The parameter pair with the maximum fitness is determined as the target α parameter and the target β parameter; The determining the fitness corresponding to each parameter pair in the parameter pair set based on the fitness function includes: Obtain the structural similarity between the enhanced image and the image before enhancement corresponding to the parameter pair; Obtain the entropy value and grayscale standard deviation of the enhanced image corresponding to the parameter pair; The fitness of the parameter pair is determined according to the entropy value of the enhanced image, the grayscale standard deviation and the structural similarity between the enhanced image and the image before enhancement.

2. The method according to claim 1, characterized in that Adaptively enhancing the pulse sequence phase distribution image based on the image enhancement model to obtain an enhanced pulse sequence phase distribution image, including: Convert the pulse sequence phase distribution image into double format to obtain a first image; Adaptive image enhancement is performed on the first image based on the image enhancement model to obtain an enhanced pulse sequence phase distribution image.

3. The method according to claim 1, characterized in that Determine the target α parameter and the target β parameter based on the fitness function, including: Get initial α parameters and initial β parameters; Determine the initial position of the moth according to the initial α parameter and the initial β parameter; Generate a moth matrix based on the initial positions of the moths; Determine the fitness corresponding to each moth in the moth matrix based on the fitness function; The target α parameter and the target β parameter are determined according to the position corresponding to the moth with the largest fitness.

4. The method according to claim 1, characterized in that Determine the type of partial discharge defects based on the enhanced pulse sequence phase distribution image, including: Determine the local discharge characteristic parameters based on the enhanced pulse sequence phase distribution image; The local discharge characteristic parameters are input into the target model to obtain the local discharge defect type.

5. A partial discharge defect type identification device, which passes voltage into a GIS experimental chamber to cause a target defect object in the GIS experimental chamber to undergo partial discharge, characterized in that: include: An acquisition module, used for acquiring partial discharge signals of target defective objects; A conversion module, used for converting a partial discharge signal into a pulse sequence phase distribution image; A model building module is used to build an image enhancement model and determine a target α parameter and a target β parameter in the image enhancement model based on a fitness function; An image enhancement module, used for performing adaptive image enhancement on the pulse sequence phase distribution image based on an image enhancement model to obtain an enhanced pulse sequence phase distribution image; A type determination module, used for determining the type of partial discharge defect based on the enhanced pulse sequence phase distribution image; The image enhancement model is a non-complete Beta function; The model building module comprises: A first acquisition unit is used to acquire a parameter pair set, wherein the parameter pair set includes at least two parameter pairs, and the parameter pairs include: an α parameter and a β parameter; A first determining unit, configured to determine the fitness corresponding to each parameter pair in the parameter pair set based on the fitness function; A second determination unit is used to determine the parameter pair with the maximum fitness as the target α parameter and the target β parameter; The first determining unit is specifically configured to: Obtain the structural similarity between the enhanced image and the image before enhancement corresponding to the parameter pair; Obtain the entropy value and grayscale standard deviation of the enhanced image corresponding to the parameter pair; The fitness of the parameter pair is determined according to the entropy value of the enhanced image, the grayscale standard deviation and the structural similarity between the enhanced image and the image before enhancement.

6. The device according to claim 5, characterized in that Image enhancement module, including: A conversion unit, used for converting the pulse sequence phase distribution image into a double format to obtain a first image; The image enhancement unit is used to perform adaptive image enhancement on the first image based on the image enhancement model to obtain an enhanced pulse sequence phase distribution image.

7. The device according to claim 5, characterized in that The model building module also includes: A second acquisition unit is used to acquire an initial α parameter and an initial β parameter; A third determining unit is used to determine the initial position of the moth according to the initial α parameter and the initial β parameter; A generating unit, used for generating a moth matrix according to an initial position of the moth; A fourth determining unit, used for determining the fitness corresponding to each moth in the moth matrix based on the fitness function; The fifth determining unit is used to determine the target α parameter and the target β parameter according to the position corresponding to the moth with the largest fitness.

8. The device according to claim 5, characterized in that Type determination module, specifically used for: Determine the local discharge characteristic parameters based on the enhanced pulse sequence phase distribution image; The local discharge characteristic parameters are input into the target model to obtain the local discharge defect type.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the partial discharge defect type identification method according to any one of claims 1 to 4.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the partial discharge defect type identification method according to any one of claims 1 to 4 when executed.

Images