Defect detection method, device, equipment, medium and product

Abstract

The invention discloses a defect detection method, device and equipment, a medium and a product. The method comprises the steps that if it is detected that target GIS equipment breaks down, original defect signals corresponding to the target GIS equipment are preprocessed, so that effective signal components are obtained; based on a preset feature extraction method, carrying out extraction processing on the effective signal component, and determining an energy moment feature corresponding to the effective signal component; and according to the energy moment characteristics, based on a pre-trained target defect detection model, determining a defect type corresponding to the target GIS equipment so as to realize defect detection. According to the technical scheme provided by the invention, the original defect signal is identified and detected by using the target defect detection model, the defect type of the GIS equipment can be rapidly and accurately identified, and the maintenance of the GIS equipment is assisted, so that the operation safety of the equipment is guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment maintenance, and in particular to a defect detection method, device, equipment, medium and product. Background Art

[0002] Gas insulated switchgear (GIS) has been widely recognized by the power industry due to its advantages such as small size, convenient maintenance, high reliability and strong environmental adaptability. However, with the increase in installed capacity and operating time of GIS equipment in recent years, various abnormalities and failures will inevitably occur in the equipment. Due to the sealing of GIS equipment, when an abnormality occurs inside the equipment, it is difficult to detect it in time through human senses. In addition, GIS equipment has many components, complex structure and various fault types, which increases the difficulty of defect detection.

[0003] Therefore, how to quickly and accurately identify the defect types of GIS equipment and assist in the maintenance of GIS equipment to ensure the safe operation of equipment is a problem that needs to be solved urgently. Summary of the invention

[0004] The present invention provides a defect detection method, device, equipment, medium and product to quickly and accurately identify the defect type of GIS equipment, assist in GIS equipment maintenance, and thus ensure the safe operation of the equipment.

[0005] According to one aspect of the present invention, there is provided a defect detection method, comprising:

[0006] If a fault is detected in the target gas-insulated metal-enclosed switch GIS device, the original defect signal corresponding to the target GIS device is preprocessed to obtain an effective signal component;

[0007] Based on a preset feature extraction method, the effective signal component is extracted and processed to determine the energy moment feature corresponding to the effective signal component;

[0008] According to the energy moment characteristics, based on the pre-trained target defect detection model, the defect type corresponding to the target GIS equipment is determined to achieve defect detection.

[0009] According to another aspect of the present invention, there is provided a defect detection device, comprising:

[0010] A processing module, for preprocessing an original defect signal corresponding to the target gas-insulated metal-enclosed switchgear GIS device to obtain an effective signal component if a fault is detected in the target GIS device;

[0011] A determination module, used to extract and process effective signal components based on a preset feature extraction method, and determine energy moment features corresponding to the effective signal components;

[0012] The detection module is used to determine the defect type corresponding to the target GIS equipment according to the energy moment characteristics and based on the pre-trained target defect detection model to achieve defect detection.

[0013] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0014] at least one processor; and

[0015] a memory communicatively connected to the at least one processor; wherein,

[0016] 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 defect detection method described in any embodiment of the present invention.

[0017] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the defect detection method described in any embodiment of the present invention when executed.

[0018] According to another aspect of the present invention, a computer program product is provided. The computer program product includes a computer program. When the computer program is executed by a processor, the defect detection method of any embodiment of the present invention is implemented.

[0019] The technical solution of the embodiment of the present invention is that if a fault is detected in the target gas-insulated metal-enclosed switch GIS device, the original defect signal corresponding to the target GIS device is preprocessed to obtain an effective signal component; based on a preset feature extraction method, the effective signal component is extracted and processed to determine the energy moment feature corresponding to the effective signal component; according to the energy moment feature, based on a pre-trained target defect detection model, the defect type corresponding to the target GIS device is determined to achieve defect detection. By using the target defect detection model to identify and detect the original defect signal, the defect type of the GIS equipment can be quickly and accurately identified, and the GIS equipment maintenance can be assisted, thereby ensuring the safe operation of the equipment.

[0020] 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

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0022] Figure 1 is a flow chart of a defect detection method provided by Embodiment 1 of the present invention;

[0023] Figure 2 is a flow chart of a defect detection method provided by Embodiment 2 of the present invention;

[0024] Figure 3 is a structural block diagram of a defect detection device provided by Embodiment 3 of the present invention;

[0025] Figure 4 It is a schematic diagram of the structure of an electronic device provided in Embodiment 4 of the present invention. DETAILED DESCRIPTION

[0026] 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.

[0027] It should be noted that the terms "first", "second", "target", "candidate", "alternative", 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 interchangeable 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. The acquisition, storage, use, processing, etc. of data in the technical solution of this application comply with the relevant provisions of national laws and regulations.

[0028] Embodiment 1

[0029] Figure 1is a flow chart of a defect detection method provided in the first embodiment of the present invention; this embodiment can be applied to the situation where the defect signal of the gas-insulated metal-enclosed switchgear is analyzed to identify the defect category so as to facilitate the subsequent maintenance operation. The method can be executed by a defect detection device, which can be implemented in the form of hardware and / or software. The defect detection device can be configured in an electronic device, such as an electronic device with a defect detection function, and executed by a power system, such as Figure 1 As shown, the defect detection method includes:

[0030] S101. If a target gas-insulated metal-enclosed switch GIS device is detected to have a fault, an original defect signal corresponding to the target GIS device is preprocessed to obtain an effective signal component.

[0031] The target gas insulated metal-enclosed switchgear (GIS) refers to the GIS equipment under the management of the power system, the original defect signal refers to the vibration signal when the target GIS equipment fails, and the original defect signal can specifically be a GIS mechanical defect signal. The effective signal component refers to the signal component whose similarity with the original signal reaches a threshold value among the candidate signal components after the original defect signal is decomposed.

[0032] Optionally, the target GIS equipment may produce equipment mechanical vibration defects during operation. When the power system detects the original defect signal emitted by the target GIS equipment, it can consider that the target gas-insulated metal-enclosed switch GIS equipment has failed, and decompose and filter the original defect signal to obtain the effective signal component corresponding to the original defect signal.

[0033] Optionally, the original defect signal corresponding to the target GIS equipment is preprocessed to obtain effective signal components, including: decomposing the original defect signal based on the adaptive noise complete ensemble empirical mode decomposition ICEEMDAN method to obtain at least two candidate signal components; determining the mutual correlation coefficient between each candidate signal component and the original defect signal, and determining the effective signal component from the candidate signal components based on the mutual correlation coefficient.

[0034] Among them, the Improved Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (ICEEMDAN) algorithm is a preset signal decomposition algorithm, which is based on the EMD (Empirical Mode Decomposition) algorithm and introduces adaptive noise and complete integration strategy, which can effectively improve the stability and accuracy of signal decomposition. The candidate signal component is obtained by decomposing the original defect signal. The mutual correlation coefficient refers to the coefficient that can characterize the similarity between the candidate signal component and the original defect signal. The effective signal component refers to the signal component in the candidate signal component whose similarity with the original defect signal meets the conditions.

[0035] Optionally, based on the adaptive noise complete ensemble empirical mode decomposition ICEEMDAN method, the original defect signal is decomposed and processed to obtain at least two candidate signal components, including: adding white noise to the original defect signal to obtain the signal to be decomposed, and processing the signal to be decomposed based on the ICEEMDAN method to obtain residual terms of different orders; determining the inherent mode function of the current order according to the residual terms of the current order and the residual terms of the previous order, so as to obtain the inherent mode functions of different orders corresponding to the signal to be decomposed; and determining at least two candidate signal components according to the values ​​of the inherent mode functions of different orders.

[0036] Among them, the candidate signal components can be, for example, IMF components. The intrinsic mode function (IMF) is also called the intrinsic mode function. The signal can be decomposed into at least two intrinsic mode functions, that is, at least two IMF components, by the EMD (Empirical Mode Decomposition) algorithm.

[0037] Optionally, the difference between the current order residual term and the previous order residual term may be determined as the intrinsic mode function of the current order.

[0038] For example, white noise E1[w i ]The signal to be decomposed can be expressed by the following formula:

[0039] X( i )=X+β0E1[w i ]

[0040] Among them, X (i) is the signal to be decomposed. X represents the original signal; β0 is the weight coefficient of the 0th Gaussian white noise; [w i] is the i-th Gaussian white noise added. E1 is the first component of the EMD decomposed white noise.

[0041] Furthermore, the original defect signal can be decomposed based on the following formula to obtain the first-order IMF component:

[0042] R1= <M[X i ]>

[0043] IMF1=X-R1

[0044] Where R1 is the first residual term, IMF1 is the first IMF component, and M is the local mean of the signal. i is the signal to be decomposed, and X is the original signal. <> is to find the overall mean, that is, X i First find the local mean, and then use the results of the local mean to find the overall mean to obtain R1.

[0045] Furthermore, the second residual term R2 can be obtained based on the following formula:

[0046] R2= <M{R1+β1E2[w i ]}>

[0047] Among them, β1 is the first Gaussian white noise weight coefficient, which can be the coefficient multiplied when adding the noise component. β1 and β0 have different values. R1 is the first residual term, and R2 is the second residual term. M is the local mean of the signal. <> is the overall mean, [w i ] is the i-th Gaussian white noise added. E2 is the second component of the EMD decomposed white noise.

[0048] Furthermore, based on the first residual term and the second residual term, the difference between the two can be determined as the second-order intrinsic mode function, expressed as:

[0049] IMF2=R1-R2

[0050] Among them, IMF2 is the second IMF component, that is, the second-order intrinsic mode function. R1 is the first residual term, and R2 is the second residual term.

[0051] By analogy, the hth residual term and solid mode function can be expressed as:

[0052] R h = <M{R h-1 +β h-1 ·E h [w i ]}>

[0053] IMF h =Rh-1 -R h

[0054] Among them, R h and R h-1 are the hth and h-1th residual terms, and IMFh is the hth IMF component. Finally, the decomposition of the original signal is completed, and all IMFs of signal X are obtained. h-1 is the weight coefficient of the h-1th Gaussian white noise, and M is the local mean of the signal. i ] is the i-th Gaussian white noise added. E h is the hth component of the EMD decomposed white noise.

[0055] Optionally, the signal to be decomposed may be decomposed to obtain intrinsic mode functions corresponding to different orders, and then the values ​​of the intrinsic mode functions of different orders are respectively determined as candidate signal components to obtain at least two candidate signal components.

[0056] Optionally, a mutual correlation coefficient between each candidate signal component and the original defect signal is determined, and based on the mutual correlation coefficient, a valid signal component is determined from the candidate signal components, including: determining the mutual correlation coefficient between each candidate signal component and the original defect signal according to a preset similarity calculation rule; if the mutual correlation coefficient is greater than a preset coefficient threshold, determining the corresponding candidate signal component as a valid signal component.

[0057] The similarity calculation rule may be, for example, a cosine similarity calculation rule. The mutual correlation coefficient may be, for example, the similarity between each candidate signal component and the original defect signal. The preset coefficient threshold may be, for example, 0.1.

[0058] It should be noted that, since the correlation between each IMF component and the original defect signal is different, the components are screened by obtaining the mutual correlation coefficient between the two to eliminate the interference caused by irrelevant signals.

[0059] Exemplarily, the mutual correlation coefficient between the candidate signal component and the original defect signal may be determined based on the following formula:

[0060]

[0061] Among them, xi is the original defect signal, yi is the candidate signal component, and are the means of the original defect signal xi and the candidate signal component yi, respectively, xy is the cross-correlation coefficient between the candidate signal component and the original defect signal.

[0062] S102: extract and process the effective signal component based on a preset feature extraction method to determine the energy moment feature corresponding to the effective signal component.

[0063] The preset feature extraction method is a feature extraction method that considers the time scale, such as an energy moment extraction method. Compared with the simple feature extraction method based on energy, the energy moment extraction method can better characterize the original defect signal. The energy moment feature refers to the feature vector obtained by extracting the energy moment of the effective signal component.

[0064] Exemplarily, the energy moment feature corresponding to the effective signal component may be determined based on the following formula:

[0065]

[0066] Where Δt is the sampling period, D k,j is the amplitude of the k-th order intrinsic mode function at the j-th discrete point, n is the number of sampling points. Ek is the energy moment characteristic corresponding to the effective signal component.

[0067] S103. According to the energy moment characteristics, based on a pre-trained target defect detection model, determine the defect type corresponding to the target GIS equipment to achieve defect detection.

[0068] Among them, the target defect detection model is the Kernel Extreme Learning Machine (KELM), which improves the classification accuracy by introducing the kernel function into the extreme learning machine. Its essence is the training algorithm of the single hidden layer forward neural network. The regularization coefficient and kernel parameter of the target defect detection model are obtained by genetic algorithm optimization. The defect types are the grinding of the disconnector contact finger, the loosening of the shield cover bolts, the loosening of the bellows bolts or normal without defects.

[0069] Exemplarily, the target defect detection model can be preliminarily expressed by the following formula:

[0070] y(x)=h(x)·β=H·β

[0071] Among them, y(x) is the output of the target defect detection model; x is the energy moment feature; β is the hidden layer output layer link weight; H is the hidden layer output matrix of the target defect detection model. H=h(x)=[h1(x),h2(x),h3(x),…] T , each h i (x) represents the output of the i-th hidden layer node.

[0072] Exemplarily, the hidden layer output layer link weight β can be expressed by the following formula:

[0073] β=H T(HH T +ηI) -1 T

[0074] Where H is the hidden layer output matrix of the target defect detection model. η is the regularization coefficient; T is the class sign vector corresponding to the energy moment feature. I is the identity matrix. β is the hidden layer output layer link weight.

[0075] Exemplarily, combined with the preset kernel function, the preliminary representation formula of the target defect detection model can be converted into the following final form:

[0076]

[0077] Among them, y(x) is the output of the target defect detection model; K(x,xi) is the preset kernel function. ELM =HH T , H is the hidden layer output matrix of the target defect detection model. η is the regularization coefficient; I is the unit matrix. T is the class mark vector corresponding to the energy moment feature.

[0078] The preset kernel function K(x,xi) may be, for example, an RBF kernel function, which is expressed as:

[0079]

[0080] Among them, δ is the kernel parameter, ||xx i || 2 Represents the sum of squared distances between energy moment features.

[0081] Optionally, the energy moment feature can be input into a pre-trained target defect detection model to obtain an output class flag vector. According to the class flag vector, combined with the correspondence between the preset defect type and the class flag vector value, the defect type corresponding to the target GIS device is determined.

[0082] Optionally, a kernel extreme learning machine algorithm can be used to construct an initial defect detection model. According to the sample feature set, the regularization coefficient η and the kernel parameter δ of the initial defect detection model can be optimized based on a genetic algorithm to train the initial defect model and obtain a target defect detection model.

[0083] Optionally, a pre-trained target defect detection model can be used to classify the defect types of the target GIS equipment to achieve defect detection of GIS machinery.

[0084] Optionally, according to the energy moment characteristics and based on a pre-trained target defect detection model, before determining the defect type corresponding to the target GIS device, a sample feature set can be generated by analyzing the historical defect signals, so as to train the target defect detection module. Specifically, the method includes: determining the historical defect signals of the target GIS device and their corresponding historical valid signal components; extracting and processing the historical valid signal components based on a feature extraction method that considers the time scale, and generating a sample feature set based on the extracted historical energy moments and the defect types corresponding to the historical defect signals; dividing the sample feature set into a training set and a validation set, and optimizing the regularization coefficient and kernel parameter of the target defect detection model through a genetic algorithm to train the target defect detection model.

[0085] Among them, the historical energy moment is a component of the sample feature set.

[0086] It should be noted that the method for determining the historical valid signal component corresponding to the historical defect signal is the same as the method for determining the valid signal component corresponding to the original defect signal in the above embodiment of the present invention, and the present invention will not be repeated here.

[0087] Optionally, according to the sample feature set, it can be divided into a training set and a validation set in a ratio of 2:1 to train the initial defect detection model and obtain a target defect detection model.

[0088] Optionally, considering that the regularization coefficient η and the kernel parameter δ are important factors affecting the KELM classification, a genetic algorithm (GA) can be introduced to optimize the regularization coefficient η and the kernel parameter δ, and the optimization result is substituted into the target defect detection model to identify the accurate defect type.

[0089] The technical solution of the embodiment of the present invention is that if a fault is detected in the target gas-insulated metal-enclosed switch GIS device, the original defect signal corresponding to the target GIS device is preprocessed to obtain an effective signal component; based on a preset feature extraction method, the effective signal component is extracted and processed to determine the energy moment feature corresponding to the effective signal component; according to the energy moment feature, based on a pre-trained target defect detection model, the defect type corresponding to the target GIS device is determined to achieve defect detection. By using the target defect detection model to identify and detect the original defect signal, the defect type of the GIS equipment can be quickly and accurately identified, and the GIS equipment maintenance can be assisted, thereby ensuring the safe operation of the equipment.

[0090] Embodiment 2

[0091] Figure 2It is a flow chart of a defect detection method provided in the second embodiment of the present invention; based on the above embodiment, this embodiment provides a preferred solution for analyzing the original defect signal of the target GIS equipment by using a target defect detection model to perform defect detection.

[0092] Specifically, Figure 2 As shown, the method may include:

[0093] S201. If a fault is detected in the target gas-insulated metal-enclosed switchgear GIS device, white noise is added to the original defect signal to obtain a signal to be decomposed, and the signal to be decomposed is processed based on the ICEEMDAN method to obtain residual items of different orders.

[0094] S202 , determining the intrinsic mode function of the current order according to the residual term of the current order and the residual term of the previous order, thereby obtaining the intrinsic mode functions of different orders corresponding to the signal to be decomposed.

[0095] S203: Determine at least two candidate signal components according to the values ​​of intrinsic mode functions of different orders.

[0096] S204: Determine the correlation coefficient between each candidate signal component and the original defect signal according to a preset similarity calculation rule.

[0097] S205: If the mutual correlation coefficient is greater than a preset coefficient threshold, the corresponding candidate signal component is determined as a valid signal component.

[0098] S206. Based on a preset feature extraction method, extract and process the effective signal components, determine the energy moment characteristics corresponding to the effective signal components, and determine the historical defect signals of the target GIS equipment and their corresponding historical effective signal components.

[0099] S207. Based on a feature extraction method that takes time scale into consideration, extract and process historical effective signal components, and generate a sample feature set based on the extracted historical energy moments and the defect types corresponding to the historical defect signals.

[0100] S208, dividing the sample feature set into a training set and a validation set, optimizing the regularization coefficient and kernel parameter of the target defect detection model through a genetic algorithm, and training the target defect detection model.

[0101] S209. According to the energy moment characteristics and based on the trained target defect detection model, the defect type corresponding to the target GIS equipment is determined to achieve defect detection.

[0102] Embodiment 3

[0103] Figure 3is a structural block diagram of a defect detection device provided in the third embodiment of the present invention; this embodiment can be applied to the situation where the defect signal of the gas-insulated metal-enclosed switchgear is analyzed to identify the defect category so as to facilitate the subsequent maintenance operation. The defect detection device provided in the embodiment of the present invention can execute the defect detection method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method; the defect detection device can be implemented in the form of hardware and / or software, and configured in an electronic device with a defect detection function, such as an electronic device with a defect detection function, such as Figure 3 As shown, the defect detection device specifically includes:

[0104] The processing module 301 is used to pre-process the original defect signal corresponding to the target GIS device to obtain an effective signal component if a fault is detected in the target GIS device;

[0105] A determination module 302 is used to extract and process the effective signal component based on a preset feature extraction method to determine the energy moment feature corresponding to the effective signal component;

[0106] The detection module 303 is used to determine the defect type corresponding to the target GIS device according to the energy moment characteristics and based on a pre-trained target defect detection model to achieve defect detection.

[0107] The technical solution of the embodiment of the present invention is that if a fault is detected in the target gas-insulated metal-enclosed switch GIS device, the original defect signal corresponding to the target GIS device is preprocessed to obtain an effective signal component; based on a preset feature extraction method, the effective signal component is extracted and processed to determine the energy moment feature corresponding to the effective signal component; according to the energy moment feature, based on a pre-trained target defect detection model, the defect type corresponding to the target GIS device is determined to achieve defect detection. By using the target defect detection model to identify and detect the original defect signal, the defect type of the GIS equipment can be quickly and accurately identified, and the GIS equipment maintenance can be assisted, thereby ensuring the safe operation of the equipment.

[0108] Furthermore, the processing module 301 may include:

[0109] A decomposition unit, used for decomposing the original defect signal based on an adaptive noise complete ensemble empirical mode decomposition (ICEEMDAN) method to obtain at least two candidate signal components;

[0110] The screening unit is used to determine the mutual correlation coefficient between each candidate signal component and the original defect signal, and determine the effective signal component from the candidate signal components according to the mutual correlation coefficient.

[0111] Furthermore, the decomposition unit is specifically used for:

[0112] White noise is added to the original defect signal to obtain the signal to be decomposed, and the signal to be decomposed is processed based on the ICEEMDAN method to obtain residual items of different orders;

[0113] According to the residual term of the current order and the residual term of the previous order, the intrinsic mode function of the current order is determined, so as to obtain the intrinsic mode functions of different orders corresponding to the signal to be decomposed;

[0114] At least two candidate signal components are determined according to the values ​​of the intrinsic mode functions of different orders.

[0115] Furthermore, the screening unit is specifically used for:

[0116] According to the preset similarity calculation rules, the mutual correlation coefficient between each candidate signal component and the original defect signal is determined;

[0117] If the mutual correlation coefficient is greater than a preset coefficient threshold, the corresponding candidate signal component is determined as a valid signal component.

[0118] Furthermore, the defect types are polished contacts of the isolating switch, loose bolts of the shielding cover, loose bolts of the bellows, or normal without defects; the preset feature extraction method is a feature extraction method that considers the time scale; the target defect detection model is a kernel extreme learning machine model; the regularization coefficient and kernel parameter of the target defect detection model are obtained by optimizing the genetic algorithm.

[0119] Furthermore, the above device is also used for:

[0120] Determine the historical defect signal of the target GIS equipment and its corresponding historical valid signal component;

[0121] Based on the feature extraction method considering the time scale, the historical effective signal components are extracted and processed, and the sample feature set is generated according to the extracted historical energy moment and the defect type corresponding to the historical defect signal;

[0122] The sample feature set is divided into a training set and a validation set. The regularization coefficient and kernel parameter of the target defect detection model are obtained by optimizing the genetic algorithm to train the target defect detection model.

[0123] Embodiment 4

[0124] Figure 4 is a schematic diagram of the structure of an electronic device provided by Embodiment 4 of the present invention; Figure 4A 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.

[0125] like Figure 4 As 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.

[0126] 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.

[0127] 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 defect detection method.

[0128] In some embodiments, the defect detection 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 defect detection method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the defect detection method in any other appropriate manner (e.g., by means of firmware).

[0129] 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), system-on-chips (SOCs), complex 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.

[0130] 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.

[0131] 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 conjunction 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, 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.

[0132] 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).

[0133] 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.

[0134] 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.

[0135] In one embodiment, the present invention further includes a computer program product, the computer program product includes a computer program, and the computer program implements the defect detection method of any embodiment of the present invention when executed by a processor.

[0136] In the process of implementation, the computer program product can be written in one or more programming languages ​​or a combination thereof to perform the computer program code of the present invention, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, 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 can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0137] 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.

[0138] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A defect detection method, characterized in that: include: If a fault is detected in the target gas-insulated metal-enclosed switch GIS device, the original defect signal corresponding to the target GIS device is preprocessed to obtain an effective signal component; Based on a preset feature extraction method, the effective signal component is extracted and processed to determine the energy moment feature corresponding to the effective signal component; According to the energy moment characteristics, based on the pre-trained target defect detection model, the defect type corresponding to the target GIS equipment is determined to achieve defect detection.

2. The method according to claim 1, characterized in that Preprocess the original defect signal corresponding to the target GIS equipment to obtain effective signal components, including: Based on the adaptive noise complete ensemble empirical mode decomposition (ICEEMDAN) method, the original defect signal is decomposed to obtain at least two candidate signal components; The mutual correlation coefficient between each candidate signal component and the original defect signal is determined, and the effective signal component is determined from the candidate signal components according to the mutual correlation coefficient.

3. The method according to claim 2, characterized in that Based on the adaptive noise complete ensemble empirical mode decomposition ICEEMDAN method, the original defect signal is decomposed to obtain at least two candidate signal components, including: White noise is added to the original defect signal to obtain the signal to be decomposed, and the signal to be decomposed is processed based on the ICEEMDAN method to obtain residual items of different orders; According to the residual term of the current order and the residual term of the previous order, the intrinsic mode function of the current order is determined, so as to obtain the intrinsic mode functions of different orders corresponding to the signal to be decomposed; At least two candidate signal components are determined according to the values ​​of the intrinsic mode functions of different orders.

4. The method according to claim 2, characterized in that: Determine the mutual correlation coefficient between each candidate signal component and the original defect signal, and determine the effective signal component from the candidate signal components according to the mutual correlation coefficient, including: According to the preset similarity calculation rules, the mutual correlation coefficient between each candidate signal component and the original defect signal is determined; If the mutual correlation coefficient is greater than a preset coefficient threshold, the corresponding candidate signal component is determined as a valid signal component.

5. The method according to claim 1, characterized in that in, The defect types are grinding of the disconnector contact finger, loosening of the shield cover bolts, loosening of the bellows bolts or normal without defects; The preset feature extraction method is a feature extraction method that considers the time scale; The target defect detection model is a kernel extreme learning machine model; the regularization coefficient and kernel parameter of the target defect detection model are obtained by optimizing the genetic algorithm.

6. The method according to claim 1, characterized in that According to the energy moment characteristics, based on the pre-trained target defect detection model, before determining the defect type corresponding to the target GIS equipment, it also includes: Determine the historical defect signal of the target GIS equipment and its corresponding historical valid signal component; Based on the feature extraction method considering the time scale, the historical effective signal components are extracted and processed, and the sample feature set is generated according to the extracted historical energy moment and the defect type corresponding to the historical defect signal; The sample feature set is divided into a training set and a validation set. The regularization coefficient and kernel parameter of the target defect detection model are obtained by optimizing the genetic algorithm to train the target defect detection model.

7. A defect detection device, characterized in that: include: A processing module, for preprocessing an original defect signal corresponding to the target gas-insulated metal-enclosed switchgear GIS device to obtain an effective signal component if a fault is detected in the target GIS device; A determination module, used to extract and process effective signal components based on a preset feature extraction method, and determine energy moment features corresponding to the effective signal components; The detection module is used to determine the defect type corresponding to the target GIS equipment according to the energy moment characteristics and based on the pre-trained target defect detection model to achieve defect detection.

8. 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 executed 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 defect detection method according to any one of claims 1 to 6.

9. 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 defect detection method according to any one of claims 1 to 6 when executed.

10. A computer program product, characterized in that The computer program product comprises a computer program, which, when executed by a processor, implements the defect detection method according to any one of claims 1 to 6.

Images