Power distribution cabinet and preparation method and system thereof

Abstract

The invention provides a power distribution cabinet and a preparation method and system thereof, and relates to the technical field of power distribution cabinets, and the method comprises the steps: obtaining a plurality of shot images of a to-be-detected power distribution cabinet under different ultrasonic frequencies and a standard three-dimensional image of a standard power distribution cabinet; generating a three-dimensional simulation generation image of the power distribution cabinet by using a generative adversarial network based on the plurality of shot images of the to-be-detected power distribution cabinet under different ultrasonic frequencies; constructing a graph structure; the graph structure is processed based on a graph auto-encoder to determine the visual defect degree of the power distribution cabinet to be detected; acquiring a video that the to-be-detected power distribution cabinet is knocked; based on the knocked video of the to-be-detected power distribution cabinet, using a knocked video processing model to determine the structural deformation degree of the to-be-detected power distribution cabinet; and determining whether the to-be-detected power distribution cabinet is qualified based on the visual flaw degree of the to-be-detected power distribution cabinet and the structural deformation degree of the to-be-detected power distribution cabinet. The method can quickly and accurately evaluate the quality of the power distribution cabinet.

Description

Technical Field

[0001] The present invention relates to the technical field of power distribution cabinets, and in particular to a power distribution cabinet and a preparation method and system thereof. Background Art

[0002] The switchboard is an indispensable and important equipment in the power system, which is used to distribute and control electric energy. Its quality and performance are directly related to the safety and reliability of the power grid. Therefore, it is very important to ensure the quality of the switchboard during the manufacturing process. Traditional quality inspection methods mainly rely on manual inspection and limited mechanical testing. This method is not only inefficient, but also easily affected by subjective factors, making it difficult to accurately evaluate the quality of the switchboard every time.

[0003] Therefore, how to quickly and accurately evaluate the quality of distribution cabinets is an urgent problem to be solved. Summary of the invention

[0004] The main technical problem solved by the present invention is how to quickly and accurately evaluate the quality of a power distribution cabinet.

[0005] According to a first aspect, the present invention provides a method for preparing a distribution cabinet, comprising: obtaining multiple captured images of a distribution cabinet to be detected at different ultrasonic frequencies and a standard three-dimensional image of a standard distribution cabinet; generating a three-dimensional simulated image of the distribution cabinet based on the multiple captured images of the distribution cabinet to be detected at different ultrasonic frequencies using a generative adversarial network; constructing a graph structure, the graph structure comprising two nodes and an edge between the two nodes, the two nodes comprising a detection node and a standard node, the node feature of the detection node being the three-dimensional simulated image of the distribution cabinet, the node feature of the standard node being the standard three-dimensional image of the standard distribution cabinet, and the edge between the two nodes being the similarity between the three-dimensional simulated image of the distribution cabinet and the standard three-dimensional image of the standard distribution cabinet; processing the graph structure based on a graph autoencoder to determine the visual defect degree of the distribution cabinet to be detected; obtaining a video of the distribution cabinet to be detected being knocked; determining the structural deformation degree of the distribution cabinet to be detected using a knocking video processing model based on the video of the distribution cabinet to be detected being knocked; determining whether the distribution cabinet to be detected is of qualified quality based on the visual defect degree of the distribution cabinet to be detected and the structural deformation degree of the distribution cabinet to be detected.

[0006] In a possible implementation, the tap video processing model is a gated recurrent unit.

[0007] In a possible implementation, the input of the graph autoencoder is the graph structure, and the output of the graph autoencoder is the visual defect degree of the power distribution cabinet to be detected.

[0008] In a possible implementation, determining whether the power distribution cabinet to be detected is of qualified quality based on the visual defect degree of the power distribution cabinet to be detected and the structural deformation degree of the power distribution cabinet to be detected includes: The visual defect degree of the distribution cabinet to be tested and the structural deformation degree of the distribution cabinet to be tested are weightedly summed according to predetermined weights to obtain the qualification degree of the distribution cabinet to be tested; determine whether the qualification degree of the distribution cabinet to be tested is greater than the qualification threshold; if the qualification degree of the distribution cabinet to be tested is greater than the qualification threshold, it is determined that the quality of the distribution cabinet to be tested is qualified; if the qualification degree of the distribution cabinet to be tested is less than the qualification threshold, it is determined that the quality of the distribution cabinet to be tested is unqualified.

[0009] According to a second aspect, the present invention provides a system for preparing a power distribution cabinet, comprising: a first acquisition module, for acquiring a plurality of photographed images of a power distribution cabinet to be detected at different ultrasonic frequencies and a standard three-dimensional image of a standard power distribution cabinet; A generation module, used to generate a three-dimensional simulated image of the distribution cabinet using a generative adversarial network based on a plurality of photographed images of the distribution cabinet to be detected at different ultrasonic frequencies; A construction module is used to construct a graph structure, wherein the graph structure includes two nodes and an edge between the two nodes, the two nodes include a detection node and a standard node, the node feature of the detection node is a three-dimensional simulated image of a power distribution cabinet, the node feature of the standard node is a standard three-dimensional image of a standard power distribution cabinet, and the edge between the two nodes is a similarity between the three-dimensional simulated image of the power distribution cabinet and the standard three-dimensional image of the standard power distribution cabinet; A visual defect degree determination module, used to process the graph structure based on the graph autoencoder to determine the visual defect degree of the power distribution cabinet to be detected; The second acquisition module is used to acquire a video of the distribution cabinet to be detected being knocked; A structural deformation degree determination module, used to determine the deformation degree of the power distribution cabinet to be detected by using a knocking video processing model based on a video of the power distribution cabinet to be detected being knocked; The quality determination module is used to determine whether the distribution cabinet to be detected is of qualified quality based on the visual defect degree of the distribution cabinet to be detected and the structural deformation degree of the distribution cabinet to be detected.

[0010] In a possible implementation, the tap video processing model is a gated recurrent unit.

[0011] In a possible implementation, the input of the graph autoencoder is the graph structure, and the output of the graph autoencoder is the visual defect degree of the power distribution cabinet to be detected.

[0012] In a possible implementation, the quality qualification determination module is further used to: The visual defect degree of the power distribution cabinet to be detected and the structural deformation degree of the power distribution cabinet to be detected are weighted and summed according to a predetermined weight to obtain the qualification degree of the power distribution cabinet to be detected; Determine whether the qualification of the power distribution cabinet to be tested is greater than a qualification threshold; If the qualification degree of the distribution cabinet to be detected is greater than the qualification threshold, the quality of the distribution cabinet to be detected is determined to be qualified. If the qualification degree of the distribution cabinet to be detected is less than the qualification threshold, the quality of the distribution cabinet to be detected is determined to be unqualified.

[0013] According to a third aspect, an embodiment of the present invention provides an electronic device, comprising: a processor; a memory; and a computer program; wherein the computer program is stored in the memory and configured to be executed by the processor to implement the method as described above, the method comprising: obtaining a plurality of photographed images of a distribution cabinet to be detected at different ultrasonic frequencies and a standard three-dimensional image of a standard distribution cabinet; generating a three-dimensional simulated image of the distribution cabinet using a generative adversarial network based on the plurality of photographed images of the distribution cabinet to be detected at different ultrasonic frequencies; constructing a graph structure, the graph structure comprising two nodes and an edge between the two nodes, the two nodes comprising a detection node and a standard Node, the node feature of the detection node is the three-dimensional simulated image of the distribution cabinet, the node feature of the standard node is the standard three-dimensional image of the standard distribution cabinet, and the edge between the two nodes is the similarity between the three-dimensional simulated image of the distribution cabinet and the standard three-dimensional image of the standard distribution cabinet; based on the graph autoencoder, the graph structure is processed to determine the visual defect degree of the distribution cabinet to be detected; a video of the distribution cabinet to be detected being knocked is obtained; based on the video of the distribution cabinet to be detected being knocked, a knocking video processing model is used to determine the structural deformation degree of the distribution cabinet to be detected; based on the visual defect degree of the distribution cabinet to be detected and the structural deformation degree of the distribution cabinet to be detected, it is determined whether the distribution cabinet to be detected is of qualified quality.

[0014] According to the fourth aspect, the present embodiment provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements a method for preparing a distribution cabinet provided above, the method comprising: obtaining a plurality of photographed images of a distribution cabinet to be detected at different ultrasonic frequencies and a standard three-dimensional image of a standard distribution cabinet; using a generative adversarial network to generate a three-dimensional simulated image of the distribution cabinet based on the plurality of photographed images of the distribution cabinet to be detected at different ultrasonic frequencies; constructing a graph structure, the graph structure comprising two nodes and an edge between the two nodes, the two nodes comprising a detection node and a standard node, and the node of the detection node The feature is a three-dimensional simulated image of a distribution cabinet, the node feature of a standard node is a standard three-dimensional image of a standard distribution cabinet, and the edge between two nodes is the similarity between the three-dimensional simulated image of a distribution cabinet and the standard three-dimensional image of a standard distribution cabinet; the graph structure is processed based on a graph autoencoder to determine the visual defect degree of the distribution cabinet to be detected; a video of the distribution cabinet to be detected being knocked is obtained; based on the video of the distribution cabinet to be detected being knocked, a knocking video processing model is used to determine the structural deformation degree of the distribution cabinet to be detected; based on the visual defect degree of the distribution cabinet to be detected and the structural deformation degree of the distribution cabinet to be detected, it is determined whether the distribution cabinet to be detected is of qualified quality.

[0015] The present invention provides a power distribution cabinet and a preparation method and system thereof. The method comprises obtaining a plurality of photographed images of a power distribution cabinet to be detected at different ultrasonic frequencies and a standard three-dimensional image of a standard power distribution cabinet; using a generative adversarial network to generate a three-dimensional simulated generated image of the power distribution cabinet based on the plurality of photographed images of the power distribution cabinet to be detected at different ultrasonic frequencies; constructing a graph structure, wherein the graph structure comprises two nodes and edges between the two nodes, the two nodes comprise a detection node and a standard node, the node feature of the detection node is the three-dimensional simulated generated image of the power distribution cabinet, and the node feature of the standard node is the standard Quasi-three-dimensional image, the edge between two nodes is the similarity between the three-dimensional simulation image of the distribution cabinet and the standard three-dimensional image of the standard distribution cabinet; based on the graph autoencoder, the graph structure is processed to determine the visual defect degree of the distribution cabinet to be detected; a video of the distribution cabinet to be detected being knocked is obtained; based on the video of the distribution cabinet to be detected being knocked, a knocking video processing model is used to determine the structural deformation degree of the distribution cabinet to be detected; based on the visual defect degree of the distribution cabinet to be detected and the structural deformation degree of the distribution cabinet to be detected, whether the distribution cabinet to be detected is of qualified quality is determined, and how this method can quickly and accurately evaluate the quality of the distribution cabinet. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A schematic diagram of an application scenario of a method for preparing a power distribution cabinet provided in an embodiment of the present invention; Figure 2 A schematic diagram of a process for preparing a power distribution cabinet provided in an embodiment of the present invention; Figure 3 A schematic diagram of a system for preparing a power distribution cabinet provided by an embodiment of the present invention; Figure 4 A schematic diagram of an electronic device provided by an embodiment of the present invention; Figure 5 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0017] The present invention is further described in detail below by specific embodiments in conjunction with the accompanying drawings. Wherein similar elements in different embodiments adopt associated similar element numbers. In the following embodiments, many detailed descriptions are for making the present invention better understood. However, those skilled in the art can easily recognize that some features can be omitted in different situations, or can be replaced by other elements, materials, methods. In some cases, some operations related to the present invention are not shown or described in the specification, this is to avoid the core part of the present invention being overwhelmed by too much description, and for those skilled in the art, it is not necessary to describe these related operations in detail, and they can fully understand the related operations according to the description in the specification and the general technical knowledge in the art.

[0018] Figure 1 A schematic diagram of an application scenario of a method for preparing a power distribution cabinet provided in an embodiment of the present invention. Figure 1 An application scenario of a method for preparing a power distribution cabinet may include a server 11, a network 12, a terminal 13 and a storage device 14.

[0019] In some embodiments, the server 11 may be a single server or a server group. The server 11 may access information and / or data stored in the terminal 13 or the storage device 14 through the network 12. In some embodiments, the server 11 may be used to execute Figure 2 A method for preparing a distribution cabinet is shown in .

[0020] The network 12 may facilitate the exchange of information and / or data. In some embodiments, the network 12 may be any form of wired or wireless network, or any combination thereof.

[0021] Terminal 13 may refer to one or more terminal devices used by a user. In some embodiments, terminal 13 may include one or more combinations of a mobile device, a tablet computer, a laptop computer, and the like.

[0022] The storage device 14 may store data and / or instructions. For example, the storage device 14 may store data instructions of a method for preparing a power distribution cabinet.

[0023] In an embodiment of the present invention, there is provided Figure 2 A method for preparing a power distribution cabinet is shown, and the method for preparing a power distribution cabinet comprises steps S1 to S7: Step S1, obtaining a plurality of images of the distribution cabinet to be inspected at different ultrasonic frequencies and a standard three-dimensional image of a standard distribution cabinet.

[0024] Different ultrasound frequencies can penetrate to different depths in a material, thereby capturing more information about the internal structure.

[0025] A series of two-dimensional images generated by the power distribution cabinet at each ultrasonic frequency are multiple images captured at different ultrasonic frequencies.

[0026] The standard 3D image of the standard distribution cabinet is an accurate 3D image artificially constructed in advance for comparative analysis.

[0027] Step S2: Generate a three-dimensional simulated image of the distribution cabinet using a generative adversarial network based on a plurality of images captured at different ultrasonic frequencies of the distribution cabinet to be detected.

[0028] The Generative Adversarial Network consists of a generator and a discriminator. The generator tries to create realistic data samples, while the discriminator tries to distinguish whether these generated data samples are real. The two compete with each other, and through iterative training, the generator can eventually generate highly realistic data. The input of the Generative Adversarial Network is multiple images of the distribution cabinet to be tested at different ultrasonic frequencies, and the output of the Generative Adversarial Network is a three-dimensional simulated image of the distribution cabinet.

[0029] The three-dimensional simulated image is a three-dimensional simulated image of a distribution cabinet generated by a generative adversarial network based on multiple images of the distribution cabinet to be detected at different ultrasonic frequencies.

[0030] Different ultrasonic frequencies can penetrate different depths of the material, thus capturing multi-level information about the internal and external structure of the switchboard. High-frequency ultrasound (such as 5MHz) can provide finer surface details, while low-frequency ultrasound (such as 20kHz) can penetrate deeper and reveal the internal structure. By combining images of multiple frequencies, more comprehensive information can be obtained.

[0031] The 3D simulation of the switchboard generates an image that provides a more intuitive and comprehensive visual reference, helping to detect subtle defects or anomalies, such as cracks and uneven thickness, which may not be easily detected in 2D images.

[0032] Step S3, constructing a graph structure, wherein the graph structure includes two nodes and an edge between the two nodes, the two nodes include a detection node and a standard node, the node feature of the detection node is a three-dimensional simulated image generated by the distribution cabinet, the node feature of the standard node is a standard three-dimensional image of the standard distribution cabinet, and the edge between the two nodes is the similarity between the three-dimensional simulated image generated by the distribution cabinet and the standard three-dimensional image of the standard distribution cabinet.

[0033] A graph is a data structure consisting of nodes (vertices) and edges (edges). Each node represents an entity or state, and the edge represents the relationship between these entities.

[0034] The graph structure consists of two nodes - a detection node and a standard node, and an edge between them.

[0035] In some embodiments, the similarity between the three-dimensional simulated image of the power distribution cabinet and the standard three-dimensional image of the standard power distribution cabinet can be determined by a deep neural network model. The input of the deep neural network model is the three-dimensional simulated image of the power distribution cabinet and the standard three-dimensional image of the standard power distribution cabinet, and the output of the deep neural network model is the similarity between the three-dimensional simulated image of the power distribution cabinet and the standard three-dimensional image of the standard power distribution cabinet.

[0036] Step S4: Process the graph structure based on the graph autoencoder to determine the visual defect degree of the distribution cabinet to be detected.

[0037] Graph Autoencoder (GAE) is a deep learning model specifically designed to process graph-structured data. Graph Autoencoder can capture complex association patterns between nodes and reconstruct the input graph structure. The graph structure contains two nodes - detection nodes and standard nodes, and edges between them. Each node represents a specific object or state, and the edge reflects the similarity between the two objects. The graph structure can intuitively show the relationship between different images and their impact on quality, which helps to understand the relationship between each image more comprehensively and deeply. By calculating the similarity score between the 3D simulated image of the distribution cabinet and the standard 3D image (such as 0.85 means 85% similarity), and using this score as an edge, the difference between the two can be accurately measured. The graph autoencoder not only considers the information of a single node, but also the relationship between nodes (that is, the information of the edge). This allows the graph autoencoder to use both the global perspective (overall similarity) and local details (specific defect locations) for evaluation.

[0038] The input of the graph autoencoder is the graph structure, and the output of the graph autoencoder is the visual defect degree of the distribution cabinet to be detected. The visual defect degree is a quantification of the degree of defects in the appearance and structure of the distribution cabinet, and is a value between 0 and 1. The graph autoencoder can extract valuable features from the graph structure and quantify the visual defect degree.

[0039] Step S5, obtaining a video of the distribution cabinet to be detected being knocked.

[0040] The video of the distribution cabinet to be tested being struck is a video recording the dynamic changes of the distribution cabinet under stress.

[0041] Step S6, determining the structural deformation degree of the power distribution cabinet to be detected by using a knocking video processing model based on the video of the power distribution cabinet to be detected being knocked.

[0042] The knocking video processing model is a gated recurrent unit. The input of the knocking video processing model is the video of the distribution cabinet to be detected being knocked, and the output of the knocking video processing model is the structural deformation degree of the distribution cabinet to be detected. The knocking video is essentially a continuous time series data set, in which each frame has a certain correlation with the previous frame. The gated recurrent unit can capture this temporal correlation well, so as to understand the behavioral changes of the distribution cabinet during the entire knocking process.

[0043] The Gated Recurrent Unit (GRU) can effectively remember long-term information and selectively update or reset the state, which makes the GRU very suitable for processing data with time series characteristics such as videos.

[0044] In some embodiments, the knocking video processing model includes a segmentation layer, a sound stability analysis layer, a visual deformation analysis layer, and a structural deformation judgment layer. The input of the segmentation layer is the knocking video processing model, and the output of the segmentation layer is the knocking audio sequence and the knocking image sequence. The input of the sound stability analysis layer is the knocking audio sequence, and the output of the sound stability analysis layer is the stability of the knocking sound in the knocking audio sequence. The input of the visual deformation analysis layer is the knocking image sequence, and the output of the visual deformation analysis layer is the deformation of the distribution cabinet to be detected during the knocking process. The input of the structural deformation judgment layer is the stability of the knocking sound in the knocking audio sequence and the deformation of the distribution cabinet to be detected during the knocking process. The output of the structural deformation judgment layer is the structural deformation of the distribution cabinet to be detected.

[0045] Step S7, determining whether the power distribution cabinet to be inspected is of qualified quality based on the visual defect degree of the power distribution cabinet to be inspected and the structural deformation degree of the power distribution cabinet to be inspected.

[0046] In some embodiments, the visual defect degree of the distribution cabinet to be inspected and the structural deformation degree of the distribution cabinet to be inspected can be weighted and summed according to predetermined weights to obtain the qualification degree of the distribution cabinet to be inspected; judge whether the qualification degree of the distribution cabinet to be inspected is greater than the qualification threshold; if the qualification degree of the distribution cabinet to be inspected is greater than the qualification threshold, it is determined that the quality of the distribution cabinet to be inspected is qualified; if the qualification degree of the distribution cabinet to be inspected is less than the qualification threshold, it is determined that the quality of the distribution cabinet to be inspected is unqualified.

[0047] Based on the same inventive concept, Figure 3 A schematic diagram of a system for preparing a power distribution cabinet provided in an embodiment of the present invention, wherein the system for preparing a power distribution cabinet comprises: A first acquisition module 31 is used to acquire a plurality of images of the distribution cabinet to be detected at different ultrasonic frequencies and a standard three-dimensional image of a standard distribution cabinet; A generating module 32, configured to generate a three-dimensional simulated image of the power distribution cabinet using a generative adversarial network based on a plurality of images captured at different ultrasonic frequencies of the power distribution cabinet to be detected; A construction module 33 is used to construct a graph structure, wherein the graph structure includes two nodes and an edge between the two nodes, wherein the two nodes include a detection node and a standard node, wherein the node feature of the detection node is a three-dimensional simulated image of a power distribution cabinet, the node feature of the standard node is a standard three-dimensional image of a standard power distribution cabinet, and the edge between the two nodes is a similarity between the three-dimensional simulated image of the power distribution cabinet and the standard three-dimensional image of the standard power distribution cabinet; A visual defect degree determination module 34, configured to process the graph structure based on a graph autoencoder to determine the visual defect degree of the power distribution cabinet to be detected; The second acquisition module 35 is used to acquire a video of the distribution cabinet to be detected being knocked; A structural deformation degree determination module 36, configured to determine the deformation degree of the power distribution cabinet to be detected using a knocking video processing model based on the video of the power distribution cabinet to be detected being knocked; The quality qualification determination module 37 is used to determine whether the distribution cabinet to be detected is of qualified quality based on the visual defect degree of the distribution cabinet to be detected and the structural deformation degree of the distribution cabinet to be detected.

[0048] Based on the same inventive concept, an embodiment of the present invention provides an electronic device, such as Figure 4 As shown, including: The invention comprises: a processor 41; a memory 42; and a computer program; wherein the computer program is stored in the memory 42 and is configured to be executed by the processor 41 to implement a method for preparing a power distribution cabinet as provided above, the method comprising: obtaining a plurality of photographed images of the power distribution cabinet to be detected at different ultrasonic frequencies and a standard three-dimensional image of a standard power distribution cabinet; using a generative adversarial network to generate a three-dimensional simulated image of the power distribution cabinet based on the plurality of photographed images of the power distribution cabinet to be detected at different ultrasonic frequencies; constructing a graph structure, the graph structure comprising two nodes and an edge between the two nodes, the two nodes comprising a detection node and a standard node, The node feature of the detection node is the three-dimensional simulated image of the distribution cabinet, the node feature of the standard node is the standard three-dimensional image of the standard distribution cabinet, and the edge between the two nodes is the similarity between the three-dimensional simulated image of the distribution cabinet and the standard three-dimensional image of the standard distribution cabinet; the graph structure is processed based on the graph autoencoder to determine the visual defect degree of the distribution cabinet to be detected; a video of the distribution cabinet to be detected being knocked is obtained; based on the video of the distribution cabinet to be detected being knocked, a knocking video processing model is used to determine the structural deformation degree of the distribution cabinet to be detected; based on the visual defect degree of the distribution cabinet to be detected and the structural deformation degree of the distribution cabinet to be detected, it is determined whether the distribution cabinet to be detected is of qualified quality.

[0049] Based on the same inventive concept, this embodiment provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor 41, implements a method for preparing a distribution cabinet provided above, the method comprising: obtaining a plurality of captured images of a distribution cabinet to be detected at different ultrasonic frequencies and a standard three-dimensional image of a standard distribution cabinet; using a generative adversarial network to generate a three-dimensional simulated image of the distribution cabinet based on the plurality of captured images of the distribution cabinet to be detected at different ultrasonic frequencies; constructing a graph structure, the graph structure comprising two nodes and an edge between the two nodes, the two nodes comprising a detection node and a standard node, the detection node's The node feature is a three-dimensional simulated image of a distribution cabinet, the node feature of a standard node is a standard three-dimensional image of a standard distribution cabinet, and the edge between two nodes is the similarity between the three-dimensional simulated image of a distribution cabinet and the standard three-dimensional image of a standard distribution cabinet; the graph structure is processed based on a graph autoencoder to determine the visual defect degree of the distribution cabinet to be detected; a video of the distribution cabinet to be detected being knocked is obtained; based on the video of the distribution cabinet to be detected being knocked, a knocking video processing model is used to determine the structural deformation degree of the distribution cabinet to be detected; based on the visual defect degree of the distribution cabinet to be detected and the structural deformation degree of the distribution cabinet to be detected, it is determined whether the distribution cabinet to be detected is of qualified quality.

[0050] A method for preparing a power distribution cabinet provided in an embodiment of the present application can be applied to terminal devices (such as mobile phones), tablet computers, laptops, ultra-mobile personal computers (UMPCs), handheld computers, netbooks, personal digital assistants (PDAs), wearable devices (such as smart watches, smart glasses or smart helmets, etc.), augmented reality (AR) and virtual reality (VR) devices, smart home devices, car computers and other electronic devices, and the embodiments of the present application do not impose any restrictions on this.

[0051] Taking the mobile phone 100 as an example of the electronic device, Figure 5 A schematic structural diagram of the mobile phone 100 is shown.

[0052] like Figure 5As shown, the mobile phone 100 may include a processing module 110, an external memory interface 120, an internal memory 121, a universal serial bus (USB) interface 130, a charging management module 140, a power management module 141, a battery 142, an antenna 1, an antenna 2, a mobile communication module 150, a wireless communication module 160, an audio module 170, a speaker 170A, a receiver 170B, a microphone 170C, an earphone interface 170D, a sensor module 180, a button 190, a motor 191, an indicator 192, a camera 193, a display screen 194, and a subscriber identification module (SIM) card interface 195, etc.

[0053] The processing module 110 may include one or more processing units, for example, the processing module 110 may include an application processor (AP), a modem processor, a graphics processor (GPU), an image signal processor (ISP), a controller, a memory, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural-network processing unit (NPU), etc. Different processing units may be independent devices or integrated into one or more processors.

[0054] The controller can be the nerve center and command center of the mobile phone 100, and is the decision maker that commands the various components of the mobile phone 100 to work in coordination according to the instructions. The controller can generate an operation control signal according to the instruction operation code and timing signal to complete the control of fetching and executing instructions.

[0055] The application processor may be installed with an operating system of the mobile phone 100, which is used to manage the hardware and software resources of the mobile phone 100. For example, it may manage and configure memory, determine the priority of system resource supply and demand, manage file systems, manage drivers, etc. The operating system may also be used to provide an operating interface for users to interact with the system. Various types of software may be installed in the operating system, such as drivers, applications (applications, apps), etc. Exemplarily, the operating system of the mobile phone 100 may be an Android system, a Linux system, etc.

[0056] A memory may also be provided in the processing module 110 for storing instructions and data. In some embodiments, the memory in the processing module 110 is a cache memory. The memory may store instructions or data that have just been used or are cyclically used by the processing module 110. If the processing module 110 needs to use the instruction or data again, it may be directly called from the memory. This avoids repeated access, reduces the waiting time of the processing module 110, and thus improves the efficiency of the system.

[0057] In some embodiments, the processing module 110 may include one or more interfaces. The interface may include an inter-integrated circuit (I2C) interface, an inter-integrated circuits sound (I2S) interface, a pulse code modulation (PCM) interface, a universal asynchronous receiver / transmitter (UART) interface, a mobile industry processor interface (MIPI), a general-purpose input / output (GPIO) interface, a subscriber identity module (SIM) interface, and / or a universal serial bus (USB) interface, etc.

[0058] The processing module 110 can be used to: obtain multiple captured images of the distribution cabinet to be detected at different ultrasonic frequencies and a standard three-dimensional image of a standard distribution cabinet; use a generative adversarial network to generate a three-dimensional simulated generated image of the distribution cabinet based on the multiple captured images of the distribution cabinet to be detected at different ultrasonic frequencies; construct a graph structure, the graph structure includes two nodes and an edge between the two nodes, the two nodes include a detection node and a standard node, the node feature of the detection node is the three-dimensional simulated generated image of the distribution cabinet, the node feature of the standard node is the standard three-dimensional image of the standard distribution cabinet, and the edge between the two nodes is the similarity between the three-dimensional simulated generated image of the distribution cabinet and the standard three-dimensional image of the standard distribution cabinet; process the graph structure based on a graph autoencoder to determine the visual defect degree of the distribution cabinet to be detected; obtain a video of the distribution cabinet to be detected being knocked; use a knocking video processing model based on the video of the distribution cabinet to be detected being knocked to determine the structural deformation degree of the distribution cabinet to be detected; determine whether the distribution cabinet to be detected is of qualified quality based on the visual defect degree of the distribution cabinet to be detected and the structural deformation degree of the distribution cabinet to be detected.

[0059] Similarly, it should be noted that in order to simplify the description disclosed in this specification and thus help understand one or more embodiments of the invention, in the above description of the embodiments of this specification, multiple features are sometimes combined into one embodiment, figure or description thereof. However, this disclosure method does not mean that the features required by the subject matter of this specification are more than the features mentioned in the claims. In fact, the features of the embodiments are less than all the features of the single embodiment disclosed above.

[0060] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, as an example and not a limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.

Claims

1. A method for preparing a power distribution cabinet, characterized in that: include: Acquire multiple images of the power distribution cabinet to be inspected at different ultrasonic frequencies and a standard three-dimensional image of a standard power distribution cabinet; Generate a three-dimensional simulated image of the power distribution cabinet using a generative adversarial network based on a plurality of images captured at different ultrasonic frequencies of the power distribution cabinet to be detected; Constructing a graph structure, wherein the graph structure includes two nodes and an edge between the two nodes, the two nodes include a detection node and a standard node, the node feature of the detection node is a three-dimensional simulated image of the power distribution cabinet, the node feature of the standard node is a standard three-dimensional image of the standard power distribution cabinet, and the edge between the two nodes is a similarity between the three-dimensional simulated image of the power distribution cabinet and the standard three-dimensional image of the standard power distribution cabinet; Processing the graph structure based on the graph autoencoder to determine the visual defect degree of the power distribution cabinet to be detected; Obtain a video of the power distribution cabinet to be tested being knocked; Determine the structural deformation degree of the power distribution cabinet to be detected by using a knocking video processing model based on the video of the power distribution cabinet to be detected being knocked; Whether the power distribution cabinet to be inspected is of qualified quality is determined based on the visual defect degree of the power distribution cabinet to be inspected and the structural deformation degree of the power distribution cabinet to be inspected.

2. The method for preparing a power distribution cabinet according to claim 1, characterized in that: The percussion video processing model is a gated recurrent unit.

3. The method for preparing a power distribution cabinet according to claim 1, characterized in that: The input of the graph autoencoder is the graph structure, and the output of the graph autoencoder is the visual defect degree of the power distribution cabinet to be detected.

4. The method for preparing a power distribution cabinet according to claim 1, characterized in that: The determining whether the power distribution cabinet to be detected is of qualified quality based on the visual defect degree of the power distribution cabinet to be detected and the structural deformation degree of the power distribution cabinet to be detected comprises: The visual defect degree of the power distribution cabinet to be detected and the structural deformation degree of the power distribution cabinet to be detected are weighted and summed according to a predetermined weight to obtain the qualification degree of the power distribution cabinet to be detected; Determine whether the qualification of the power distribution cabinet to be tested is greater than a qualification threshold; If the qualification degree of the distribution cabinet to be detected is greater than the qualification threshold, the quality of the distribution cabinet to be detected is determined to be qualified. If the qualification degree of the distribution cabinet to be detected is less than the qualification threshold, the quality of the distribution cabinet to be detected is determined to be unqualified.

5. A system for preparing a power distribution cabinet, characterized in that: include: A first acquisition module is used to acquire a plurality of images of the distribution cabinet to be detected at different ultrasonic frequencies and a standard three-dimensional image of a standard distribution cabinet; A generation module, used to generate a three-dimensional simulated image of the distribution cabinet using a generative adversarial network based on a plurality of photographed images of the distribution cabinet to be detected at different ultrasonic frequencies; A construction module is used to construct a graph structure, wherein the graph structure includes two nodes and an edge between the two nodes, the two nodes include a detection node and a standard node, the node feature of the detection node is a three-dimensional simulated image of a power distribution cabinet, the node feature of the standard node is a standard three-dimensional image of a standard power distribution cabinet, and the edge between the two nodes is a similarity between the three-dimensional simulated image of the power distribution cabinet and the standard three-dimensional image of the standard power distribution cabinet; A visual defect degree determination module, used to process the graph structure based on the graph autoencoder to determine the visual defect degree of the power distribution cabinet to be detected; The second acquisition module is used to acquire a video of the distribution cabinet to be detected being knocked; A structural deformation degree determination module, used to determine the deformation degree of the power distribution cabinet to be detected by using a knocking video processing model based on a video of the power distribution cabinet to be detected being knocked; The quality determination module is used to determine whether the distribution cabinet to be detected is of qualified quality based on the visual defect degree of the distribution cabinet to be detected and the structural deformation degree of the distribution cabinet to be detected.

6. A system for preparing a power distribution cabinet according to claim 5, characterized in that: The percussion video processing model is a gated recurrent unit.

7. A system for preparing a power distribution cabinet according to claim 5, characterized in that: The input of the graph autoencoder is the graph structure, and the output of the graph autoencoder is the visual defect degree of the power distribution cabinet to be detected.

8. A system for preparing a power distribution cabinet according to claim 6, characterized in that: The quality qualification determination module is also used for: The visual defect degree of the power distribution cabinet to be detected and the structural deformation degree of the power distribution cabinet to be detected are weighted and summed according to a predetermined weight to obtain the qualification degree of the power distribution cabinet to be detected; Determine whether the qualification of the power distribution cabinet to be tested is greater than a qualification threshold; If the qualification degree of the distribution cabinet to be detected is greater than the qualification threshold, the quality of the distribution cabinet to be detected is determined to be qualified. If the qualification degree of the distribution cabinet to be detected is less than the qualification threshold, the quality of the distribution cabinet to be detected is determined to be unqualified.

9. An electronic device, characterized in that: include: processor; Memory; And a computer program; wherein the computer program is stored in the memory and is configured to be executed by the processor to implement a method for preparing a distribution cabinet as described in any one of claims 1 to 4.

10. A power distribution cabinet prepared according to the method for preparing a power distribution cabinet according to claim 1.

Images