Intelligent visual recognition detection method and system for control cabinet

Abstract

The application discloses a kind of control cabinet intelligent visual identification detection method, system.The method comprises: according to the first mark of the control cabinet to be measured, determine file information;According to file information, determine pin coordinate information;Pin coordinate information is used to represent the coordinate information of the electrical component of control cabinet;Pin coordinate information is used to represent the design correlation information of component and wire in the control cabinet to be measured;According to the first mark, determine picture information;Picture information is used to represent the image information of the control cabinet to be measured;Picture information and pin coordinate information are input into first detection model, and target detection result is obtained;Target detection result is used to represent the detection result of the control cabinet to be measured, and first detection model is used to determine the actual correlation information of component and wire in the control cabinet to be measured according to picture information.The embodiment of the application is beneficial to improve detection accuracy, and is beneficial to improve work efficiency;It can be widely applied in computer technology field.

Description

Technical Field

[0001] This invention relates to the field of electrical control cabinet technology, and in particular to an intelligent visual recognition and detection method for control cabinets. Background Technology

[0002] A control cabinet is a unit that integrates various electrical components to centrally power and manage electrical equipment. It provides timely power-off protection in case of overload, short circuit, or leakage. During the production process, if there are problems with the internal wiring of the control cabinet, it may malfunction, rendering the equipment unusable or even burning out components, causing significant losses. Traditional methods of quality inspection for control cabinets rely on manual checks. Operators need to be familiar with electrical schematics and use multimeters and other testing tools to verify the correctness of the wiring. This method is highly dependent on the operator's skill level, has low accuracy, and is inefficient. Summary of the Invention

[0003] The purpose of this invention is to at least partially solve one of the technical problems existing in the prior art.

[0004] Therefore, the purpose of this invention is to provide a highly accurate and efficient intelligent visual recognition and detection method and system for control cabinets.

[0005] To achieve the above-mentioned technical objectives, the technical solutions adopted in the embodiments of the present invention include:

[0006] On one hand, embodiments of the present invention provide an intelligent visual recognition and detection method for control cabinets, comprising the following steps:

[0007] This invention discloses an intelligent visual recognition and detection method for control cabinets. The method includes: determining file information based on a first identifier of the control cabinet under test; the file information representing basic data of the control cabinet under test; determining pin coordinate information based on the file information; the pin coordinate information representing the coordinate information of electrical components of the control cabinet; the pin coordinate information representing the design association information of components and wires in the control cabinet under test; determining image information based on the first identifier; the image information representing the image information of the control cabinet under test; inputting the image information and the pin coordinate information into a first detection model to obtain a target detection result; the target detection result representing the detection result of the control cabinet under test, and the first detection model determining the actual association information of components and wires in the control cabinet under test based on the image information. This invention, by determining pin coordinate information through file information, alleviates the need for operators to read electrical schematic diagrams, improving accuracy. Simultaneously, by using image information and pin coordinate information to detect the control cabinet under test, it alleviates the inefficiency of manual detection, improving work efficiency. Therefore, this invention is beneficial for improving detection accuracy and work efficiency.

[0008] In addition, the intelligent visual recognition and detection method for control cabinets according to the above embodiments of the present invention may also have the following additional technical features:

[0009] Furthermore, in the intelligent visual recognition and detection method for control cabinets according to embodiments of the present invention, the step of inputting the image information and the pin coordinate information into a first detection model to obtain the target detection result includes:

[0010] Based on the pin coordinate information and the actual association information, the target detection result is determined and displayed.

[0011] Furthermore, in one embodiment of the present invention, the step of inputting the image information and the pin coordinate information into the first detection model to obtain the target detection result includes:

[0012] The image information is segmented to obtain smaller blocks of information;

[0013] The small block information is subjected to target recognition processing to obtain component information;

[0014] The component information is processed by text recognition to obtain character information;

[0015] The wire number information is determined based on the character information and the component information;

[0016] Color information is obtained by performing color recognition processing on the component information;

[0017] The target detection result is obtained based on the color information, the line number information, and the pin coordinate information.

[0018] Furthermore, in one embodiment of the present invention, the method includes the following steps:

[0019] Obtain all line number information from the image;

[0020] Based on the distance between each wire number and the component, all wire numbers are first eliminated to obtain the first information;

[0021] Based on their positional relationship with the component, the first information is classified to obtain classification information; the positional relationship includes the upper and lower wiring categories of the component and the left and right wiring categories of the component.

[0022] Based on the matching result between each wire number information in the classification information and the pin coordinate information, the classification information is subjected to a second elimination to obtain the wire number information.

[0023] Furthermore, in one embodiment of the present invention, the method further includes:

[0024] Component matching is performed on the component information to obtain component information;

[0025] The component information is normalized and spatially transformed to obtain transformed information;

[0026] The transformed information is binarized to obtain binary information;

[0027] The color sequence information is obtained by performing a percentage-based statistical analysis on the binary information.

[0028] Color information is obtained by performing color matching on the color sequence information.

[0029] Furthermore, in one embodiment of the present invention, the method further includes:

[0030] Based on the first identifier, file information is determined in the preset directory;

[0031] If problematic files exist in the preset directory, the problematic files will be reclassified.

[0032] Furthermore, in one embodiment of the present invention, the file information includes a device identifier file, a component style file, a coordinate connection information file, and a wiring diagram file, and the method includes:

[0033] Based on the first identifier, identify the device identifier file, coordinate connection information file, and wiring diagram file;

[0034] Based on the first identifier, identify the component style file under the preset target;

[0035] Based on the device identifier file, determine the first correspondence between the device identifier and the component;

[0036] Based on the wiring diagram file, determine the second correspondence between the wires and the components;

[0037] Based on the first correspondence and the second correspondence, the pin coordinate information is obtained.

[0038] On the other hand, embodiments of the present invention propose an intelligent visual recognition and detection system for control cabinets, comprising:

[0039] The first module is used to determine file information based on the first identifier of the control cabinet under test; the file information is used to characterize the basic data of the control cabinet under test.

[0040] The second module is used to determine pin coordinate information based on the file information; the pin coordinate information is used to characterize the coordinate information of the electrical components of the control cabinet; the pin coordinate information is used to characterize the design association information of the components and wires in the control cabinet under test;

[0041] The third module is used to determine image information based on the first identifier; the image information is used to characterize the image information of the control cabinet under test.

[0042] The fourth module is used to input the image information and the pin coordinate information into the first detection model to obtain the target detection result; the target detection result is used to characterize the detection result of the control cabinet under test, and the first detection model is used to determine the actual association information of the components and wires in the control cabinet under test based on the image information.

[0043] On the other hand, embodiments of the present invention provide an intelligent visual recognition and detection device for control cabinets, comprising:

[0044] At least one processor;

[0045] At least one memory for storing at least one program;

[0046] When the at least one program is executed by the at least one processor, the at least one processor implements the above-described intelligent visual recognition and detection method for control cabinets.

[0047] On the other hand, embodiments of the present invention provide a storage medium storing a processor-executable program, which, when executed by a processor, is used to implement the above-described intelligent visual recognition and detection method for control cabinets.

[0048] This invention, through its embodiment, determines pin coordinate information using file information, alleviating the need for operators to read electrical schematics and improving accuracy. Simultaneously, by using image information and pin coordinate information to inspect the control cabinet under test, it alleviates the inefficiency of manual inspection and improves work efficiency. Therefore, this invention is beneficial for improving inspection accuracy and work efficiency. Attached Figure Description

[0049] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following description is provided with accompanying drawings of the relevant technical solutions in the embodiments of the present invention or the prior art. It should be understood that the accompanying drawings described below are only for the purpose of clearly illustrating some embodiments of the technical solutions of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without any creative effort.

[0050] Figure 1 A schematic diagram of the structure of one embodiment of the control cabinet provided by the present invention;

[0051] Figure 2 A flowchart illustrating one embodiment of the intelligent visual recognition and detection method for control cabinets provided by the present invention;

[0052] Figure 3 This is a flowchart illustrating another embodiment of the intelligent visual recognition and detection method for control cabinets provided by the present invention.

[0053] Figure 4 A flowchart illustrating one embodiment of the image processing procedure provided by the present invention;

[0054] Figure 5 A flowchart illustrating one embodiment of the wire number information determination process provided by the present invention;

[0055] Figure 6 A flowchart illustrating one embodiment of the color information determination process provided by the present invention;

[0056] Figure 7 A flowchart illustrating one embodiment of the document information judgment process provided by the present invention;

[0057] Figure 8 A schematic diagram showing an embodiment of the target detection results provided by the present invention;

[0058] Figure 9 A schematic diagram of one embodiment of the intelligent visual recognition and detection system for control cabinets provided by the present invention;

[0059] Figure 10 This is a schematic diagram of one embodiment of the intelligent visual recognition and detection device for control cabinets provided by the present invention. Detailed Implementation

[0060] The embodiments of the present invention are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and should not be construed as limiting the present invention. The step numbers in the following embodiments are set only for ease of explanation, and there is no limitation on the order between the steps. The execution order of each step in the embodiments can be adaptively adjusted according to the understanding of those skilled in the art.

[0061] Reference Figure 1 As shown, a control cabinet, also known as an electrical control cabinet, is a cabinet that integrates various electrical components to achieve centralized power supply and management control of electrical equipment. It can provide timely power-off protection in case of circuit overload, short circuit, or leakage. Correct wiring of the components inside the control cabinet is a fundamental requirement during the production process. If the internal wiring of the control cabinet is faulty, the cabinet may malfunction, rendering the equipment unusable, or even burning out components, causing significant losses. In more serious cases, it can lead to major production safety accidents, endangering lives.

[0062] Currently, most control cabinet quality inspections rely on traditional manual methods. Electricians, after reading and familiarizing themselves with the electrical schematics and understanding the wiring, first visually confirm the correctness of component models. Then, using multimeters and other testing tools, they check the continuity of the actual wiring terminals and compare the results with the electrical schematic to verify the wiring's correctness. This method demands a high level of skill from the inspectors, its efficiency depends heavily on their proficiency, and its low level of automation leads to low work efficiency and high labor costs. Furthermore, the quality of the inspection is closely related to the employee's work attitude and performance, making it difficult to control output accuracy. Manual inspection has consistently failed to meet the quality inspection needs of modern enterprises producing electrical control cabinets.

[0063] Therefore, modern industry urgently needs a new, high-precision, low-labor-consumption, and efficient inspection method. This invention utilizes an automatic inspection system based on machine vision recognition. It processes images of wiring inside a control cabinet using machine vision methods and identifies labels using template matching, thereby enabling the detection of the correctness of electrical cabinet components and wiring. Deep learning neural networks possess greater adaptability and versatility, enabling effective recognition of labels in distorted text and complex backgrounds.

[0064] The intelligent visual recognition and detection method and system for control cabinets according to embodiments of the present invention will be described in detail below with reference to the accompanying drawings. First, the intelligent visual recognition and detection method for control cabinets according to embodiments of the present invention will be described with reference to the accompanying drawings.

[0065] Reference Figure 2 This invention provides an intelligent visual recognition and detection method for control cabinets. This method can be applied to terminals, servers, or software running on either terminal or server. Terminals can be tablets, laptops, desktop computers, etc., but are not limited to these. Servers can be independent physical servers, server clusters or distributed systems composed of multiple physical servers, or cloud servers providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The intelligent visual recognition and detection method for control cabinets in this invention mainly includes the following steps:

[0066] S100: Determine the file information based on the first identifier of the control cabinet under test; the file information is used to characterize the basic data of the control cabinet under test.

[0067] S200: Determine pin coordinate information based on document information; pin coordinate information is used to characterize the coordinate information of electrical components in the control cabinet; pin coordinate information is used to characterize the design association information of components and wires in the control cabinet under test;

[0068] S300: Determine the image information based on the first identifier; the image information is used to characterize the image information of the control cabinet under test;

[0069] S400: Input the image information and pin coordinate information into the first detection model to obtain the target detection result; the target detection result is used to characterize the detection result of the control cabinet under test, and the first detection model is used to determine the actual association information of the components and wires in the control cabinet under test based on the image information.

[0070] In some possible implementations, the document information in this embodiment of the invention may be documents containing basic information about the electrical control cabinet. The image information may be actual components and wiring diagrams obtained by photographing the control cabinet under test. The operating principle of the detection system algorithm in this embodiment of the invention is to obtain the coordinates of each pin of the component (equipment identifier) ​​in the design drawing through the basic data, and match the pin names to the wire numbers in the wiring diagram. The positional relationship of the wire numbers is checked against the positional relationship of the wire numbers surrounding the equipment identifier (component) identified in the photograph, and the check results are output to the finished photograph in the wiring diagram. Specifically, refer to... Figure 3As shown, a specific embodiment of the control cabinet inspection method provided by the present invention will be described:

[0071] Step S31: When the wiring of a certain layer (the wiring components of the upper and lower layers with obstructions) or all components of the control cabinet project is completed, take a finished product photo file according to certain requirements. The format should be jpeg or png. At least one photo is required.

[0072] Step S32: Object Detection: First, the photo is segmented into small blocks. Then, the YOLOv5 algorithm model is used to detect vertical and horizontal device identifiers and line numbers in each small block. The detection results of the segmented blocks are then merged to obtain all the detection results for the entire photo.

[0073] Step S33: Text Recognition: Recognize the characters in the detection results of the previous step and extract the strings.

[0074] Step S34: Wire number determination: Determine the wire number in sequence according to the device identifier in a single picture. The order is determined by the pin position diagram of multiple device identifiers in the picture.

[0075] Step S35: Wire color identification: A rectangular area is cut off from the other end of the connector and the color of the area is determined.

[0076] Step S36: Output of test results: After adding test items to the composite data of the wiring diagram, the output is in Excel file format, and the file name is "Product Name + _Test Results.xls".

[0077] In other possible implementations, the system scans various directories in the configuration file during runtime to process basic data. By comparing CSS components, device identifiers, and wiring diagrams, it processes all photos of a product and outputs the product's test results. It then processes the tests of another product, and so on, until all photos have been processed.

[0078] Optionally, in one embodiment of the present invention, image information and pin coordinate information are input into a first detection model to obtain target detection results, including:

[0079] Based on the pin coordinate information and actual association information, determine the target detection result and display the target detection result.

[0080] Optionally, in one embodiment of the present invention, image information and pin coordinate information are input into a first detection model to obtain target detection results, including:

[0081] The image information is segmented to obtain smaller pieces of information;

[0082] Target recognition processing is performed on small pieces of information to obtain component information;

[0083] The component information is processed by text recognition to obtain character information;

[0084] The wire number information is determined based on the character information and component information;

[0085] Color information is obtained by performing color recognition processing on the component information;

[0086] The target detection result is obtained based on the color information, wire number information, and pin coordinate information.

[0087] In some possible implementations, refer to Figure 4 As shown, the processing of the finished image includes: character recognition; line number recognition; and color recognition.

[0088] Specifically, in images captured from typical electrical cabinets, most wire labels are vertically arranged against complex backgrounds, making it impossible to accurately locate and identify wire labels using a single text detection method. To address these issues, this invention proposes an electrical cabinet wiring detection method based on improved YOLOv5 and PP-OCRv3. The improved YOLOv5 network, YOLOv5s-CBS, is used to detect wire label regions. YOLOv5s-CBS is an optimization of YOLOv5s. A coordinated attention mechanism is added to the backbone network modules, a weighted bidirectional feature pyramid network is introduced in the neck region, and the loss function is changed from CIoU to SIoU. These measures improve the feature fusion capability, detection performance, and detection speed of the YOLOv5s model. PP-OCRv3 is used for fine-grained detection and label recognition. The fine-grained detection part uses the DB algorithm to detect text regions, and the label recognition part uses the SVTR_LCNet algorithm to recognize text. Then, YOLOv5s-CBS and PP-OCRv3 are cascaded to determine the absolute position of the input image based on the identified equipment labels and to perform data comparison of the corresponding equipment wiring labels.

[0089] In some possible implementations, the image file name can be output_all.json with the .json extension, and historical files can include timestamps down to the second. Using the above method, images can be recognized, and the results output can show whether the recognized label is a wire number or a device identifier, corresponding to the recognized string content. The coordinates within the recognized image frame correspond one-to-one with the pin wiring coordinates mentioned earlier.

[0090] In some possible implementations, this application embodiment uses the YOLOv5s-CBS algorithm to detect the line label region, then segments the detected image and sends it to PP-OCRv3 for text region detection and label text recognition. Specifically, the original dataset comes from images of connected electrical cabinets provided by a company. These photos were taken with a mobile phone. The original dataset is divided into 1340 images, each 640*640 pixels. The images are calibrated using software and divided into training, validation, and test sets for an improved 7:1.5:1.5 network according to a 7:1.5:1.5 ratio. A coarse check mainly detects five types of wire label regions: wire_white_p, wire_white_v, device_white_p, device_yellow_p, and device_yellow_v. Different types of wire labels can be set according to actual needs, and this invention does not impose specific limitations.

[0091] Understandably, after a rough inspection, the line label regions were divided, and then the vertically organized line label regions (line_white_v and device_yellow_v) were rotated 90 degrees to the right to create an image with normal text arrangement. A total of 4550 images were generated. The images were labeled using software and then divided into training, validation, and test sets in a 6:2:2 ratio for text region detection and recognition. The model that passed the test can be used for subsequent object detection.

[0092] Understandably, after each small region is identified, the identification results of each small region are comprehensively processed to obtain the target detection result.

[0093] Optionally, in one embodiment of the present invention, the method further includes:

[0094] Retrieve all line number information from the image;

[0095] Based on the distance between each wire number and the component, all wire numbers are first eliminated to obtain the first information;

[0096] Based on their positional relationship with the components, the first information is classified to obtain classification information; the positional relationship includes the upper and lower wiring of the components and the left and right wiring of the components.

[0097] Based on the matching results of each wire number information and pin coordinate information in the classification information, a second elimination is performed on the classification information to obtain the wire number information.

[0098] In some possible implementations, refer to Figure 5 As shown, the wire number information identification process provided by the embodiment of the present invention is described using a specific example:

[0099] Step S51: Determine the identified device identifier and line number. Based on the distance between the line number and the component (device identifier), remove duplicate device identifiers in a single photo (keep the closer ones and invalidate the farther ones).

[0100] Step S52: Determine if there are unsorted device identifiers in a single photo. If so, remove the matched wire numbers, classify the wires according to the device identifier (top and bottom, left and right), match the wire numbers with the pin design wire numbers in sequence, and select the ones with the most matches and the closest distance.

[0101] Step S53: Continue until all components are matched to their positions, then end the determination of wire number information.

[0102] Optionally, in one embodiment of the present invention, the method further includes:

[0103] Component matching is performed on the component information to obtain component information;

[0104] The component information is normalized and spatially transformed to obtain the transformed information;

[0105] The transformed information is binarized to obtain binary information;

[0106] By performing a percentage analysis on the binary information, color sequence information is obtained;

[0107] Color information is obtained by performing color matching on the color sequence information.

[0108] In some possible implementations, embodiments of the present invention can perform component matching using the LAB mode. It is understood that the LAB mode also consists of three channels, the first being lightness, or "L". The color of channel A ranges from red to dark green; channel B ranges from blue to yellow. Both components vary from -120 to +120. When A=0 and B=0, gray is displayed; when L=100, it is white; and when L=0, it is black.

[0109] Both LAB and HSV closely resemble colors as perceived by the human eye, but their value ranges differ. The color of a conductor is cropped from the photograph; therefore, the value range of commonly used conductor colors needs to be determined through sample analysis. The color structure is as follows:

[0110]

[0111]

[0112] Reference Figure 6 As shown, the process of determining color information provided in the embodiment of the present invention is described using a specific example:

[0113] Step S61: Normalize the image region by matching the LAB components of the color table, perform color space conversion, and then binarize the color regions one by one according to the color table.

[0114] Step S62: Obtain the number of binarized white dots, get the percentage, and record the maximum percentage and color sequence number.

[0115] Step S63: After completion, you can determine whether there is a line number matching the color, whether it is a two-color, and then get the matching color and return it.

[0116] Optionally, in one embodiment of the present invention, the method further includes:

[0117] Based on the first identifier, determine the file information in the preset directory;

[0118] If problematic files exist in the preset directory, they will be reclassified and processed.

[0119] In some possible implementations, refer to Figure 7 As shown, the process of determining document information provided in the embodiments of the present invention is described using a specific example:

[0120] Step S71: Process the CSS component style file. Since the style file name generated by EPLAN's character set contains some special characters, this needs to be noted when naming the component and should be avoided as much as possible.

[0121] Step S72: Determine if there are any unprocessed problem files in the directory. If so, determine the file extension, obtain the complete directory of photo files, determine the file name, read the connection information file, read the wiring diagram file, and read the device identifier file.

[0122] Step S73: If all files in the directory have been processed, associate the basic data information of this project by model, check the component style corresponding to the device identifier, check the correspondence between the device identifier and the device in the wiring, and compare the connection information with the above processing results to obtain the pin wiring coordinates of the component. The pin wiring coordinates can be simply understood as the wiring position, and are a key parameter for determining whether the component is connected correctly. Only by obtaining the component pin wiring coordinates can they be compared one by one with the device identifier, wire number, and color of the actual component at the corresponding position to determine whether the wiring is correct.

[0123] Step S74: When checking the device identifier corresponding to the component style, some device identifiers do not correspond to or correspond to multiple component styles, which makes it impossible to obtain the unique pin information of the component and therefore cannot be associated with the connection information file.

[0124] Optionally, in one embodiment of the present invention, the file information includes a device identifier file, a component style file, a coordinate connection information file, and a wiring diagram file, and the method includes:

[0125] Based on the first identifier, identify the device identifier file, coordinate connection information file, and wiring diagram file;

[0126] Based on the first identifier, identify the component style file under the preset target;

[0127] Based on the device identifier file, determine the first correspondence between the device identifier and the component;

[0128] Based on the wiring diagram file, determine the second correspondence between the wires and the components;

[0129] Based on the first and second correspondences, the pin coordinate information is obtained.

[0130] In some possible implementations, the system input of the intelligent visual recognition and detection system for control cabinets provided in this embodiment of the invention consists of basic project data and finished product photos. Specifically, the basic data in this embodiment of the invention is exported by the relevant electrical design software system upon completion of the project design, and mainly includes:

[0131] (1) The device identifier file used in the control cabinet project can be a maximum of 1 file, and the name can be "*device identifier.xls".

[0132] (2) Place the wiring style files of the components used in the control cabinet project in the css_file directory, one CSV file for each component, such as "SIE.6ES7515-2FM02-0AB0.csv".

[0133] (3) The control cabinet project includes a file containing the coordinate connection information of component pins in the cabinet, with a maximum of 1 file named "*connection.xls".

[0134] (4) Wiring diagram files for the control cabinet project, up to 3 types, named as "*Automatic Wiring Diagram.xls", "*Parallel Wiring Diagram.xls", and "*Semi-automatic Wiring Diagram.xls".

[0135] The intelligent visual recognition and detection system software for the control cabinet obtains the pin coordinates of each electrical component based on the correlation between these file records.

[0136] This invention is an image recognition program based on photographs of the interior of an electrical control cabinet. By processing the corresponding wiring data, device identifiers, connection point arrangements of device components, and the coordinates of these connection points within the cabinet, the pin coordinates of each component on the cabinet under test are obtained. Then, using an algorithmic model of the photograph of the cabinet under test, the device identifiers and wire numbers are detected. The program then provides a description of the detection results, which are used to determine if there are wiring errors in the electrical control cabinet. Figure 8 As shown, the target detection results can be obtained through methods such as... Figure 8 The images are displayed in a format that lists any non-compliant items, making it easier for operators to correct them. Furthermore, the program involved in this embodiment employs the latest YOLOv5 algorithm, improving its ability to extract and detect image content. Annotations are also added to enhance recognition efficiency and lay the foundation for accurate character recognition. The program also utilizes an ultra-lightweight optical character recognition system, enabling it to extract corresponding character information even from less-than-ideal or blurry images. This provides strong support for character content extraction and recognition without sacrificing accuracy, significantly improving detection efficiency.

[0137] Secondly, refer to the appendix Figure 9 This invention describes an intelligent visual recognition and detection system for control cabinets according to embodiments of the present invention.

[0138] Figure 9 This is a schematic diagram of the intelligent visual recognition and detection system for control cabinets according to an embodiment of the present invention. The system specifically includes:

[0139] The first module 910 is used to determine the file information based on the first identifier of the control cabinet under test; the file information is used to characterize the basic data of the control cabinet under test.

[0140] The second module 920 is used to determine the pin coordinate information based on the file information; the pin coordinate information is used to characterize the coordinate information of the electrical components of the control cabinet; the pin coordinate information is used to characterize the design association information of the components and wires in the control cabinet under test;

[0141] The third module 930 is used to determine the image information based on the first identifier; the image information is used to characterize the image information of the control cabinet under test.

[0142] The fourth module 940 is used to input image information and pin coordinate information into the first detection model to obtain the target detection result; the target detection result is used to characterize the detection result of the control cabinet under test, and the first detection model is used to determine the actual correlation information of components and wires in the control cabinet under test based on the image information.

[0143] It is evident that the content of the above method embodiments is applicable to this system embodiment. The specific functions implemented in this system embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0144] Reference Figure 10 This invention provides an intelligent visual recognition and detection device for control cabinets, comprising:

[0145] At least one processor 101;

[0146] At least one memory 102 is used to store at least one program;

[0147] When the at least one program is executed by the at least one processor 101, the at least one processor 101 implements the intelligent visual recognition and detection method for the control cabinet.

[0148] Similarly, the content of the above method embodiments is applicable to this device embodiment. The specific functions implemented by this device embodiment are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0149] This invention also provides a computer-readable storage medium storing a processor-executable program, which, when executed by a processor, is used to perform the above-described intelligent visual recognition and detection method for control cabinets.

[0150] Similarly, the content of the above method embodiments is applicable to this storage medium embodiment. The specific functions implemented in this storage medium embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0151] In some alternative embodiments, the functions / operations mentioned in the block diagrams may not occur in the order shown in the operation diagrams. For example, depending on the functions / operations involved, two consecutively shown blocks may actually be executed substantially simultaneously, or the blocks may sometimes be executed in reverse order. Furthermore, the embodiments presented and described in the flowcharts of this invention are provided by way of example to provide a more comprehensive understanding of the technology. The disclosed methods are not limited to the operations and logic flows presented herein. Alternative embodiments are contemplated in which the order of various operations is altered and sub-operations described as part of a larger operation are executed independently.

[0152] Furthermore, although the invention has been described in the context of functional modules, it should be understood that, unless otherwise stated, one or more of the functions and / or features may be integrated into a single physical device and / or software module, or one or more functions and / or features may be implemented in a separate physical device or software module. It is also understood that a detailed discussion of the actual implementation of each module is unnecessary for understanding the invention. Rather, given the properties, functions, and internal relationships of the various functional modules in the apparatus disclosed herein, the actual implementation of the module will be understood within the scope of conventional skill of an engineer. Therefore, those skilled in the art can implement the invention as set forth in the claims using ordinary techniques without excessive experimentation. It is also understood that the specific concepts disclosed are merely illustrative and not intended to limit the scope of the invention, which is determined by the full scope of the appended claims and their equivalents.

[0153] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several programs to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0154] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequential list of executable programs for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, a program execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can retrieve and execute a program from or in conjunction with such a program execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can mean any means that can contain, store, communicate, propagate, or transmit a program for use by or in conjunction with a program execution system, apparatus, or device.

[0155] More specific examples of computer-readable media (a non-exhaustive list) include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0156] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable program execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0157] In the foregoing description of this specification, references to terms such as "one embodiment," "another embodiment," or "some embodiments" indicate that a specific feature, structure, material, or characteristic described in connection with an embodiment or example is included in at least one embodiment or example of the present invention. In this specification, illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0158] Although embodiments of the invention have been shown and described, those skilled in the art will understand that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.

[0159] The above is a detailed description of the preferred embodiments of the present invention. However, the present invention is not limited to the embodiments described. Those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of the present invention. All such equivalent modifications or substitutions are included within the scope defined by the claims of the present invention.

Claims

1. A method for intelligent visual recognition and detection of control cabinets, characterized in that, Includes the following steps: Determine the file information based on the first identifier of the control cabinet under test; The document information is used to characterize and record the basic data of the control cabinet under test; Based on the file information, determine the pin coordinate information; The pin coordinate information is used to characterize the coordinate information of the components of the control cabinet; The pin coordinate information is used to characterize the design association information of components and wires in the control cabinet under test; Based on the first identifier, determine the image information; The image information is used to characterize the image information of the control cabinet under test; The image information and the pin coordinate information are input into the first detection model to obtain the target detection result; The target detection result is used to characterize the detection result of the control cabinet under test, and the first detection model is used to determine the actual association information of the components and wires in the control cabinet under test based on the image information; The step of inputting the image information and the pin coordinate information into the first detection model to obtain the target detection result includes: The image information is segmented to obtain smaller blocks of information; The small block information is subjected to target recognition processing to obtain component information; The component information is processed by text recognition to obtain character information; The wire number information is determined based on the character information and the component information; Color information is obtained by performing color recognition processing on the component information; The target detection result is obtained based on the color information, the line number information, and the pin coordinate information; The method further includes the following steps: Obtain all line number information from the image; Based on the distance between each wire number and the component, all wire numbers are first eliminated to obtain the first information; Based on their positional relationship with the component, the first information is classified to obtain classification information; the positional relationship includes the upper and lower wiring categories of the component and the left and right wiring categories of the component. Based on the matching result between each wire number information in the classification information and the pin coordinate information, the classification information is subjected to a second elimination to obtain the wire number information.

2. The intelligent visual recognition and detection method for control cabinets according to claim 1, characterized in that, The step of inputting the image information and the pin coordinate information into the first detection model to obtain the target detection result includes: Based on the pin coordinate information and the actual association information, the target detection result is determined and displayed.

3. The intelligent visual recognition and detection method for control cabinets according to claim 1, characterized in that, The method further includes: Component matching is performed on the component information to obtain component information; The component information is normalized and spatially transformed to obtain transformed information; The transformed information is binarized to obtain binary information; The color sequence information is obtained by performing a percentage-based statistical analysis on the binary information. Color information is obtained by performing color matching on the color sequence information.

4. The intelligent visual recognition and detection method for control cabinets according to claim 1, characterized in that, The method further includes: Based on the first identifier, file information is determined in the preset directory; If problematic files exist in the preset directory, the problematic files will be reclassified.

5. The intelligent visual recognition and detection method for control cabinets according to claim 1, characterized in that, The file information includes a device identifier file, a component style file, a coordinate connection information file, and a wiring diagram file; the method includes: Based on the first identifier, identify the device identifier file, coordinate connection information file, and wiring diagram file; Based on the first identifier, identify the component style file under the preset target; Based on the device identifier file, determine the first correspondence between the device identifier and the component; Based on the wiring diagram file, determine the second correspondence between the wires and the components; Based on the first correspondence and the second correspondence, the pin coordinate information is obtained.

6. A system for implementing the intelligent visual recognition and detection method for control cabinets as described in any one of claims 1-5, characterized in that, include: The first module is used to determine the file information based on the first identifier of the control cabinet under test; The document information is used to characterize and record the basic data of the control cabinet under test; The second module is used to determine the pin coordinate information based on the file information; The pin coordinate information is used to characterize the coordinate information of the components of the control cabinet; The pin coordinate information is used to characterize the design association information of components and wires in the control cabinet under test; The third module is used to determine image information based on the first identifier; The image information is used to characterize the image information of the control cabinet under test; The fourth module is used to input the image information and the pin coordinate information into the first detection model to obtain the target detection result; The target detection result is used to characterize the detection result of the control cabinet under test, and the first detection model is used to determine the actual association information of the components and wires in the control cabinet under test based on the image information.

7. A control cabinet intelligent visual recognition and detection device, characterized in that, include: At least one processor; At least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the intelligent visual recognition and detection method for control cabinets as described in any one of claims 1 to 5.

8. A computer-readable storage medium storing a processor-executable program, characterized in that, The processor-executable program, when executed by the processor, is used to implement the intelligent visual recognition and detection method for control cabinets as described in any one of claims 1 to 5.

Images