Vehicle circuit schematic diagram component identification realization method and device

By modeling and deep learning recognition of components in the electrical system of rail transit vehicles, combining feature data and multi-scale feature fusion algorithm, automatic identification of components and connection relationships in electrical schematic diagrams is achieved, and identification in the existing technology is solved The problem of low efficiency improves recognition accuracy and efficiency.

CN119068506APending Publication Date: 2024-12-03NANJING ZHONGCHE PUZHEN URBAN RAIL VEHICLE CO LTD
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202411199583.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-29
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

In the debugging of electrical system functions of rail transit vehicles, it is difficult for the existing technology to quickly and accurately identify the electrical components and their contact connection relationships in the schematic diagram of non-logical relationships, resulting in low recognition efficiency and a lot of manual participation, which affects the implementation of dynamic simulation systems. .

Method used

By introducing modeling and training various components, a multi-scale feature fusion algorithm based on feature data and deep learning methods is adopted, and the CSPDarknet architecture and IoU object detection algorithm of YOLOv7 are used to realize automatic identification and connection of components in electrical schematic diagrams. Relationship identification.

Benefits of technology

It improves the accuracy and efficiency of component recognition, reduces manual participation, completes the key steps of the dynamic simulation system, optimizes the original circuit schematic recognition method, and improves the recognition accuracy and efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119068506A_ABST
    Figure CN119068506A_ABST
Patent Text Reader

Abstract

The invention discloses a vehicle circuit schematic diagram component identification implementation method and device, and belongs to the technical field of rail transit, and the method comprises the steps: obtaining an electrical schematic diagram source file, and converting the electrical schematic diagram source file into a webpage structure file; analyzing the webpage structure file based on the feature data to obtain a first analysis result of the circuit components and the connection relationship thereof; analyzing the webpage structure file based on a deep learning method to obtain a second analysis result of the circuit components and the connection relationship thereof; comparing the circuit components in the first analysis result with the circuit components in the second analysis result and the connection relation of the circuit components to generate a difference comparison report; further generating a component library of the electrical schematic diagram and a corresponding connection relation table; according to the method, automatic conversion from an electrical schematic diagram to a corresponding interactive webpage structure is realized, so that automatic identification from a schematic diagram with a non-logical relationship to electrical elements in the schematic diagram and a contact connection relationship of the elements is realized.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to a method and a device for realizing component identification of a vehicle circuit schematic diagram, belonging to the technical field of rail transportation. Background Art

[0002] The electrical system function debugging of rail transit vehicles is an important line of defense in the production process of rail transit vehicles, which is directly related to the operation and safety performance of the vehicle. With the diversified development of rail transit vehicle varieties, the completion of all electrical system function debugging within the prescribed project cycle requires more and more proficiency of debugging skills personnel. Therefore, it is particularly important to use a set of dynamic simulation of vehicle system functions. Among them, the conversion from CAD electrical schematics to SVG diagrams dynamically simulated on the WEB is a very critical technology in the system. How to realize the automatic recognition of electrical components and component contact connection relationships in the schematic diagram from non-logical relationships is the premise of dynamic simulation of vehicle system functions. Summary of the invention

[0003] The purpose of the present invention is to overcome the deficiencies in the prior art and provide a method and device for realizing component recognition in a vehicle circuit schematic diagram. By introducing modeling and training of various components, the system can quickly and accurately identify various types of components in the electrical schematic diagram, thereby realizing automatic recognition from schematic diagrams with non-logical relationships to electrical components and component contact connection relationships in the schematic diagram, reducing manual participation, improving recognition efficiency, and completing a key step in the dynamic simulation system.

[0004] To achieve the above object, the present invention is implemented by adopting the following technical solutions: In a first aspect, the present invention provides a method for identifying components in a vehicle circuit schematic diagram, comprising: Get the electrical schematic source file and convert it into a web page structure file; Parsing the webpage structure file based on the characteristic data to obtain a first parsing result of circuit components and their connection relationships; Parsing the webpage structure file based on a deep learning method to obtain a second parsing result of circuit components and their connection relationships; Compare the circuit components and their connection relationships in the first analysis result with those in the second analysis result, and generate a difference comparison report; Screen the circuit components and their connection relationships in the difference comparison report to generate the component library of the electrical schematic and the corresponding connection relationship table; The components of the vehicle circuit schematic are identified based on the generated component library of the electrical schematic and the corresponding connection relationship table.

[0005] Furthermore, the step of converting the acquired electrical schematic source file into a web page structure file includes: Using Kabeja class packaging technology, extract the characteristic data of graphics in the electrical schematic source file; Reading the group code and group value of the characteristic data and determining its attributes; Selecting corresponding elements to describe the attributes, and writing the corresponding elements into a temporary web page structure file; Convert the temporary web page structure file from ASCII code to Unicode code and write it into the web page structure file in binary format.

[0006] Furthermore, the electrical schematic diagram converted into a webpage structure file is parsed based on the characteristic data to obtain a first parsing result of circuit components and their connection relationships, including: Build a circuit component library using pre-acquired original design data; By using the characteristic values ​​of the circuit components in the circuit component library, the electrical schematic converted into the web page structure file is parsed to identify the coordinate position relationship of the elements corresponding to each circuit component in the web page structure file; Based on the coordinate position relationship of circuit components, analyze each circuit component and its connection relationship; The first parsing results of the circuit components and their connection relationships obtained after parsing are formed into structured data and stored in a temporary circuit component library.

[0007] Furthermore, the electrical schematic diagram converted into a webpage structure file is parsed based on a deep learning method to obtain a second parsing result of circuit components and their connection relationships, including: Use the CSPDarknet architecture algorithm of YOLOv7 to model and identify each component in the electrical schematic and obtain the bounding box of each component; Based on the IoU object detection algorithm, the overlap between the components identified in the electrical schematic and various components is calculated. For the bounding boxes A and B of any two components, the overlap is evaluated by the IoU algorithm. The degree of overlap between the components in the electrical schematic diagram and various components is compared with a set threshold value to determine and obtain a second analysis result of the circuit components and their connection relationship.

[0008] Furthermore, for any two bounding boxes A and B, the degree of overlap is evaluated by the IoU algorithm, and the calculation formula is as follows: (1); in, Indicates the degree of overlap between bounding boxes A and B.

[0009] Furthermore, the method further comprises: In the regression process of the IoU target detection algorithm, when calculating the relative position of any two bounding boxes, the angle between the vector between the center points of the two bounding boxes and the coordinate axis is introduced as a penalty term in the regression process. The loss includes four parts: angle loss, distance loss, shape loss, and IoU loss. For the angle loss M, the formula is as follows: (2); in is the sine of the angle between the vector between the center points and the coordinate axis, and the formula is as follows: (3); in is the distance between the center point of the target box and the predicted box, is the angle between the line connecting the two center points and the horizontal direction, is the vertical distance between the two center points, and The formula is as follows: (4); (5); in , and , are the vertical and horizontal coordinates of the center points of the two; Among them, if The regression process first minimizes , otherwise minimize , and Mutual redundancy; The distance loss formula is: (6); in , They are the squares of the deviation rates of the center points of the target box and the predicted box in the horizontal and vertical directions, respectively. The formulas are as follows: (7); in is the distance deviation between the center point of the target box and the predicted box in the horizontal direction. The formula is as follows: (8); Among them, when When , the contribution of distance loss is significantly reduced. On the contrary, when When , the distance loss contribution increases.

[0010] In a second aspect, the present invention provides a vehicle circuit schematic component identification implementation device, comprising: An acquisition module is used to acquire the electrical schematic source file and convert it into a web page structure file; A first parsing module, used to parse the webpage structure file based on the feature data to obtain a first parsing result of circuit components and their connection relationships; A second parsing module is used to parse the webpage structure file based on a deep learning method to obtain a second parsing result of circuit components and their connection relationships; A comparison module, used to compare the circuit components and their connection relationships in the first analysis result with those in the second analysis result, and generate a difference comparison report; A generation module is used to screen the circuit components and their connection relationships in the difference comparison report, and generate a component library of the electrical schematic diagram and a corresponding connection relationship table; The identification module is used to identify the components of the vehicle circuit schematic diagram based on the generated component library of the electrical schematic diagram and the corresponding connection relationship table.

[0011] In a third aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any of the aforementioned methods.

[0012] In a fourth aspect, the present invention provides a computer device, comprising: Memory, for storing computer programs / instructions; A processor is used to execute the computer program / instructions to implement the steps of any of the aforementioned methods.

[0013] In a fifth aspect, the present invention provides a computer program product, comprising a computer program / instruction, which implements the steps of any one of the aforementioned methods when executed by a processor.

[0014] Compared with the prior art, the present invention has the following beneficial effects: 1. The present invention provides a method and device for realizing component recognition in a vehicle circuit schematic diagram. By introducing modeling and training of various components, the system can quickly and accurately recognize various types of components in the electrical schematic diagram, thereby realizing automatic recognition from the schematic diagram with non-logical relationship to the electrical components and the connection relationship of the component contacts in the schematic diagram, reducing manual participation, improving recognition efficiency, and completing a key step of the dynamic simulation system; 2. The present invention optimizes the basic functions of the original circuit schematic recognition method. In terms of recognition mode, in addition to the original method based on eigenvalues, it also provides a method based on deep learning. By introducing a new multi-scale feature fusion algorithm based on YOLOv7, training and optimization based on the CSPDarknet architecture, and modeling and training various types of components, it can quickly and accurately identify various types of components in SVG images. By comparing the two recognition methods, the recognition accuracy and efficiency are improved, and the time for manual participation is reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a flow chart of a method for realizing identification of components of a vehicle circuit schematic diagram provided by an embodiment of the present invention; Figure 2 It is a schematic diagram of calculating the degree of overlap between components and various components in an image provided by an embodiment of the present invention; Figure 3 It is a schematic diagram of the relative position between the calculation target box and the prediction box provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0016] The present invention will be further described below in conjunction with the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present invention, and cannot be used to limit the protection scope of the present invention.

[0017] Embodiment 1: This embodiment introduces a method for identifying components in a vehicle circuit schematic diagram, including: Get the electrical schematic source file and convert it into a web page structure file; Parsing the webpage structure file based on the characteristic data to obtain a first parsing result of circuit components and their connection relationships; Parsing the webpage structure file based on a deep learning method to obtain a second parsing result of circuit components and their connection relationships; Compare the circuit components and their connection relationships in the first analysis result with those in the second analysis result, and generate a difference comparison report; Screen the circuit components and their connection relationships in the difference comparison report to generate the component library of the electrical schematic and the corresponding connection relationship table; The components of the vehicle circuit schematic are identified based on the generated component library of the electrical schematic and the corresponding connection relationship table.

[0018] Figure 1 This is a flow chart of a method for realizing the identification of components in a vehicle circuit schematic diagram provided by an embodiment of the present invention. This flow chart only shows the logical sequence of the method of this embodiment. In other possible embodiments of the present invention, different methods may be used without conflict. Figure 1The steps shown or described are accomplished in the order shown.

[0019] The vehicle circuit schematic component identification implementation method provided in this embodiment can be applied to a terminal and can be executed by a vehicle system function dynamic simulation device, which can be implemented by software and / or hardware, and can be integrated in a terminal, such as any tablet computer or computer device with communication function. Figure 1 The method of this embodiment specifically includes the following steps: S1: Convert the electrical schematic source file into a web page structure file; Converting electrical schematic source files into web page structure files includes the following steps: Step a: Using Kabeja class packaging technology, extract the characteristic data of the graphics in the electrical schematic source file; Step b: Read the group code and group value of the feature data and determine its attributes; Step c: Select the corresponding element description attribute and write the corresponding element into a temporary web page structure file; Step d: Convert the temporary web page structure file from ASCII code to Unicode code, and write it into the web page structure file in binary format.

[0020] In this embodiment, by analyzing the electrical schematic DXF file and the web page structure SVG file, we find out the similarities between the two files, that is, both are text files, and describe vector graphics by recording the characteristic data of the graphics, such as a circle, and both record data such as the center radius of the circle. However, in the description of some graphics, the recorded characteristic data is different, such as an ellipse. Therefore, to realize the conversion from DXF file to SVG file, it is necessary not only to analyze the corresponding entity description of each type of two-dimensional vector graphic object in the electrical schematic and the elements in the web page structure file corresponding to the entities in the electrical schematic file, such as the "line" element of the entity in the electrical schematic file corresponds to the "line" in the web page structure file, and the "component" element of the entity in the electrical schematic file corresponds to the "use" in the web page structure file, but also to use the formula to derive the data required by the web page structure according to the characteristic data recorded in the electrical schematic. The formula is as follows: After selecting the DXF file, read the DXF file, display all the layers contained in the graphics, enter the target file name, select the layer to be converted, judge the type of the object according to the group code and group value read from the DXF file, different types of objects obtain different attributes, and then perform necessary attribute conversion, describe each different object with the corresponding element in SVG, write the converted result to a temporary SVG file, and then convert the temporary SVG file from ASCII code to Unicode encoding, and finally write the Unicode encoding to the target file in binary mode. After detailed and in-depth analysis, a one-to-one correspondence between the entities in the electrical schematic file and the elements in the web page structure file is obtained, and the conversion of the electrical schematic source file to the web page structure file is realized.

[0021] S2: parsing the electrical schematic converted into a webpage structure file based on the characteristic value, and storing the parsed circuit components in a circuit component library; Parsing the electrical schematic converted into a web page structure file and storing the parsed circuit components in a circuit component library includes the following steps: Step a: constructing a circuit component library through pre-acquired original design data; Step b: using support vector training classifier to parse the electrical schematic diagram converted into a web page structure file; Step c: Identify the coordinate position relationship of the elements corresponding to each circuit component in the web page structure file, and analyze each circuit component and its connection relationship; Step d: The parsed circuit components and their connection relationships are organized into structured data and stored in a temporary circuit component library.

[0022] S3: Parse the electrical schematic SVG image converted into a web page structure file based on a deep learning algorithm, and store the parsed circuit components in an XML file; Before recognition, the system will model and identify each component based on the CSPDarknet architecture algorithm of YOLOv7 to obtain the bounding box of each component. First, the known component image is machine-learned as the original prediction target of the component, and then the overlap degree of the component in the image with various components is calculated based on the IoU target detection algorithm (such as Figure 2 As shown in Figure 2). If the two bounding boxes are represented by A and B respectively, the calculation result of IoU can be expressed as: (1); Among them, Figure 3 As indicated, when calculating the relative position between the target box and the predicted box during the regression process, the angle between the vector between the center points of the two bounding boxes and the coordinate axis is introduced as a penalty term in the regression process. The loss consists of four parts: angle loss, distance loss, shape loss, and IoU loss. For the angle loss M, it is defined as follows: (2); in is the sine of the angle between the vector between the center points and the coordinate axis, defined as follows: (3); in is the distance between the center point of the target box and the predicted box, is the angle between the line connecting the two center points and the horizontal direction, is the vertical distance between the two center points, and The formula is as follows: (4); (5); in , and , are the vertical and horizontal coordinates of the center points of the two.

[0023] According to the angle loss formula, if The regression process first minimizes , otherwise minimize , and The purpose of this loss is to make the bounding box align vertically or horizontally first.

[0024] The distance loss is defined as: (6); in , They are the squares of the deviation rates of the center points of the target box and the predicted box in the horizontal and vertical directions, respectively. The formulas are as follows: (7); in is the distance deviation between the center point of the target box and the predicted box in the horizontal direction. The formula is as follows: (8); From the formula, we can see that when When , the contribution of distance loss is significantly reduced. On the contrary, when Therefore, as the angle increases, the center of gravity of the regression loss tends to be towards the distance loss.

[0025] Finally, the recognition result is determined based on the calculated overlap threshold between the target frame and the test frame.

[0026] According to the training and optimization of the bounding box regression algorithm, the recognition accuracy of various components will gradually improve. After selecting the circuit principle SVG diagram to be recognized, the system will automatically recognize all the component objects and their attributes in the diagram according to the algorithm and generate the corresponding XML file.

[0027] S4: Compare the results of the eigenvalue-based method and the deep learning intelligent recognition method, and generate a comparison report of the comparison results.

[0028] Through the component data in the result XML file of deep learning recognition, SQL statements are generated one by one to query the temporary circuit component library in the database, and the components with differences are written into the comparison result report. The components with differences are manually confirmed and corrected by referring to this comparison report.

[0029] S5: Automatically generate the component library of the electrical schematic and the corresponding connection relationship table.

[0030] According to the results of manual confirmation, the temporary circuit component library is modified and automatically converted into the formal circuit component library.

[0031] Embodiment 2: This embodiment provides a device for realizing component identification of a vehicle circuit schematic diagram, comprising: An acquisition module is used to acquire the electrical schematic source file and convert it into a web page structure file; A first parsing module, used to parse the webpage structure file based on the feature data to obtain a first parsing result of circuit components and their connection relationships; A second parsing module is used to parse the webpage structure file based on a deep learning method to obtain a second parsing result of circuit components and their connection relationships; A comparison module, used to compare the circuit components and their connection relationships in the first analysis result with those in the second analysis result, and generate a difference comparison report; A generation module is used to screen the circuit components and their connection relationships in the difference comparison report, and generate a component library of the electrical schematic diagram and a corresponding connection relationship table; The identification module is used to identify the components of the vehicle circuit schematic diagram based on the generated component library of the electrical schematic diagram and the corresponding connection relationship table.

[0032] The specific functional implementation of each of the above modules can be found in the relevant contents of the method in Example 1 and will not be elaborated here.

[0033] Embodiment 3, this embodiment provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the steps of any one of the methods described in Embodiment 1 are implemented.

[0034] Embodiment 4: This embodiment provides a computer device, including: Memory, for storing computer programs / instructions; A processor, configured to execute the computer program / instructions to implement the steps of any one of the methods described in Example 1.

[0035] Embodiment 5: This embodiment provides a computer program product, including a computer program / instruction, which implements the steps of any method described in Embodiment 1 when executed by a processor.

[0036] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the technical principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

[0037] It should be understood by those skilled in the art that the embodiments of the present disclosure may be provided as methods, systems or computer program products. Therefore, the present disclosure may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware aspects. Moreover, the present disclosure may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0038] The present disclosure is described with reference to flowcharts and / or block diagrams of methods, devices (systems) and computer program products according to embodiments of the present disclosure. It should be understood that each process and / or block in the flowchart and / or block diagram and the combination of processes and / or blocks in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0039] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0040] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0041] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present disclosure rather than to limit its protection scope. Although the present disclosure has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that after reading the present disclosure, those skilled in the art can still make various changes, modifications or equivalent substitutions to the specific implementation methods of the invention, but these changes, modifications or equivalent substitutions are all within the protection scope of the disclosed claims to be approved.

Claims

1. A method for identifying components in a vehicle circuit schematic diagram, It is characterized in that include: Get the electrical schematic source file and convert it into a web page structure file; Parsing the webpage structure file based on the characteristic data to obtain a first parsing result of circuit components and their connection relationships; Parsing the webpage structure file based on a deep learning method to obtain a second parsing result of circuit components and their connection relationships; Compare the circuit components and their connection relationships in the first analysis result with those in the second analysis result, and generate a difference comparison report; Screen the circuit components and their connection relationships in the difference comparison report to generate the component library of the electrical schematic and the corresponding connection relationship table; The components of the vehicle circuit schematic are identified based on the generated component library of the electrical schematic and the corresponding connection relationship table.

2. The vehicle circuit schematic component identification implementation method according to claim 1, It is characterized in that The step of converting the acquired electrical schematic source file into a web page structure file includes: Using Kabeja class packaging technology, extract the characteristic data of graphics in the electrical schematic source file; Reading the group code and group value of the characteristic data and determining its attributes; Selecting corresponding elements to describe the attributes, and writing the corresponding elements into a temporary web page structure file; Convert the temporary web page structure file from ASCII code to Unicode code and write it into the web page structure file in binary format.

3. The vehicle circuit schematic component identification implementation method according to claim 1, It is characterized in that The electrical schematic diagram converted into a webpage structure file is parsed based on the characteristic data to obtain a first parsing result of circuit components and their connection relationships, including: Build a circuit component library using pre-acquired original design data; The electrical schematic converted into a web page structure file is parsed through the characteristic values ​​of the circuit components in the circuit component library to identify the coordinate position relationship of the elements corresponding to each circuit component in the web page structure file; Based on the coordinate position relationship of circuit components, analyze each circuit component and its connection relationship; The first parsing results of the circuit components and their connection relationships obtained after parsing are formed into structured data and stored in a temporary circuit component library.

4. The vehicle circuit schematic component identification implementation method according to claim 1, It is characterized in that The electrical schematic diagram converted into a webpage structure file is parsed based on a deep learning method to obtain a second parsing result of circuit components and their connection relationships, including: Use the CSPDarknet architecture algorithm of YOLOv7 to model and identify each component in the electrical schematic and obtain the bounding box of each component; Based on the IoU object detection algorithm, the overlap between the components identified in the electrical schematic and various components is calculated. For the bounding boxes A and B of any two components, the overlap is evaluated by the IoU algorithm. The degree of overlap between the components in the electrical schematic diagram and various components is compared with a set threshold value to determine and obtain a second analysis result of the circuit components and their connection relationship.

5. The vehicle circuit schematic component identification implementation method according to claim 4, It is characterized in that For any two bounding boxes A and B, the IoU algorithm is used to evaluate their degree of overlap, and the calculation formula is as follows: (1); in, Indicates the degree of overlap between bounding boxes A and B.

6. The vehicle circuit schematic component identification implementation method according to claim 4, It is characterized in that The method further comprises: In the regression process of the IoU target detection algorithm, when calculating the relative position of any two bounding boxes, the angle between the vector between the center points of the two bounding boxes and the coordinate axis is introduced as a penalty term in the regression process. The loss includes four parts: angle loss, distance loss, shape loss, and IoU loss. For the angle loss M, the formula is as follows: (2); in is the sine of the angle between the vector between the center points and the coordinate axis, and the formula is as follows: (3); in is the distance between the center point of the target box and the predicted box, is the angle between the line connecting the two center points and the horizontal direction, is the vertical distance between the two center points, and The formula is as follows: (4); (5); in , and , are the vertical and horizontal coordinates of the center points of the two; Among them, if The regression process first minimizes , otherwise minimize , and Mutual redundancy; The distance loss formula is: (6); in , They are the squares of the deviation rates of the center points of the target box and the predicted box in the horizontal and vertical directions, respectively. The formulas are as follows: (7); in is the distance deviation between the center point of the target box and the predicted box in the horizontal direction. The formula is as follows: (8); Among them, when When , the contribution of distance loss is significantly reduced. On the contrary, when When , the distance loss contribution increases.

7. A device for identifying components in a vehicle circuit schematic diagram, It is characterized in that include: An acquisition module is used to acquire the electrical schematic source file and convert it into a web page structure file; A first parsing module, used to parse the webpage structure file based on the feature data to obtain a first parsing result of circuit components and their connection relationships; A second parsing module is used to parse the webpage structure file based on a deep learning method to obtain a second parsing result of circuit components and their connection relationships; A comparison module, used to compare the circuit components and their connection relationships in the first analysis result with those in the second analysis result, and generate a difference comparison report; A generation module is used to screen the circuit components and their connection relationships in the difference comparison report, and generate a component library of the electrical schematic diagram and a corresponding connection relationship table; The identification module is used to identify the components of the vehicle circuit schematic diagram based on the generated component library of the electrical schematic diagram and the corresponding connection relationship table.

8. A computer-readable storage medium having a computer program stored thereon, Features: When the program is executed by a processor, the steps of the method described in any one of claims 1 to 6 are implemented.

9. A computer device, It is characterized in that include: Memory, for storing computer programs / instructions; A processor, configured to execute the computer program / instructions to implement the steps of the method according to any one of claims 1 to 6.

10. A computer program product comprising a computer program / instructions, It is characterized in that When the computer program / instructions are executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Citation Information

Cited By

  • Circuit grouping analysis method, system, terminal and medium based on graphic processing

    CN119760806A