Fixture unit intelligent generation method based on graph structure and path search

Abstract

The invention relates to the technical field of automobile processing assistance of artificial intelligence and computer-aided design, and discloses an intelligent generation method for a clamp unit based on a graph structure and path search, which constructs a knowledge graph of unit design with graph structure data according to the existing historical scheme of clamp unit design. According to the intelligent generation method for the clamp unit based on the graph structure and the path search, historical experience of designers is effectively utilized: data is designed by utilizing the historical clamp unit, so that a generated new design scheme conforms to artificial specifications in historical design to a certain extent; according to the method, various design schemes can be flexibly combined, partial splicing and grafting of different units can be achieved, the new design scheme can be generated, the working efficiency of clamp designers can be effectively improved, and the production cost is reduced. Therefore, the automobile generation efficiency is improved, and the automobile generation cost is reduced.

Description

Technical Field

[0001] The invention relates to the field of artificial intelligence and computer-aided design for automobile processing auxiliary technology, in particular to a method for intelligently generating a fixture unit based on a graph structure and path search. Background Art

[0002] Automobile welding fixtures are key equipment for positioning and fixing body parts in modern manufacturing. Their main function is to ensure the accurate and stable position between parts during welding to improve welding quality and production efficiency. Usually, the components of automobile welding fixtures are relatively fixed, including standard parts such as base, connection block, cylinder, contact end parts, etc. By using standard parts, manufacturers can not only shorten the design and manufacturing time, but also reduce production costs and improve the reliability of fixtures; With the development of digital manufacturing and intelligent manufacturing, automobile manufacturers are paying more and more attention to using design and production data to optimize fixture design.

[0003] For example, by constructing graph-structured data of the relationships between fixture parts, these part relationships and assembly information can be systematically analyzed, stored, and reused. Graph-structured data can effectively help engineers quickly reference and match existing design solutions when designing new fixture units, thus achieving automation and intelligence in design.

[0004] At the same time, this graph-based data structure can also be applied to fields such as simulation and fault diagnosis, helping manufacturing companies accelerate innovation and improve design quality and accuracy. Therefore, by analyzing the relationship between different components in the fixture unit and forming graph structure data, companies can achieve data-driven intelligent decision-making in fixture design.

[0005] Therefore, a method for intelligent generation of fixture units based on graph structure and path search is proposed. Summary of the invention

[0006] Technical issues solved In view of the shortcomings of the prior art, the present invention provides an intelligent generation method of fixture units based on graph structure and path search, which has the advantages of assisting designers to quickly carry out fixture unit structure design and installation design processes in the automobile welding design process, and solves the above-mentioned problems.

[0007] Technical Solution In order to achieve the purpose of assisting designers to quickly carry out fixture unit structure design and installation design process in the process of automobile welding design, the present invention provides the following technical solution: a method for intelligently generating fixture units based on graph structure and path search, comprising the following steps: Step 1: Construct a knowledge graph of unit design with graph structure data based on the existing fixture unit design history plan; Step 2: Intelligently generate fixture unit design scheme based on the knowledge graph of unit design; Step 3: Update the knowledge graph of unit design regularly.

[0008] Preferably, the specific steps of step 2 include: Step A: Enter a pair of specified base parts and contact end parts, and activate the start node and end node of the path; Step B: Calculate the path search algorithm to search for the path and obtain the path; Step C: According to the design scheme obtained by path search, the various parts are assembled and several characteristics of the unit are measured and evaluated; Step D: Record the final solution that meets the results and feed it back into the knowledge graph of the unit design; Based on the historical fixture unit design library, a graph structure data is constructed with the parts in the fixture unit as nodes and the assembly relationships as edges; The geometric characteristics of the fixture unit are used as evaluation indicators of the path to form a complete set of path search solutions; Based on the path search algorithm, the base and contact end parts of the fixture unit are used as the starting and ending points of the path to intelligently generate the structure of the unit fixture; By utilizing the historical fixture unit design data, the generated new design scheme is made to a certain extent consistent with the artificial specifications in the historical design; the parts used in it have been actually produced and used, and the assembly scheme of the parts has also been verified.

[0009] Preferably, in step 2, if the search result meets the evaluation index, the result is output to the candidate design library.

[0010] Preferably, in step 2, if the number of design solutions in the candidate design library reaches a preset requirement, the entire result is output for designers to select and make subsequent adjustments.

[0011] Preferably, in step 2, if the number of design solutions to be selected does not reach a preset number, a new round of path search is performed.

[0012] Preferably, if the search result in step 2 does not match the result, a new round of search is also performed. This method can flexibly combine multiple design schemes, realize partial splicing and grafting of different units, and generate new design schemes.

[0013] Preferably, in step 2, the path search algorithm is stopped until the number of design solutions in the candidate design library reaches a preset requirement, or the number of searches reaches a preset maximum number; It can effectively improve the work efficiency of fixture designers, thereby improving the efficiency of vehicle production and reducing vehicle production costs.

[0014] Compared with the prior art, the present invention provides a method for intelligently generating fixture units based on graph structure and path search, which has the following beneficial effects: 1. This intelligent generation method of fixture units based on graph structure and path search effectively utilizes the historical experience of designers: by using historical fixture unit design data, the generated new design scheme is consistent with the artificial specifications in the historical design to a certain extent; the parts used are actually produced and used, and the assembly scheme of the parts has also been verified.

[0015] 2. The intelligent generation method of fixture units based on graph structure and path search can generate new design schemes: this method can flexibly combine multiple design schemes, realize partial splicing and grafting of different units, and generate new design schemes.

[0016] 3. The intelligent generation method of fixture units based on graph structure and path search improves work efficiency: it can effectively improve the work efficiency of fixture designers, thereby improving the efficiency of vehicle generation and reducing vehicle generation costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 A schematic diagram of a flow chart for a fixture unit generation process based on graph structure data and path selection of the present invention; Figure 2 This is a schematic diagram of map structure data composed of historical unit design schemes in the present invention; Figure 3 A schematic diagram of the path start node and end node is activated for the present invention; Figure 4 A schematic diagram of a unit design path searched for by the present invention; Figure 5 Schematic diagram of the fixture unit (right) and some typical evaluation indicators (left) obtained by combining the path search results of the present invention. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] See also Figure 1-Figure 5 ; A method for intelligently generating fixture units based on graph structure and path search comprises the following steps: Step 1: Construct a knowledge graph of unit design with graph structure data based on the existing fixture unit design history plan; Step 2: Intelligently generate fixture unit design scheme based on the knowledge graph of unit design; Step 3: Update the knowledge graph of unit design regularly.

[0020] The specific steps of step 2 include: Step A: Enter a pair of specified base parts and contact end parts, and activate the start node and end node of the path; Step B: Calculate the path search algorithm to search for the path and obtain the path; Step C: According to the design solution obtained by path search, the various parts are assembled and several characteristics of the unit are measured and evaluated; Step D: Record the final solution that meets the results and feed it back into the knowledge graph of the unit design; Based on the historical fixture unit design library, a graph structure data is constructed with the parts in the fixture unit as nodes and the assembly relationships as edges; The geometric characteristics of the fixture unit are used as evaluation indicators of the path to form a complete set of path search solutions; Based on the path search algorithm, the base and contact end parts of the fixture unit are used as the starting and ending points of the path to intelligently generate the structure of the unit fixture; In step 2, if the search result meets the evaluation index, the result is output to the candidate design library; In step 2, if the number of design solutions in the candidate design library reaches the preset requirement, the entire result is output for the designer to select and make subsequent adjustments; In step 2, if the number of design solutions to be selected does not reach the preset number, a new round of path search is performed; If the search results in step 2 do not match the results, a new round of search will also be conducted; In step 2, the path search algorithm is stopped until the number of design solutions in the candidate design library reaches a preset requirement, or the number of searches reaches a preset maximum number.

[0021] Example: In order to make the relevant graph structure data and technical routes in the present invention clearly and completely described, a typical fixture unit is taken as an example and decomposed into graph structure data representation; Step 1: Input a graph structure data consisting of historical design plans; Step 2: Enter a pair of specified base and contact end parts, and activate the start and end nodes of the path; Step 3: Perform path search and obtain a path. The path length is 4 and contains 5 nodes. The ring formed by the structure connected by the solid line is a design scheme based on historical experience and can be regarded as a large node; Step 4: According to the design solution obtained by path search, assemble the parts and measure and evaluate several characteristics of the unit; Step 5: If the search results meet the evaluation criteria, the results are output to the candidate design library. If the number of design solutions in the candidate design library meets the preset requirements, the entire result is output for designers to choose and make later adjustments. If the number of candidate design solutions does not meet the preset requirements, a new round of path search is performed. If the search results do not meet the results, a new round of search is also performed. This continues until the number of design solutions in the candidate design library meets the preset requirements, or the number of searches reaches the preset maximum number.

[0022] The beneficial effects of the present invention are as follows: the intelligent generation method of fixture units based on graph structure and path search effectively utilizes the historical experience of designers: the historical fixture unit design data is used to make the generated new design scheme conform to the artificial specifications in the historical design to a certain extent; the parts used are all actually produced and used, and the assembly scheme of the parts has also been verified, and a new design scheme can be generated: this method can flexibly combine multiple design schemes, realize partial splicing and grafting of different units, generate new design schemes, and improve work efficiency: it can effectively improve the work efficiency of fixture designers, thereby improving the efficiency of automobile generation and reducing the cost of automobile generation.

[0023] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for intelligently generating fixture units based on graph structure and path search, characterized in that: The following steps are involved: Step 1: Construct a knowledge graph of unit design with graph structure data based on the existing fixture unit design history plan; Step 2: Intelligently generate fixture unit design scheme based on the knowledge graph of unit design; Step 3: Update the knowledge graph of unit design regularly.

2. According to claim 1, a method for intelligently generating fixture units based on graph structure and path search is characterized in that: The specific steps of step 2 include: Step A: Input a pair of specified base parts and contact end parts, and activate the start node and end node of the path; Step B: Calculate the path search algorithm to search for the path and obtain the path; Step C: According to the design solution obtained by path search, the various parts are assembled and several characteristics of the unit are measured and evaluated; Step D: Record the final solution that meets the results and feed it back into the knowledge graph of the unit design.

3. The method for intelligently generating fixture units based on graph structure and path search according to claim 2, characterized in that: In the step 2, if the search result meets the evaluation index, the result is output to the candidate design library.

4. The method for intelligently generating fixture units based on graph structure and path search according to claim 2, characterized in that: In the step 2, if the number of design solutions in the candidate design library reaches the preset requirement, the entire result is output for the designer to select and make subsequent adjustments.

5. The method for intelligently generating fixture units based on graph structure and path search according to claim 2, characterized in that: If the number of design solutions to be selected does not reach the preset number in step 2, a new round of path search is performed.

6. The method for intelligently generating fixture units based on graph structure and path search according to claim 2, characterized in that: If the search result in step 2 does not match the result, a new round of search is also performed.

7. The method for intelligently generating fixture units based on graph structure and path search according to claim 2, characterized in that: In the step 2, the path search algorithm is stopped until the number of design solutions in the candidate design library reaches a preset requirement, or the number of searches reaches a preset maximum number.

Images