Rectangular intelligent layout method and system based on knowledge migration

Abstract

The invention discloses a rectangular intelligent layout method and system based on knowledge migration, and belongs to the field of optimized blanking of structural parts, and the method comprises the steps: (1) selecting a plurality of groups of parts to be subjected to layout as source tasks, and extracting the relevant information of the parts and plates; (2) solving the selected multiple groups of source tasks by using an ant colony reinforcement learning algorithm, and storing the learned optimal knowledge matrix into a knowledge base; (3) extracting two groups of source tasks most similar to the target task to be solved from the knowledge base, and linearly migrating the knowledge matrixes corresponding to the two groups of source tasks to the target task; (4) enabling the target task to calculate an optimal layout scheme by means of a migration knowledge matrix and an ant colony reinforcement learning algorithm; and (5) outputting an optimal layout scheme of the target task. According to the rectangular intelligent layout method based on knowledge migration, the plate utilization rate can be increased, the solving speed can be increased, and the rectangular intelligent layout method has good practicability in solving the large-scale and medium-scale rectangular layout problem.

Description

technical field [0001] The invention belongs to the field of optimized blanking of structural parts, and more specifically relates to a method and system for intelligent rectangular layout based on knowledge transfer. Background technique [0002] In recent years, with the intensification of market competition, enterprises are eager to reduce production costs and improve efficiency. The traditional manual nesting method can no longer meet the requirements of large-scale and personalized customized production. Enterprises increasingly need an intelligent optimization nesting method with high efficiency and less waste. Rectangular optimal nesting is a branch of the optimal blanking problem, which refers to arranging rectangular parts of different specifications on a specific rectangular plate according to the optimal nesting scheme. Since a variety of regular graphics such as triangles, fans, etc., and irregular graphics can be converted into rectangles by splicing or envelop...

AI Technical Summary

Problems solved by technology

[0005] First of all, although the heuristic method and advanced intelligent optimization method have been used to solve the rectangular layout, there are still problems of long solution time and low utilization rate;

[0006] Secondly, the current solution only focuses on the current task itself, and the tasks are optimized independently of each other. When solving and optimizing similar new tasks, the existing experience and knowledge cannot be effectively used, and the search optimization needs to be restarted, resulting in low efficiency;

[0007] Thirdly, even with personalized customization, due to standardized production, there are many identical parts in the same type of product, so there is a certain degree of "duplication" in different groups of parts to be arranged

Images