Plasticity forming technique regulation obtaining method based on numerical value simulation and policy-making tree algorithm

Abstract

The present invention relates to a flastic forming process rule obtaining method based on numerical simulationand decision tree algorithm. Said method mainly includes the following steps: firstly, creating numerical simulation defining decision attribute set for evaluating forming property, making defining decision attribute set for evaluating forming property, making numerical simulation test design to obtain plastic forming process information source, forming decision table, successively defining node of every level of decision tree to form initial decision tree, then pruning the initial decision tree so as to obtain the invented process rule. Said invention also provides the advantages and application field of said method.

Description

technical field [0001] The invention relates to a method for obtaining plastic forming process rules based on numerical simulation and decision tree (Decision Tree) algorithm, which is used for mining potential process rules from plastic forming numerical simulation results, and belongs to the technical field of knowledge engineering of plastic processing. Background technique [0002] Process rules are very important to guide the process design of plastic forming, and are the basis for establishing plastic processing expert system or other intelligent plastic forming process design systems. At present, the plastic forming process rules are mainly obtained through the existing process design manual and domain expert inheritance. However, the original process design manual cannot adapt to the ever-changing product structure update; inheriting the experience of domain experts requires good cooperation and hard work between knowledge engineers and domain experts, and largely de...

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to propose a new plastic forming process rule acquisition method based on numerical simulation and decision tree algorithm in view of the difficulty in obtaining process rules in the field of plastic processing and the lack of development and utilization of the result data generated by plastic forming simulation. Excavate a large amount of potential process knowledge contained in the numerical simulation result data, obtain explicit rules that are easy to be expressed and stored by the computer, shorten the establishment cycle of the process rule base, improve the quality of the rule base, and provide effective and directional explanation for the deep-level directional interpretation of the simulation results. approach to elevate numerical simulation from the design verification level to the design-driven level

Images