A method and device for springback compensation of a stamped part based on a machine learning model

By using a machine learning model-based method, finite element simulation and convolutional neural network training data sets to establish a rebound compensation big data model, the problems of high mold development cost and long cycle in traditional methods are solved, and fast and effective mold surface compensation and part dimensional accuracy are achieved.

CN118095000BActive Publication Date: 2025-10-17GUANGZHOU ZHIYUAN TECH CO LTD
2 Cites 2 Cited by

Patent Information

Application Number
CN202410211644.9
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-02-27
Publication Date
2025-10-17
Estimated Expiration
2044-02-27

AI Technical Summary

Technical Problem

Traditional methods of compensating for springback of stamped parts are highly dependent on technicians' process experience and stamping simulation technology, resulting in high mold development costs and long cycles, making it difficult to effectively ensure the dimensional accuracy of stamped parts.

Method used

A method based on machine learning model is adopted to establish a rebound compensation big data model through finite element simulation prediction and data acquisition. The sample data set is trained using the convolutional neural network algorithm to directly predict the optimal rebound compensation result, reducing the trial and error iterative process.

Benefits of technology

It achieves fast, effective and low-cost mold surface compensation, improves the dimensional accuracy of stamping parts, reduces dependence on process experience, and shortens the mold production cycle.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The present application relates to the technical field of sheet stamping forming, and provides a stamping part springback compensation method and device based on a machine learning model, which comprises the following steps: setting process parameter conditions for a stamping part, setting initial values for the set process parameter conditions, and obtaining initial process parameter conditions; performing finite element sampling on the stamping part, performing CAE forming simulation springback prediction and compensation calculation, and obtaining sample data under the initial process parameter conditions; traversing parameters in the initial process parameter conditions, cyclically adjusting parameter values of each parameter, and obtaining a sample data set; preprocessing the sample data set, training a machine learning model by using the preprocessed sample data set, and obtaining a springback compensation big data model; and taking measured deviation vector values of the stamping part as input, and obtaining predicted springback compensation vector values by the springback compensation big data model. The present application can efficiently, accurately and at low cost complete stamping die surface compensation.
Need to check novelty before this filing date? Find Prior Art