Small sample area selection laser melting process parameter multi-objective optimization method and related equipment

By constructing relative density and crack density prediction models using Gaussian process regression and Bayesian optimization algorithms, the high cost and low efficiency problems in the optimization of selective laser melting process parameters are solved, achieving high-precision and rapid multi-objective optimization, which is applicable to selective laser melting processes with different equipment and materials.

CN122366077APending Publication Date: 2026-07-10SHANGHAI ZHONGTIAN SCIENCE & TECHNOLOGY AEROSPACE TECHNOLOGY CO LTD
View PDF 1 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN Β· China
Patent Type
Applications(China)
Current Assignee / Owner
SHANGHAI ZHONGTIAN SCIENCE & TECHNOLOGY AEROSPACE TECHNOLOGY CO LTD
Filing Date
2026-03-06
Publication Date
2026-07-10

AI Technical Summary

Technical Problem

Existing methods for optimizing selective laser melting process parameters suffer from high experimental costs, long cycles, and low efficiency. They also struggle to simultaneously achieve the goals of high relative density and low crack density, and the models lack accuracy and reliability, especially with small sample data where they are prone to overfitting and insufficient validation.

Method used

A Gaussian process regression method is used to construct a prediction model for relative density and crack density. The Matrn kernel function is used to describe the nonlinear relationship. White noise is introduced to kernelize the noise. The optimal parameters are searched in the process parameter space by combining the Bayesian optimization algorithm.

Benefits of technology

It achieves high-precision prediction and multi-objective optimization with small sample data, quickly finds the optimal process parameters, reduces experimental costs and time, and is applicable to selective laser melting processes with different equipment and materials.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122366077A_ABST
    Figure CN122366077A_ABST
Patent Text Reader

Abstract

This invention discloses a multi-objective optimization method and related equipment for small-sample selected area laser melting process parameters, relating to the field of metal additive manufacturing technology. The method includes: acquiring a sample dataset obtained from selected area laser melting forming experiments under a preset combination of laser power and scanning speed parameters; constructing a relative density prediction model and a crack density prediction model using a Gaussian process regression method, and training the relative density prediction model and crack density prediction model respectively using the sample dataset; wherein the covariance function used in the Gaussian process regression method is the Matrn kernel function, and a white noise kernel is introduced into the covariance function; based on the trained relative density prediction model and crack density prediction model, searching for the optimal process parameters in the process parameter space using a Bayesian optimization algorithm. This invention can efficiently and accurately achieve multi-objective optimization of selected area laser melting process parameters.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • SLM forming performance prediction and process parameter optimization method and system

    CN116204998A