Residual stress field inference method using structured latent Gaussian process with structured-covariances

Zhiwei Zhao, Yingguang Li*, Changqing Liu, Yifan Zhang

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

Abstract

Residual stress field distributed within materials is one of the important properties of the material, which influences the manufacturing precision and fatigue life of part, especially for component with large size and complex residual stress field. Accurately obtaining the overall residual stress field within parts serves as a vital reference for optimizing manufacturing and assembly processes. Although the residual stress fields could be estimate by related observable physical quantity, the characteristics of residual stress fields, including a large number of unknowns and multiple fields, present significant challenge for the solving process. Introducing prior knowledge as the constrains for the possible solution is an effective method for achieving accurate inference of residual stress fields. In this paper, a method for inferring residual stress field which employed Structured Latent Gaussian Process with structured covariance is proposed. The unobservable residual stress field is modeled as a latent Gaussian process with structured covariance, formed by Kronecker product considering the correlations across different directions of the residual stress and the prior knowledge of similarities between partial fields. By introducing structured prior information, the large covariance matrix estimation is transformed into the estimation of several smaller matrices, which significantly reduces the number of unknowns to be estimated, and it makes the inference of residual stress fields with numerous variables using limited observable data feasible. Simulation and experimental validation results demonstrate that the incorporation of such prior information can enhance the accuracy and reliability of the inferred residual stress fields.
Original languageEnglish
Pages (from-to)14-26
JournalJournal of Manufacturing Systems
Volume79
Early online date03 Jan 2025
DOIs
Publication statusEarly online date - 03 Jan 2025

Keywords

  • stress field inference
  • Gaussian
  • structured-covariances
  • Residual stress

Fingerprint

Dive into the research topics of 'Residual stress field inference method using structured latent Gaussian process with structured-covariances'. Together they form a unique fingerprint.

Cite this