Simple Heuristic for Data-Driven Computational Elasticity with Material Data Involving Noise and Outliers: A Local Robust Regression Approach

TL;DR

This paper introduces a robust local regression method for data-driven elasticity analysis that effectively handles noise and outliers in material data, improving reliability in real-world applications.

Contribution

It proposes a simple heuristic using nearest neighbors and robust regression for data-driven elasticity, enhancing robustness against noise and outliers compared to existing methods.

Findings

Method is robust against noise and outliers.

Numerical experiments confirm effectiveness for real-world data.

Improves reliability of data-driven structural analysis.

Abstract

Data-driven computing in applied mechanics utilizes the material data set directly, and hence is free from errors and uncertainties stemming from the conventional material modeling. This paper presents a data-driven approach that is robust against noise and outliers in the data set. For each structural element, we extract the material property from some nearest data points. Using the nearest neighbors reduces the influence of noise, compared with the existing method that uses a single data point. Also, the robust regression is adopted to reduce the influence of the outliers. Numerical experiments on static equilibrium analysis of trusses are performed to illustrate that the proposed method is robust against the presence of noise and outliers and, hence, is effective for dealing with real-world data.