Simple heuristic for data-driven computational elasticity with material data involving noise and outliers: a local robust regression approach
- 39 Downloads
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. For data-driven computing in elasticity, this paper presents a simple heuristic that is robust against noise and outliers in a 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 outliers. Numerical experiments on the static equilibrium analysis of trusses are performed to illustrate that the proposed method is robust against the presence of noise and outliers.
KeywordsData-driven computing Model-free computational mechanics Outlier Local regression Robust statistics
Mathematics Subject Classification62J05 80M50 90C20
This work is partially supported by JSPS KAKENHI 17K06633 and 18K18898.
- 4.Chen, H., Chiang, R.H.L., Storey, V.C.: Business intelligence and analytics: from big data to big impact. MIS Q. Arch. 36, 1165–1188 (2012)Google Scholar
- 34.Wang, H., O’Brien, J.F., Ramamoorthi, R.: Data-driven elastic models for cloth: modeling and measurement. ACM Trans. Graph. 30, Article No. 71 (2011)Google Scholar