Exploiting the adaptive neural fuzzy inference system for predicting the effect of notch depth on elastic new strain-concentration factor under combined loading

Document Type

Article

Publication Date

6-1-2024

Abstract

In this paper, a novel machine-learning based models are presented to predict the effect of notch depth on elastic new strain-concentration factor of rectangular bars with single edge U-notch under combined loading of static tension and pure bending. Regarding the importance of this study, the database with 162 samples is utilized to develop the new methodology of machine learning based models. The database includes the notch radius, the Poisson’s ratio, and the thick ratio that represent the influential inputs. The predicted key feature is the elastic new strain-concentration factor under combined loading of static tension and pure bending. These samples were tested with high precision and the predicted values of SNCF were obtained. For comparison, adaptive neural fuzzy inference system, artificial neural network, fine tree, ensemble boosted tree, and ensemble optimized bagged tree were designed and developed in this study. To evaluate and compare the performance of the models, four statistical indices of MAE, MSE, root mean square error (RMSE)and determination coefficient (R) were utilized. Based on the results, all models can predict the SNCF appropriately. However, the Ensemble optimized Bagged tree model had a better performance than other models and it had a significant priority in term of prediction accuracy. Finally, the results indicated that the elastic SNCF increased with increasing notch depth from 0.2 ≤ ho/Ho ≤ 0.7 and sharply decreases with increasing notch depth for shallow notches (0.8 ≤ ho/Ho ≤ 0.95).

Identifier

85170359612 (Scopus)

Publication Title

Cluster Computing

External Full Text Location

https://doi.org/10.1007/s10586-023-04131-6

e-ISSN

15737543

ISSN

13867857

First Page

3055

Last Page

3073

Issue

3

Volume

27

This document is currently not available here.

Share

COinS