Predicting crack in a beam-like structure through an over fitting verified regression model

Abstract

Purpose The purpose of this paper is to identify the crack in beam-like structures before the complete failure or damage occurs to the structure. The beam-like structure plays an important role in modern architecture; hence, the safety of this structure is much dependent on the safety of the beam. Hence, predicting the cracks is much more important for the safety of the overall structure. Design/methodology/approach In the present work, the regression analysis has been carried out through LASSO and Ridge regression models. Both the statistical models have been well implemented in the detection of crack depth and crack location. A cantilever beam-like structure has been taken for the analysis in which the first three natural frequencies have been considered as the independent variable and crack location and depth is used as the dependent variable. The first three natural frequencies, f1, f2 and f3 are used as an independent variable. The crack location and crack depth are estimated though the regressor models and the accuracy are compared, to verify the correctness of the estimation. Findings As stated in the purpose of work, the main aim of the present work is to identify the crack parameters using an inverse technique, which will be more effective and will provide the results with less time. The data used for regression analysis are obtained from theoretical analysis and later the theoretical results are also verified through experimental analysis. The regression model developed is tested for its Bias Variance Trade-off (“Bias” – Overfitting, “variance” – generalization). The regression results have been compared with the theoretical results to check the robustness in the subsequent result section. Originality/value The idea is an amalgamation of existing and well-established technologies, that is aimed to achieve better performance for the given task. A regressor is trained from the data obtained through numerical simulation. The model is developed taking bias variance trade-off into consideration. This generalized model gives us very much acceptable performance.