Machine learning‐based genetic feature identification and fatigue life prediction

Abstract

Considering the nonlinear relationship between variables and fatigue life and the computational burden, a machine learning method integrating the artificial neural network (ANN) and partial least squares (PLS) algorithm was proposed as a framework to identify the genetic features through optimizing fatigue life prediction. Twenty‐seven specimens of 316LN stainless steel under uniaxial and multiaxial loadings were used as examples. As results, early fatigue data were proved to be informative for fatigue life prediction. Moreover, five genetic features were identified out of them, and a predicting model was developed. The predicted fatigue life of these samples using only these five genetic features were all located within the 1.5‐factor band. This framework can be easily extended to identify genetic features and to predict fatigue life of other materials under different loadings. Therefore, it provides an efficient option in this field to greatly reduce experimental time and cost.

Effect of the porosity on the fatigue strength of metals

“…12-18), and biaxial loading (test No. [19][20][21][22][23][24][25][26][27][28][29][30][31][32][33][34][35][36]. Note that, for tests performed at the same stress level (for instance, test No.…”

“…12-18), and biaxial loading (test No. [19][20][21][22][23][24][25][26][27][28][29][30][31][32][33][34][35][36]. Moreover, also the experimental values of fracture plane orientation, θ exp , 9,10 (see Section 4) are reported in Table 5.…”

“…It is worth noting that the great potential of the present procedure is that the defect content analysis (performed by means of a statistical method deriving from EVT) can be easily performed by using machine learning techniques. It deserves to be mentioned that, in the last years, a great effort has been made by researchers in order to extend the use of the machine learning techniques to the fatigue field 18–20 . As a matter of fact, it has been proven that fatigue problems are appropriate for the machine learning analysis, mainly due to the large amount, complexity, and uncertainty of the available data 21 …”

“…It deserves to be mentioned that, in the last years, a great effort has been made by researchers in order to extend the use of the machine learning techniques to the fatigue field. [18][19][20] As a matter of fact, it has been proven that fatigue problems are appropriate for the machine learning analysis, mainly due to the large amount, complexity, and uncertainty of the available data. 21 The present work is structured as follows.…”

Fatigue damage detection and risk assessment via neural network modeling of ultrasonic signals

“…Zapico 17 studied the damage assessment of steel structures using the ANN method. Zhou et al 18 applied the concepts of ANN and partial least squares to identify the genetic features through optimizing fatigue life prediction. Bao et al 19 used the support vector regression model to study the influence of defect location, size, and morphology on the fatigue life of a selective laser melted Ti‐6Al‐4V alloy.…”