Machine Learning Based Prognostics of Fatigue Crack Growth in Notch Pre-cracked Aluminum 7075-T6 Rivet Hole

Abstract

Constant stress amplitude fatigue tests were conducted on the notch pre-cracked Aluminum 7075-T6 rivet hole dog-bone coupons. Monitoring of visible surface crack length by special surface engraving using digital microscope images and by ultrasonic sensors signals was carried out to yield fatigue crack length measurements in relation to number of fatigue cycles applied. The experimental results provide ultrasonic sensor validation for fatigue crack length measurements. Fracto-graphic examination of failed fatigue surfaces has provided further confirmation of notch pre-crack length, crack initiation process, and crack growth marker bands. These experimental inputs were used in NASGRO and AFGROW software fatigue crack growth simulations. The simulation results did not match the crack initiation fatigue life measured by experiments. However, there was good agreement with crack growth simulations of larger cracks. Hence, we plan to develop a machine learning application that will learn the fatigue crack initiation and crack growth processes from data obtained from our own experiments and other fatigue data available from AFGROW databases. Nonlinear AutoRegressive models with eXogenous input (NARX) artificial neural network were used to predict crack growth longer than 5.0-mm. Particle filtering modeling with Bayesian updating was applied to these experimental data for prognostics of fatigue crack growth. A concept design and preliminary implementation results will be presented.

Fatigue modeling using neural networks: A comprehensive review

“…The physical meaning is that the slope of the N – a curve is larger than the real value, which means an unstable crack growth. Similar work can be found in Haynes et al 153 Ma et al 154 developed an FNN model for a – N curve extrapolation with small data size in another recent work. The data on the first part of the curve is used as training data to predict the remaining part, as shown in Figure 12.…”

Machine learning and finite element analysis: An integrated approach for fatigue lifetime prediction of adhesively bonded joints

“…Several authors have applied ML-based models for the prediction of fatigue crack growth. [30][31][32] Shiraiwa et al 33 have combined FEA and ML-based methods (artificial neural network, henceforth ANN) to predict the fatigue performance of welded structures. Kadi and Al-Assaf 34 employed an ANN to predict the fatigue of unidirectional composites.…”

Prediction of Fatigue Crack Growth Behaviour in Ultrafine Grained Al 2014 Alloy Using Machine Learning

“…Haynes e al. [7] reported that the NASGRO and AFGRO approaches to predict the fatigue life cycles were found to be incorrect by ten-folds because of its inability to predict equivalent initial flaw size. An et al [8] used Bayesian approach using Markov Chain Monte Carlo (MCMC) technique to predict fatigue life of the turbine components using available field data.…”