Prediction of fatigue crack growth rate in aircraft aluminum alloys using optimized neural networks

In aerospace industry, Fatigue Crack Propagation pose a serious threat to the professionals involved in designing mechanical assembly of aircraft structures. these structures crack growth is problem that needs be handled seriously, as human life risk concerned addition economic loss. Growth (FCG) Rate rate at which grows with number cycles subjected constant amplitude loading. FCG curve drawn between on y-axis and Stress Intensity Factor (SIF) range x-axis. It predicted accurately avoid losses. Upon analyzing curve, it becomes obvious correlation ranges “?K” “da/dN” deviating linear relationship considering region II also called Paris Region. Empirical formulation methods cannot deal linearity factor satisfactorily. Other hybrid techniques are found incapable dealing non-linearity suitably. contrast prior methods, machine learning algorithms capable issue much better way owing their admirable ability flexible nature. this research work three distinct MLA based Optimized Neural Networks utilized for prediction rate. The used include Genetic Algorithm Network, Hill Climbing Network Simulated Annealing Network. presented proposed technique validated by testing different aluminum alloys industry includes 2324-T39, 7055-T7511 6013-T651 alloys. least MSE 2324-T39 alloy achieved 3.1069×10-8. For alloy, minimum 1.4284×10-9 Finally, 1.0559×10-9 optimized Taking all experiments were held algorithms, attained Aluminum Alloy Moreover, results demonstrate an exceptional conformity data conceived during experimentation process.