Analysing the Fatigue Behaviour and Residual Stress Relaxation of Gradient Nano-Structured 316L Steel Subjected to the Shot Peening via Deep Learning Approach

Abstract

In this study, the effect of kinetic energy of the shot peening process on microstructure, mechanical properties, residual stress, fatigue behavior and residual stress relaxation under fatigue loading of AISI 316L stainless steel were investigated to figure out the mechanisms of fatigue crack initiation and failure. Varieties of experiments were applied to obtain the results including microstructural observations, measurements of hardness, roughness, induced residual stress and residual stress relaxation as well as axial fatigue test. Then deep learning approach through neural networks was used for modelling of mechanical properties and fatigue behavior of shot peened material. Comprehensive parametric analyses were performed to survey the effects of different key parameters. Afterward, according to the results of neural network analysis, further experiments were performed to optimize and experimentally validate the desirable parameters. Based on the obtained results the favorable range of shot peening coverage regarding improved mechanical properties and fatigue behavior was identified as no more than 1750% considering Almen intensity of 21 A (0.001 inch). Graphic abstract

Application of Deep Neural Network to Predict the High-Cycle Fatigue Life of AISI 1045 Steel Coated by Industrial Coatings

“…Overall, 77 and 23% of obtained experimental data was used for networks training and testing processes, respectively. Employed methodology in this study is presented in Figure 3a (similar methodology to the one used by Maleki et al [63,65]). Different SNNs and DNNs by trial-and-error approach were developed; Figure 3b depicts the architecture of the DNN with four hidden layers that w, b and f represent the weight matrixes, bias vectors, and transfer function in each related layer, respectively.…”

“…As the primary generation of artificial neural networks, shallow neural networks (SNNs) that have 1 or 2 hidden layers were mostly used in simulations of the ill-defined problems [63]. However, it is approved by developing Deep Neural Network (DNN) that has more hidden layers (more than 2), higher accuracy in the predicted results can be obtained with same or smaller data set [64,65]. The NNs are the most frequently employed machine learning approach for fatigue life prediction in the last decade [66].…”

Influences of Shot Peening Parameters on Mechanical Properties and Fatigue Behavior of 316 L Steel: Experimental, Taguchi Method and Response Surface Methodology

“…Moreover, the results of microstructural characterization were used to calculate the depth of the deformed layer. The depth of this layer of coarse grains (similar to the grains of the not shot peened material) can be considered as the depth of the deformed layer [76,77]. In this study, an average of seven times measurements of depth in different areas was regarded as the depth of the deformed layer.…”

High-cycle fatigue S-N curve prediction of steels based on a transfer learning-guided convolutional neural network

“…For example, fatigue research based on ML has made significant progress in both fatigue strength prediction [18][19][20][21][22][23][24] and fatigue crack-driving force prediction [25] . Several researchers have recently developed ML-based models for fatigue life prediction [26][27][28][29][30][31][32] . Zhang et al proposed a neuro-fuzzy-based ML method for predicting the high-cycle fatigue life of laser powder bed fusion stainless steel 316 L under different processing conditions, postprocessing treatments, and cyclic stresses [26] .…”

“…Furthermore, based on deep learning of long short-term memory networks, Yang et al established a more general life-prediction method for the multiaxial fatigue of materials [30] . In a study by Maleki et al, a deep neural network was utilized for fatigue behavior prediction and analysis of a coated AISI 1045 mild carbon steel and AISI 316L stainless steel, which demonstrated a promising approach for deep learning in fatigue behavior modeling [31,32] . The above-mentioned works show that ML-based models present good applicability for the fatigue life prediction of different materials facing complex mechanisms and various conditions.…”