Investigation of Single and Dual Step Shot Peening Effects on Mechanical and Metallurgical Properties of 18CrNiMo7-6 Steel Using Artificial Neural Network

Abstract

Abstract-Shot peening is a process of cold working a part that increase its resistance to metal fatigue and some forms of stress corrosion. Shot peening causes plastic deformation in the surface of the peened part and leads some changes in mechanical and metallurgical properties of it. Artificial intelligence (AI) systems such as artificial neural networks (ANNs) have found many applications to predict and optimize the engineering problems in the last few years. In present study effects of SP on mechanical and metallurgical properties of 18CrNiMo7

Prediction of residual stress fields after shot-peening of TRIP780 steel with second-order and artificial neural network models based on multi-impact finite element simulations

“…However, no new data with different process parameters were predicted in this study. In another study from [50] on shot-peening of 18CrNiMo-6 steel exhibiting an austenite to martensite phase transformation, an ANN algorithm was used to predict the residual stress profiles in austenite and martensite, the volume fraction of retained austenite, microhardness, and domain size obtained from Cauchy breadth of diffraction peaks. Only 3 different profiles obtained from 3 different sets of process parameters were used.…”

Parametric analysis of collapse load factor of planar frames

“…well-known algorithms such as the feed-forward error back-propagation (BP) algorithm are employed to train the networks that are using a gradient descent technique to minimize the error for a particular training pattern. The accuracy of the developed model can increase along with the number of datasets [44]. In the present study, CLF of the planar frames was modeled using the ANN technique.…”

Modeling of Severe Shot Peening Effects to Obtain Nanocrystalline Surface on Cast Iron Using Artificial Neural Network

“…The best solution is obtained by trial and error. One can get an idea by looking at a problem and decide to start with simple networks; going on to complex ones till the solution is within the acceptable limits of error.In the present study, the feed forward error back propagation algorithm is used for ANN training.The Back Propagation algorithm defines a systematic way to update the synaptic weights of multi-layer feed forward supervised networks composed of an input layer that receives the input values, an output layer, which calculates the neural network output, and one or more intermediary layers, so called hidden layers [24]. The back propagation supervised learning process is based on the gradient descent method that usually minimizes the sum of squared errors between the target value and the output of the neural network [25].…”