Topological Optimization of Artificial Neural Networks to Estimate Mechanical Properties in Metal Forming Using Machine Learning

Abstract

The ability of a metal to be subjected to forming processes depends mainly on its plastic behavior and, thus, the mechanical properties belonging to this region of the stress–strain curve. Forming techniques are among the most widespread metalworking procedures in manufacturing, and aluminum alloys are of great interest in fields as diverse as the aerospace sector or the food industry. A precise characterization of the mechanical properties is crucial to estimate the forming capability of equipment, but also for a robust numerical modeling of metal forming processes. Characterizing a material is a very relevant task in which large amounts of resources are invested, and this paper studies how to optimize a multilayer neural network to be able to make, through machine learning, precise and accurate predictions about the mechanical properties of wrought aluminum alloys. This study focuses on the determination of the ultimate tensile strength, closely related to the strain hardening of a material; more precisely, a methodology is developed that, by randomly partitioning the input dataset, performs training and prediction cycles that allow estimating the average performance of each fully-connected topology. In this way, trends are found in the behavior of the networks, and it is established that, for networks with at least 150 perceptrons in their hidden layers, the average predictive error stabilizes below 4%. Beyond this point, no really significant improvements are found, although there is an increase in computational requirements.

A Survey of Datasets, Preprocessing, Modeling Mechanisms, and Simulation Tools Based on AI for Material Analysis and Discovery

“…The study [70] focuses on determining the ultimate tensile strength pertaining to the strain hardening of a material. In other words, the authors developed a methodology by dividing a data set into different categories randomly.…”

New approaches for a reliable fatigue life prediction of powder metallurgy components using machine learning

“…Merayo et al 35 studied the influence of the number of neurons of a two layer ANN to predict the tensile strength of wrought aluminum alloys based on material composition and heat treatments. The study finds that large ANNs with more than 150 neurons in both layers show good results with errors below 4% while not investigating the influence on the computational resources.…”

Management Control and Integration Technology of Intelligent Production Line for Multi-Variety and Complex Aerospace Ring Forgings: A Review

“…In the field of movement posture, Merayo et al [50] accurately predicted the UTS (ultimate tensile strength) in the mechanical properties of materials through machine learning so as to judge whether the product would suffer from plastic instability. Hua et al [51] established an analytical model based on the relationship between rolling power, torque, and force in the rolling process and found that the revised analytical model was in good agreement with the finite element analysis results, which provided a design basis for the key force parameters.…”