Topological Optimization of Artificial Neural Networks to Estimate Mechanical Properties in Metal Forming Using Machine Learning
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...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-08-01
|
| Series: | Metals |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4701/11/8/1289 |
| _version_ | 1827684736162594816 |
|---|---|
| author | David Merayo Alvaro Rodríguez-Prieto Ana María Camacho |
| author_facet | David Merayo Alvaro Rodríguez-Prieto Ana María Camacho |
| author_sort | David Merayo |
| collection | DOAJ |
| description | 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 <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>4</mn><mo>%</mo></mrow></semantics></math></inline-formula>. Beyond this point, no really significant improvements are found, although there is an increase in computational requirements. |
| first_indexed | 2024-03-10T08:35:22Z |
| format | Article |
| id | doaj.art-9f744476b5ac487eb76669cd191288a4 |
| institution | Directory Open Access Journal |
| issn | 2075-4701 |
| language | English |
| last_indexed | 2024-03-10T08:35:22Z |
| publishDate | 2021-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Metals |
| spelling | doaj.art-9f744476b5ac487eb76669cd191288a42023-11-22T08:42:22ZengMDPI AGMetals2075-47012021-08-01118128910.3390/met11081289Topological Optimization of Artificial Neural Networks to Estimate Mechanical Properties in Metal Forming Using Machine LearningDavid Merayo0Alvaro Rodríguez-Prieto1Ana María Camacho2Department of Manufacturing Engineering, UNED, Juan del Rosal 12, 28040 Madrid, SpainDepartment of Manufacturing Engineering, UNED, Juan del Rosal 12, 28040 Madrid, SpainDepartment of Manufacturing Engineering, UNED, Juan del Rosal 12, 28040 Madrid, SpainThe 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 <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>4</mn><mo>%</mo></mrow></semantics></math></inline-formula>. Beyond this point, no really significant improvements are found, although there is an increase in computational requirements.https://www.mdpi.com/2075-4701/11/8/1289aluminum alloyartificial neural networkmechanical property<i>UTS</i>machine learningtopological optimization |
| spellingShingle | David Merayo Alvaro Rodríguez-Prieto Ana María Camacho Topological Optimization of Artificial Neural Networks to Estimate Mechanical Properties in Metal Forming Using Machine Learning Metals aluminum alloy artificial neural network mechanical property <i>UTS</i> machine learning topological optimization |
| title | Topological Optimization of Artificial Neural Networks to Estimate Mechanical Properties in Metal Forming Using Machine Learning |
| title_full | Topological Optimization of Artificial Neural Networks to Estimate Mechanical Properties in Metal Forming Using Machine Learning |
| title_fullStr | Topological Optimization of Artificial Neural Networks to Estimate Mechanical Properties in Metal Forming Using Machine Learning |
| title_full_unstemmed | Topological Optimization of Artificial Neural Networks to Estimate Mechanical Properties in Metal Forming Using Machine Learning |
| title_short | Topological Optimization of Artificial Neural Networks to Estimate Mechanical Properties in Metal Forming Using Machine Learning |
| title_sort | topological optimization of artificial neural networks to estimate mechanical properties in metal forming using machine learning |
| topic | aluminum alloy artificial neural network mechanical property <i>UTS</i> machine learning topological optimization |
| url | https://www.mdpi.com/2075-4701/11/8/1289 |
| work_keys_str_mv | AT davidmerayo topologicaloptimizationofartificialneuralnetworkstoestimatemechanicalpropertiesinmetalformingusingmachinelearning AT alvarorodriguezprieto topologicaloptimizationofartificialneuralnetworkstoestimatemechanicalpropertiesinmetalformingusingmachinelearning AT anamariacamacho topologicaloptimizationofartificialneuralnetworkstoestimatemechanicalpropertiesinmetalformingusingmachinelearning |