https://popups.uliege.be/esaform21/index.php?id=2813 Index terms fr 0 https://popups.uliege.be/esaform21/index.php?id=2812 In the last decade, machine learning is increasingly attracting researchers in several scientific areas and, in particular, in the additive manufacturing field. Meanwhile, this technique remains as a black box technique for many researchers. Indeed, it allows obtaining novel insights to overcome the limitation of classical methods, such as the finite element method, and to take into account multi-physical complex phenomena occurring during the manufacturing process. This work presents a comprehensive study for implementing a machine learning technique (artificial neural network) to predict the thermal field evolution during the direct energy deposition of 316L stainless steel and tungsten carbides. The framework consists of a finite element thermal model and a neural network. The influence of the number of hidden layers and the number of nodes in each layer was also investigated. The results showed that an architecture based on 3 or 4 hidden layers and the rectified linear unit as the activation function lead to obtaining a high fidelity prediction with an accuracy exceeding 99%. The impact of the chosen architecture on the model accuracy and CPU usage was also highlighted. The proposed framework can be used to predict the thermal field when simulating multi-layer deposition. Wed, 24 Mar 2021 19:04:24 +0100 Mon, 12 Apr 2021 11:18:39 +0200 https://popups.uliege.be/esaform21/index.php?id=2812 https://popups.uliege.be/esaform21/index.php?id=1995 In this paper, an Artificial Neural Network (ANN) is used to predict the stress-strain behavior of PET at conditions relevant to Stretch Blow Moulding i.e. Large equibiaxial deformation at elevated temperature and high strain rate. The input vectors considered are temperature, strain, and strain rate with a corresponding output parameter of stress. In the present work, a feed-forward back backpropagation algorithm was used to train the ANN. The ANN is able to approximate the relationship between stress and strain at various strain rates & temperatures to a high degree of accuracy for all conditions tested. Tue, 23 Mar 2021 12:22:27 +0100 Mon, 12 Apr 2021 10:21:39 +0200 https://popups.uliege.be/esaform21/index.php?id=1995 https://popups.uliege.be/esaform21/index.php?id=4140 A limited number of material models or flow curves are available in commercial finite element softwares at varying temperature and strain rate ranges for plasticity analysis. To obtain more realistic finite element results, flow curves at wide temperature and strain rate ranges are required. For this purpose, a material model for a medium carbon alloy steel material which is used for fastener production was prepared. Firstly, flow curves of the material were obtained at 4 temperatures (20, 100, 200, 400 °C) and 3 strain rates (1, 10, 50 s-1). Then, experimental data was used to construct an artificial neural networks model (ANN) for the material. 75% of the experimental data was used to train the model and the rest was employed for validation and verification. ANN model used in flow curve prediction was developed using the scikit-learn library on Python. Temperature, strain rate and strain were employed as input parameters and flow stress as output parameter in ANN model. In order to increase the accuracy of the ANN model, the number of hidden layers and the number of neurons were also optimized by mean squared error approach. As a result of studies, an ANN-based material model that can be used for wide range of temperature and strain rate values were developed based on the experimental data. Wed, 31 Mar 2021 14:41:13 +0200 Wed, 31 Mar 2021 14:41:13 +0200 https://popups.uliege.be/esaform21/index.php?id=4140