Session: 03-10-02: Laser-Based Advanced Manufacturing and Materials Processing

Paper Number: 145983

145983 - Accelerating Microstructure and Melt Pool Prediction in Laser Powder Bed Fusion Processes Using Data Driven Neural Network 

 Laser powder bed fusion (LPBF) is a pivotal additive manufacturing process characterized by selective melting and solidification of powder layers to form complex parts. The microstructure of the final part plays a crucial role in determining its proper􀆟es, which is heavily influenced by process parameters such as laser power, scanning speed, powder layer thickness, and material proper􀆟es. Understanding the influence of process parameters on melt pool geometry is crucial for minimizing defects due to unmelted powder regions and optimizing hatch spacing. Additionally, the microstructure plays a vital role, as process parameters can lead to the formation of columnar grains, promoting anisotropy in the fabricated parts. Therefore, understanding microstructural characteristics is key to ensuring the reliability of manufactured parts. Predicting the microstructure and melt pool geometry in laser powder bed fusion (LPBF) processes via finite element modeling is computationally demanding and 􀆟me-intensive. To mitigate these challenges, we propose the development of a machine learning model capable of accurately predicting melt pool geometry and microstructure based on process parameter variation, thereby reducing time in the identification of optimal process parameters for further experimental investigation. This study utilizes a physics-based numerical model within ANSYS Additive to predict melt pool geometry and microstructure in LPBF process. The model's accuracy was validated using single-track metal additive manufacturing (AM) experiments extracted from relevant literature. A comprehensive database was compiled by combining numerical and experimental data, including melt pool geometry, microstructure, process parameters, and material properties. This dataset was then employed to train a data-driven model, with process parameters and material properties serving as inputs and melt pool width, depth, and microstructure images as outputs. Additionally, the images were resized to 256x256 pixels for computational efficiency. Various neural network architectures, including Multilayer Perceptron (MLP) and convolutional Neural Networks (CNN), were utilized to enhance the predictive capabilities of the model. These architectures were trained and fine-tuned to achieve precise predictions that closely matched both experimental and numerical findings. The study showcased the efficiency of neural networks in accurately predicting melt pool geometry and microstructure, significantly reducing prediction time compared to conventional numerical simulations by several orders of magnitude. Future research direction will focus on incorporating physics constraints into the loss function to accelerate the training process, thereby reducing the number of epochs required. However, the development of a rapid data-driven model with minimal mean absolute error is vital for enhancing part optimization and promoting the widespread adoption of MAM.

Presenting Author: Samir Mekid King Fahd University of Petroleum and Minerals

Presenting Author Biography: Dr. Samir Mekid Professor of Mechanical Engineering at the Department of Mechanical Engineering (KFUPM) and the Director of Intelligent Manufacturing and Robotics Research Center at KFUPM. He is a Chartered Engineer registered in London (UK) by IMECHEH. His research is focused on Intelligent Manufacturing including processes, I4.0, automation, and high-performance materials, robotics in underwater, ground, and aerial with fault tolerance and AI-based control. Before joining KFUPM, Samir served as an Assistant Professor at UMIST (UK) since 2001 which became later The University of Manchester (UK). He worked with Caterpillar in the Design Office for two years and consultant to many industrial companies. He has published more than 120 research papers, 2 books in CRC and Springer, and about two dozen Patents.

Authors:

Abdul Qadeer King Fahd University of Petroleum and Minerals
Syed Sohail Akhtar King Fahd University of Petroleum and Minerals
Abba Abdulhamid Abubakar King Fahd University of Petroleum and Minerals
Abul Fazal Arif King Fahd University of Petroleum and Minerals
Samir Mekid King Fahd University of Petroleum and Minerals
Khaled Saleh Al-Athel King Fahd University of Petroleum and Minerals