Enhancing 3D Printing Workflows through Multi-Objective Optimization and Reinforcement Learning Techniques

Materials, 2021

This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY

Engineering, 2019

Additive manufacturing (AM), also known as three-dimensional printing, is gaining increasing attention from academia and industry due to the unique advantages it has in comparison with traditional subtractive manufacturing. However, AM processing parameters are difficult to tune, since they can exert a huge impact on the printed microstructure and on the performance of the subsequent products. It is a difficult task to build a process-structure-property-performance (PSPP) relationship for AM using traditional numerical and analytical models. Today, the machine learning (ML) method has been demonstrated to be a valid way to perform complex pattern recognition and regression analysis without an explicit need to construct and solve the underlying physical models. Among ML algorithms, the neural network (NN) is the most widely used model due to the large dataset that is currently available, strong computational power, and sophisticated algorithm architecture. This paper overviews the progress of applying the NN algorithm to several aspects of the AM whole chain, including model design, in situ monitoring, and quality evaluation. Current challenges in applying NNs to AM and potential solutions for these problems are then outlined. Finally, future trends are proposed in order to provide an overall discussion of this interdisciplinary area.

GCSP Seminar, 2024

This study investigates the interconnection between 3D printing and artificial intelligence. The accelerated evolution of 3D printing and AI technologies presents a unique opportunity to enhance digital design and manufacturing processes. This article will provide an initial theoretical framework addressing the three main themes: generative design, additive manufacturing, and artificial intelligence. Additionally, it will outline the methodology employed in the research, detailing the approach taken to explore these interconnections. Furthermore, case studies will be presented to illustrate how these three topics converge in practical applications, demonstrating the potential for innovation and efficiency in various industries.

Elsevier, 2025

The necessity to produce intricate components results in considerable progress in manufacturing methods. Additive manufacturing (AM) is a disruptive technology that allows intricate and custom-tailored components to be fabricated with great precision and efficiency. It is applied in advanced sectors like aerospace, healthcare, automotive industries, and it starts having their interest in many other areas. Machine learning (ML) has become a powerful tool for overcoming problems in AM, offering process efficiency, defect detection, quality assurance, and predictive modelling of mechanical properties. This review discusses how ML transforms AM by providing design evaluation, process optimization, and production control innovation. The approach taken in the study is systematic, examining the current literature and case studies of ML application to AM. Hybrid data collection techniques that combine machine settings with physics aware features and yield robust predictive models are the focus. Additionally, the review evaluates various ML algorithms used to predict mechanical properties, optimize process parameters, and characterize AM processes. The measurements indicate groundbreaking improvements in ML powered solutions, like process monitoring in real time, automatic parameter adaptation, and defect mitigation that offer greater accuracy, ease, and reliability in AM. Yet, data scarcity, computational challenges and a gap between research and industrial applications of ML exist. To realize the full potential of ML in AM it is critical to address these challenges. It closes with the identification of promising research directions including standardization of data improvement, developing

This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY

Journal of Materials Engineering and Performance, 2022

Additive manufacturing (AM) has emerged as a promising technology to cater to the increasing demand for the fabrication of multi-functional, multi-material, and complex parts. AM is revolutionizing production and product development in the aerospace, automotive, and medical fields. However, mismatch in material properties, pervasive imperfections in the printed part, and lack of build consistency are crucial concerns. Higher accuracy in AM processes primarily depends on controlling various aspects of the process. In the last few years, machine learning, data analytics, and design for additive manufacturing have been the most extensively used techniques to address the vital concerns of additive manufacturing. Despite well-known techniques, very few studies reported applications of these techniques for aerospace. Specifically, this study comprehensively reviews recent advancements in the design for additive manufacturing (DfAM) and applications of machine learning and big data analytics to address the prime concerns of AM. The DfAM emphasizes issues and opportunities for topology optimization and methods for generative design for weight reduction and manufacturing of products with high resolution. Simulation and modeling techniques that are being used to improve geometric quality and process analysis are discussed to enable its potential for different applications. Further, automation of AM process using the Internet of things and knowledge-based systematic process planning is discussed to address key issues in process planning of multiple parts. Finally, the current challenges and scope for algorithmically driven AM processes are summarized with the trends of automation in AM to ensure greater efficiency and a better lifecycle of AM products in the era of industry 4.0.

International Journal for Numerical Methods in Engineering, 2019

SummaryThe ever‐present drive for increasingly high‐performance designs realized on shorter timelines has fostered the need for computational design generation tools such as topology optimization. However, topology optimization has always posed the challenge of generating difficult, if not impossible to manufacture designs. The recent proliferation of additive manufacturing technologies provides a solution to this challenge. The integration of these technologies undoubtedly has the potential for significant impact in the world of mechanical design and engineering. This work presents a new methodology which mathematically considers additive manufacturing cost and build time alongside the structural performance of a component during the topology optimization procedure. Two geometric factors, namely, the surface area and support volume required for the design, are found to correlate to cost and build time and are controlled through the topology optimization procedure. A novel methodolo...

Materials

Technological and material issues in 3D printing technologies should take into account sustainable development, use of materials, energy, emitted particles, and waste. The aim of this paper is to investigate whether the sustainability of 3D printing processes can be supported by computational intelligence (CI) and artificial intelligence (AI) based solutions. We present a new AI-based software to evaluate the amount of pollution generated by 3D printing systems. We input the values: printing technology, material, print weight, etc., and the expected results (risk assessment) and determine if and what precautions should be taken. The study uses a self-learning program that will improve as more data are entered. This program does not replace but complements previously used 3D printing metrics and software.

2018

Machine learning is becoming an increasingly popular concept in the modern world since its main goal is to optimize systems by allowing one to make smarter and effective use of materials, products and services. In the manufacturing industry machine learning can lead to increased quality, lead time reduction, minimized cost, etc. At the same time, it enables systems to be designed for managing human behaviour. This research study used a systematic review to investigate the different machine learning algorithms within the sustainable manufacturing context. This paper focuses on additive manufacturing with optimized scheduling, process chains and quality assurance as applications.

ArXiv, 2021

In this paper, we propose PATO—a producibility-aware topology optimization (TO) framework to help efficiently explore the design space of components fabricated using metal additive manufacturing (AM), while ensuring manufacturability with respect to cracking. Specifically, parts fabricated through Laser Powder Bed Fusion (LPBF) are prone to defects such as warpage or cracking due to high residual stress values generated from the steep thermal gradients produced during the build process. Maturing the design for such parts and planning their fabrication can span months to years, often involving multiple handoffs between design and manufacturing engineers. PATO is based on the a priori discovery of crack-free designs, so that the optimized part can be built defect-free at the outset. To ensure that the design is crack free during optimization, producibility is explicitly encoded within the standard formulation of TO, using a crack index. Multiple crack indices are explored and using ex...