Machine learning in additive manufacturing: State-of-the-art and perspectives
TL;DR: A comprehensive review on the state-of-the-art of ML applications in a variety of additive manufacturing domains can be found in this paper, where the authors provide a section summarizing the main findings from the literature and provide perspectives on some selected interesting applications.
Abstract: Additive manufacturing (AM) has emerged as a disruptive digital manufacturing technology. However, its broad adoption in industry is still hindered by high entry barriers of design for additive manufacturing (DfAM), limited materials library, various processing defects, and inconsistent product quality. In recent years, machine learning (ML) has gained increasing attention in AM due to its unprecedented performance in data tasks such as classification, regression and clustering. This article provides a comprehensive review on the state-of-the-art of ML applications in a variety of AM domains. In the DfAM, ML can be leveraged to output new high-performance metamaterials and optimized topological designs. In AM processing, contemporary ML algorithms can help to optimize process parameters, and conduct examination of powder spreading and in-process defect monitoring. On the production of AM, ML is able to assist practitioners in pre-manufacturing planning, and product quality assessment and control. Moreover, there has been an increasing concern about data security in AM as data breaches could occur with the aid of ML techniques. Lastly, it concludes with a section summarizing the main findings from the literature and providing perspectives on some selected interesting applications of ML in research and development of AM.
Citations
More filters
TL;DR: In this article, the authors review the most recent research momentum regarding the formation mechanisms (elemental segregation, dislocation cell and oxide inclusion), the kinetics of the size and morphology, the growth orientation and the thermodynamic stability of these cellular structures by taking AM austenitic stainless steel as an exemplary material.
Abstract: The quick-emerging paradigm of additive manufacturing technology has revealed salient advantages in enabling the tailored-design of structural components with more exceptional performances over ordinary subtractive processing routines. As a peculiar feature, sub-micro cellular structures widely exist in additively manufactured (AM) metallic materials. This phenomenon primarily appears with high-density dislocations and segregated elements or precipitates at the cellular boundaries. The discovery of novel metastable substructures in various alloys through numerous investigations has proven their substantial effects on the engineering properties of AM components. This paper reviews the most recent research momentum regarding the formation mechanisms (elemental segregation, dislocation cell and oxide inclusion), the kinetics of the size and morphology, the growth orientation and the thermodynamic stability of these cellular structures by taking AM austenitic stainless steel as an exemplary material. Another topic of concern here is the inherent correlation between the unique cellular microstructure and the corresponding mechanical properties (strength, ductility, fatigue, etc.) and corrosion responses (passivity, irradiation damage, hydrogen embrittlement, etc.) for this category of AM materials. The design, control, and optimization of cellular structures for additive manufacturing techniques are expected to inspire new strategies for advancing high-performance structural alloy development.
149 citations
TL;DR: The adoption of laser powder bed fusion (L-PBF) for metals by the industry has been limited despite the significant progress made in the development of the process chain this paper.
Abstract: The adoption of laser powder bed fusion (L-PBF) for metals by the industry has been limited despite the significant progress made in the development of the process chain. One of the key obstacles i...
87 citations
Journal Article•
TL;DR: In this article, a new approach to design hierarchical materials using machine learning, trained with a database of hundreds of thousands of structures from finite element analysis, together with a self-learning algorithm for discovering high-performing materials where inferior designs are phased out for superior candidates.
Abstract: Biomimicry, adapting and implementing nature's designs provides an adequate first-order solution to achieving superior mechanical properties. However, the design space is too vast even using biomimetic designs as prototypes for optimization. Here, we propose a new approach to design hierarchical materials using machine learning, trained with a database of hundreds of thousands of structures from finite element analysis, together with a self-learning algorithm for discovering high-performing materials where inferior designs are phased out for superior candidates. Results show that our approach can create microstructural patterns that lead to tougher and stronger materials, which are validated through additive manufacturing and testing. We further show that machine learning can be used as an alternative method of coarse-graining – analyzing and designing materials without the use of full microstructural data. This novel paradigm of smart additive manufacturing can aid in the discovery and fabrication of new material designs boasting orders of magnitude increase in computational efficacy over conventional methods.
84 citations
TL;DR: In this article, the authors focus on the processing-microstructure-property relationships in the DED-processed titanium alloys (Ti-6Al-4V and beyond) with the following aspects: (1) microstructure evolution induced by solidification, thermal cycles, and post-processing heat treatment; (2) tensile properties of as-deposited and heat-treated titanium alloy; (3) defects, residual stresses, and fatigue properties; and (4) micro/nanomechanical properties.
Abstract: Titanium alloys are expensive and difficult to process into large complex components for aerospace applications. Directed energy deposition (DED), one of the additive manufacturing (AM) technologies, offers a high deposition rate, being suitable for fabricating large metallic components. So far, most review articles on the AM of titanium discuss the popular powder bed fusion method with the emphasis on the “workhorse” titanium alloy—Ti-6Al-4V. There have been few review articles on the DED process of a broad range of titanium alloys—near-α, β, and other α + β alloys beyond Ti-6Al-4V. This article focuses on the processing–microstructure–property relationships in the DED-processed titanium alloys (Ti-6Al-4V and beyond) with the following aspects: (1) microstructure evolution induced by solidification, thermal cycles, and post-processing heat treatment; (2) tensile properties of as-deposited and heat-treated titanium alloys; (3) defects, residual stresses, and fatigue properties; and (4) micro/nanomechanical properties. The article concludes with perspectives about future directions in this field.
81 citations
TL;DR: In this paper, the main part of this review focuses on applications of ML in prediction of mechanical behavior and fracture of 3D-printed parts, and the review and analysis indicate limitations, challenges, and perspectives for industrial applications of machine learning in the field of additive manufacturing.
Abstract: Although applications of additive manufacturing (AM) have been significantly increased in recent years, its broad application in several industries is still under progress. AM also known as three-dimensional (3D) printing is layer by layer manufacturing process which can be used for fabrication of geometrically complex customized functional end-use products. Since AM processing parameters have significant effects on the performance of the printed parts, it is necessary to tune these parameters which is a difficult task. Today, different artificial intelligence techniques have been utilized to optimize AM parameters and predict mechanical behavior of 3D-printed components. In the present study, applications of machine learning (ML) in prediction of structural performance and fracture of additively manufactured components has been presented. This study first outlines an overview of ML and then summarizes its applications in AM. The main part of this review, focuses on applications of ML in prediction of mechanical behavior and fracture of 3D-printed parts. To this aim, previous research works which investigated application of ML in characterization of polymeric and metallic 3D-printed parts have been reviewed and discussed. Moreover, the review and analysis indicate limitations, challenges, and perspectives for industrial applications of ML in the field of AM. Considering advantages of ML increase in applications of ML in optimization of 3D printing parameters, prediction of mechanical performance, and evaluation of 3D-printed products is expected.
70 citations
References
More filters
[...]
TL;DR: Deep learning is making major advances in solving problems that have resisted the best attempts of the artificial intelligence community for many years, and will have many more successes in the near future because it requires very little engineering by hand and can easily take advantage of increases in the amount of available computation and data.
Abstract: Deep learning allows computational models that are composed of multiple processing layers to learn representations of data with multiple levels of abstraction. These methods have dramatically improved the state-of-the-art in speech recognition, visual object recognition, object detection and many other domains such as drug discovery and genomics. Deep learning discovers intricate structure in large data sets by using the backpropagation algorithm to indicate how a machine should change its internal parameters that are used to compute the representation in each layer from the representation in the previous layer. Deep convolutional nets have brought about breakthroughs in processing images, video, speech and audio, whereas recurrent nets have shone light on sequential data such as text and speech.
46,982 citations
01 Jan 1998
TL;DR: In this article, a graph transformer network (GTN) is proposed for handwritten character recognition, which can be used to synthesize a complex decision surface that can classify high-dimensional patterns, such as handwritten characters.
Abstract: Multilayer neural networks trained with the back-propagation algorithm constitute the best example of a successful gradient based learning technique. Given an appropriate network architecture, gradient-based learning algorithms can be used to synthesize a complex decision surface that can classify high-dimensional patterns, such as handwritten characters, with minimal preprocessing. This paper reviews various methods applied to handwritten character recognition and compares them on a standard handwritten digit recognition task. Convolutional neural networks, which are specifically designed to deal with the variability of 2D shapes, are shown to outperform all other techniques. Real-life document recognition systems are composed of multiple modules including field extraction, segmentation recognition, and language modeling. A new learning paradigm, called graph transformer networks (GTN), allows such multimodule systems to be trained globally using gradient-based methods so as to minimize an overall performance measure. Two systems for online handwriting recognition are described. Experiments demonstrate the advantage of global training, and the flexibility of graph transformer networks. A graph transformer network for reading a bank cheque is also described. It uses convolutional neural network character recognizers combined with global training techniques to provide record accuracy on business and personal cheques. It is deployed commercially and reads several million cheques per day.
42,067 citations
08 Dec 2014
TL;DR: A new framework for estimating generative models via an adversarial process, in which two models are simultaneously train: a generative model G that captures the data distribution and a discriminative model D that estimates the probability that a sample came from the training data rather than G.
Abstract: We propose a new framework for estimating generative models via an adversarial process, in which we simultaneously train two models: a generative model G that captures the data distribution, and a discriminative model D that estimates the probability that a sample came from the training data rather than G. The training procedure for G is to maximize the probability of D making a mistake. This framework corresponds to a minimax two-player game. In the space of arbitrary functions G and D, a unique solution exists, with G recovering the training data distribution and D equal to ½ everywhere. In the case where G and D are defined by multilayer perceptrons, the entire system can be trained with backpropagation. There is no need for any Markov chains or unrolled approximate inference networks during either training or generation of samples. Experiments demonstrate the potential of the framework through qualitative and quantitative evaluation of the generated samples.
38,211 citations
Book•
[...]
TL;DR: Deep learning as mentioned in this paper is a form of machine learning that enables computers to learn from experience and understand the world in terms of a hierarchy of concepts, and it is used in many applications such as natural language processing, speech recognition, computer vision, online recommendation systems, bioinformatics, and videogames.
Abstract: Deep learning is a form of machine learning that enables computers to learn from experience and understand the world in terms of a hierarchy of concepts. Because the computer gathers knowledge from experience, there is no need for a human computer operator to formally specify all the knowledge that the computer needs. The hierarchy of concepts allows the computer to learn complicated concepts by building them out of simpler ones; a graph of these hierarchies would be many layers deep. This book introduces a broad range of topics in deep learning. The text offers mathematical and conceptual background, covering relevant concepts in linear algebra, probability theory and information theory, numerical computation, and machine learning. It describes deep learning techniques used by practitioners in industry, including deep feedforward networks, regularization, optimization algorithms, convolutional networks, sequence modeling, and practical methodology; and it surveys such applications as natural language processing, speech recognition, computer vision, online recommendation systems, bioinformatics, and videogames. Finally, the book offers research perspectives, covering such theoretical topics as linear factor models, autoencoders, representation learning, structured probabilistic models, Monte Carlo methods, the partition function, approximate inference, and deep generative models. Deep Learning can be used by undergraduate or graduate students planning careers in either industry or research, and by software engineers who want to begin using deep learning in their products or platforms. A website offers supplementary material for both readers and instructors.
38,208 citations
01 May 1993
TL;DR: The architecture and learning procedure underlying ANFIS (adaptive-network-based fuzzy inference system) is presented, which is a fuzzy inference System implemented in the framework of adaptive networks.
Abstract: The architecture and learning procedure underlying ANFIS (adaptive-network-based fuzzy inference system) is presented, which is a fuzzy inference system implemented in the framework of adaptive networks. By using a hybrid learning procedure, the proposed ANFIS can construct an input-output mapping based on both human knowledge (in the form of fuzzy if-then rules) and stipulated input-output data pairs. In the simulation, the ANFIS architecture is employed to model nonlinear functions, identify nonlinear components on-line in a control system, and predict a chaotic time series, all yielding remarkable results. Comparisons with artificial neural networks and earlier work on fuzzy modeling are listed and discussed. Other extensions of the proposed ANFIS and promising applications to automatic control and signal processing are also suggested. >
15,085 citations