Data-Driven Design Space Exploration and Exploitation for Design for Additive Manufacturing

Abstract

Recently, design for additive manufacturing has been proposed to maximize product performance through the rational and integrated design of the product, its materials, and their manufacturing processes. Searching design solutions in such a multidimensional design space is a challenging task. Notably, no existing design support method is both rapid and tailored to the design process. In this study, we propose a holistic approach that applies data-driven methods in design search and optimization at successive stages of a design process. More specifically, a two-step surrogate model-based design method is proposed for the embodiment and detailed design stages. The Bayesian network classifier is used as the reasoning framework to explore the design space in the embodiment design stage, while the Gaussian process regression model is used as the evaluation function for an optimization method to exploit the design space in detailed design. These models are constructed based on one dataset that is created by the Latin hypercube sampling method and then refined by the Markov Chain Monte Carlo sampling method. This cost-effective data-driven approach is demonstrated in the design of a customized ankle brace that has a tunable mechanical performance by using a highly stretchable design concept with tailored stiffnesses.

The Potential of Additive Manufacturing in the Smart Factory Industrial 4.0: A Review

“…Lately, CAD (computer-aided design)/CAM (computer-aided manufacturing), and Design for Additive Manufacturing (DFAM) have been developed to improve product performance by process, design, and materials [102,103]. Xiong et al [104] proposed a method, which uses a data-driven approach in design and optimizes the successive steps of a design procedure. Another framework that benefits various businesses and technologies is big data and it is forming an interdependent relationship with AM.…”

“…The use of big data-based analytics in the context of industry 4.0 helps to improve the process performance and energy efficiency and increases the quality of manufactured products. AM's reliance on big data grows with increasing AM applications in the industry since by its growth it needs more data to perform its capabilities [104]. Big data plays a role in CAD and quality control aspects of AM processes.…”

Evaluation of Ti–Mn Alloys for Additive Manufacturing Using High-Throughput Experimental Assays and Gaussian Process Regression

“…Although this strategy has produced reliable data points, the size of the dataset (i.e., the number of data points obtained) is still rather small for the extraction of PSP linkages using emergent machine learning techniques. In this paper, we demonstrate novel workflows that extend significantly the previously demonstrated assays in multiple research directions: (i) the prototyping of a much larger library of AM Ti–Mn alloys employing intentionally induced compositional gradients coupled with different post-build heat treatments, and (ii) the use of data-driven model-building strategies such as Gaussian process regression (GPR) [ 40 , 41 , 42 , 43 , 44 , 45 , 46 ] for extracting practically useful correlations from experimental datasets. GPR offers many potential advantages compared to other machine learning approaches, including the ability to utilize smaller data sets (i.e., smaller numbers of data points) [ 42 , 44 ], rigorous treatment of uncertainty [ 47 , 48 ] and dynamic selection of new experiments that maximize the expected information gain [ 49 , 50 , 51 ].…”

Design Complexity as a Driver for Additive Manufacturing Process Improvement

“…This study proposes that this gap can be filled by a thorough statistical design space exploration of a component and furthermore describes its implications to the AM PDD process. Design space exploration has been described as a data-driven design method defined as the search of potential solutions which meet design targets within a specified range [6]. The study concluded that a multidisciplinary data-driven optimization method was able to effectively design simultaneously for product performance, material and manufacturing process.…”

“…The study concluded that a multidisciplinary data-driven optimization method was able to effectively design simultaneously for product performance, material and manufacturing process. Data-driven methods provide rapid search of potentially optimal designs through design exploration and exploitation [6]. Therefore, through the combination of a data-driven design method such as multi-objective optimization paired with the previously employed complexity index, an optimal design solution for target manufacturability may be attained.…”