Data‐Driven Approaches Toward Smarter Additive Manufacturing

Abstract

The latest industrial revolution, Industry 4.0, is driven by the emergence of digital manufacturing and, most notably, additive manufacturing (AM) technologies. The simultaneous material and structure forming in AM broadens the material and structural design space. This expanded design space holds a great potential in creating improved engineering materials and products that attract growing interests from both academia and industry. A major aspect of this growing interest is reflected in the increased adaptation of data‐driven tools that accelerate the exploration of the vast design space in AM. Herein, the integration of data‐driven tools in various aspects of AM is reviewed, from materials design in AM (i.e., homogeneous and composite material design) to structure design for AM (i.e., topology optimization). The optimization of AM tool path using machine learning for producing best‐quality AM products with optimal material and structure is also discussed. Finally, the perspectives on the future development of holistically integrated frameworks of AM and data‐driven methods are provided.

Machine learning-assisted ultrafast flash sintering of high-performance and flexible silver–selenide thermoelectric devices

“…Previous efforts to discover the optimum flash sintering variables relied on expert-driven Edisonian trial-and-error search, which is time-and labor-intensive. 32 Enabled by recent advances in machine learning, data-driven approaches such as Bayesian optimization (BO) have rapidly permeated many fields including TE materials, [33][34][35] smart manufacturing, [36][37][38] and molecular modeling of chemical products. 39,40 Novel artificial intelligence (AI) systems enable automated prediction and optimization of materials and additive manufacturing processes.…”

“…39,40 Novel artificial intelligence (AI) systems enable automated prediction and optimization of materials and additive manufacturing processes. 33,[36][37][38] Moreover, machine learning algorithms can help to both intelligently maximize specific performance metrics and aid in revealing the underlying physical mechanisms. Although classical statistical design of experiments (e.g., full/partial factor design, response surface methods, and ANOVA analysis) has been used to improve TE materials and manufacturing, [41][42][43] these approaches require experimental designs to be fixed at the beginning of an optimization iteration and the experimental design cannot be updated as new data become available during the optimization iteration.…”

“…39,40 Novel artificial intelligence (AI) systems enable automated prediction and optimization of materials and additive manufacturing processes. 33,36–38 Moreover, machine learning algorithms can help to both intelligently maximize specific performance metrics and aid in revealing the underlying physical mechanisms. Although classical statistical design of experiments ( e.g.…”

Recent Advancements in Design Optimization of Lattice‐Structured Materials

“…Light reactive photopolymer curing Material Polymer, metal, ceramic [215] Metal [12] Polymer, ceramic, [216] metal [38] Polymer [217] Polymer, metal, ceramic [12] Polymer, metal, ceramic [12] Polymeric composite [12] Material feedstock [12] Powder material Filament/wire material Filament material Melted material Powder material Sheet material Liquid material Energy source Liquid binder [13] Electron beam, laser [12] Thermal heating [12] Ultra-violet curing [217] Electron beam, laser [12] Ultrasound [12] Ultra-violet curing [217] was smaller than that of the latter. This difference explained the superiority of the PBF samples over the BJ samples in terms of microhardness, tensile strength, and compressive yield strength.…”

Hot Isostatic Pressing for Fatigue Critical Additively Manufactured Ti-6Al-4V

“…For this popular structural alloy, controlling the formation of microscopic build defects during fabrication can be key towards the goal of reliable fatigue performance [ 9 ]. Despite significant progress to better understand, predict, improve, and monitor the AM process, the control of build defects is not yet sufficient to assure safety in demanding fatigue critical applications [ 10 , 11 , 12 , 13 , 14 , 15 , 16 , 17 , 18 , 19 , 20 ]. In such cases, post processing treatments, such as hot isostatic pressing (HIP) followed by surface machining, have been used in an effort to minimize the negative implications of build defects [ 21 , 22 , 23 ].…”