Artificial intelligence and additive manufacturing are primary drivers of Industry 4.0, which is reshaping the manufacturing industry. Based on the progressive layer-by-layer principle, additive manufacturing allows for the manufacturing of mechanical parts with a high degree of complexity. In this chapter, a deep learning neural network (DLNN) is introduced to rationalize the effect of cellular structure design factors as well as process variables on physical and mechanical properties utilizing laser powder bed fusion. The models developed were validated and utilized to create process maps. For both design and process optimization, the trained deep learning neural network model showed the highest accuracy. Deep learning neural networks were found to be an effective technique for predicting material properties from limited data sets, as per the findings.
TopIntroduction
Two essential pillars of Industry 4.0, which is transforming the manufacturing industry's paradigm, are additive manufacturing (AM) and deep learning (DL). Based on the incremental layer-by-layer principle, additive manufacturing allows for the manufacturing of mechanical parts with a high degree of complexity and flexibility (Davidson & Singamneni, 2016; Ge, Lin & Guo, 2018; Kayacan, Özsoy, Duman, Yilmaz & Kayacan, 2019; Scherillo et al., 2019). Laser powder bed fusion (L-PBF) has been widely used in a variety of industries, including biomedical (Brambilla, Okafor-Muo, Hassanin & ElShaer, 2021; Hany Hassanin, Modica, El-Sayed, Liu & Essa, 2016; Langford, Mohammed, Essa, Elshaer & Hassanin, 2021; Okafor-Muo, Hassanin, Kayyali & ElShaer, 2020), aerospace (Galatas, Hassanin, Zweiri & Seneviratne, 2018; Hany Hassanin, Abena, Elsayed & Essa, 2020; Hany Hassanin, Alkendi, Elsayed, Essa & Zweiri, 2020; Klippstein, Hassanin, Diaz De Cerio Sanchez, Zweiri & Seneviratne, 2018), and automotive (Schmitt, Mehta & Kim, 2020), since it can produce high-quality components from a variety of materials, including metals, ceramics, and polymers (El-Sayed, Hassanin & Essa, 2016; K. Essa et al., 2017; H. Hassanin & Jiang, 2010; Jiménez et al., 2021; Mohammed, Elshaer, Sareh, Elsayed & Hassanin, 2020). In this L-PBF process, a fast-moving laser beam is employed as an energy source to selectively melt the metal powder, resulting in dense metal components. L-PBF technology has the potential to revolutionize metal component manufacturing by making it more cost-effective, efficient and faster. Statistical tools such as the design of experiments (DOE) are commonly used to investigate and optimize the influence of AM process parameters. Although these methods proved to be effective, a common flaw is that the AM process parameters were believed to be static, even though AM is a dynamic process (Khamis Essa, Khan, Hassanin, Attallah & Reed, 2016; Sabouri et al., 2017). AM is characterized by scattered results due to repeated heating and cooling cycles, inter-layer interactions, change in the heat distribution within the build platform, and oxygen (O2) level variability, even if it is within a defined range (Olson, 1997).
On the other side, metal cellular structures are lightweight-engineered high-performance materials with a unique mix of high load-bearing capacity, high energy absorption, and thermal and acoustic insulation properties. These characteristics made them suitable for high-performance products such as filters, catalytic converters, acoustic absorbers, heat exchangers, abradable seals, porous burners, biomedical implants, and oil sensors (Delgoshaei, Ariffin, Leman, Baharudin & Gomes, 2016; Guillame-Gentil et al., 2010; Sabouri et al., 2017; Tan, Tan, Chow, Tor & Yeong, 2017; L. Yang et al., 2015). Periodic and stochastic porous structures are two types of porous structures. Pores in periodic lattice structures are homogenous because they are made up of repeated unit cells, but pores in stochastic porous structures are randomly dispersed. Because of their intrinsic defects, the mechanical properties of periodic lattice structures generally outperform those of stochastic porous structures. The complexity and time required to create periodic lattice structures using traditional production technologies such as casting and machining are very high and that prevents their widespread application (Al-Ketan, Soliman, AlQubaisi & Abu Al-Rub, 2018; Felzmann et al., 2012).