A comprehensive review of supervised machine learning algorithms integrated with vat photopolymerization process for enhanced prediction of functionalities

Global technologies have started embracing Industry 4.0 and unleashing its potential by integrating the elements to reduce human intervention. Vat photopolymerization (VPP) additive manufacturing is one such technology renowned for its precision, versatility, and low-cost fabrication. With the advancements in artificial intelligence and machine learning (AI/ML) algorithms, the integration of these technologies has resulted in enhanced performance in VPP in terms of process optimization, quality control, and material performance. This review paper delves into the scope of supervised machine learning in enhancing the performance of the VPP process and providing augmented predictions of its functionalities. The study elaborately classifies the VPP process into conventional and advanced systems that have been recently developed for functional applications. Key developments in artificial neural networks (ANN), support vector machines (SVM), genetic algorithms (GA), and regression models are discussed, along with their applications in diverse fields such as healthcare, pharmaceuticals, and nanoscale fabrication. Some of the recent developments that have arisen with the integration such as digital pharmacy, intelligent nanofabrication, mechanoluminescent composites, and the design of lattice structures have been discussed. Finally, the recent commercial 3D printers with advanced AI features that are launched by various firms have been briefly discussed. This review paper serves as a guiding tool for researchers who want to realize the vision of Industry 5.0 where human creativity and machine intelligence work in synchronization.