Review of machine learning applications in additive manufacturing

• Recent advancements of Machine learning applications in additive manufacturing have been carefully examined. • ML improves product quality and sustainable production by optimizing material design and topology, geometry accuracy, material characteristics, and defects. • ML uses decision trees, support vector machines, and neural networks to analyze sensor data and find trends and irregularities in real time to enhance fault detection. • ML optimizes parameters for print quality, speed, and construction time, resulting in efficient production planning and high-quality prints. • ML analyzes massive datasets and continually monitors and adjusts settings to maximize output, cut costs, and maintain quality. • ML predicts and improves tensile, impact, compressive, and flexural strength for consistent quality and performance. • Industrial applications of ML in AM and its tangible improvements • Critical Issues, Challenges, and Future scopes of ML in AM Were Highlighted. The necessity to produce intricate components results in considerable progress in manufacturing methods. Additive manufacturing (AM) is a disruptive technology that allows intricate and custom-tailored components be fabricated with great precision and efficiency. It is applied in advanced sectors like aerospace, healthcare, automotive industries, and it starts having their interest in many other areas. Machine learning (ML) has become a powerful tool for overcoming problems in AM, offering process efficiency, defect detection, quality assurance, and predictive modelling of mechanical properties. This review discusses how ML transforms AM by providing design evaluation, process optimization, and production control innovation. The approach taken in the study is systematic, examining the current literature and case studies of ML application to AM. Hybrid data collection techniques that combine machine settings with physics aware features and yield robust predictive models are the focus. Additionally, the review evaluates various ML algorithms used to predict mechanical properties, optimize process parameters, and characterize AM processes. The measurements indicate groundbreaking improvements in ML powered solutions, like process monitoring in real time, automatic parameter adaptation, and defect mitigation that offer greater accuracy, ease, and reliability in AM. Yet, data scarcity, computational challenges and a gap between research and industrial applications of ML exist. To realize the full potential of ML in AM it is critical to address these challenges. It closes with the identification of promising research directions including standardization of data improvement, developing new advanced ML algorithms, and building an interdisciplinary research effort to spur additional progress in this field.