Advancing Sustainable Smart Manufacturing: A Comprehensive Review of Machine Learning Techniques in Assembly Lines

Assembly lines are critical to modern manufacturing, facilitating efficient and consistent large-scale production. Nonetheless, traditional assembly lines struggle with challenges such as downtime, operational inefficiencies, and quality control. Integrating artificial intelligence (AI) and machine learning (ML) offers transformative solutions to these longstanding issues, enhancing not only productivity and quality but also sustainability across various sectors. This study provides a comprehensive review of recent advancements in the application of AI and ML to assembly line operations. It categorizes the existing literature and analyzes the various models and algorithms used to optimize operational efficiency. This review makes a distinctive contribution by integrating AI/ML applications with manufacturing principles driven by sustainability. It introduces longitudinal analysis concerning algorithmic evolution from 2015 to 2025 and provides a novel approaches–challenges matrix that maps real industrial problems to specific AI/ML techniques. The review further links available datasets to their corresponding industrial sectors, allowing researchers to choose the contextually appropriate data source for optimizing assembly lines. By offering both a theoretical foundation and practical insights, this study aims to support researchers and contribute to the broader adoption and continued development of ML technologies in smart assembly line environments.