Artificial Intelligence in Manufacturing Quality: Applications, Challenges, and Emerging Research Directions

Aditya Sawant, Pratima Shinde

Abstract: Artificial intelligence (AI) is increasingly integral to managing manufacturing quality. Techniques such as machine learning, deep learning, and computer vision are employed for tasks like defect detection, quality forecasting, process surveillance, fault diagnosis, and process enhancement. Recently, large language models (LLMs), retrieval-augmented generation (RAG), and knowledge-graph strategies have introduced innovative methods for utilizing engineering documents and other unstructured manufacturing data in quality assessments. This review analyzes peer-reviewed studies published between January 2021 and September 2026, categorizing the literature by the quality function AI supports rather than by specific algorithms. It explores six domains: automated inspection and defect detection, predictive quality, process monitoring and anomaly detection, explainable AI and diagnosis, quality knowledge management, and integrated decision support. The findings suggest a gradual broadening of AI's functional role, evolving from merely detecting and predicting isolated quality outcomes to interpreting diverse information, aiding diagnosis, supporting engineering decisions, and starting to coordinate quality-related tasks. The review also highlights ongoing challenges related to data quality, rare failures, model drift, explainability, interoperability, industrial validation, and human oversight. Industrial evidence is more mature in inspection, predictive quality, and selected monitoring applications, whereas generative and agentic methods remain at an earlier stage of industrial validation.

Keywords: Artificial intelligence; manufacturing quality; Quality 4.0; predictive quality; generative AI

How to Cite?: Aditya Sawant, Pratima Shinde, "Artificial Intelligence in Manufacturing Quality: Applications, Challenges, and Emerging Research Directions", Volume 15 Issue 9, September 2026, International Journal of Science and Research (IJSR), Pages: 1659-1667, https://www.ijsr.net/getabstract.php?paperid=SR26925083358, DOI: https://dx.doi.org/10.21275/SR26925083358

Download Citation: APA | MLA | BibTeX | EndNote | RefMan