Review of manufacturing integration between production, maintenance and quality artificial intelligence systems

High inflation is causing major manufacturing cost increases, making optimizing production lines a priority in Industry 5.0 manufacturing. As a result, there has been a rising interest in reducing these costs by more efficiently optimizing production, maintenance, and quality costs. This can be accomplished in manufacturing systems by integrating production task and maintenance activity scheduling, predictive maintenance, and quality control, with the application of artificial intelligence, information integration, and interoperability techniques. Accordingly, the present paper’s premise is to perform a literature review regarding production, maintenance, and quality integration in manufacturing environments. It aims to answer the main research question: “What are the current state-of-the-art artificial intelligence techniques applied in production/maintenance scheduling, predictive maintenance, and quality control integration?”. To investigate this, a Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA)-like methodology is followed to find the most efficient, reliable, and robust artificial intelligence techniques for production, maintenance, and quality optimization in production lines. Results show that Genetic Algorithms, Reinforcement Learning, Artificial Neural Networks, and Random Forests are among the most often used algorithms in the literature. Furthermore, integration between production/maintenance scheduling and predictive maintenance is done primarily through the rescheduling of production plans when a machine failure is detected. In addition, the same system employed for predictive maintenance is often integrated into also predicting product quality. However, while there have been some accomplishments in this field, research that considers full production, maintenance, and quality integration is still lacking, even if there is an increasing trend of research on this topic.