Fuzzy Logic-Based Fault Detection in Industrial Production Systems: A Case Study

The burgeoning application of artificial intelligence (AI) technologies for the diagnosis and detection of defects has marked a significant area of interest among researchers in recent years. This study presents a fuzzy logic-based approach to identify failures within industrial systems, with a focus on operational anomalies in a real-world context, particularly within the competitive landscape of Omar Benamour, in Al-Fajjouj region, Guelma, Algeria. The analysis has been started with the employment of the Activity-Based Costing (ABC) method to identify the critical machinery within the K-short dough production line. Subsequently, an elaborate failure tree analysis has been conducted on the pressing machine, enabling the deployment of a fuzzy logic approach for the detection of failures in the dough cutter of AMOR BENAMOR's K production line press. The effectiveness of the proposed method has been validated through an evaluation conducted with an authentic and real-time data from the facility, where the study took place. The results underscore the efficacy of the fuzzy logic approach in enhancing fault detection within industrial systems, offering substantial implications for the advancement of defect diagnosis methodologies. The study advocates for the integration of fuzzy logic principles in the operational oversight of industrial machinery, aiming to mitigate potential failures and optimize production efficiency.