Multiple-sensor fault detection and isolation using video processing in production lines

Production-line sensors are essential for synchronisation and execution of the correct workflow in a manufacturing process. Usually, sensor faults lead to serious delays, or even the complete termination of the manufacturing process, to carry out maintenance. Thus, sensor faults compromise the reliability of the manufacturing system and disturb the production schedule. This study proposes a multiple-sensor fault detection and isolation scheme for manufacturing series production lines. The proposed scheme adopts a global-redundancy method, using a digital camera and an ad-hoc video processing algorithm to detect and isolate faulty sensors. The main objective of this research is to preserve continuity of the production workflow and solve the problem of production delays and interruptions. Moreover, the scheme provides the possibility of online and post-process system maintenance. Further, the collected information on sensor false alarm rates can be used for a reliability analysis of the production line. The proposed scheme was tested using a laboratory production line model. The results show that the proposed scheme achieves the established objectives and improves the reliability of the manufacturing process.