Multiple Fault Diagnosis in Manufacturing Processes and Machines Using Probabilistic Boolean Networks.

Developing methodologies for fault diagnosis in industrial/manufacturing systems is an active area of research. In this paper, a fault diagnosis scheme based on the Probabilistic Boolean Networks (PBN) model is proposed for a group of machines in a manufacturing process. The proposal takes into account the failure modes which affect the function and performance of the system. Firstly, the modes are identified and divided into two groups: faults and failures. The former implies detectable degradation of system function until the threshold for fault, which is eventual catastrophic loss of system, is surpassed. The latter leads to catastrophic fault. Then, using PBN, both classifications can be diagnosed and actions to mitigate them can be taken. The proposal also allows to forecast a time in hours by which the fault or failure will be imminent. The method herein discussed was applied to a ultrasound welding cycle, and a PBN model was created, simulated and verified through by means of model checking in PRISM. Results obtained show the validity of this methodology.