Design of control chart for monitoring time-between-failures of a repairable system - A case study

This article designs a statistical process control chart for monitoring the time-between-failures of a repairable system. We discussed the design procedure and verified it for a truck-cooling system. It was possible to identify opportunities for improvements, and understand the systems' critical components and their failure modes, causes and consequences. Furthermore, using failure data it was possible to get relevant reliability function for critical components and simulate and measure the rate of occurrence of failure for the system. Optimum replacement times for critical components were calculated using a suitable replacement model; then a practical preventive maintenance schema was suggested. Finally, a statistical process control chart was designed and used to monitor the time-between-failures of the system based on the calculated rate of occurrence of failures. Monitoring the time-between-failures helps in discovering and understating any deterioration of the system reliability and determine whether the current state of the system reliability is acceptable or not. Monitoring could detect any changes that might lead to failures over time, investigate and determine the root causes and reasons of the shift in reliability of the system. Furthermore, it gives indication about the effectiveness and the impact of the different maintenance policies on the overall system's reliability.