Machine performance monitoring and proactive maintenance in computer-integrated manufacturing: review and perspective

Abstract A major problem confronting American manufacturers today is how lo economically achieve high quality in the goods which they manufacture. Equipment reliability and maintenance drastically affect the three key elements of competitiveness: quality, cost and product lead time. Well-maintained machines hold tolerances better, help reduce scrap and rework, and raise consistency and quality of the part. They increase uptime and yields of good parts, thereby cutting total production costs, and also can shorten lead limes by reducing downtime and the need for retooling. The recent rush to embrace computer-integrated manufacturing (CIM) has further increased the use of relatively unknown and untested technology. In a computer-integrated manufacturing system, a fault can cause machine and production downtime and create serious productivity losses. Today, many factories are still performing maintenance on equipment in a reactive, or breakdown, mode, since traditional process monitoring systems can detect machine or process faults only when they occur. Reactive maintenance is expensive because of extensive unplanned downtime and damage to machinery. In high-performance systems one often cannot tolerate significant degradation in performance during normal system operation. This had led many US manufacturers to look to suppliers for smarter equipment that will ease the need for strong technical support. The proactive maintenance approach is to use integrated, investigative and corrective practices to significantly extend machinery life. The goal of proactive maintenance is to eliminate failures of equipment forever. If the behaviour of a machine can be monitored adaptively then an early warning of possible faults can be generated. By doing this, maintenance personnel can perform early diagnostics and part replacement during regular daily maintenance hours. Therefore, the mean-time-between-failure can be extended to an unlimited length. The author believes that the development of in-process monitoring of machine degradation and faults is one of the most important research tasks for increasing machine uptime and improving production quality. This paper examines various methods in machine monitoring, fault detection, and fault diagnostics. A perspective on proactive maintenance and research needs is also presented.