A predictive maintenance approach based on real-time internal parameter monitoring

Abstract

Since continuous real-time components or equipment condition monitoring is not available for injection molding machines, we propose a predictive maintenance approach that uses injection molding process parameters instead of machine components to evaluate the condition of equipment. In the proposed approach, maintenance decisions are made based on the statistical process control technique with real-time data monitoring of injection molding process parameters. First, machine components or equipment of injection molding machines, which require maintenance, is identified and then injection molding process parameters, which may be affected by malfunctioning of the previously identified components, are identified. Second, regression analysis is performed to select the process parameters that significantly affect the quality of the lens and require a high degree of attention. By analyzing the patterns of real-time monitored data series of process parameters, we can diagnose the status of the components or equipment because the process parameters are affected by machine components or equipment. Third, statistical predictive models for the selected process parameters are developed to apply statistical analysis techniques to the monitored data series of parameters, in order to identify abnormal trends. Fourth, when abnormal trends or patterns are found based on statistical process control techniques, maintenance information for related components or equipment is notified to maintenance workers. Finally, a prototype system is developed to show feasibility in a LabVIEWA (R) environment and an experiment is performed to validate the proposed approach.