Data-driven dynamic predictive maintenance for a manufacturing system with quality deterioration and online sensors

Manufacturing systems are generally subject to product quality deterioration as a result of degradation of machine tooling-components, and thus tooling-component replacement has always been an effective way to ensure high product quality. For individual tooling components, online degradation data from sensors contain the information about their unique degradation patterns, which can be used to achieve precise degradation prediction. Therefore, this paper proposes a data-driven dynamic predictive maintenance policy which utilizes online degradation data to continuously enhance the degradation prediction of tooling components and further constantly revise the maintenance schedule. To account for individual heterogeneity, the tooling-component degradation rates are assumed as random variables, whose posteriori distributions are continuously updated using the online degradation data based on Bayesian approach. The real-time degradation prediction of tooling components is further used to predict the deterioration of product quality and machine reliability based on the response model and integrated hazard function. The quality and reliability deteriorations are measured by costs to construct a dynamic cost rate function, which is used to make adaptive PM schedules. Case study shows that the proposed policy can make practical maintenance schedules and achieve cost saving in general.