Efficient Bayesian sampling inspection for industrial processes based on transformed spatio-temporal data

Abstract

Efficient inspection and maintenance of complex industrial systems, subject to degradation effects such as corrosion, are important for safety and economic reasons. With appropriate statistical modelling, the utilization of inspection resources and the quality of inferences can be greatly improved. We develop a suitable Bayesian spatio-temporal dynamic linear model for problems such as wall thickness monitoring. We are concerned with problems where the inspection method used collects transformed data, for example minimum regional remaining wall thicknesses. We describe how the model may be used to derive efficient inspection schedules by identifying when, where and how much inspection should be made in the future.