Prognostics for Optimal Maintenance: Maintenance Cost Versus Product Quality Optimization for Industrial Cases

Abstract

Correlation between the quality degradation of a product and maintenance of a machine is often established by the production engineers. To asses this correlation, some assumptions are made. In most cases it is assumed that the quality of the product degrades after a fixed number of operation cycles of the production machine. Therefore, maintenance of the production machine is only performed after this number of cycles is accomplished. This kind of assumptions is often not valid in modern industry since high variability of products, tolerances of machines/components, reliability variations of these components, extensive/smooth usage, etc., make this degradation quite dynamic in time. As a result, the quality of the product could get degraded in a fast way if this variability is high or in a slow way if this variability is low. Both cases will lead to low benefit because of lost production in the former case or redundant maintenance in the latter one. In this paper, we propose a solution to this problem by maximizing the benefit using online monitoring of product’s quality degradation and maintenance cost evolution. A Condition Based Maintenance framework for industry developed in Prognostics for Optimal Maintenance (POM) project [1] and described in [2] is applied to two industrial use cases in order to deploy and validate the proposed technique.