An unsupervised method for the reconstruction of maintenance intervention times

This paper presents a method for identifying when maintenance interventions have been performed on industrial components. The knowledge of the maintenance intervention times is essential in many situations, such as accident analysis, maintenance planning and development of prognostics and health management models. The proposed method is based on the application of a spectral clustering algorithm to raw data signals collected during the component life. A novel measure of similarity, based on Pearson's correlation coefficient, is used to build the similarity graph. The method is shown able to correctly identify the maintenance intervention times of nuclear power plants steam generators and cutting machines used in the packaging industry.