A method for fault diagnosis in evolving environment using unlabeled data

Industrial components and systems typically operate in an evolving environment characterized by modifications of the working conditions. Methods for diagnosing faults in components and systems must, therefore, be capable of adapting to the changings in the environment of operation. In this work, we propose a novel fault diagnostic method based on the compacted object sample extraction algorithm for fault diagnostics in an evolving environment from where unlabeled data are collected. The developed diagnostic method is shown able to correctly classify data taken from synthetic and real-world case studies.