In this paper we present our work on cycle detection and clustering using unsupervised Machine Learning methods on manufacturing data. First we discuss the overall architecture of our cyber-physical system specially designed to gather large quantities of heterogeneous industrial data. Next, we detail several analysis steps, focusing on core tasks such as cycle detection and identification. Finally we show that even relatively simple data can be successfully used for predictive maintenance and fault detection.
CITATION STYLE
Iuhasz, G., Panica, S., & Duma, A. (2023). Cycle Detection and Clustering for Cyber Physical Systems. In Lecture Notes in Networks and Systems (Vol. 655 LNNS, pp. 100–114). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-031-28694-0_10
Mendeley helps you to discover research relevant for your work.