Author:
Bankole-Oye T,El-Thalji I,Zec J
Abstract
Abstract
Large companies are investing heavily in digitalization to be more competitive and economically viable. Hence, physical assets and maintenance operations have been digitally transformed to transmit a high volume of data, e.g., condition monitoring data. Such high-volume data can be useful to optimize maintenance operations and minimize maintenance and replacement costs. A tool to optimize maintenance using condition monitoring data is the Proportional hazard model (PHM). However, it is challenging to implement PHM for industrial complex systems that generate big data. Therefore, machine learning algorithms shall support PHM method to handle such a high volume of data. Thus, the purpose of this paper is to explore how to support PHM with Principal Component Analysis (PCA) to maintenance optimization of complex industrial systems. A case study of hydraulic power unit was purposefully selected to apply and validate the proposed analytical approach. The results show that PCA supported PHM optimizes and extends the preventive maintenance interval by 79.27% which might lead to maintenance cost reductions. This model enables PHM to handle complex systems where big data is collected.