Skip to content

CeRULEo

Welcome tu CeRULEo

CeRULEo: Comprehensive utilitiEs for Remaining Useful Life Estimation methOds

Predictive Maintenance

Efficient management of maintenance in modern industrial environments is having a major impact on decreasing costs associated with defective products and equipment inactivity. Therefore, it is critical for companies to develop an efficient and well-implemented maintenance strategy to prevent unexpected outages, improve overall reliability, and reduce operating costs 1.

The evolution of information systems has transformed traditional manufacturing into factories equipped with intelligent sensors that allow better knowledge about what happens during industrial processes. All the information collected can be used to optimize decision-making processes. The use of this information in maintenance processes has caused a transition from Preventive Maintenance (PM) techniques to Predictive Maintenance (PdM) methods 2. PM is carried out regularly while the asset is still in a working condition to prevent sudden breakdowns. In contrast, PdM can statistically assess the health status of a piece of equipment, allowing early detection of pending failures, and enabling timely pre-failure interventions, thanks to prediction models based on historical data. The data-driven methods use condition monitoring data acquired from sensors to provide effective solutions in these areas 3.

Remaining useful life estimation

The remaining useful life (RUL) estimation has been considered as a central technology of PdM 45. RUL estimation is a process that uses prediction methods to forecast the future performance of machinery and obtain the time left before machinery loses its operation ability.

Bibliography

  1. Lei Han, Yisheng Zou, Guofu Ding, Menghao Zhu, Lei Jiang, Shengfeng Qin, and Hongqin Liang. Development of an online tool condition monitoring system for nc machining based on spindle power signals. In 2018 24th International Conference on Automation and Computing (ICAC), volume, 1–6. 2018. doi:10.23919/IConAC.2018.8748978. ↩

  2. Liam Damant, Amy Forsyth, Ramona Farcas, Melvin Voigtländer, Sumit Singh, Ip-Shing Fan, and Essam Shehab. Exploring the transition from preventive maintenance to predictive maintenance within erp systems by utilising digital twins. In Transdisciplinary Engineering for Resilience: Responding to System Disruptions, pages 171–180. IOS Press, 2021. ↩

  3. Gian Antonio Susto, Andrea Schirru, Simone Pampuri, Seán McLoone, and Alessandro Beghi. Machine learning for predictive maintenance: a multiple classifier approach. IEEE Transactions on Industrial Informatics, 11(3):812–820, 2014. ↩

  4. Felix O Heimes. Recurrent neural networks for remaining useful life estimation. In 2008 international conference on prognostics and health management, 1–6. IEEE, 2008. ↩

  5. Xiang Li, Qian Ding, and Jian-Qiao Sun. Remaining useful life estimation in prognostics using deep convolution neural networks. Reliability Engineering & System Safety, 172:1–11, 2018. ↩