Data-Driven Virtual Sensing for Probabilistic Condition Monitoring of Solenoid Valves

There is an emerging industrial demand for predic- tive maintenance algorithms that exhibit high levels of predictive accuracy. Such condition monitoring tools must estimate dynamic quantities, such as Remaining Useful Lifetime (RUL) and the State of Health (SOH), based on a, typically, restricted set of measurements that can be obtained in an operational setting. These quantities exhibit inherent stochasticity and can only be approximately determined a posteriori to system failure. This paper proposes a generic prognostic tool for probabilistic condi- tion monitoring of mechatronic systems, with the aim to improve the probabilistic prediction of condition metrics, specifically RUL and SOH. Therefore we propose to identify a Hidden Markov Model (HMM) from a fully instrumented measurement set, that is only available for a restricted set of run-to-failure experiments, typically gathered in an R&D setting. Although being artificial and retrospectively constructed metrics, we interpret RUL and SOH as physical measurements with the purpose to identify accurate degradation dynamics. Once the degradation model is identified, we practice the mathematical flexibility of the HMM framework to estimate several of the no longer available dynamic quantities of interest in real-time, from the limited set of measurements that are available in an operational setting. This modelling paradigm is known as virtual sensing. Predictive performance and computational efficiency are further improved by domain knowledge based pre-processing of the measurements. We apply our methodology to solenoid valves (SV), a widely used and often critical component in many industrial systems, which display a large variation in useful lifetime. Benchmark results show that the predictive capabilities of the presented methodology compares with prognostic techniques that are more computationally and memory demanding. Note to Practitioners—The motivation for this research is twofold. First there is a pending industrial need for improved diagnostic and prognostic tools. Second there is the observation that lifetime tests usually take place in an R&D setting and that expert labelling of Remaining Useful Lifetime (RUL) or State Manuscript received 3 March 2023; revised 12 May 2023; accepted 30 May 2023. This article was recommended for publication by Editor P. Zhou upon evaluation of the reviewers’ comments. This work was supported in part by the Flanders Make Projects QUASIMO and HAIEM and in part by the Flemish Government [Artificial Intelligence (AI) Research Program]. (Victor Vantilborgh and Tom Lefebvre contributed equally to this work.) (Corresponding author: Victor Vantilborgh.) Victor Vantilborgh, Tom Lefebvre, and Guillaume Crevecoeur are with the Dynamic Design Laboratory (D2LAB), Department of Electromechanical, Systems and Metal Engineering, Ghent University, 9052 Ghent, Belgium, and also with the Core Laboratory MIRO, Strategic Research Centre for the Manufacturing Industry, Flanders Make, 3920 Flanders, Belgium (e-mail: victor.vantilborgh@ugent.be; tom.lefebvre@ugent.be; guillaume.crevecoeur@ugent.be). Kerem Eryilmaz is with the Strategic Research Centre for the Manufacturing Industry, Decisions, Flanders Make, 3920 Flanders, Belgium. Color versions of one or more figures in this article are available at https://doi.org/10.1109/TASE.2023.3287598. Digital Object Identifier 10.1109/TASE.2023.3287598 of Health (SOH) of a component or system is often based on measurement data that is not available in the industrial setting where the prognostic tools are to be deployed in the end. These two observations suggest that there is large potential in methods that can correlate the expert labelling, in particular RUL & SOH signals, with measurement data that is available in the industrial setting. Our approach has been tested in detail on the case of Solenoid Valves, which are widely used in industry and that are often safety critical. Our experiments demonstrate that the method compares with brute force approaches that overpower ours both in terms of computational as well as memory requirements. The method is furthermore generic and there is no reason to assume it would not work for other applications.