Estimation of remaining useful life (RUL) for pneumatic actuator without apriori RUL history: A hybrid prognostic approach

Abstract

Predicting the Remaining Useful Life (RUL) of an industrial pneumatic actuator is crucial for enhancing maintenance strategies, reducing downtime and optimizing resource allocation. However, estimation becomes challenging when no historical RUL data is available for modeling. In this paper, a novel hybrid prognostic approach that combines Dynamic Time Warping (DTW), Exponential Degradation Model (EDM) and Random Forest Regressor (RFR) is proposed to estimate the RUL of pneumatic actuators under the absence of apriori RUL history. The DTW technique is employed to identify the onset of potential degradation. By aligning the healthy and faulty data, DTW provides a robust measure of distance and time at the point of deviation as the threshold value. Subsequently, the EDM is introduced to capture the degradation pattern in the actuator behavior. The EDM accounts for the relationship between threshold value, operating conditions, degradation rate and exponential coefficients through curve fitting methods. To further enhance prediction accuracy, RFR is employed to predict the RUL based on input features of aligned data from DTW and the derived degradation rates from EDM. In the simulation studies, the proposed methodology is applied to a synthetic dataset and benchmark DAMADICS dataset of the industrial pneumatic actuator in sugar processing unit to estimate RUL. The estimated RUL for each health indicator is quantified and the severity of each fault is discussed. The proposed method is implemented on a real time laboratory setup. The results are also validated on the benchmark NASA turbo-engine dataset by comparing the actual and estimated RULs, achieving 82.5 % range-based accuracy.