A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Degradation Data–Driven Analysis for Estimation of the Remaining Useful Life of a Motor
Highly dynamic loading conditions on clutch motors used in four-wheeled passenger vehicles cause them to fail quite often. The current diagnostic tools have proven to be inefficient to detect the onset of system degradation. This paper presents a degradation model to exhibit the state of health of the clutch. A novel condition indicator (CI) and a threshold for conditionally independent noisy signal from the motor subjected to cumulative degradation have been established. A dominating feature characterizing the motor health was discerned to be spectral entropy kurtosis which was identified while analyzing the time-series signal composed of agglomeration of different frequencies that produce higher octaves. Tests for monotonocity and trendability metrics affirmed that spectral entropy kurtosis is a distinguishing CI. Principal component analysis (PCA) allowed the fusion of features for the selection of the best-performing CI. The proposed CI was used in an exponential degradation model to predict the remaining useful life (RUL) of the motor with improved accuracy.
Degradation Data–Driven Analysis for Estimation of the Remaining Useful Life of a Motor
Highly dynamic loading conditions on clutch motors used in four-wheeled passenger vehicles cause them to fail quite often. The current diagnostic tools have proven to be inefficient to detect the onset of system degradation. This paper presents a degradation model to exhibit the state of health of the clutch. A novel condition indicator (CI) and a threshold for conditionally independent noisy signal from the motor subjected to cumulative degradation have been established. A dominating feature characterizing the motor health was discerned to be spectral entropy kurtosis which was identified while analyzing the time-series signal composed of agglomeration of different frequencies that produce higher octaves. Tests for monotonocity and trendability metrics affirmed that spectral entropy kurtosis is a distinguishing CI. Principal component analysis (PCA) allowed the fusion of features for the selection of the best-performing CI. The proposed CI was used in an exponential degradation model to predict the remaining useful life (RUL) of the motor with improved accuracy.
Degradation Data–Driven Analysis for Estimation of the Remaining Useful Life of a Motor
Banerjee, Ahin (author) / Gupta, Sanjay K. (author) / Putcha, Chandrasekhar (author)
2021-02-27
Article (Journal)
Electronic Resource
Unknown
Remaining useful life estimation under degradation and shock damage
| Online Contents | 2015
A Data-Driven Neural Network Approach for Remaining Useful Life Prediction
| British Library Online Contents | 2011
| Elsevier | 2025
Data-Driven Remaining Useful Life Prognosis Techniques : Stochastic Models, Methods and Applications
| UB Braunschweig | 2017
| DOAJ | 2022