Subrata Rath

Mr. Subrata Rath

orcid

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
31 December 2024 in Mathematics
Verified
Journal Article
Open access
PDF file
SRSubrata Rath
Subrata Rath
DSDEEPJYOTI SAHA
DEEPJYOTI SAHA
SCSubhashis Chatterjee
Subhashis Chatterjee
ACAshis Kumar Chakraborty
Ashis Kumar Chakraborty
In the era of Internet of Things (IoT), remaining useful life (RUL) prediction of turbofan engines is crucial. Various deep learning (DL) techniques proposed recently to predict RUL for such systems have remained silent on the effect of environmental changes on machine reliability. This paper aims (i) to identify the change point in RUL trends and patterns (ii) to select the most relevant features, and (iii) to predict RUL with the selected features and identified change points. A two-stage feature-selection algorithm was developed, followed by a change point identification mechanism, and finally, a Bidirectional Long Short-Term Memory (BiLSTM) model was designed to predict RUL. The study utilizes NASA’s C-MAPSS data set to check the performance of the proposed methodology. The findings affirm that the proposed method enhances the stability of DL models, resulting in a 27.8% improvement in RUL prediction compared to popular and cutting-edge DL models.

20 November 2024 in Preprints.org
Verified
Preprint
Open access
PDF file
SRSubrata Rath
Subrata Rath
DSDEEPJYOTI SAHA
DEEPJYOTI SAHA
SCSubhashis Chatterjee
Subhashis Chatterjee
ACAshis Kumar Chakraborty
Ashis Kumar Chakraborty
In the era of Internet of Things (IoT), remaining useful life (RUL) prediction of turbofan engines is crucial. Various deep learning (DL) techniques are proposed recently to predict RUL for such systems, have remained silent on the effect of environmental changes on machine reliability. This paper has proposed three-fold aims, (i) to identify the change point in RUL trend and pattern (ii) to select most relevant features, and (iii) to predict RUL with the selected features and identified change point. A two-stage feature selection algorithm was developed, followed by a change point identification mechanism and finally, a Bi-directional long short-term memory (BiLSTM) model has been designed to predict RUL. The study utilizes NASA’s C-MAPSS dataset to check the performance of the proposed methodology. The findings affirm that the proposed method enhances the stability of DL models, resulting in an approximate 30% improvement in RUL prediction compared to popular and cutting-edge DL models.