Demonstrating Aleatoric Uncertainty in Remaining Useful Life Prediction Using LSTM with Probabilistic Layer

Ahmad Kamal Bin Mohd Nor; Srinivasa Rao Pedapati; Masdi Muhammad; Mohd Amin Abdul Majid

doi:10.1007/978-981-19-1939-8_41

Demonstrating Aleatoric Uncertainty in Remaining Useful Life Prediction Using LSTM with Probabilistic Layer

Ahmad Kamal Bin Mohd Nor, Srinivasa Rao Pedapati^*, Masdi Muhammad, Mohd Amin Abdul Majid

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

A Remaining Useful Life prediction with Aleatoric uncertainty is presented in this paper.A Long Short-Term Memory (LSTM) architecture with probabilistic layer is employed where a normal distribution layer is incorporated to produce the predicted Health Index (HI) distribution of turbofan engines.Compared to the performance of other point estimates techniques in the literature, the probabilistic LSTM achieved a competitive performance in predicting the turbofan’s RUL and RUL sequence and have the advantage to express the level of uncertainty along its sequence prediction.This work is important as it reflect a real-world deep learning application where uncertainty indication is needed to evaluate prediction for important decision-making process.

Original language	English
Title of host publication	ICPER 2020 - Proceedings of the 7th International Conference on Production, Energy and Reliability
Editors	Faiz Ahmad, Hussain H. Al-Kayiem, William Pao King Soon
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	529-544
Number of pages	16
ISBN (Print)	9789811919381
DOIs	https://doi.org/10.1007/978-981-19-1939-8_41
State	Published - 2023
Externally published	Yes
Event	7th International Conference on Production, Energy and Reliability, ICPER 2020 - Kuching, Malaysia Duration: 14 Jul 2020 → 16 Jul 2020

Publication series

Name	Lecture Notes in Mechanical Engineering
ISSN (Print)	2195-4356
ISSN (Electronic)	2195-4364

Conference

Conference	7th International Conference on Production, Energy and Reliability, ICPER 2020
Country/Territory	Malaysia
City	Kuching
Period	14/07/20 → 16/07/20

Bibliographical note

Publisher Copyright:
© 2023, Institute of Technology PETRONAS Sdn Bhd.

Keywords

Aleatoric uncertainty
CMAPPS
Probabilistic neural network
Remaining useful life
Turbofan

ASJC Scopus subject areas

Automotive Engineering
Aerospace Engineering
Mechanical Engineering
Fluid Flow and Transfer Processes

Access to Document

10.1007/978-981-19-1939-8_41

Cite this

Bin Mohd Nor, A. K., Pedapati, S. R., Muhammad, M., & Abdul Majid, M. A. (2023). Demonstrating Aleatoric Uncertainty in Remaining Useful Life Prediction Using LSTM with Probabilistic Layer. In F. Ahmad, H. H. Al-Kayiem, & W. P. King Soon (Eds.), ICPER 2020 - Proceedings of the 7th International Conference on Production, Energy and Reliability (pp. 529-544). (Lecture Notes in Mechanical Engineering). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-19-1939-8_41

Bin Mohd Nor, Ahmad Kamal ; Pedapati, Srinivasa Rao ; Muhammad, Masdi et al. / Demonstrating Aleatoric Uncertainty in Remaining Useful Life Prediction Using LSTM with Probabilistic Layer. ICPER 2020 - Proceedings of the 7th International Conference on Production, Energy and Reliability. editor / Faiz Ahmad ; Hussain H. Al-Kayiem ; William Pao King Soon. Springer Science and Business Media Deutschland GmbH, 2023. pp. 529-544 (Lecture Notes in Mechanical Engineering).

@inproceedings{44eac82a9fee41a9844b504956f63a52,

title = "Demonstrating Aleatoric Uncertainty in Remaining Useful Life Prediction Using LSTM with Probabilistic Layer",

abstract = "A Remaining Useful Life prediction with Aleatoric uncertainty is presented in this paper.A Long Short-Term Memory (LSTM) architecture with probabilistic layer is employed where a normal distribution layer is incorporated to produce the predicted Health Index (HI) distribution of turbofan engines.Compared to the performance of other point estimates techniques in the literature, the probabilistic LSTM achieved a competitive performance in predicting the turbofan{\textquoteright}s RUL and RUL sequence and have the advantage to express the level of uncertainty along its sequence prediction.This work is important as it reflect a real-world deep learning application where uncertainty indication is needed to evaluate prediction for important decision-making process.",

keywords = "Aleatoric uncertainty, CMAPPS, Probabilistic neural network, Remaining useful life, Turbofan",

author = "\{Bin Mohd Nor\}, \{Ahmad Kamal\} and Pedapati, \{Srinivasa Rao\} and Masdi Muhammad and \{Abdul Majid\}, \{Mohd Amin\}",

note = "Publisher Copyright: {\textcopyright} 2023, Institute of Technology PETRONAS Sdn Bhd.; 7th International Conference on Production, Energy and Reliability, ICPER 2020 ; Conference date: 14-07-2020 Through 16-07-2020",

year = "2023",

doi = "10.1007/978-981-19-1939-8\_41",

language = "English",

isbn = "9789811919381",

series = "Lecture Notes in Mechanical Engineering",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "529--544",

editor = "Faiz Ahmad and Al-Kayiem, \{Hussain H.\} and \{King Soon\}, \{William Pao\}",

booktitle = "ICPER 2020 - Proceedings of the 7th International Conference on Production, Energy and Reliability",

address = "Germany",

}

Bin Mohd Nor, AK, Pedapati, SR, Muhammad, M & Abdul Majid, MA 2023, Demonstrating Aleatoric Uncertainty in Remaining Useful Life Prediction Using LSTM with Probabilistic Layer. in F Ahmad, HH Al-Kayiem & WP King Soon (eds), ICPER 2020 - Proceedings of the 7th International Conference on Production, Energy and Reliability. Lecture Notes in Mechanical Engineering, Springer Science and Business Media Deutschland GmbH, pp. 529-544, 7th International Conference on Production, Energy and Reliability, ICPER 2020, Kuching, Malaysia, 14/07/20. https://doi.org/10.1007/978-981-19-1939-8_41

Demonstrating Aleatoric Uncertainty in Remaining Useful Life Prediction Using LSTM with Probabilistic Layer. / Bin Mohd Nor, Ahmad Kamal; Pedapati, Srinivasa Rao; Muhammad, Masdi et al.
ICPER 2020 - Proceedings of the 7th International Conference on Production, Energy and Reliability. ed. / Faiz Ahmad; Hussain H. Al-Kayiem; William Pao King Soon. Springer Science and Business Media Deutschland GmbH, 2023. p. 529-544 (Lecture Notes in Mechanical Engineering).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Demonstrating Aleatoric Uncertainty in Remaining Useful Life Prediction Using LSTM with Probabilistic Layer

AU - Bin Mohd Nor, Ahmad Kamal

AU - Pedapati, Srinivasa Rao

AU - Muhammad, Masdi

AU - Abdul Majid, Mohd Amin

PY - 2023

Y1 - 2023

N2 - A Remaining Useful Life prediction with Aleatoric uncertainty is presented in this paper.A Long Short-Term Memory (LSTM) architecture with probabilistic layer is employed where a normal distribution layer is incorporated to produce the predicted Health Index (HI) distribution of turbofan engines.Compared to the performance of other point estimates techniques in the literature, the probabilistic LSTM achieved a competitive performance in predicting the turbofan’s RUL and RUL sequence and have the advantage to express the level of uncertainty along its sequence prediction.This work is important as it reflect a real-world deep learning application where uncertainty indication is needed to evaluate prediction for important decision-making process.

AB - A Remaining Useful Life prediction with Aleatoric uncertainty is presented in this paper.A Long Short-Term Memory (LSTM) architecture with probabilistic layer is employed where a normal distribution layer is incorporated to produce the predicted Health Index (HI) distribution of turbofan engines.Compared to the performance of other point estimates techniques in the literature, the probabilistic LSTM achieved a competitive performance in predicting the turbofan’s RUL and RUL sequence and have the advantage to express the level of uncertainty along its sequence prediction.This work is important as it reflect a real-world deep learning application where uncertainty indication is needed to evaluate prediction for important decision-making process.

KW - Aleatoric uncertainty

KW - CMAPPS

KW - Probabilistic neural network

KW - Remaining useful life

KW - Turbofan

UR - https://www.scopus.com/pages/publications/85140712927

U2 - 10.1007/978-981-19-1939-8_41

DO - 10.1007/978-981-19-1939-8_41

M3 - Conference contribution

AN - SCOPUS:85140712927

SN - 9789811919381

T3 - Lecture Notes in Mechanical Engineering

SP - 529

EP - 544

BT - ICPER 2020 - Proceedings of the 7th International Conference on Production, Energy and Reliability

A2 - Ahmad, Faiz

A2 - Al-Kayiem, Hussain H.

A2 - King Soon, William Pao

PB - Springer Science and Business Media Deutschland GmbH

T2 - 7th International Conference on Production, Energy and Reliability, ICPER 2020

Y2 - 14 July 2020 through 16 July 2020

ER -

Bin Mohd Nor AK, Pedapati SR, Muhammad M, Abdul Majid MA. Demonstrating Aleatoric Uncertainty in Remaining Useful Life Prediction Using LSTM with Probabilistic Layer. In Ahmad F, Al-Kayiem HH, King Soon WP, editors, ICPER 2020 - Proceedings of the 7th International Conference on Production, Energy and Reliability. Springer Science and Business Media Deutschland GmbH. 2023. p. 529-544. (Lecture Notes in Mechanical Engineering). doi: 10.1007/978-981-19-1939-8_41

Demonstrating Aleatoric Uncertainty in Remaining Useful Life Prediction Using LSTM with Probabilistic Layer

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this