Prediction of the remaining useful life for plate heat exchanger at Hai Thach - Moc Tinh fields

  • Ngoc Trung Tran Bien Dong Petroleum Operating Company (Bien Dong POC)
  • Thanh Trung Nguyen Bien Dong Petroleum Operating Company (Bien Dong POC)
  • Duy Minh Nguyen Bien Dong Petroleum Operating Company (Bien Dong POC)
  • Quang Khoa Dao Bien Dong Petroleum Operating Company (Bien Dong POC)
  • Vu Tung Tran Bien Dong Petroleum Operating Company (Bien Dong POC)
  • Duc Thang Tran Bien Dong Petroleum Operating Company (Bien Dong POC)
Keywords: Remaining useful life, plate heat exchanger, Hai Thach - Moc Tinh fields


Predictive maintenance is an advanced and widely adopted approach in the industry that helps maximize the equipment uptime by estimating its remaining useful life (RUL) and predicting any potential failure point. The authors have made a short-term prediction of the seawater flow pressure difference at a plate heat exchanger using a long short-term memory (LSTM) network, and thereby predicted the RUL using a nonlinear regression model. The proposed model achieved high accuracy by continuously detecting checkpoints and predicting RUL values every 24 hours. Checkpoints are identified through detecting differential pressure anomalies at the plate heat exchanger during operation. Thereby, it helps update the RUL value promptly upon any unforeseen deviation during equipment operation.


Zhenghua Chen, Min Wu, Rui Zhao, Feri Guretno, Ruqiang Yan, and Xiaoli Li, “Machine remaining useful life prediction via an attention-based deep learning approach”, IEEE Transactions on Industrial Electronics, Volume 68, Issue 3, pp. 2521 - 2531, 2021. DOI: 10.1109/ TIE.2020.2972443.

Zuozhou Pan, Zong Meng, Zijun Chen, Wenqing Gao, and Ying Shi, “A two-stage method based on extreme learning machine for predicting the remaining useful life of rolling-element bearings”, Mechanical Systems and Signal Processing, Volume 144, 2020. DOI: 10.1016/j.ymssp.2020.106899.

Jason Deutsch and David He, “Using deep learning-based approach to predict remaining useful life of rotating components”, IEEE Transactions on Systems, Man, and Cybernetics: Systems, Volume 48, Issue 1, pp. 11 - 20, 2018. DOI: 10.1109/TSMC.2017.2697842.

James Carroll, Sofia Koukoura, Alasdair McDonald, Anastasis Charalambous, Stephan Weiss, and Stephen McArthur, “Wind turbine gearbox failure and remaining useful life prediction using machine learning techniques”, Wind Energy, Volume 22, Issue 3, pp. 360 - 375, 2019.

Yongmeng Zhu, Jiechang Wu, Xing Liu, Jun Wu, Kai Chai, Gang Hao, and Shuyong Liu, “Hybrid scheme through read-first-LSTM encoder-decoder and broad learning system for bearings degradation monitoring and remaining useful life estimation”, Advanced Engineering Informatics, Volume 56, 2023. DOI: 10.1016/j.aei.2023.102014.

Xiaoyu Li, Changgui Yuan, and Zhenpo Wang, “Multi-time-scale framework for prognostic health condition of lithium battery using modified Gaussian process regression and nonlinear regression”, Journal of Power Sources, Volume 467, 2020. DOI: 10.1016/j. jpowsour.2020.228358.

Venkat P. Nemani, Hao Lu, Adam Thelen, Chao Hu, and Andrew T. Zimmerman, “Ensembles of probabilistic LSTM predictors and correctors for bearing prognostics using industrial standards”, Neurocomputing, Volume 491, pp. 575 - 596, 2022. DOI: 10.1016/j.neucom.2021.12.035.

Colah's blog, "Understanding LSTM networks", 7/22/2022. [Online]. Available:

Sepp Hochreiter and Jürgen Schmidhuber, “Long short-term memory”, Neural Compututation, Volume 9, Issue 8, pp. 1735 - 1780, 1997. DOI: 10.1162/ neco.1997.9.8.1735.

N.A. Sitnik, “Growth and the energy budget of flat oyster (Ostrea edulis) in early ontogenesis”, Biosystems Diversity, Volume 18, Issue 1, pp. 110 - 116, 2010. DOI: 10.15421/011016.

How to Cite
Tran, N. T., Nguyen, T. T., Nguyen, D. M., Dao, Q. K., Tran, V. T., & Tran, D. T. (2024). Prediction of the remaining useful life for plate heat exchanger at Hai Thach - Moc Tinh fields. Petrovietnam Journal, (1), 78-87.

Most read articles by the same author(s)