Optimized Hybrid CNN-Residual BiLSTM with Adaptive Prediction System for Enhanced Gas Turbine Performance Forecasting

  • Andika Pratama Master's Program in Technology Management, School of Interdisciplinary Management and Technology, Institut Teknologi Sepuluh Nopember, Surabaya
  • Chastine Fatichah Department of Informatics, Institut Teknologi Sepuluh Nopember, Surabaya
https://doi.org/10.25139/inform.v10i2.10226
Abstract views: 215 , PDF downloads: 171
Keywords: Compressor Discharge Pressure (PCD), Deep Learning, Gas Turbine, Hybrid Model, Hyperparameter Optimization, Predictive Maintenance, Residual Bi-LSTM, Time Series Forecasting

Abstract

Accurately forecasting critical performance parameters, such as Compressor Discharge Pressure (PCD), in gas turbines is a strategic imperative for ensuring operational reliability and energy efficiency, particularly in vital facilities like Central Processing Plants (CPPs). However, achieving reliable forecasts presents significant analytical challenges due to the complex multivariate, non-linear, and noisy nature of industrial sensor data, compounded by dynamic operational loads. This study introduces and validates an integrated analytical framework centered on a systematically optimized Hybrid Convolutional Neural Network-Residual Bi-Directional Long Short-Term Memory (CNN-Residual BiLSTM) architecture. This hybrid design synergistically leverages CNN layers for multi-scale temporal pattern extraction and Residual BiLSTM blocks for robust long-range dependency modelling, enhanced by residual connections for training stability. The framework emphasizes rigorous data pre-processing and the selection of a comprehensive feature set, incorporating thermodynamic, electrical, and operational control signals to provide a holistic view of the turbine's state. Automated hyperparameter optimization via the Optuna framework is employed to maximize the model's predictive potential. Empirical validation demonstrates that the optimized configuration's performance is superior to that of baseline models (RMSE = 0.0611, MAE = 0.0298, R² = 0.9601), confirming the framework's contribution to advancing data-driven performance diagnostics and predictive maintenance (PdM) strategies for gas turbines.

References

M. P. Boyce, Gas Turbine Engineering Handbook, 5th ed. Elsevier, 2022.

M. H. Pashaei and A. Bagheri, "A comprehensive review on gas turbine performance and fault diagnosis using artificial intelligence methods," Energy Reports, vol. 8, pp. 5649–5678, Apr. 2022, doi: 10.1016/j.egyr.2022.04.021.

Z. Che, S. Purushotham, K. Cho, D. Sontag, and Y. Liu, "Recurrent neural networks for multivariate time series with missing values," Sci Rep, vol. 8, no. 1, p. 6085, Apr. 2018, doi: 10.1038/s41598-018-24271-9.

R. J. Abinaya and G. Rajakumar, "Accurate Liver Fibrosis Detection Through Hybrid MRMR-BiLSTM-CNN Architecture with Histogram Equalization and Optimization," Journal of Imaging Informatics in Medicine, 2024, doi: 10.1007/s10278-024-00995-1.

Z. Zare and A. Ordys, "Gas turbine prognostic and health management: A review of methods and applications," Renewable and Sustainable Energy Reviews, vol. 152, p. 111669, Dec. 2021, doi: 10.1016/j.rser.2021.111669.

W. Zhang, D. Yang, and H. Wang, "Recent advances and trends of predictive maintenance from data-driven machine prognostics perspective," Measurement, vol. 176, p. 109121, Jun. 2021, doi: 10.1016/j.measurement.2021.109121.

N. H. Hussin et al., "Handling Volatility and Non-linearity in Wind Speed Data: A Comparative Analysis between ARIMA-GARCH and ARIMA-MLP," Journal of Advanced Research in Applied Mechanics, vol. 121, no. 1, pp. 44–57, Jul. 2024, doi: 10.37934/aram.121.1.4457.

S. Hochreiter and J. Schmidhuber, "Long short-term memory," Neural Comput, vol. 9, no. 8, pp. 1735–1780, Nov. 1997, doi: 10.1162/neco.1997.9.8.1735.

J. Zhang, X. Li, J. Tian, and H. Luo, "An integrated multi-head dual sparse self-attention network for remaining useful life prediction," Reliab Eng Syst Saf, vol. 233, p. 109096, May 2023, doi: 10.1016/j.ress.2023.109096.

D. P. Kingma and J. Ba, "Adam: A method for stochastic optimization," in Proc. 3rd Int. Conf. Learning Representations (ICLR), San Diego, CA, USA, May 2015.

Y. A. Ramaziyah and E. B. Setiawan, "Hybrid deep learning CNN and BiLSTM with FastText as feature expansion for sentiment analysis in President Election 2024," in Proc. 2024 IEEE International Conference on Communication, Networks and Satellite (COMNETSAT), Kuta, Bali, Indonesia, Feb. 2024, pp. 176–183. doi: 10.1109/COMNETSAT63286.2024.10862946.

S. Ahmad, M. Asghar, F. Alotaibi, and Y. D. Al-Otaibi, "A hybrid CNN + BiLSTM deep learning-based DSS for efficient prediction of judicial case decisions," Expert Syst Appl, vol. 209, p. 118318, Dec. 2022, doi: 10.1016/j.eswa.2022.118318.

M. A. Dar and J. Pushparaj, "Hybrid architecture CNN-BLSTM for automatic speech recognition," in Proc. 2024 3rd International Conference on Artificial Intelligence For Internet of Things (AIIoT), Coimbatore, India, Mar. 2024, pp. 1–4. doi: 10.1109/AIIoT58432.2024.10574740.

K. He, X. Zhang, S. Ren, and J. Sun, "Deep residual learning for image recognition," in Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, Jun. 2016, pp. 770–778. doi: 10.1109/CVPR.2016.90.

R. Huan, Z. Zhan, L. Ge, K. Chi, P. Chen, and R. Liang, "A hybrid CNN and BLSTM network for human complex activity recognition with multi-feature fusion," Multimed Tools Appl, vol. 80, no. 28–29, pp. 36159–36182, Nov. 2021, doi: 10.1007/s11042-021-11363-4.

Y. Chen and Z.-P. Fu, "Multi-Step Ahead Forecasting of the Energy Consumed by the Residential and Commercial Sectors in the United States Based on a Hybrid CNN-BiLSTM Model," Sustainability, vol. 15, no. 3, p. 1895, Jan. 2023, doi: 10.3390/su15031895.

A. Tabiti, "Neuro-Genetic System: A Hybrid System of CNN-BiLSTM Optimized by Genetic Algorithm for Road Accident Severity Prediction," in Intelligent Systems and Pattern Recognition. ISPR 2024, vol. 991, in Lecture Notes in Networks and Systems, vol. 991. , Springer, Singapore, 2024, pp. 29–40. doi: 10.1007/978-981-97-5495-3_3.

M. T. Pawitra, H. Fakhrurroja, and L. Abdurrahman, "Predicting stock market using CNN and BiLSTM model," in Proc. 2024 International Conference on Computer, Control, Informatics and its Applications (IC3INA), Bandung, Indonesia, Oct. 2024, pp. 267–272. doi: 10.1109/IC3INA64086.2024.10732245.

T. Akiba, S. Sano, T. Yanase, T. Ohta, and M. Koyama, "Optuna: A next-generation hyperparameter optimization framework," in Proc. 25th ACM SIGKDD Int. Conf. Knowledge Discovery and Data Mining, Anchorage, AK, USA, Aug. 2019, pp. 2623–2631. doi: 10.1145/3292500.3330701.

Y. Song, Y. Wu, S. Duan, C. Dou, B. Liu, and B. Hou, "CNN-BiLSTM combined with Bayesian optimization for short-term wind power prediction," J Phys Conf Ser, vol. 2938, no. 1, p. 12002, Mar. 2025, doi: 10.1088/1742-6596/2938/1/012002.

L. Brahimi, N. Hadroug, and A. Iratni, "Advancing predictive maintenance for gas turbines: An intelligent monitoring approach with ANFIS, LSTM, and reliability analysis," Comput Ind Eng, vol. 191, p. 110094, May 2024, doi: 10.1016/j.cie.2024.110094.

S. M. Rezvanizaniani and T. Dempsey, "An effective predictive maintenance approach based on historical maintenance data using a probabilistic risk assessment," Int J Progn Health Manag, vol. 14, no. 1, p. 13, 2023.

C. M. T. Yunanda, M. Hanafi, and W. M. P. Dhuhita, "Sentiment Analysis on TikTok Shop Reviews Using Long Short-Term Memory Method to Find Business Opportunity," Inform: Jurnal Ilmiah Bidang Teknologi Informasi dan Komunikasi, vol. 9, pp. 1–7, Jan. 2024.

C. Yustitia and N. Charibaldi, "Chili Price Prediction One Year Ahead Using the Gated Recurrent Unit Method," Inform: Jurnal Ilmiah Bidang Teknologi Informasi dan Komunikasi, vol. 10, no. 1, pp. 1–7, Jan. 2025.

Y. Zhang and H. Wang, "Multi-head attention-based probabilistic CNN-BiLSTM for day-ahead wind speed forecasting," Energy, vol. 281, p. 127865, Oct. 2023, doi: 10.1016/j.energy.2023.127865.

T. Hastie, R. Tibshirani, and J. Friedman, The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd ed. New York: Springer, 2009.

R. J. Hyndman and A. B. Koehler, "Another look at measures of forecast accuracy," Int J Forecast, vol. 22, no. 4, pp. 679–688, Oct. 2006, doi: 10.1016/j.ijforecast.2006.03.001

Published
2025-07-31
How to Cite
Pratama, A., & Fatichah, C. (2025). Optimized Hybrid CNN-Residual BiLSTM with Adaptive Prediction System for Enhanced Gas Turbine Performance Forecasting . Inform : Jurnal Ilmiah Bidang Teknologi Informasi Dan Komunikasi, 10(2), 159-169. https://doi.org/10.25139/inform.v10i2.10226
Issue
Vol. 10 No. 2 (2025)
Section
Articles

Copyright (c) 2025 Andika Pratama, Chastine Fatichah

Creative Commons License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Authors who publish with Inform: Jurnal Ilmiah Bidang Teknologi Informasi dan Komunikasi agree to the following terms:

  1. Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (CC BY-SA 4.0) that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal. 

  2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.

  3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.