PERTANIKA JOURNAL OF SCIENCE AND TECHNOLOGY

Boiler tube leaks significantly reduce the operational availability of power units, yet their early detection and prediction have not been fully realised in the industry. This paper introduces a novel approach employing deep feedforward neural networks for early detection of boiler tube leaks in pulverised coal-fired boilers. Early detection enhances repair planning, minimising downtime and production losses. It also improves monitoring and control of boiler tube failures, thereby optimising power plant operations and revenue. Diverse deep neural network models were developed and rigorously tested by leveraging 9 years of operational data (2012–2020). Exhaustive hyper-parameter optimisation, involving seven parameters, substantially improved predictive accuracy. By achieving training and testing accuracies of 82.8% to 99.3%, the study assessed their ability to detect boiler tube leaks over the same 9-year span, providing insights into leak detection capabilities. The models notably predicted all 12 identified tube leak events, averaging a 14-day lead time before boiler shutdown. In addition to leak prediction, a leak detection matrix was devised to analyse residual behaviour and reduce the likelihood of false alarms. However, the models’ predictive performance was observed to be limited to the following year, with satisfactory results for 2021 only. Incorporating the 2021 data into retraining significantly improved the predictions for 2022. The study concludes that while the models demonstrate robust short-term prediction capabilities, they require continuous retraining to maintain accuracy and relevance. This ongoing refinement is essential for keeping the models up-to-date and reliable in predicting future boiler tube leaks.

• Alouani, A. T., & Chang, P. S. (2003). Artificial neural network and fuzzy logic based boiler tube leak detection systems. U.S. Patent No. 6,192,352. Washington, DC: U.S. Patent and Trademark Office.

• Barszcz, T., & Czop, P. (2011). A feedwater heater model intended for model-based diagnostics of power plant installations. Applied Thermal Engineering, 31(8-9), 1357-1367. https://doi.org/10.1016/j.applthermaleng.2010.12.012

• Behera, S. K., Rene, E. R., Kim, M. C., & Park, H. S. (2014). Performance prediction of a RPF‐fired boiler using artificial neural networks. International Journal of Energy Research, 38(8), 995-1007. https://doi.org/10.1002/er.3108

• Ismail, F. B., Singh, D., & Nasif, M. S. (2020). Adoption of intelligent computational techniques for steam boilers tube leak trip. Malaysian Journal of Computer Science, 33(2), 133-151. https://doi.org/10.22452/mjcs.vol33no2.4

• Ismail, F. B., Singh, D., Maisurah, N., & Musa, A. B. B. (2016). Early tube leak detection system for steam boiler at KEV power plant. In MATEC Web of Conferences (Vol. 74, p. 00006). EDP Sciences. https://doi.org/10.1051/matecconf/20167400006

• Karim, A. M. A., & Mustafah, Y. M. (2022). Early detection of tube leaks faults in pulverised coal-fired boiler using deep neural network. In 8th International Conference on Mechatronics Engineering (ICOM 2022) (Vol. 2022, pp. 125-132). IET Publishing. https://doi.org/10.1049/icp.2022.2277

• Khalid, S., Lim, W., Kim, H. S., Oh, Y. T., Youn, B. D., Kim, H. S., & Bae, Y. C. (2020). Intelligent steam power plant boiler waterwall tube leakage detection via machine learning-based optimal sensor selection. Sensors, 20(21), Article 6356. https://doi.org/10.3390/s20216356

• Kim, K. H., Lee, H. S., & Park, J. H. (2019). Detection of boiler tube leakage fault in a thermal power plant using k-means algorithm based on auto-associative neural network. In 2019 20th International Conference on Intelligent System Application to Power Systems (ISAP) (pp. 1-5). IEEE Publishing. https://doi.org/10.1109/ISAP48318.2019.9065940

• Kim, K. H., Lee, H. S., Kim, J. H., & Park, J. H. (2019). Detection of boiler tube leakage fault in a thermal power plant using machine learning based data mining technique. In 2019 IEEE International Conference on Industrial Technology (ICIT) (pp. 1006-1010). IEEE Publishing. https://doi.org/10.1109/ICIT.2019.8755058

• Kokkinos, A. (2019). Coal R&D Beyond 2020. In DOE-NETL-EPRI Technical Exchange Meeting. Pittsburgh, PA, USA: EPRI.

• Lang, F. D., Rodgers, D. A., & Mayer, L. E. (2004). Detection of tube leaks and their location using input/loss methods. In ASME Power Conference (Vol. 41626, pp. 143-150). https://doi.org/10.1115/power2004-52027

• Mishra, S., Bordin, C., Taharaguchi, K., & Palu, I. (2020). Comparison of deep learning models for multivariate prediction of time series wind power generation and temperature. Energy Reports, 6, 273-286. https://doi.org/10.1016/j.egyr.2019.11.009

• Nistah, N. N. M., Lim, K. H., Gopal, L., & Alnaimi, F. B. I. (2018). Coal-fired boiler fault prediction using artificial neural networks. International Journal of Electrical and Computer Engineering, 8(4), Article 2486. https://doi.org/10.11591/ijece.v8i4.pp2486-2493

• Pfeuffer, S. (2009). Update: Benchmarking boiler tube failures. Power, 153(10), 68-71.

• Ramezani, M. G., Hasanian, M., Golchinfar, B., & Saboonchi, H. (2020). Automatic boiler tube leak detection with deep bidirectional LSTM neural networks of acoustic emission signals. In Sensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems 2020 (Vol. 11379, pp. 205-213). SPIE Publishing. https://doi.org/10.1117/12.2558885

• Rostek, K., Morytko, Ł., & Jankowska, A. (2015). Early detection and prediction of leaks in fluidized-bed boilers using artificial neural networks. Energy, 89, 914-923. https://doi.org/10.1016/j.energy.2015.06.042

• Singh, D., Ismail, F. B., & Nasif, M. S. (2017). Hybrid intelligent warning system for boiler tube leak trips. In MATEC Web of Conferences (Vol. 131, p. 03003). EDP Sciences. https://doi.org/10.1051/matecconf/201713103003

• Sun, X., Chen, T., & Marquez, H. J. (2002). Efficient model-based leak detection in boiler steam-water systems. Computers & Chemical Engineering, 26(11), 1643-1647. https://doi.org/10.1016/S0098-1354(02)00147-3

• Tam, A. S., Price, J. W., & Beveridge, A. (2007). A maintenance optimisation framework in application to optimise power station boiler pressure parts maintenance. Journal of Quality in Maintenance Engineering, 13(4), 364-384. https://doi.org/10.1108/13552510710829461

• Torres, J. F., Hadjout, D., Sebaa, A., Martínez-Álvarez, F., & Troncoso, A. (2021). Deep learning for time series forecasting: A survey. Big Data, 9(1), 3-21. https://doi.org/10.1089/big.2020.0159