Monitoring regenerative heat exchanger in steam power plant by making use of the recurrent neural network

• Autorzy: Niksa-Rynkiewicz Tacjana , Szewczuk-Krypa Natalia , Witkowska Anna , Cpałka Krzysztof , Zalasiński Marcin , Cader Andrzej

Identyfikatory

DOI

10.2478/jaiscr-2021-0009

• Języki publikacji: EN

Abstrakty

EN

Artificial Intelligence algorithms are being increasingly used in industrial applications. Their important function is to support operation of diagnostic systems. This paper presents a new approach to the monitoring of a regenerative heat exchanger in a steam power plant, which is based on a specific use of the Recurrent Neural Network (RNN). The proposed approach was tested using real data. This approach can be easily adapted to similar monitoring applications of other industrial dynamic objects.

Słowa kluczowe

EN

recurrent neural network; intelligent industrial monitoring; Almeida–Pineda recurrent back-propagation; regenerative heat exchanger; steam power plant

• Wydawca: University of Social Sciences
• Czasopismo: Journal of Artificial Intelligence and Soft Computing Research
• Rocznik: 2021
• Tom: Vol. 11, No. 2
• Strony: 143--155
• Opis fizyczny: Bibliogr. 36 poz., rys.

Twórcy

autor

Niksa-Rynkiewicz Tacjana

• Gdansk University of Technology, Faculty of Ocean Engineering and Ship Technology, 1112 Gabriela Narutowicza Street, 80-233 Gdansk, Poland

autor

Szewczuk-Krypa Natalia

• Gdansk University of Technology, Faculty of Ocean Engineering and Ship Technology, 1112 Gabriela Narutowicza Street, 80-233 Gdansk, Poland

autor

Witkowska Anna

• Gdansk University of Technology, Faculty of Ocean Engineering and Ship Technology, 1112 Gabriela Narutowicza Street, 80-233 Gdansk, Poland

autor

Cpałka Krzysztof

• Czestochowa University of Technology, Department of Intelligent Computer Systems Al. Armii Krajowej 36, 42-200 Czestochowa, Poland

autor

Zalasiński Marcin

• Czestochowa University of Technology, Department of Intelligent Computer Systems Al. Armii Krajowej 36, 42-200 Czestochowa, Poland

autor

Cader Andrzej

• University of Social Sciences, Information Technology Institute, Lodz, Poland
• Clark University, Worcester, MA 01610, USA

Bibliografia

• [1] L. B. Almeida, Backpropagation in non-feedforward networks, Proc. of the NATO ARW on Neural Computers, Springer Verlag, Heidelberg, 74–91, 1993.
• [2] J. Bilski, B. Kowalczyk, A. Marchlewska, J.M. Zurada, Local Levenberg-Marquardt Algorithm for Learning Feedforwad Neural Networks, Journal of Artificial Intelligence and Soft Computing Research, 10(4), 2020.
• [3] T. Chmielniak, P. Krzys´lak, Comparative analysis of energy potential of three ways of configuration of a condenser power plant thermal cycle, Polish Marit. Res., 15, 30–36, 2008.
• [4] T. Chmielniak, H. Łukowicz, Condensing power plant cycle-Assessing possibilities of improving its efficiency, Arch. Thermodyn., 31, 105–113, 2010.
• [5] K. Cpałka, Design of interpretable fuzzy systems, Springer, 2017.
• [6] P. Deshpande, N. Warke, P. Khandare, V. Deshpande, Thermal power plant analysis using artificial neural network, Proc. of the 3rd Nirma Univ. Int. Conf. Eng. NUiCONE 2012, 1–6, 2012.
• [7] R. Dixit, J. Kumar, T. Soota, Modeling of a Thermal Power Plant using Neural Network and Regression Modeling of a Thermal Power Plant using Neural Network and Regression Technique, 2018.
• [8] P. Duda, M. Jaworski, A. Cader, L. Wang, On Training Deep Neural Networks Using a Streaming Approach Journal of Artificial Intelligence and Soft Computing Research, 10(1), pp. 15–26, 2020.
• [9] A. Gardzilewicz, J. Głuch, M. Bogulicz, R. Walkowiak, M. Najwer, J. Kiebdoj, Experience in Application of Thermal Diagnostics in the Turow Power Station, Proc. of the Int. Joint Power Generation Conference collocated with TurboExpo 2003 (2003 Int. Joint Power Generation Conference, Atlanta, Georgia, USA), 371–378, 2003.
• [10] J. C. Gallagher, S. K. Boddhu, S. Vigraham, A reconfigurable continuous time recurrent neural network for evolvable hardware applications, In Proc. of the 2005 IEEE Congress on Evolutionary Computation, Piscataway, NJ: IEEE, 2005.
• [11] J. Głuch, Fault detection in measuring systems of power plants, Polish Marit. Res., 15, 45–51, 2008.
• [12] Y. Guo, Y. Liu, T. Georgiou, M. S. Lew, A review of semantic segmentation using deep neural networks, Int. Journal of Multimedia Information Retrieval, 2, 1–7, 2017.
• [13] R. Isermann, Supervision FDD Methods-An Introduction, Control Eng. Pract., 5, 639–652, 1997.
• [14] F. B. Ismail Alnaimi, H. H. Al-Kayiem, Artificial intelligent system for steam boiler diagnosis based on superheater monitoring, J. Appl. Sci., 11, 2011.
• [15] A. M. Kler, P. V. Zharkov, N. O. Epishkin, Parametric optimization of supercritical power plants using gradient methods, Energy, 189, 2019.
• [16] K. Kosowski, Introduction to the Theory of Marine Turbines, Foundation for the Promotion of Maritime Industry, Gdańsk, 2005.
• [17] K. Kosowski, Ship Turbine Power Plants, Fundamentals of Thermodynamical Cycles, Foundation for the Promotion of Maritime Industry, Gdańsk, 2005.
• [18] Ł. Kowalczyk, W. Elsner, P. Niegodajew, M. Marek, Gradient-free methods applied to optimisation of advanced ultra-supercritical power plant, Appl. Therm. Eng., 96, 200–208, 2016.
• [19] J. K Mohanty., A. Adarsh, P. R. Dash, K. Parida, P. K. Pradhan, Integrated Condition Monitoring of Large Captive Power Plants and Aluminum Smelters, Sound&Vibration., 53, 223–235, 2019.
• [20] T. Niksa-Rynkiewicz, A. Witkowska, Analisis of impact of ship model parameters on changes of control quality index in ship dynamic positioning system, Polish Maritime Research, 2019.
• [21] S. Osowski, Signal flow graphs and neural networks. Biological Cybernetics, 70, 387–395, 1994.
• [22] F. J. Pineda, Generalization of Back-Propagation to Recurrent Neural Network, The American Physical Society, 59(19), 1988.
• [23] F. J. Pineda, Recurrent Back-Propagation and the Dynamical Approach to Adaptive Neural Computation, Neural Computation, 1(2), 161–172, 1989.
• [24] M. A. Ranzato, A. Szlam, J. Bruna, M. Mathieu, R. Collobert, S. Chopra, Video (language) modeling: A baseline for generative models of natural videos. arXiv:1412.6604, 2014.
• [25] W. Rawat, Z. Wang, Deep convolutional neural Networks for image classification: A comprehensive review, Neural Computation, 29(9), 1–10, 2017.
• [26] A. J. Robinson, F. Fallside, The utility driven dynamic error propagation network. Cambridge: University of Cambridge Department of Engineering, 1987.
• [27] L. Rutkowski, Computational intelligence: methods and techniques, Springer Science & Business Media, 2008.
• [28] A. Saeed A. Rashid, Development of Core Monitoring System for a Nuclear Power Plant using Artificial Neural Network Technique, Annals of Nuclear Energy, 144(1), 2020.
• [29] M. Saghafia, M. B. Ghofranib, Real-time estimation of break sizes during LOCA in nuclear power plants using NARX neural network, Nuclear Engineering and Technology 51(3), 702–708, 2019.
• [30] T. K. Sai, K. A. Reddy, Neural Network Applications in a Power Station, Int. J. Soft Comput., 6, 01–16, 2015.
• [31] P. Sharma, A. Singh, Era of deep neural networks: A review, In Proc. of the 8th Int. Conf. on Computing, Communication and Networking Technologies, Piscataway, NJ: IEEE, 1–5, 2017.
• [32] J. Smrekar, D. Pandit, M. Fast, M. Assadi, D. Sudipta, Prediction of power output of a coal-fired power plant by artificial neural network, Neural Comput. Appl., 19, 725–740, 2010.
• [33] A. Witkowska., T. Niksa-Rynkiewicz, Dynamically positioned ship steering making use of backstepping method and artificial neural networks, Polish Maritime Research, 2018.
• [34] P. J. Werbos, Generalization of backpropagation with application to a recurrent gas market model. Neural Networks, 1(4), 339–356, 1988.
• [35] G. Yang Y. Wang, X. Li, Prediction of the NOx emissions from thermal power plant using long-short term memory neural network, Energy, 192(1), 2020.
• [36] Y. Yu, X. Si, C. Hu, J. Zhang, A Review of Recurrent Neural Networks: LSTM Cells and Network Architectures, Neural Computation, 31(7), 1235–1270, 2019.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa Nr 461252 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2021).