Heysem KAYA, Pınar TÜFEKCİ, Erdinç UZUN

Predicting CO and NOx emissions from gas turbines: novel data and a benchmark PEMS

Predictive emission monitoring systems (PEMS) are important tools for validation and backing up of costlycontinuous emission monitoring systems used in gas-turbine-based power plants. Their implementation relies on theavailability of appropriate and ecologically valid data. In this paper, we introduce a novel PEMS dataset collected overfive years from a gas turbine for the predictive modeling of the CO and NOx emissions. We analyze the data using arecent machine learning paradigm, and present useful insights about emission predictions. Furthermore, we present abenchmark experimental procedure for comparability of future works on the data.

PDF

___

[1] Skalska K, Miller JS, Ledakowicz S. Trends in NOx abatement: a review. Science of the Total Environment 2010; 408 (19): 3976-3989. doi: 10.1016/j.scitotenv.2010.06.001
[2] Korpela T, Kumpulainen P, Majanne Y, Häyrinen A. Model based NOx emission monitoring in natural gas fired hot water boilers. IFAC-PapersOnLine 2015; 48 (30): 385-390. doi: 10.1016/j.ifacol.2015.12.409
[3] Shakil M, Elshafei M, Habib MA, Maleki F, Soft sensor for NOx and O2 using dynamic neural networks. Computers & Electrical Engineering 2009; 35 (4): 578-586. doi: 10.1016/j.compeleceng.2008.08.007
[4] Fichet V, Kanniche M, Plion P, Gicquel O. A reactor network model for predicting NOx emissions in gas turbines. Fuel 2010; 89 (9): 2202-2210. doi: 10.1016/j.fuel.2010.02.010
[5] Traver ML, Atkinson RJ, Atkinson CM. Neural network-based diesel engine emissions prediction using in-cylinder combustion pressure. SAE Transactions 1999; 108: 1166-1180.
[6] Radl BJ. Neural networks prove effective at NOx reduction. Modern Power Systems 2000; 20 (5): 59-62.
[7] Iliyas SA, Elshafei M, Habib MA, Adeniran AA. RBF neural network inferential sensor for process emission monitoring. Control Engineering Practice 2013; 21 (7): 962-970. doi: 10.1016/j.conengprac.2013.01.007
[8] Lv Y, Liu J, Yang T, Zeng D. A novel least squares support vector machine ensemble model for NOx emission prediction of a coal-fired boiler. Energy 2013; 55: 319-329. doi: 10.1016/j.energy.2013.02.062
[9] Smrekar J, Potočnik P, Senegačnik A. Multi-step-ahead prediction of NOx emissions for a coal-based boiler. Applied Energy 2013; 106: 89-99. doi: 10.1016/j.apenergy.2012.10.056
[10] Ćirić I, Ćojbašić Z, Nikolić V, Živković P, Tomić M. Air quality estimation by computational intelligence methodologies. Thermal Science 2012; 16: S493-S504. doi: 10.2298/TSCI120503186C
[11] Lazzaretto A, Toffolo A. Prediction of performance and emissions of a two-shaft gas turbine from experimental data. Applied Thermal Engineering 2008; 28 (17-18): 2405-2415. doi: 10.1016/j.applthermaleng.2008.01.021
[12] Rizk N, Mongia H. Semianalytical correlations for NOx , CO, and UHC emissions. Journal of Engineering for Gas Turbines and Power 1993; 115 (3): 612-619. doi: 10.1115/1.2906750
[13] Dragomir EG, Oprea M. A multi-agent system for power plants air pollution monitoring. IFAC Proceedings Volumes 2013; 46 (6): 89-94. doi: 10.3182/20130522-3-RO-4035.00017
[14] Saiful Idzwan B, Phing CC, Kiong TS. Prediction of NOx using support vector machine for gas turbine emission at Putrajaya power station. Journal of Advanced Science and Engineering Research 2014; 4 (1): 37-46.
[15] Liukkonen M, Hiltunen T. Monitoring and analysis of air emissions based on condition models derived from process history. Cogent Engineering 2016; 3 (1): 1174182. doi: 10.1080/23311916.2016.1174182
[16] Huang GB, Zhu QY, Siew CK. Extreme learning machine: theory and applications. Neurocomputing 2006; 70 (1-3): 489-501. doi: 10.1016/j.neucom.2005.12.126
[17] Huang GB, Wang DH, Lan Y. Extreme learning machines: a survey. International Journal of Machine Learning and Cybernetics 2011; 2 (2): 107-122. doi: 10.1007/s13042-011-0019-y
[18] Huang GB, Zhou H, Ding X, Zhang R. Extreme learning machine for regression and multiclass classification. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics) 2012; 42 (2): 513-529. doi: 10.1109/TSMCB.2011.2168604
[19] Liu H, Tian H, Li Y. Four wind speed multi-step forecasting models using extreme learning machines and signal decomposing algorithms. Energy Conversion and Management 2015; 100: 16-22. doi: 10.1016/j.enconman.2015.04.057
[20] Kaya H, Karpov AA, Salah AA. Robust acoustic emotion recognition based on cascaded normalization and extreme learning machines. In: International Symposium on Neural Networks; St. Petersburg, Russia; 2016. pp. 115-123. doi: 10.1007/978-3-319-40663-3_14
[21] Kaya H, Gürpınar F, Salah AA. Video-based emotion recognition in the wild using deep transfer learning and score fusion. Image and Vision Computing 2017; 65: 66-75. doi: 10.1016/j.imavis.2017.01.012
[22] Huang GB, Zhu QY, Siew C. Extreme learning machine: a new learning scheme of feedforward neural networks. In: IEEE 2004 International Joint Conference on Neural Networks; Budapest, Hungary; 2004. pp. 985-990.
[23] Rao CR, Mitra SK. Generalized Inverse of Matrices and Its Applications. Vol. 7, New York, NY, USA: Wiley, 1971.
[24] Kaya H, Tüfekci P, Gürgen FS. Local and global learning methods for predicting power of a combined gas & steam turbine. In: International Conference on Emerging Trends in Computer and Electronics Engineering; Dubai, UAE, 2012. pp. 13-18.
[25] Tüfekci P. Prediction of full load electrical power output of a base load operated combined cycle power plant using machine learning methods. International Journal of Electrical Power & Energy Systems 2014; 60: 126-140. doi: 10.1016/j.ijepes.2014.02.027
[26] Alpaydin E. Introduction to Machine Learning, 2nd ed. Cambridge, MA, USA: The MIT Press, 2010.
[27] Breiman L. Random forests. Machine Learning 2001; 45 (1): 5-32. doi: 10.1023/A:1010933404324
[28] Kaya H, Eyben F, Salah AA, Schuller BW. CCA based feature selection with application to continuous depression recognition from acoustic speech features. In: IEEE 2014 International Conference on Acoustics, Speech, and Signal Processing; Florence, Italy; 2014. pp. 3757-3761. doi:10.1109/ICASSP.2014.6854298
[29] Hotelling H. Relations between two sets of variates, Biometrika 1936; 28: 321-377.
[30] Hardoon DR, Szedmak S, Shawe-Taylor J. Canonical correlation analysis: an overview with application to learning methods, Neural Computation 2004; 16 (12): 2639-2664. doi: 10.1162/0899766042321814