A systematic comparison of machine learning methods for modeling of dynamic processes applied to combustion emission rate modeling. (15th June 2021)

• Record Type: Journal Article
• Authors: Tuttle, Jacob F.; Blackburn, Landen D.; Andersson, Klas; Powell, Kody M.
• Is Part Of: Applied energy. Volume 292(2021)
• Publication Date: 2021-06-15
• Subjects: Nonlinear dynamical systems -- Intelligent systems -- Computational intelligence -- Recurrent neural networks -- Combustion modeling & optimization -- NOx emissions; Power (Mechanics) -- Periodicals; Energy conservation -- Periodicals; Energy conversion -- Periodicals; 621.042
• DOI: 10.1016/j.apenergy.2021.116886
• Languages: English
• ISSNs: 0306-2619

Abstract

Highlights: ARX, NARX, VARX, SVR, FFNN, RNN, LSTM, GRU, and DBN models introduced and evaluated. Case study on NOx emissions at a coal-fired power plant during transient operation. Optimal model hyperparameters identified using exhaustive search or genetic algorithm. Predictions made over a 60-minute horizon in 1-minute steps over a three week period. GRU network exhibits most accurate and stable prediction RMSE across future horizon. Abstract: Ten established, data-driven dynamic algorithms are surveyed and a practical guide for understanding these methods generated. Existing Python programming packages for implementing each algorithm are acknowledged, and the model equations necessary for prediction are presented. A case study on a coal-fired power plant's NOx emission rates is performed, directly comparing each modeling method's performance on a mutual system. Each model is evaluated by its root mean squared error (RMSE) on out-of-sample future horizon predictions. Optimal hyperparameters are identified using either an exhaustive search or genetic algorithm. The top five model structures of each method are used to recursively predict future NOx emission rates over a 60-step time horizon. The RMSE at each future timestep is determined, and the recursive output prediction trends compared against measurements in time. The GRU neural network is identified as the best candidate for representing the system, demonstrating accurate and stable predictions across the future horizon by all considered models, while satisfactory performance was observed in several of the ARX/NARX formulations. These efforts have contributed 1) a concise resource of multiple proven dynamic machine learning methods, 2) a practical guide explaining the use of these methods, effectively lowering the "barrier-to-entry" of deploying such models in control systems, 3) a comparison study evaluating each method's performance on a mutual system, 4) demonstration of accurate multi-timestep emissions modeling suitable for systems-level control, and 5) generalizable results demonstrating the suitability of each method for prediction over a multi-step future horizon to other complex dynamic systems.