Dynamic modeling of NOX emission in a 660 MW coal-fired boiler with long short-term memory. (1st June 2019)

• Record Type: Journal Article
• Authors: Tan, Peng; He, Biao; Zhang, Cheng; Rao, Debei; Li, Shengnan; Fang, Qingyan; Chen, Gang
• Is Part Of: Energy. Volume 176(2019)
• Page Start: 429
• Page End: 436
• Publication Date: 2019-06-01
• Subjects: Recurrent neural network (RNN) -- Long short-term memory (LSTM) -- Dynamic model -- NOX emission -- Coal-fired utility boiler; Power resources -- Periodicals; Power (Mechanics) -- Periodicals; Energy consumption -- Periodicals; 333.7905
• DOI: 10.1016/j.energy.2019.04.020
• Languages: English
• ISSNs: 0360-5442

Abstract

Abstract: With the rapid development of renewables, increasing demands for the participation of coal-fired power plants in peak load regulation is expected. Frequent transients result in continuous, wide variations in NOX emission at the furnace exit, which represents a substantial challenge to the operation of SCR systems. A precise NOX emission prediction model under both steady and transient states is critical for solving this issue. In this study, a deep learning algorithm referred to as long short-term memory (LSTM) was introduced to predict the dynamics of NOX emission in a 660 MW tangentially coal-fired boiler. A total of 10000 samples from the real power plant, covering 7 days of operation, were employed to train and test the model. The learning rate, look-back time steps, and number of hidden layer nodes were meticulously optimized. The results indicate that the LSTM model has excellent accuracy and generalizability. The root mean square errors of the training data and test data are only 7.6 mg/Nm 3 and 12.2 mg/Nm 3, respectively. The mean absolute percentage errors are within 3%. Additionally, a comparative study between the LSTM and the widely used support vector machine (SVM) was conducted, and the result indicates that the LSTM outperforms the SVM. Highlights: Dynamic modeling of NOx emission under both steady and transient conditions. Long short-term memory (LSTM) based NOx emission prediction framework. Excellent accuracy and generalization ability with the LSTM based model. Performance comparison between the LSTM and the widely used support vector machine. Case study based on operation data from a real power plant.