Adaptive LSSVM based iterative prediction method for NOx concentration prediction in coal-fired power plant considering system delay

Soft sensing of NOx emission from waste incineration process based on data de-noising and bidirectional long short-term memory neural networks

Continuous emission monitoring system is commonly employed to monitor NOx emissions in municipal solid waste incineration (MSWI) processes. However, it still encounters the challenges of regular maintenance and measurement lag. These issues significantly impact the accurate and stable control of NOx emissions. Therefore, developing a soft NOx emission sensor to complement hardware monitoring becomes imperative. Considering data noise, dynamic nonlinearity, time series characteristics and volatility in the MSWI process, this article introduces a soft sensor model for NOx emission prediction utilizing the complete ensemble empirical mode decomposition adaptive noise (CEEMDAN)-wavelet threshold (WT) method and bidirectional long short-term memory (Bi-LSTM). Firstly, the original data signal is decomposed into a group of intrinsic mode functions (IMFs) using the CEEMDAN. Subsequently, the WT processes the high-frequency IMFs that are noise-dominant. Then, all IMFs are reconstructed to obtain the denoized signal. Finally, the Bi-LSTM model is employed to predict NOx emissions. Compared to conventional modelling approaches, the model proposed in this article demonstrates the best predictive performance. The mean absolute percentage error, root-mean-squared error and average absolute error on the test set of the proposed model are 3.75%, 5.34 mg m-3 and 4.34 mg m-3, respectively. The proposed model provides a new method to soft sensing NOx emissions. It holds significant practical value for precise and stable monitoring of NOx emissions in MSWI processes and provides a reference for research on modelling key process parameters.

Multi-objective prediction for denitration systems in cement: an approach combining process analysis and bi-directional long short-term memory network

Selective Non-Catalytic Reduction (SNCR) can improve the denitration process and reduce NOx emissions by accurizing prediction of NOx concentration and ammonia escape. However, there are inevitable time delays and nonlinearity problems in the prediction of NOx emission. To reduce NOx concentration quickly in SNCR, excessive ammonia spraying often causes a large amount of ammonia to escape, resulting in secondary pollution. Therefore, it is particularly important to monitor ammonia escape. To solve the above problems, this paper proposes a framework by specifically analyzing the cement denitration process and combining a multi-objective time series bi-directional long short-term memory network (MT-BiLSTM). Among them, the model achieves multi-objective prediction of NOx emission concentration and ammonia escape simultaneously. In addition, time series containing delay information are introduced in the input layer to eliminate the influence of delay. Based on the bi-directional LSTM model, the dropout strategy is adopted to improve the generalization of the model and the Adam optimizer is applied to improve the network performance. Besides, through the multi-step prediction of NOx emission at 3 time points, the dynamic nature of the data is preserved, which provides dynamic information support for realizing the automation of denitration system. The prediction performance of the MT-BiLSTM model is experimentally validated, and the results demonstrate that it can reliably predict both NOx and ammonia escape. The model achieves more accurate and reliable results for the prediction of flue gas concentrations compared with other methods such as SVR, DTR and LSTM. Therefore, the MT-BiLSTM model provides a basis for achieving NOx emission reduction and accurate ammonia injection.

A novel online modeling for NOx generation prediction in coal-fired boiler

The selective catalytic reduction (SCR) denitration technology is widely used in coal-fired generating units. The NOx concentration of boiler outlet is an important parameter in the feedforward control of SCR denitration. However, its measurement lag leads to a large range fluctuation of NOx emission, which affects the safe and economic operation of the unit. In order to solve the problem of boiler outlet NOx concentration measurement lag in denitration control, and improve the timeliness of fluctuation response for denitration control. Many studies have reported on NOx concentration prediction models based on the long short-term memory (LSTM) algorithm, support vector machines (SVM) algorithm, et al. However, there are no reports on online modeling, particularly none on predictive values of boiler outlet NOx concentration ahead of the measured values. Thus, in this study, a 1000 MW ultra-supercritical coal-fired boiler was selected, and 2404 sets of measured samples were collected to predict NOx concentration. A novel online modeling method for NOx concentration of boiler outlet was proposed. For the first time, a high-precision online real-time prediction model of boiler outlet NOx concentration was innovatively established based on improved long short-term memory network (ILSTM). A feature quantity weight analysis method based on the RRelieff algorithm is adopted, and the change rates of feature quantities were used as input in the model. The results showed that the root mean square error (δ_R) and computation time of ILSTMN reduced relatively by 17.97 % and 1.97 s, respectively. The online model with satisfied accuracy is trained in 1 s, which uses the latest recent data from decentralized control system (DCS). The NOx concentration of boiler outlet predicted by the online model is 22 s ahead of the measurement NOx concentration, and the prediction accuracy is still as high as 96 % without the intervention after two years of operation. As a feedforward of SCR denitration control system, NOx concentration predicted by the model can significantly improve the timeliness of control response. The online model provides theoretical support for suppressing large fluctuations of NOx emissions.

Closed-Loop Combustion Optimization Based on Dynamic and Adaptive Models with Application to a Coal-Fired Boiler

To increase combustion efficiency and reduce pollutant emissions, this study presents an online closed-loop optimization method and its application in a boiler combustion system. To begin with, three adaptive dynamic models are established to predict NOx emission, the carbon content of fly ash (Cfh), and exhaust gas temperature (Teg), respectively. In these models, the orders of the input variables are considered to enable them to reflect the dynamics of the combustion system under load changes. Meanwhile, an adaptive least squares support vector machine (ALSSVM) algorithm is adopted to cope with the nonlinearity and the time-varying characteristics of the combustion system. Subsequently, based on the established models, an economic model predictive control (EMPC) problem is formulated and solved by a sequential quadratic programming (SQP) algorithm to calculate the optimal control variables satisfying the constraints on the control and control moves. The closed-loop optimization system is applied on a 600 MW boiler, and the performance analysis is conducted based on the operation data. The results show that the system can effectively increase boiler efficiency by about 0.5%.

Dynamic NOx emission prediction based on composite models adapt to different operating conditions of coal-fired utility boilers

An accurate NO_x concentration prediction model plays an important role in low NO_x emission control in power stations. Predicting NO_x in advance is of great significance in satisfying stringent environmental policies. This study aims to accurately predict the NO_x emission concentration at the outlet of boilers on different operating conditions to support the DeNO_x procedure. Through mutual information analysis, suitable features are selected to build models. Long short-term memory (LSTM) models are utilized to predict NO_x concentration at the boiler's outlet from selected input features and exhibit power in fitting multivariable coupling, nonlinear, and large time-delay systems. Moreover, a composite LSTM model composed of models on different operating conditions, like steady-state and transient-state condition, is prosed. Results of one whole day of typical operating data show that the accuracy of the NO_x concentration and fluctuation trend prediction based on this composite model is superior to that using a single LSTM model and other non-time-sequence models. The root mean square error (RMSE) and R² of the composite LSTM model are 3.53 mg/m³ and 0.89, respectively, which are better than those of a single LSTM (i.e., 5.50 mg/m³ and 0.78, respectively).

An Ensemble Deep Belief Network Model Based on Random Subspace for NO x Concentration Prediction

An effective NO _x prediction model is the basis for reducing pollutant emissions. In this paper, a real-time NO _x prediction model based on an ensemble deep belief network (DBN) is proposed. Variable importance projection analysis is adopted to screen variables, the time delay of each variable is estimated, and the phase space of the original sample is reconstructed by analyzing the historical data. An ensemble strategy based on random subspace is presented, including the data set partition method and ensemble mode of the model. First, subspaces are constructed according to the component information extracted by partial least squares. Then, the deep belief network is used as a submodel. Finally, a back propagation neural network is developed for model combination. The ensemble deep belief network model has been used to model the NO _x emission prediction of a 660 MW boiler. The simulation results show that the ensemble DBN model can fully exploit the nonlinear mapping relationship between input variables and NO _x concentration by using various learning learners. Compared with the back propagation neural network and support vector machine, which are commonly used in NO _x modeling, the ensemble DBN model has better prediction performance and generalization ability.