The development of accurate data-driven models is of great significance for online monitoring and control of industrial processes. In this study, a nonlinear dynamic soft-sensing algorithm for measuring and predicting the nitrogen oxides (NOx) emissions of the denitration system of a power plant was developed. First, the processes and principles of the denitration system were studied. Second, a soft-sensing algorithm based on long short-term memory (LSTM) and least absolute shrinkage and selection operator (LASSO) was proposed. The dynamics of the process were captured by LSTM, and the selection of influential input variables was achieved by LASSO. A moving window cross validation (MWCV) strategy was applied to determine the hyperparameters of the proposed algorithm. Third, the proposed algorithm was implemented to predict NOx emissions from a denitration system. The experimental results demonstrated that the proposed approach had superior accuracy and higher precision of variable selection compared with other state-of-the-art soft-sensing algorithms. In addition, the variable importance analysis provided by the proposed algorithm is consistent with the principles of chemical reactions and field experiences. The proposed algorithm could provide theoretical and technical support for the optimization of the denitration system and predictive control design of the denitration process.

In the study, we propose an adaptive variable selection algorithm for multi-layer perceptron (MLP)-based soft sensors. The proposed algorithm employs nonnegative garrote (NNG) to shrink the input weights of the trained MLP. To improve the shrinkage efficiency of the NNG, adaptive operators are designed using the mean impact value estimate. Moreover, the adaptive operators are data dependent, and are introduced into the constraints of NNG to make the shrinkage more efficient and effective. Cross-validation and Bayesian information criterion are used to determine the optimal garrote parameter for the NNG. The performance of the algorithm is validated using artificial datasets and a practical industrial application in coke dry quenching (CDQ) systems. The simulation results demonstrate that the adaptive mechanism improves the efficiency and precision of NNG, and has superior performance to other state-of-the-art algorithms. The result of variable selection is consistent with the experience of the field operator, and can provide technical supports for the optimisation and control of the CDQ process.

Soft sensor, as a significant intelligent inspection technology, has been widely used in modern process industries to achieve effective monitoring and prediction of product quality. However, the redundancy of model inputs and structure in practical industrial process modeling usually results in increased modeling complexity and decreased model performance. In this study, an input variable selection and structure optimization algorithm for long short-term memory (LSTM)-based soft sensor with a dual nonnegative garrote (DNNG) approach was proposed. Firstly, a well-trained initial LSTM model is constructed using the process dataset to capture the temporal dynamic behavior of the industrial process. Secondly, the DNNG algorithm is integrated into the LSTM to reduce the redundancy of input variables and hidden nodes. The strategy efficiently selects the most consequential input variables for the model, and simultaneously simplifies the LSTM structure by eliminating redundant recurrent hidden nodes to reduce model overfitting risk. Moreover, the hyperparameters of the model are determined by combining grid search with blocked cross-validation. Finally, the developed algorithm is compared to other state-of-the-art algorithms using a numerical case and employed to forecast the SO ₂ concentration in the net flue gas emissions of a coal-fired power plant desulphurization system. Comparative results show that the proposed algorithm effectively eliminates redundant variables and streamlines the model structure while presenting better prediction performance than other algorithms.

In this paper, normalized mutual information feature selection (NMIFS) and tabu search (TS) are integrated to develop a new variable selection algorithm for soft sensors. NMIFS is applied to select influential variables contributing to the output variable and avoids selecting redundant variables by calculating mutual information (MI). A TS based strategy is designed to prevent NMIFS from falling into a local optimal solution. The proposed algorithm performs the variable selection by combining the entropy information and MI and validating error information of artificial neural networks (ANNs); therefore, it has advantages over previous MI-based variable selection algorithms. Several simulation datasets with different scales, correlations and noise parameters are implemented to demonstrate the performance of the proposed algorithm. A set of actual production data from a power plant is also used to check the performance of these algorithms. The experiments showed that the developed variable selection algorithm presents better model accuracy with fewer selected variables, compared with other state-of-the-art methods. The application of this algorithm to soft sensors can achieve reliable results.