NOx Emissions Prediction With a Brain-Inspired Modular Neural Network in Municipal Solid Waste Incineration Processes

Abstract

The timely and accurate measurement of nitrogen oxide (NOx) emissions is important for efficient pollution controlling of municipal solid waste incineratio plants. To design an efficient and effective prediction model for NOx concentrations, a brain-inspired modular neural network (BIMNN) is developed in this study. First, a biologically-inspired modularization technique is proposed, in which the topological modularity gives rise to functional modularity. Consequently, different modules correspond to different tasks, improving the network efficiency by performing task decomposition. Subsequently, an adaptive task-oriented radial basis function (ATO-RBF) neural network is applied to construct each module. The ATO-RBF neural network is comprised of a structure self-organizing mechanism and an adaptive second-order learning algorithm, providing basis for generalization ability of BIMNN. Finally, during the testing or application stages, a competitive strategy is utilized to integrate the modules. The proposed prediction methodology is verified using industrial data, and the experimental results demonstrate its outperformance.