Large-Scale and Knowledge-Based Dynamic Multiobjective Optimization for MSWI Process Using Adaptive Competitive Swarm Optimization

Municipal solid waste incineration (MSWI) process is a complex industrial process with strong nonlinearity. It is a challenge to build a model for the MSWI process and carry out the corresponding optimization works. To solve this problem, the multiobjective optimization studies are conducted for both modeling and concerned indexes of the MSWI process, including the nitrogen oxides (NOx) emissions and the combustion efficiency (CE). First, a data-driven-based multiple-input multiple-output model is established for the NOx emissions and the CE of the MSWI process based on Takagi–Sugeno–Kang fuzzy neural network. Second, an adaptive large-scale multiobjective competitive swarm optimization (ALMOCSO) algorithm is designed for solving the multiobjective optimization problems (MOPs) of the MSWI process. A comprehensive evaluation system is proposed to complete the optimization foundation, and an adaptive scheme and multistrategy learning are proposed to improve the optimization effect of the ALMOCSO algorithm in solving complex MOPs. Then, a Pareto optimal set obtained from massive historical data is utilized as optimization reference to realize the dynamic multiobjective optimization for the NOx emissions and the CE of the MSWI process. Finally, the feasibility and effectiveness of the proposed methodology for optimizing the MSWI process are confirmed by the experiments using the data collected from a real MSWI plant. The results indicate that the modeling accuracy is satisfactory, and the CE is improved over 10% and the reduction of the NOx emissions is achieved 15.58%.