Event-Triggered Online Learning Fuzzy-Neural Robust Control for Furnace Temperature in Municipal Solid Waste Incineration Process

Affected by high temperature and serious pollution, some key parameters in incinerator are difficult to obtain directly, and the detectable data also contain outliers and noise, which makes it extremely difficult to mine the relationship between variables and derive control rules. To solve these problems, an event-triggered online learning fuzzy-neural robust controller is proposed and applied to the furnace temperature control of municipal solid waste incineration (MSWI) process. First, the outliers are eliminated by the box-plot method, and the data is denoised with a Gaussian filter. Second, the controlled object model based on T-S fuzzy neural network is constructed by data-driven method. Third, an online learning fuzzy neural controller is designed to be imposed on the established controlled object model, which adaptively adjusts the network structure by calculating the information transmission strength of the rule neurons. Meanwhile, an event-triggered mechanism is introduced to reduce actuator wear and save energy while maintaining control effectiveness. Then, the convergence of the controller is deduced by Lyapunov’s second law. Finally, the validity of the proposed method is verified by process data from a real MSWI plant in Beijing, China. The results show that the method proposed in this paper can build the furnace temperature model from imperfect data, and the controller can grow and prune neurons autonomously, which improves the control accuracy and efficiency of the furnace temperature under external disturbances. Note to Practitioners—Municipal solid waste (MSW) has complex and variable components, and its incineration process relies on manual operations. However, manual operations have hysteresis and subjectivity, which will increase the workload of workers and also cause problems such as unstable incineration. Furnace temperature is the main controlled variable of MSWI process, which is closely related to MSW burnout rate and pollutant emission concentration. Therefore, an event-triggered online leaning fuzzy-neural robust controller is designed in this paper, which can keep the furnace temperature stable by automatically adjusting the primary air volume and drying grate speed under external disturbances. In addition, the controller can adjust its structure adaptively according to different operating conditions, and it is equipped with an event-triggered mechanism to meet the control requirements while reducing the frequency of controller updates, which improves equipment life and reduces energy consumption. Finally, the controller is validated by the process data of a real MSWI plant.