Bayesian Optimization-Based Interval Type-2 Fuzzy Neural Network for Furnace Temperature Control

The furnace temperature (FT) control is the key for ensuring the stable operation and effective pollution reduction in municipal solid waste incineration (MSWI) processes. However, conventional control strategies encounter challenges in effectively managing FT due to uncertainties associated with material composition, feeding modes, and equipment maintenance. In response to these challenges, this article introduces a control approach utilizing a Bayesian optimization-based interval type-2 fuzzy neural network (BO-IT2FNN), which achieves offline optimization and online control through the FT controller constructed by IT2FNN. In offline optimization process, the BO algorithm is used to optimize the learning rate of multiple types parameter of IT2FNN controller. In the online control process, fine-tuned by gradient descent method with multiple LR for adaptability. In addition, the stability of control system is confirmed using theorem of Lyapunov, providing the theoretical foundation. Experiments with real MSWI data, tested on a hardware-in-loop platform, prove the effectiveness of the proposed method.

I. Introduction

The amount of municipal solid waste (MSW) has risen sharply with economic growth and urbanization [1], leading to widespread “garbage siege” problems in many cities [2]. Unprocessed MSW challenges environmental cleanup and sustainable growth [1]. The MSW incineration (MSWI) process, focusing on waste reduction, resource utilization, and harmless treatment, has gained importance. Developed countries like Europe, America, and Japan have advanced MSWI systems [3], but China faces unique issues due to its climate, lifestyle, and economic status. These include unpredictable waste composition, varying calorific values, and moisture levels, making imported automatic combustion control systems less effective. Currently, MSWI in China mainly uses manual control [1], affected by limited energy and varying expertise, limiting consistent operation. Therefore, it is necessary to conduct intelligent control research on furnace temperature (FT) based on the specific situation in China to overcome the difficulties in process control [4], [5].