Research on big data-driven optimization model and intelligent control algorithm for thin-plate tobacco strip drying processes

Aiming at the problems of quality fluctuation and energy consumption in thin-plate tobacco strip drying process in tobacco processing industry, this paper proposes an optimization model and intelligent control algorithm based on big data. Thin-plate tobacco strip drying process is a complex physical and chemical change process. Traditional control methods rely on empirical data and manual control, so it is difficult to achieve accurate control. In this study, by collecting and analyzing the data of temperature, humidity, steam flow and tobacco moisture content in the process of tobacco strip drying, and combining with big data technology to mine the potential laws, an optimization model based on improved dynamic random forest (DRF) model was constructed, and an intelligent regulation algorithm combining model predictive control (MPC) with adaptive PID was designed. The experimental results show that compared with the traditional PID control, the intelligent control algorithm improves the qualified rate of tobacco moisture content from 98.92% to 99.95%. This study verified the significant advantages of optimization model and intelligent control algorithm based on big data in improving tobacco drying quality, reducing energy consumption and improving system stability, and provided new ideas and methods for intelligent production in tobacco processing industry.