固定床反应器基于改进混合模型的串级推断控制

Cascade Inferential Control for a Nonadiabatic Fixed bed Reactor Based on Improved Hybrid Model

提出了非绝热式固定床反应器基于改进混合模型的串级非线性推断控制策略。首先提出了邻二甲苯氧化非绝热式固定床反应器基于改进混合模型的推断估计器；然后设计了基于新型非线性自适应控制算法的副控制器和基于程序变增益 Ｐ Ｉ Ｄ 的主控制器，同时设计了新型非线性滤波器以解决该反应器主回路比副回路响应快的问题；最后建立了该固定床反应器基于改进混合模型的串级非线性推断控制系统。仿真结果表明该推断估计器具有良好的静态、动态特性，较高的估计精度和较好的实时性，所需训练样本少，易于理解和研究，外推性能良好等优点；该串级推断控制系统具有良好的跟踪性能和抗干扰性能，其可靠性和控制性能优于单回路推断控制系统。

A new cascade nonlinear inferential control strategy for a nonadiabatic fixed bed reactor based on improved hybrid model is proposed. Firstly a new inferential estimator of the fixed bed reactor for phthalic anhydride synthesis based on the improved hybrid model is developed. Then a new nonlinear adaptive control algorithm is employed to design secondary controller, improved program variable gain PID is proposed to design the primary controller, and a new nonlinear filter is designed to overcome the difficulty that primary process is much faster than secondary process. Finally the cascade nonlinear inferential control system based on the improved hybrid model is designed. Simulation results show that the proposed estimator possesses the advantages of high estimation accuracy, good real time nature, being accurate to interpolate and extrapolate and easier to analyze and interpret, and requiring significantly fewer training examples, and that the cascade nonlinear inferential control system provides excellent tracking performance and adequate disturbance rejection performance, substantively improves system reliability and control performance, and is much better than single loop inferential control system.