Optimal control of distillation column using Non-Dominated Sorting Genetic Algorithm-II

Many control problems involve simultaneous optimization of multiple performance measures that are often non-commensurable and competing with each other. The presence of multiple objectives in a problem usually gives rise to one set of optimal solutions, largely known as Pareto-optimal solutions. In this paper, the Non-Dominated Sorting Genetic Algorithm-II (NSGA-II) has been successfully applied to optimization of dynamic state of simple distillation process. This paper presents the tuning of Proportional-Integral-Derivative (PID) controllers by minimizing of three objective functions (overshoot, response time, and Integral of Absolute Error (IAE)) through NSGA-II. A MATLAB code for real-parameter NSGA-II has been coupled with HYSYS v.3.1 process simulator for simulation and optimization of process. Optimization numerical results show that genetic algorithm is more suitable method for optimal control of distillation columns than traditional methods.     

智能预测算法在污水处理pH值控制中的应用

在处理污水时pH值的变化过程具有高度非线性和时滞性,常规PID控制器的控制效果不够理想。介绍了污水处理过程的反应原理以及pH值控制方面存在的问题,阐述了非线性预测控制算法的一般步骤,确定了污水pH值智能预测控制的研究思路。确定了输入输出变量并搭建其数学模型,然后根据数学模型构建了神经网络预测模型。将粒子群与BP神经网络相结合,利用粒子群算法优化神经网络的初始权值阈值,既能克服BP算法局部最优的问题,又能提升收敛速度及预测精度。最后将智能预测控制算法的输出作用于PID控制回路的设定值。仿真结果表明,智能预测控制算法控制性能优于单纯PID控制,能更快跟踪设定值,具有更强的适应性。