论文部分内容阅读
概述了重油脱盐系统的BP神经网络建模以及基于遗传算法的系统优化过程,将遗传算法与惩罚函数法相结合应用于约束优化的问题,改善了遗传算法的局限性。同时为了将不等式约束优化问题转化为单目标优化问题,对惩罚函数法进行了改进。结果表明:此方法可以有效解决静电脱盐问题。
The BP neural network modeling of heavy oil desalination system and the system optimization process based on genetic algorithm are summarized. The genetic algorithm and penalty function method are applied to the problem of constrained optimization to improve the limitation of genetic algorithm. At the same time, in order to transform the inequality constrained optimization problem into a single objective optimization problem, the penalty function method is improved. The results show that this method can effectively solve the problem of electrostatic desalination.