使用博弈差分算法的电站锅炉高效低污染燃烧均衡优化

发布时间：2018-03-22 19:55

本文选题：电站锅炉　切入点：优化　出处：《化工学报》2017年06期 　论文类型：期刊论文

【摘要】：提高电站锅炉热效率,降低NO_x等污染物的排放量是电站节能减排必须解决的问题。经过采用经量子遗传算法(QGA)优化参数后的最小二乘支持向量机(LSSVM-QGA)建立燃烧优化模型,预测的锅炉热效率和NO_x排放量的平均相对误差分别达到了0.054%和1.229%,其预测精度及泛化能力均较优,有更强的适用性能。在此模型基础上,提出一种采用自适应缩放因子与交叉因子和共享函数机制的差分进化算法(DE),通过其演化博弈论中的NASH均衡,实现锅炉燃烧的多目标优化,结果表明,基于NASH均衡的优化方法可以得到操作变量的最优解集,能够更好地改善运行工况,最终可以实现削峰填谷,使电站锅炉保持一个稳定均衡的燃烧状态。
[Abstract]:It is necessary to solve the problem of energy saving and emission reduction in power plant by increasing the thermal efficiency of boiler and reducing the emission of pollutants such as NO_x. The combustion optimization model is established by using the least squares support vector machine (LSSVM-QGA) after the parameters are optimized by quantum genetic algorithm (QGA). The average relative errors of boiler thermal efficiency and NO_x emissions are 0.054% and 1.229%, respectively. The prediction accuracy and generalization ability are better and have stronger applicability. A differential evolutionary algorithm using adaptive scaling factor, crossover factor and shared function mechanism is proposed. The multi-objective optimization of boiler combustion is realized by NASH equalization in evolutionary game theory. The optimization method based on NASH equalization can get the optimal solution set of the operation variables, improve the operating conditions better, and finally realize the peak cutting and valley filling, so that the utility boiler can maintain a stable and balanced combustion state.
【作者单位】：西安建筑科技大学信息与控制工程学院;西安艾贝尔科技发展有限公司;
【基金】：国家自然科学基金青年科学基金项目(51508446) 陕西省自然科学基金项目(2015JM6337)~~
【分类号】：TM621.2;TP18

【相似文献】