基于约束多目标骨干粒子群的污水处理过程优化控制

发布时间：2018-03-25 15:16

本文选题：污水处理过程　切入点：数据驱动　出处：《电子测量与仪器学报》2017年09期

【摘要】：为了取得污水处理过程能耗和出水水质这对冲突目标之间的最佳平衡,提出一种基于约束多目标骨干粒子群的污水处理过程智能优化控制方法。首先,利用数据驱动的思想建立能耗和出水水质的模糊神经网络预测模型;其次,利用带自适应扰动的约束多目标骨干粒子群优化算法对溶解氧和硝态氮浓度的设定值进行动态寻优,并利用模糊隶属函数法设计智能决策系统用于从Pareto最优解集中确定最优设定值;最后,利用模糊逻辑控制器实现底层跟踪控制。基于国际基准平台BSM1实验结果表明,建立的数据驱动模型能够有效辨识污水处理过程;同时,所提的多目标优化控制方法在保证出水水质参数达标前提下,能够有效地降低污水处理过程的能耗。
[Abstract]:In order to achieve the best balance between energy consumption and effluent quality of wastewater treatment process, an intelligent optimization control method for wastewater treatment process based on constrained multi-objective backbone particle swarm optimization is proposed. The fuzzy neural network prediction model of energy consumption and effluent quality is established by using data-driven idea. Secondly, the dynamic optimization of dissolved oxygen and nitrate concentration is performed by using constrained multi-objective backbone particle swarm optimization algorithm with adaptive disturbance. The intelligent decision system is designed by using fuzzy membership function method to determine the optimal set value from the Pareto optimal solution set. Finally, the fuzzy logic controller is used to realize the bottom tracking control. The experimental results based on the international reference platform BSM1 show that, The established data-driven model can effectively identify the wastewater treatment process, and at the same time, the proposed multi-objective optimization control method can effectively reduce the energy consumption of the wastewater treatment process on the premise that the effluent quality parameters are up to standard.
【作者单位】：淮阴工学院自动化学院;
【基金】：淮安市科技计划(HAG2014001)资助项目
【分类号】：TP18;X703

【相似文献】