摘 要:针对污水处理的非线性系统,为了能够有效预测出水化学需氧量(COD)。提出了一种基于鸡群算法(CSO)算法优化的模糊神经网络预测模型。首先通过模糊神经网络设计了 COD 模糊神经网络预测模型;之后采用鸡群算法优化模糊神经网络模型参数,弥补预测模型容易陷入局部极小值的缺点,使模糊神经网络的预测精度有了明显提高。最后用 MATLAB 平台进行仿真实验,仿真结果清晰表明,改进型模糊神经网络预测模型具有很好的自适应性和鲁棒性,提高了 COD 预测精度和预测效果,能够满足实际污水处理的测量需求,具有一定的研究价值。
关键词:模糊神经网络;预测模型;出水 COD;污水处理;CSO 算法
DOI:10.19850/j.cnki.2096-4706.2022.23.020
基金项目:国家科技支撑计划课题(2014BAC01B04)
中图分类号:TP273.+4 文献标识码:A 文章编号:2096-4706(2022)23-0072-05
Effluent COD Prediction Model of Sewage Treatment Based on CSO Optimized Fuzzy Neural Network
SHEN Peng, LI Minghe, ZHANG Chen
(School of Electrical and Information Engineering, Anhui University of Technology, Maanshan 243032, China)
Abstract: Aiming at the nonlinear system of sewage treatment, in order to effectively predict the Chemical Oxygen Demand (COD) of effluent, this paper presents a fuzzy neural network prediction model based on CSO algorithm optimization. Firstly, the COD fuzzy neural network prediction model is designed by fuzzy neural network. Then, the Competitive Swarm Optimizer (CSO) is used to optimize the parameters of the fuzzy neural network model, which makes up for the shortcoming that the prediction model is easy to fall into local minima, so that the prediction accuracy of the fuzzy neural network has been significantly improved. Finally, the simulation experiment is carried out with MATLAB platform. The simulation results clearly show that the improved fuzzy neural network prediction model has good adaptability and robustness, improves the prediction accuracy and prediction effect of COD, and it can meet the measurement needs of actual sewage treatment, which has a certain research value.
Keywords: fuzzy neural network; prediction model; effluent COD; sewage treatment; CSO algorithm
参考文献:
[1] 苑进,胡敏,WANG K S,等 . 基于高斯过程建模的物联网数据不确定性度量与预测 [J]. 农业机械学报,2015,46(5):265-272.
[2] 李文静,李萌,乔俊飞 . 基于互信息和自组织 RBF 神经网络的出水 BOD 软测量方法 [J]. 化工学报,2019,70(2):687-695.
[3] 黄明智,马邕文,万金泉,等 . 污水处理中人工神经网络应用研究的探讨 [J]. 环境科学与技术,2008(3):131-135.
[4] 李明河,程呈,向丽 . 曝气生物滤池工艺污水处理出水 COD浓度预测模型研究 [J]. 工业控制计算机,2016,29(2):100-101.
[5] 聂勋科 . 基于神经网络的污水出水 COD 预测模型 [J]. 重庆工学院学报:自然科学版,2008(8):156-161+172.
[6] 许玥 . 污水曝气过程 COD 软测量及控制策略优化 [D]. 武汉:武汉科技大学,2018.
[7] 许鹏 . 基于 L-M 算法的模糊神经网络预测控制及初值问题研究 [D]. 马鞍山:安徽工业大学,2019.
[8] 李亚,刘丽平,李柏青,等 . 基于改进 K-Means 聚类和 BP 神经网络的台区线损率计算方法 [J]. 中国电机工程学报,2016,36(17):4543-4552.
[9] SØRENSEN P H,NØRGAARD M,RAVN O,et al. Implementation of neural network based non-linear predictive control [J].Neurocomputing,1999,28(1):37-51.
[10] 李松,刘力军,解永乐 . 遗传算法优化 BP 神经网络的短时交通流混沌预测 [J]. 控制与决策,2011,26(10):1581-1585.
[11] 冯立颖 . 改进的 BP 神经网络算法及其应用 [J]. 计算机仿真,2010,27(12):172-175.
[12] 褚辉,赖惠成.一种改进的BP神经网络算法及其应用 [J].计算机仿真,2007(4):75-77+111.
[13] ALEXANDRIDIS A,CHONDRODIMA E,EFTHIMIOU E, et al. Large Earthquake Occurrence Estimation Based on Radial Basis Function Neural Networks [J].IEEE Transactions on Geoscience and Remote Sensing, 2014, 52(9): 5443-5453.
[14] BANGALORE P, TJERNBERG L B. An Artificial Neural Network Approach for Early Fault Detection of Gearbox Bearings [J]. IEEE Transactions on Smart Grid, 2015, 6(2): 980-987.
[15] 龙文,梁昔明,龙祖强,等 . 基于混合进化算法的 RBF神经网络时间序列预测 [J]. 控制与决策,2012,27(8):1265-1268+1272.
[16] 郭通,兰巨龙,李玉峰,等 . 基于量子自适应粒子群优化径向基函数神经网络的网络流量预测 [J]. 电子与信息学报,2013,35(9):2220-2226.
[17] RENÉ D,MOGENS H. Modelling of the Secondary Clarifier Combined with the Activated Sludge Model No.1 [J].Water Science and Technology,1992,25(6):285-300.
[18] CHEN X,XUE A K,PENG D L,et al. Modeling of pH neutralization process using fuzzy recurrent neural network and DNA based NSGA-II [J].Journal of the Franklin Institute,2014,351(7):3847–3864.
[19] 郭堃,薛太林,耿杰,等 . 基于改进鸡群算法的无功优化综合分析 [J]. 电气自动化,2021,43(6):36-38.
[20] TAN Y,ZHU Y C. Fireworks Algorithm for Optimization [C]// ICSI 2010:Advances in Swarm Intelligence.Being:Springer,2010: 355-364.
[21] ZHENG Y J,SONG Q,CHEN S Y. Multiobjective fireworks optimization for variable-rate fertilization in oil crop production
[J].Applied Soft Computing, 2013,13(11):4253-4263.[22] GHOLIZADEH S,MILANY A. An improved fireworks algorithm for discrete sizing optimization of steel skeletal structures [J]. Engineering Optimization,2018,50(11):1829-1849.
作者简介:沈鹏(1997—),男,汉族,江苏扬州人,硕士在读,研究方向:污水处理智能控制研究;通讯作者:李明河(1963—),女,汉族,安徽马鞍山人,教授,硕士研究生,研究方向:复杂系统建模、智能控制研究和大型网络化控制研究。