
优化RBF神经网络控制水厂混凝剂投加的研究
庹婧艺, 徐冰峰, 徐悦, 喻岚, 王雪颖, 郭露遥
优化RBF神经网络控制水厂混凝剂投加的研究
Optimized RBF Neural Networks Predicts Coagulation in Waterworks
净水厂混凝剂投加受多重进水因素影响,且变化规律呈现高度的非线性模式,难以控制,采用PSO(粒子群算法)对RBF(径向基神经网络)进行优化,建立误差反向传播的非线性高维映射水厂投药量动态模型。相较于单一RBF模型,优化后的RBF模型平均相对误差降低了3.05%、最大相对误差降低了0.198 6,迭代收敛速度快,对不同的水厂也具有良好的适应性。
The amount of coagulation in the process of water purification in water plants is influenced by multiple water ingress factors, and the law of change presents a highly nonlinear pattern difficult to control. Based on the RBF optimized by PSO, a dynamic model of nonlinear high-dimensional mapping water plant with error reverse propagation is established. Compared with the single RBF model, the average relative error is reduced by 3.05%, the maximum relative error is reduced by 0.198 6, and has a faster iterative convergence speed,and also has good adaptability to the water plant of different processes.
混凝剂投加 / RBF / PSO / 自来水厂 {{custom_keyword}} /
coagulant dosage / RBF neural network / particle swarm optimization / waterworks {{custom_keyword}} /
表1 自来水厂常用模拟算法精度对比 |
模型 | 类别 | MRE(平均相对误差) | RE max(最大相对误差) | RE min(最小相对误差) | 分析 |
---|---|---|---|---|---|
回归分析 | 高浊[ | 0.101 0 | 0.320 0 | 0.015 2 | 数据分类复杂、精度较差 |
低浊[ | 0.086 7 | 0.326 4 | 0 | ||
机理模型 | 5~15 ℃[ | - | 0.351 0 | 0 | 难以增加计算维度来进行多因素分析 |
15~25 ℃[ | - | 0.150 8 | 0 | ||
单一神经网络 | BP[ | 0.098 2 | 0.220 5 | 0.000 8 | 迭代次数多、收敛速度慢、易陷入局部最小[ |
RBF | 0.086 8 | 0.324 1 | 0.005 4 | 收敛速度快、拟合能力高 |
表2 优化组合的RBF与单一RBF模型运行精度对比 |
算法名称模型 | MRE | MAE | RE max | RE min |
---|---|---|---|---|
PSO优化RBF神经网络 | 0.056 3 | 0.238 | 0.125 5 | 0.001 5 |
单一RBF神经网络 | 0.086 8 | 0.483 | 0.324 1 | 0.005 4 |
组合与单一网络差值 | 0.030 3 | 0.245 | 0.198 6 | 0.003 9 |
1 |
徐少川,阎相伊,刘宝伟,等.智能控制在净水混凝投药系统中的应用[J].中国给水排水,2017,33(13):60-63.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
2 |
张瑶瑶. 沈阳某给水厂水质参数回归分析与应用研究[D].哈尔滨:哈尔滨工业大学,2017.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
3 |
刘泽华. 运用数学模型方法建立投药自动化系统[D].重庆:重庆大学,2002.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
4 |
李培军. 混凝投药工艺控制技术研究[D].成都:西华大学,2010.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
5 |
唐德翠,邓晓燕,朱学峰,等.水厂混凝剂投加量建模研究[J].水处理技术,2010,36(6):54-56,89.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
6 |
王晓杰,嵇赟喆.运用人工神经网络预测净水厂混凝投药的研究[J].中国科技信息,2005(12):54-53.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
7 |
李拓. 基于BP神经网络的水厂混凝投药控制系统研究[D].昆明:昆明理工大学,2015.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
8 |
蒋绍阶,仇洪建,段果,等.基于短程反馈BP神经网络的混凝投药控制中试[J].中国给水排水,2013,29(11):26-29.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
9 |
高俊岭,张义哲.基于PSO-RBF神经网络的锂电池SOC估算[J].重庆工商大学学报(自然科学版),2020,37(2):37-41.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
10 |
AbdullahS, Rama Chandra Pradhan, PradhanDileswar, et al. Modeling and optimization of pectinase-assisted low-temperature extraction of cashew apple juice using artificial neural network coupled with genetic algorithm, 2021,339.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
11 |
Science - Applied Sciences. Data from Central South University Provide New Insights into Applied Sciences (Fast Multi-Objective Antenna Optimization Based on RBF Neural Network Surrogate Model Optimized by Improved PSO Algorithm)[J]. Computers, Networks &;Communications, 2019.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
12 |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
13 |
丁承君,张家梁,冯玉伯,等.基于PSO优化RBF神经网络的往复式压缩机故障诊断[J].制造业自动化, 2020,42(6):47-52.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
14 |
赵寅军. 混凝投药预测函数控制研究[D].杭州:浙江工业大学,2011.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
15 |
黄丽娟. 水厂混凝投药量复合控制系统的研究与应用[D].长沙:中南大学,2014.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
16 |
饶小康,贾宝良,鲁立.基于人工神经网络算法的水厂混凝投药控制系统研究与开发[J].长江科学院院报,2017,34(5):135-140.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
17 |
夏学文,刘经南,高柯夫,等.具备反向学习和局部学习能力的粒子群算法[J].计算机学报,2015,38(7):1 397-1 407.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
18 |
张栒,湛成伟,邓辉文,等.一种快速减法聚类算法[J].西南师范大学学报(自然科学版),2006(3):126-129.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
19 |
周维华. RBF神经网络隐层结构与参数优化研究[D].上海:华东理工大学,2014.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
20 |
毛湘云,徐冰峰,孟繁艺.PSO-SVM与BP神经网络组合预测供水系统余氯的方法[J].土木与环境工程学报(中英文),2019,41(4):159-164.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_ref.label}} |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
/
〈 |
|
〉 |