YANGCun-man,JUJia-wei,YUAN Fang,et al.Research on Intelligent Disinfection Prediction Model of Waterworks Based on PSO-BP Neural Network[J].China Water & Wastewater,2022,38(3):57-61.
基于PSO-BP神经网络的水厂智能消毒预测模型
- Title:
- Research on Intelligent Disinfection Prediction Model of Waterworks Based on PSO-BP Neural Network
- 关键词:
- 自来水厂; 加氯消毒; PSO-BP神经网络; BP神经网络; 预测
- Keywords:
- waterworks; chlorination; PSO-BP neural network; BP neural network; prediction
- 摘要:
- 为解决水厂运行过程中粗犷式、经验式投加氯消毒剂的问题，建立基于PSO-BP神经网络的水厂智能消毒预测模型。选取流量、矾耗、水质参数作为预测模型的输入参数，利用粒子群算法优化神经网络权值和阈值，模型评价指标平均绝对百分比误差（MAPE）、均方根误差（RMSE）都低于传统BP神经网络模型，其中RMSE值下降207 kg，MAPE值下降1.80%，相对标准偏差（RSD）下降了2.4%，有效提高了模型预测的准确性和稳定性，并在实际应用过程中有助于降低水厂氯消毒剂药耗，平均可节约生产成本约1 756 元/d。可见，PSO-BP智能消毒预测模型是合理、可行的，为城市自来水厂加氯量预测提供了一种简单可行的思路和方法。
- Abstract:
- In order to solve the problem of rough and empirical dosing of chlorination disinfectant in the operation of waterworks, an intelligent disinfection prediction model of waterworks based on PSO-BP neural network was established. The flow, alum consumption and water quality parameters were selected as the input parameters of the prediction model, and the neural network weight and threshold were optimized by particle swarm optimization algorithm. The average absolute percentage error (MAPE) and root mean square error (RMSE) of the evaluation indexes of the model were lower than those of the traditional BP neural network model, particularly RMSE decreased by 207 kg, MAPE decreased by 1.80%, and relative standard deviation (RSD) decreased by 2.4%, which could effectively improve the accuracy and stability of the model prediction. In the process of practical application, it was helpful to reduce the consumption of chlorination disinfectant and the production cost could be saved by 1 756 yuan/d, averagely. It can be seen that the PSO-BP intelligent disinfection prediction model is reasonable and feasible, which provides a simple and feasible idea and method for the prediction of chlorine addition in the disinfection system of urban waterworks.
相似文献/References:
[1]黄仲均,刘佳伟.基于一体化净水装置的自来水厂改造扩能案例分析[J].中国给水排水,2018,34(22):82.
HUANG Zhong-jun,LIU Jia-wei.Reconstruction and Expansion Design of Waterworks Based on Integrated Water Purification Device[J].China Water & Wastewater,2018,34(3):82.
[2]刘彦华,苏锡波,高迎亮,等.城镇自来水厂平流沉淀池改造技术与实践[J].中国给水排水,2020,36(14):131.
LIU Yan-hua,SU Xi-bo,GAO Ying-liang,et al.Renovation Technology and Practice of Horizontal Flow Sedimentation Tank in Urban Waterworks[J].China Water & Wastewater,2020,36(3):131.
[3]李丰庆.我国超大超滤水厂——广州北部水厂工艺设计[J].中国给水排水,2021,37(10):66.
LI Feng-qing.Process Design of the Super Large Ultrafiltration Waterworks in China: Guangzhou Beibu Waterworks[J].China Water & Wastewater,2021,37(3):66.
[4]赵新娟,刘伯一.短流程超滤膜工艺在凌庄水厂的应用[J].中国给水排水,2021,37(10):71.
ZHAO Xin-juan,LIU Bo-yi.Application of Short Process Ultrafiltration Membrane in Lingzhuang Waterworks[J].China Water & Wastewater,2021,37(3):71.
[5]黄孟斌,武洋,王梅芳,等.深圳长流陂水厂网格絮凝池提升改造应用实践[J].中国给水排水,2021,37(12):116.
HUANG Meng-bin,WU Yang,WANG Mei-fang,et al.Application Practice of Grid Flocculation Tank Upgrading and Reconstruction in Shenzhen Changliupi Waterworks[J].China Water & Wastewater,2021,37(3):116.
[6]何嘉莉,袁耀芬,周沛良,等.自来水厂混凝剂自动精准投加系统建设与运行[J].中国给水排水,2021,37(18):139.
HE Jia-li,YUAN Yao-fen,ZHOU Pei-liang,et al.Construction and Operation of Automatic and Accurate Coagulant Dosing System in Waterworks[J].China Water & Wastewater,2021,37(3):139.
[7]陈仁杰,刘明辉,丁陈龙,等.基于水厂砂滤填料附着物的BAF启动及其硝化性能[J].中国给水排水,2022,38(8):25.
CHENRen-jie,LIUMing-hui,DINGChen-long,et al.Startup of Biological Aerated Filter Seeded with Attached Microbes from Sand Filter in a Waterworks and Its Nitrification Performance[J].China Water & Wastewater,2022,38(3):25.
[8]李颖强,麻庆广,刘则华,等.我国南方典型自来水厂中游离氨基酸浓度及去除特性[J].中国给水排水,2022,38(13):28.
LIYing-qiang,MAQing-guang,LIUZe-hua,et al.Concentration Level and Removal of Fifteen Free Amino Acids in Eight Drinking Water Treatment Plants in South China[J].China Water & Wastewater,2022,38(3):28.
[9]宋欣,李燕君,黄慧,等.臭氧-上向流BAC工艺对常规及新污染物的控制效果[J].中国给水排水,2024,40(3):1.
SONGXin,LIYan-jun,HUANGHui,et al.Control of Conventional and Emerging Contaminants by Ozone-Upflow Biological Activated Carbon Process[J].China Water & Wastewater,2024,40(3):1.
[10]曾正仁,孙政,白华清,等.老旧自来水厂絮凝沉淀池技术改造实践[J].中国给水排水,2024,40(4):89.
ZENGZheng-ren,SUNZheng,BAIHua-qing,et al.Technical Transformation Practice of Flocculation Sedimentation Tank in an Aging Waterworks[J].China Water & Wastewater,2024,40(3):89.