引用本文:姚继平,郝芳华,王国强,等.人工智能技术对长江流域水污染治理的思考[J].环境科学研究,2020,33(5):1268-1275.
YAO Jiping,HAO Fanghua,WANG Guoqiang,et al.Artificial Intelligence Technology for Water Pollution Control in the Yangtze River Basin[J].Research of Environmental Sciences,2020,33(5):1268-1275.]
【打印本页】   【HTML】   【下载PDF全文】   查看/发表评论  【EndNote】   【RefMan】   【BibTex】
←前一篇|后一篇→ 过刊浏览    高级检索
本文已被:浏览 88次   下载 97 本文二维码信息
码上扫一扫!
分享到: 微信 更多
人工智能技术对长江流域水污染治理的思考
姚继平, 郝芳华, 王国强, 程红光, 薛宝林, 鱼京善
北京师范大学水科学研究院, 城市水循环与海绵城市技术北京市重点实验室, 北京 100875
摘要:
随着经济的快速发展和城市化进程的不断加速,促使水污染严重的长江流域需从污染物去除过程的建模与优化、污水处理过程的优化控制、水污染监测系统的构建开展水污染治理研究.传统的水污染处理技术存在污染物去除效率预测精度较低、污水优化控制成本较高、水污染监测滞后效应严重的问题.人工智能技术能够有效克服上述问题,因此通过梳理国内外学者利用人工智能技术在污水污染物去除过程的建模与优化、污水处理过程的优化控制及水污染监测系统的构建等方面的研究成果,为全面加强长江流域水污染治理能力提供科学可靠的技术指导.结果表明:①利用人工神经网络技术(径向基神经网络、多层前馈网络-人工神经网络、多层感知器神经网络)对污水污染物去除过程进行建模与优化,为精确预测长江流域重金属(Cr、Cu)、营养盐(TN、TP)、持久性有机污染物〔PBDEs(多溴二苯醚)、HCH(六氯环己烷)〕的去除率提供重要参考价值.②采用污水处理的自动控制技术与人工智能技术(递归神经网络、支持向量机、模糊神经网络等)构建污水智能控制系统,为长江流域实现高效节能的污水优化控制提供重要的技术指导.③利用在线监测仪器和人工智能技术(小波神经网络、多元线性回归-人工神经网络、叠层去噪自动编码器等)建立水污染智能监测系统,为解决长江流域水污染监测响应滞后问题提供有力的技术支持.因此,人工智能技术对长江流域提高污水污染物去除率,降低污水优化控制成本,提升水污染监测时效性具有重要的推广价值.
关键词:  长江流域  人工智能技术  水污染治理  污染物去除率  优化控制  水污染监测系统
DOI:10.13198/j.issn.1001-6929.2020.03.41
分类号:X52
基金项目:国家水体污染控制与治理科技重大专项(No.2017ZX07302004)
Artificial Intelligence Technology for Water Pollution Control in the Yangtze River Basin
YAO Jiping, HAO Fanghua, WANG Guoqiang, CHEN Hongguang, XUE Baolin, YU Jingshan
Beijing Key Laboratory of Urban Hydrological Cycle and Sponge City Technology, College of Water Sciences, Beijing Normal University, Beijing 100875, China
Abstract:
With the rapid development of economy and the acceleration of urbanization, research on water pollution control needs to be carried out in the heavily polluted Yangtze River Basin, including the modeling and optimization of pollutant removal processes, the optimization control of sewage treatment processes, and the construction of water pollution monitoring system. The traditional water pollution treatment technology has the problems of low prediction accuracy of pollutant removal efficiency, high cost of sewage optimization control and serious lag effect of water pollution monitoring. Artificial intelligence technology can effectively overcome the above problems. By combing the existing research results of wastewater pollutant removal modeling and optimization, wastewater treatment process optimization control and water pollution monitoring system construction using artificial intelligence technology, we can provide scientific and reliable technical guidance for comprehensively strengthening the capacity of water pollution control in the Yangtze River Basin. The results show that: (1) Using artificial neural network technology (radial basis function neural network, multilayer feedforward neural network, multilayer perceptron neural network, etc.) to model and optimize the process of wastewater pollutant removal, which provides an important reference value for accurately predicting the removal efficiency of heavy metals (Cr, Cu), nutrients (TN, TP) and persistent organic pollutants (PBDEs, HCH) in the Yangtze River Basin. (2) Using automatic sewage treatment control technology and artificial intelligence technology (recurrent neural network, support vector machine, fuzzy neural network, etc.) to establish a sewage intelligent control system, which provides important technical guidance for achieving efficient and energy-saving sewage control in the Yangtze River Basin. (3) Using on-line monitoring instruments and artificial intelligence technology (wavelet neural network, multiple linear regression artificial neural network, automatic coder of laminated noise removal, etc.) to establish a water pollution intelligent monitoring system, which provides strong technical support for solving the problem of lagging response of water pollution monitoring in the Yangtze River Basin. Consequently, artificial intelligence technology has important promotion value to improve the efficiency of sewage pollutant removal, reduce the cost of sewage optimal control, and improve the timeliness of water pollution monitoring in the Yangtze River Basin.
Key words:  Yangtze River Basin  artificial intelligence technology  water pollution control  pollutant removal efficiency  optimize control  water pollution monitoring system