| 1,236 | 17 | 21 |
| Downloads | Citas | Reads |
Machine learning is the mainstream algorithm in the field of artificial intelligence. In recent years, the amount of data in the water industry has increased exponentially, and the application of artificial intelligence technology based on machine learning as the mainstream algorithm has been gradually expanded in the water industry. This paper summarizes the application status and development prospects of machine learning in Chinese water industry. At present, machine learning, with its powerful data mining ability, has been widely applied in the optimization and scheduling of water resources, the operation and maintenance of water treatment plants, pipe network operation and maintenance, and urban stormwater management. It has made outstanding contributions to water informatization and the in-depth mining and integrated utilization of data resources. In the future, machine learning can help achieve the upgrading of sewage treatment plants under the context of achieving carbon neutrality, and continuously promote the digitalization-to-intelligence transformation of water information in the water industry.
[1] LARSEN S,HAMILTON S,LUCIDO J,et al.Supporting diverse data providers in the open water data initiative:communicating water data quality and fitness of use(rreview)[J].Journal of the American water resources association,2016,52(4):859-872.
[2] 皇甫小留,王晶瑞,龙鑫隆,等.机器学习在水处理系统中的应用[J].给水排水,2022,58(11):153-165.
[3] JAIN P,GARIBALDI J M,HIRST J D.Supervised machine learning algorithms for protein structure classification[J].Computational biology & chemistry,2009,33(3):216-223.
[4] ZOPPI T,CECCARELLI A,BONDAVALLI A.Unsupervised algorithms to detect zero-day attacks:strategy and application[J].IEEE ACCESS,2021,9:90603-90615.
[5] 黄志刚,刘全,张立华,等.深度分层强化学习研究与发展[J].软件学报,2023,34(2):733-760.
[6] 董天奥.POS优化算法在SWAT模型参数优化中的应用[J].吉林水利,2016(8):39-42.
[7] 丁晓嵘,郭腾飞,孟坤,等.水尺智能识别技术在潮白河生态补水中的应用[J].北京水务,2021(增刊1):29-32,42.
[8] 李雪清,郑航,刘悦忆,等.基于多源数据机器学习的区域水质预测方法研究[J].水利水电技术(中英文),2021,52(11):152-163.
[9] 曹佳宁.基于模糊决策树的黑臭水体遥感解译算法研究 [D].廊坊:北华航天工业学院,2021:31-37.
[10] 何慧梅,侯迪波,赵海峰,等.基于多因子融合的水质异常检测算法[J].浙江大学学报(工学版),2013,47(4):735-740.
[11] 李婵娟,焦有权,温江丽,等.BP神经网络在密云水库入库水量预测中的应用[J].北京水务,2022(4):14-20.
[12] ZHANG W,WANG H,LIN Y,et al.Reservoir inflow predicting model based on machine learning algorithm via multi-odel fusion:A case study of Jinshuitan river basin[J].IET cyber-systems and robotics,2021,3(3):265-277.
[13] 董陈超.基于遗传算法—生成对抗神经网络模型的宁夏自流灌区水资源优化调度研究[J].湖北农业科学,2021,60(15):174-180,187.
[14] 翁士创,苏明珍,李捷.基于粒子群算法的韩江流域水资源优化调度[J].人民珠江,2018,39(2):82-85.
[15] 刘子铭.基于XGBoost混合模型的MBR膜污染预测研究 [D].天津:天津工业大学,2019:39-58.
[16] 李佟,李军.基于BP神经网络与马尔可夫链的污水处理厂脱氮效果模拟预测[J].环境科学学报,2016,36(2):576-581.
[17] 穆秀春.基于统计回归的污水处理出水水质的软测量研究 [D].杭州:浙江工业大学,2005:30-50.
[18] 丛露露.基于遗传算法优化的RBF神经网络在污水处理中的研究与应用 [D].上海:华东理工大学,2014:34-40.
[19] 李佟,李军,付强.WEKA环境下模拟预测城市污水处理厂泥饼含水率[J].中国给水排水,2015,31(19):76-79.
[20] 肖红军.数据驱动的污水处理过程故障诊断与多步预测 [D].广州:华南理工大学,2016:36-51.
[21] 宋留,杨冲,张辉,等.造纸废水处理过程的高斯过程回归软测量建模[J].中国环境科学,2018,38(7):2564-2571.
[22] MJALLI F S,AL-ASHEH S,ALFADALA H E.Use of artificial neural network black-box modeling for the prediction of wastewater treatment plants performance.[J].Journal of environmental management,2006,83(3):329-338.
[23] BAGHERI M,MIRBAGHERI S A,ZAHRA B,et al.Modeling and optimization of activated sludge bulking for a real wastewater treatment plant using hybrid artificial neural networks-genetic algorithm approach[J].Process safety and environmental protection,2015,95(Part B):12-25.
[24] 宋韬略.基于神经网络的污水处理预测控制模型研究 [D].大庆:东北石油大学,2014:16-25.
[25] 义燕莲,吴纯青.一种基于粗糙集的水务预测方法[J].电脑知识与技术,2012,8(25):6118-6122.
[26] 崔东文.随机森林回归模型及其在污水排放量预测中的应用[J].供水技术,2014,8(1):31-36.
[27] 尚鑫.基于增量学习的智慧化城镇供水量预测算法研究 [D].重庆:重庆大学,2020:35-48.
[28] 徐东,张曾,周迅,等.基于机器学习的水厂短期供水量预测模型构建[J].四川水利,2022,43(4):37-40,57.
[29] 常啸.基于机器学习的自来水厂混凝剂投加控制研究 [D].南京:南京邮电大学,2021:30-42.
[30] 丁凯.基于支持向量机的出厂水水质控制方法的研究 [D].北京:华北电力大学,2019:31-54.
[31] 顾昭文.废水处理中混凝法优化—决策树模型应用可行性研究 [D].苏州:苏州科技大学,2017:14-30.
[32] 周中,张俊杰,丁昊晖,等.基于PSO-BP神经网络的隧道绿色建造污水处理预测模型[J].铁道科学与工程学报,2022,19(5):1450-1458.
[33] 崔玉莹.基于CS算法优化的管网漏损定位及预警研究 [D].郑州:华北水利水电大学,2021:15-30.
[34] 杨桃.基于机器学习的供水管网爆管诊断方法研究与实现 [D].重庆:重庆大学,2021:17-31.
[35] 王彤,杨军,张浩祥,等.基于粒子群改进FCM聚类算法优化管网压力监测点布置研究[J].给水排水,2021,57(2):140-144.
[36] 唐鹏翔,许仕荣,盛炟.基于粒子群算法的阀门协同泵站控制供水管网压力[J].湖南师范大学自然科学学报,2020,43(3):70-75.
[37] 朱伶俐.基于数据分析与监测的智慧水务系统设计与实现 [D].青岛:青岛科技大学,2022:38-44.
[38] 彭森,程蕊,吴卿,等.基于极限学习机算法的供水管网爆管识别研究[J].中国给水排水,2022,38(7):56-62.
[39] 赵桓,吕谋,岳宏宇,等.基于群体智能优化算法的供水管网漏损定位研究[J].水电能源科学,2022,40(7):128-130,75.
[40] 李玉全.城市供水管网实时建模及漏损事件侦测定位研究 [D].杭州:杭州电子科技大学,2018:25-35.
[41] 杨利伟,邢雯雯,张莉平,等.基于GA优化BP神经网络模型的污水管道系统健康状况评估[J].给水排水,2021,57(9):123-131.
[42] 李杉杉.基于机器学习的市政管网运维风险评估 [D].哈尔滨:哈尔滨工业大学,2020:8-19.
[43] 范博.投影寻踪聚类模型在城市水务体系评估中的应用[J].吉林水利,2016(11):48-51.
[44] 李星.基于GIS的城市雨水管网多目标优化设计研究 [D].合肥:合肥工业大学,2017:21-36.
[45] 曹相生,刘杰,刘婷,等.基于枚举算法的雨水管网优化设计[J].中国给水排水,2010,26(7):37-39.
[46] 杨祺琪,张书亮,戴强,等.基于SWMM和改进差分进化算法的雨水管网优化方法[J].中国给水排水,2016,32(17):115-119,124.
[47] 卫尤澜.城市雨水管道风险评估与雨水泵站优化运行研究 [D].合肥:合肥工业大学,2019:24-31.
[48] 郝亚.基于深度学习的城市洪涝灾害风险预警研究 [D].常州:常州大学,2022:46-51.
[49] 叶陈雷,徐宗学,雷晓辉,等.基于SWMM和InfoWorks ICM的城市街区尺度洪涝模拟与分析:以福州市某排水社区为例[J].水资源保护,2023,32(2):87-94.
[50] 虞佳庆,武丹丹,王海峰,等.杭州城西污水厂提标改造实践与思考[J].中国给水排水,2022,38(16):89-95.
Basic Information:
DOI:10.20040/j.cnki.1000-7709.2024.20230789
China Classification Code:TV213.4;TP181
Citation Information:
[1]LI Si-min,CHAN Qing-qing,JIN Xin ,et al.Application Status and Development Prospect of Machine Learning in Water Industry[J].Water Resources and Power,2024,42(03):43-48.DOI:10.20040/j.cnki.1000-7709.2024.20230789.
Fund Information:
国家自然科学基金青年基金项目(42207092); 河北省研究生创新资助项目(CXZZBS2021016); 河北省科技厅青年基金项目(D2020402028); 中央引导地方科技发展资金项目(226Z4203G); 河北省高等学校科学技术研究项目(BJK2023071)
2023-05-16
2023
2023-06-22
2023
2024-01-08
1
2024-02-01
2024-02-01
2024-02-01