SVR WATER QUALITY PREDICTION MODEL BASED ON GA OPTIMIZATION
-
摘要: 针对污水中BOD5参数不易直接测得的特点,提出了基于遗传算法(Genetic Algorithm,GA)优化参数的支持向量机回归(Support Vector Regression,SVR)水质预测模型。采用机器学习的方法,通过建立污水中COD等参数与BOD5的数学关系模型的方式对BOD5进行测定。使用遗传算法对SVR中的关键参数进行寻优,解决了传统SVR预测模型参数选择的问题。以北京市污水处理厂进水污水作为研究对象进行实验,结果表明,与BP神经网络与SVR相比,使用GA-SVR方法进行预测的结果更优,其平均误差与均方根误差分别降至0.009443与16.88 mg/L。Abstract: Aiming at the fact that the BOD5 in wastewater can not easily measured directly, a support vector machine regression water quality prediction model based on genetic algorithm optimization parameters was proposed. Using machine learning method, BOD5 was determined by establishing a mathematical relationship model between COD and other parameters in wastewater. The genetic algorithm was used to optimize the key parameters in the SVR, which solved the problem of parameter selection of the traditional SVR prediction model. Experiments were carried out with the influent wastewater from the Beijing Wastewater Treatment Plant as the research object. The results showed that the average error and root mean square error of the results predicted by GA-SVR method were reduced to 0.009443 and 16.88 mg/L, respectively. Compared with BP neural network and the SVR,the result of GA-SVR was with reasonable advantage.
-
Key words:
- BOD5 /
- genetic algorithm /
- support vector machine regression /
- water quality monitoring
-
LEWIS W M, WURTSBAUGH W A, PAERL H W. Rationale for Control of anthropogenic nitrogen and phosphorus to reduce eutrophication of inland waters[J]. Environmental Science & Technology, 2011, 45(24):10300-10305. 郑利杰, 高红杰, 宋永会, 等. 我国典型城市地表水水质综合评价与分析[J]. 环境工程技术学报, 2016(3):252-258. 刘长宇, 董绍俊. 水质生化需氧量快速检测新方法研究进展:现场、实时和就地监测[J]. 中国科学:化学, 2018, 48(8):194-201. 乔俊飞, 李瑞祥,柴伟,等.基于PSO-ESN神经网络的污水BOD预测[J]. 控制工程, 2016, 23(4):463-467. Predictive modeling for wastewater applications:linear and nonlinear approaches[J].Environmental Modeling&Software,2009,24(1):96-106. MIRBAGHERI S A, BAGHERI M, BOUDAGHPOUR S, et al. Performance evaluation and modeling of a submerged membrane bioreactor treating combined municipal and industrial wastewater using radial basis function artificial neural networks[J]. Journal of Environmental Health Science & Engineering, 2015, 13(1):1-15. 王树东, 葛珉昊, 陈明明. 基于混合递阶遗传算法优化RBF神经网络的BOD5软测量方法[J]. 给水排水, 2014, 40(3):149-153. 唐晓彬, 张瑞, 刘立新. 基于蝙蝠算法SVR模型的北京市二手房价预测研究[J]. 统计研究, 2018, 35(11):73-83. 墨蒙, 赵龙章, 龚嫒雯, 等. 基于遗传算法优化的BP神经网络研究应用[J].现代电子技术,2018,512(9):49-52. VAPNIK V.The Nature of Statistical Learning Theory[M]. Heidelberg:Springer, 1995. 周丽芳,文佳黎.基于遗传算法的虚拟足球游戏设计[J].计算机应用与软件,2017,34(2):209-213. 段青玲,张磊,魏芳芳,等. 基于时间序列GA-SVR的水产品价格预测模型及验证[J].农业工程学报, 2017(1):308-314. 任金霞,刘敏. 基于改进GA的云计算任务调度策略[J]. 沈阳工业大学学报, 2019, 41(3):320-325. 郭泓利,李鑫玮,任钦毅,等. 全国典型城市污水处理厂进水水质特征分析[J].给水排水,2018,54(6):12-15. 李捷, 王宏利, 隋军. 昆明某城市污水处理厂进水特征分析[J]. 给水排水, 2015(增刊1):66-69. 陈丽琼, 茹婉红, 胡勇, 等. 生化需氧量测定方法的研究进展及现状[J]. 绿色科技, 2013(2):138-141. 江梅, 范云慧, 瑞凤霞. 五日生化需氧量(BOD5)测定时防止氨氮干扰的方法探讨[J]. 净水技术, 2010, 29(6):62-65.
点击查看大图
计量
- 文章访问数: 256
- HTML全文浏览量: 39
- PDF下载量: 9
- 被引次数: 0