BP神经网络和ARIMA模型对污水处理厂出水总氮浓度的模拟预测
|
摘要
污水处理厂出水总氮(TN)浓度是评价水处理效果的关键指标之一。建立BP神经网络模型对污水处理厂脱氮工艺进行模拟,引入自回归整合移动平均模型(ARIMA模型)对污水处理厂未来短期出水TN浓度进行预测。结果表明:BP神经网络模型在训练集和测试集模拟结果的平均相对误差分别为15. 9%和16. 5%,模型预测结果的平稳性较差; ARIMA模型对未来7 d出水TN浓度的时序预测平均误差为4. 41%,预测精度较高; 2个模型相结合有助于实现污水处理厂快捷和高效的在线检测。
Total nitrogen in effluent is one of the critical indicators for evaluating the performance of wastewater treatment plants. A BP neural network model was developed to simulate the present nitrogen removal system for wastewater treatment, and an autoregressive integrated moving average( ARIMA) model was creatively applied to realize the short-term prediction of future effluent. The results showed that the simulation average relative error of BP model on training set was 15. 9%, and that on test set was 16. 5%,which revealed that the stability of model prediction was poor. The average error of the ARIMA model for predicting the total nitrogen value in the coming week was around 4. 41%, which showed high prediction accuracy. The combination of the two models could help fast and efficient on-line detection of wastewater treatment plants.
Total nitrogen in effluent is one of the critical indicators for evaluating the performance of wastewater treatment plants. A BP neural network model was developed to simulate the present nitrogen removal system for wastewater treatment, and an autoregressive integrated moving average( ARIMA) model was creatively applied to realize the short-term prediction of future effluent. The results showed that the simulation average relative error of BP model on training set was 15. 9%, and that on test set was 16. 5%,which revealed that the stability of model prediction was poor. The average error of the ARIMA model for predicting the total nitrogen value in the coming week was around 4. 41%, which showed high prediction accuracy. The combination of the two models could help fast and efficient on-line detection of wastewater treatment plants.
引文
[1]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.LI T,LI J. The prediction of denitrification efficiency of a wastewater treatment plant by using BP neural network and Markov chain method[J]. Acta Scientiae Circumstantiae,2016,36(2):576-581.
[2] WEI X,KUSIAK A,SADAT H R. Prediction of influent flow rate:data-mining approach[J]. Journal of Energy Engineering,2013,139(2):118-123.
[3] DOGAN S,DURSUN S. Error checking of input data for web based design calculations of wastewater treatment plant:7th International Scientific Conference on Modern Management of Mine Producing,Geology and Environmental Protection[C/OL].2007[2018-10-16]. https://www. researchgate. net/publication/290247295.
[4] VERMA A,WEI X,KUSIAK A. Predicting the total suspended solids in wastewater:a data-mining approach[J]. Engineering Applications of Artificial Intelligence,2013,26(4):1366-1372.
[5] ZHEN L,XU L Y. Research on overcoming the local optimum of BPNN[C]//Proceedings of the World Congress on Intelligent Control and Automation(WCICA). Dalian:IEEE Computer Society. 2006:2681-2685. DOI:10. 1109/WCICA.2016. 1712850.
[6] SHI Y,ZHAO X T,ZHANG Y M,et al. Back propagation neural network(BPNN)prediction model and control strategies of methanogen phase reactor treating traditional Chinese medicine wastewater(TCMW)[J]. Journal of Biotechnology,2009,144(1):70-74.
[7] RODRIGUEZ-JEANGROS N,RODRIGUEZ J P,CAMACHO L A,et al. Integrated urban water resources model to improve water quality management in data-limited cities with application to Bogota,Colombia[J]. Journal of Sustainable Water in the Built Environment,2018,4(2):04017019.
[8]孙国庆.智慧水务关键技术研究及应用[J].水利信息化,2018,142(1):46-49.SUN G Q. Research and application on key technologies of smart water[J]. Water Resources Informatization,2018,142(1):46-49.
[9]滕明鑫.回归神经网络预测模型归一化方法分析[J].电脑知识与技术,2014,10(7):1508-1510.TENG M X. The analysis of normalization method of recurrent neural network prediction model[J]. Computer Knowledge and Technology,2014,10(7):1508-1510.
[10] CHEN K,YANG S J,BATUR C. Effect of multi-hidden-layer structure on performance of BP neural network:probe[C]//Chongqing:2012 Eigth International Conference on Natural Computation,2012:1-5.
[11] DAI H,MACBETH C. Effects of learning parameters on learning procedure and performance of a BPNN[J]. Neural Networks,1997,10(8):1505-1521.
[12] YANG Q,HU Y J,XUE L. Back-propagation model for nanofiltration process simulation in pesticide wastewater treatment[J]. Advanced Materials Research,2010,168/169/170:404-407.
[13]辛大欣,王长元,肖峰. BP神经网络在回归分析中的应用研究[J].西安工业学院学报,2002,22(2):129-135.XIN D X,WANG C Y,XIAO F. A study on the BP neural network applied to regression analysis[J]. Journal of Xi’an Institute of Technology,2002,22(2):129-135.
[14]韩红桂,陈治远,乔俊飞,等.基于区间二型模糊神经网络的出水氨氮软测量[J].化工学报,2017,68(3):1032-1040.HAN H G,CHEN Z Y,QIAO J F,et al. Soft-sensor method for effluent ammonia nitrogen based on interval type-2 fuzzy neural networks[J]. CIESC Journal,2017,68(3):1032-1040.
[15] IHUEZE C C,ONWURAH U O. Road traffic accidents prediction modelling:an analysis of Anambra State,Nigeria[J]. Accident Analysis&Prevention,2018,112:21-29.
[2] WEI X,KUSIAK A,SADAT H R. Prediction of influent flow rate:data-mining approach[J]. Journal of Energy Engineering,2013,139(2):118-123.
[3] DOGAN S,DURSUN S. Error checking of input data for web based design calculations of wastewater treatment plant:7th International Scientific Conference on Modern Management of Mine Producing,Geology and Environmental Protection[C/OL].2007[2018-10-16]. https://www. researchgate. net/publication/290247295.
[4] VERMA A,WEI X,KUSIAK A. Predicting the total suspended solids in wastewater:a data-mining approach[J]. Engineering Applications of Artificial Intelligence,2013,26(4):1366-1372.
[5] ZHEN L,XU L Y. Research on overcoming the local optimum of BPNN[C]//Proceedings of the World Congress on Intelligent Control and Automation(WCICA). Dalian:IEEE Computer Society. 2006:2681-2685. DOI:10. 1109/WCICA.2016. 1712850.
[6] SHI Y,ZHAO X T,ZHANG Y M,et al. Back propagation neural network(BPNN)prediction model and control strategies of methanogen phase reactor treating traditional Chinese medicine wastewater(TCMW)[J]. Journal of Biotechnology,2009,144(1):70-74.
[7] RODRIGUEZ-JEANGROS N,RODRIGUEZ J P,CAMACHO L A,et al. Integrated urban water resources model to improve water quality management in data-limited cities with application to Bogota,Colombia[J]. Journal of Sustainable Water in the Built Environment,2018,4(2):04017019.
[8]孙国庆.智慧水务关键技术研究及应用[J].水利信息化,2018,142(1):46-49.SUN G Q. Research and application on key technologies of smart water[J]. Water Resources Informatization,2018,142(1):46-49.
[9]滕明鑫.回归神经网络预测模型归一化方法分析[J].电脑知识与技术,2014,10(7):1508-1510.TENG M X. The analysis of normalization method of recurrent neural network prediction model[J]. Computer Knowledge and Technology,2014,10(7):1508-1510.
[10] CHEN K,YANG S J,BATUR C. Effect of multi-hidden-layer structure on performance of BP neural network:probe[C]//Chongqing:2012 Eigth International Conference on Natural Computation,2012:1-5.
[11] DAI H,MACBETH C. Effects of learning parameters on learning procedure and performance of a BPNN[J]. Neural Networks,1997,10(8):1505-1521.
[12] YANG Q,HU Y J,XUE L. Back-propagation model for nanofiltration process simulation in pesticide wastewater treatment[J]. Advanced Materials Research,2010,168/169/170:404-407.
[13]辛大欣,王长元,肖峰. BP神经网络在回归分析中的应用研究[J].西安工业学院学报,2002,22(2):129-135.XIN D X,WANG C Y,XIAO F. A study on the BP neural network applied to regression analysis[J]. Journal of Xi’an Institute of Technology,2002,22(2):129-135.
[14]韩红桂,陈治远,乔俊飞,等.基于区间二型模糊神经网络的出水氨氮软测量[J].化工学报,2017,68(3):1032-1040.HAN H G,CHEN Z Y,QIAO J F,et al. Soft-sensor method for effluent ammonia nitrogen based on interval type-2 fuzzy neural networks[J]. CIESC Journal,2017,68(3):1032-1040.
[15] IHUEZE C C,ONWURAH U O. Road traffic accidents prediction modelling:an analysis of Anambra State,Nigeria[J]. Accident Analysis&Prevention,2018,112:21-29.