Data-driven intelligent monitoring system for key variables in wastewater treatment process

Abstract In wastewater treatment process (WWTP), the accurate and real-time monitoring values of key variables are crucial for the operational strategies. However, most of the existing methods have difficulty in obtaining the real-time values of some key variables in the process. In order to handle this issue, a data-driven intelligent monitoring system, using the soft sensor technique and data distribution service, is developed to monitor the concentrations of effluent total phosphorous (TP) and ammonia nitrogen (NH4-N). In this intelligent monitoring system, a fuzzy neural network (FNN) is applied for designing the soft sensor model, and a principal component analysis (PCA) method is used to select the input variables of the soft sensor model. Moreover, data transfer software is exploited to insert the soft sensor technique to the supervisory control and data acquisition (SCADA) system. Finally, this proposed intelligent monitoring system is tested in several real plants to demonstrate the reliability and effectiveness of the monitoring performance.

[1]  Majid Bagheri,et al.  Modeling of a sequencing batch reactor treating municipal wastewater using multi-layer perceptron and radial basis function artificial neural networks , 2015 .

[2]  Tao Chen,et al.  Soft-Sensing Method for Optimizing Combustion Efficiency of Reheating Furnaces , 2017 .

[3]  Junfei Qiao,et al.  An adaptive second order fuzzy neural network for nonlinear system modeling , 2016, Neurocomputing.

[4]  Francesco Corona,et al.  Data-derived soft-sensors for biological wastewater treatment plants: An overview , 2013, Environ. Model. Softw..

[5]  Pieter Vanormelingen,et al.  Nutrient removal from horticultural wastewater by benthic filamentous algae Klebsormidium sp., Stigeoclonium spp. and their communities: From laboratory flask to outdoor Algal Turf Scrubber (ATS). , 2016, Water research.

[6]  Rui Araújo,et al.  Review of soft sensor methods for regression applications , 2016 .

[7]  Manuel A. Rodrigo,et al.  Use of neurofuzzy networks to improve wastewater flow-rate forecasting , 2009, Environ. Model. Softw..

[8]  Víctor Cerdà,et al.  Flow analysis techniques for phosphorus: an overview. , 2005, Talanta.

[9]  José Ferrer,et al.  A methodology for sequencing batch reactor identification with artificial neural networks: A case study , 2009, Comput. Chem. Eng..

[10]  Shuhua Xue,et al.  Determination of ammonium on an integrated microchip with LED-induced fluorescence detection. , 2012, Journal of environmental sciences.

[11]  Min Zhang,et al.  On-Line Solid Phase Extraction and Spectrophotometric Detection with Flow Technique for the Determination of Nanomolar Level Ammonium in Seawater Samples , 2011 .

[12]  Tingjin Zhou,et al.  Determination of total phosphorus in natural waters with a simple neutral digestion method using sodium persulfate , 2017 .

[13]  D. Cecil,et al.  Software sensors are a real alternative to true sensors , 2010, Environ. Model. Softw..

[14]  Furong Gao,et al.  Wastewater quality monitoring system using sensor fusion and machine learning techniques. , 2012, Water research.

[15]  Roberto Baratti,et al.  Predictive control of an activated sludge process: an application to the Viikinmäki wastewater treatment plant , 2015 .

[16]  Weiming Shao,et al.  Semi-supervised selective ensemble learning based on distance to model for nonlinear soft sensor development , 2017, Neurocomputing.

[17]  Ridong Zhang,et al.  Data-Driven Modeling Using Improved Multi-Objective Optimization Based Neural Network for Coke Furnace System , 2017, IEEE Transactions on Industrial Electronics.

[18]  Víctor Cerdà,et al.  Multi-pumping flow system for the determination of dissolved orthophosphate and dissolved organic phosphorus in wastewater samples. , 2006, Analytica chimica acta.

[19]  Ivan Nunes da Silva,et al.  An approach based on neural networks for estimation and generalization of crossflow filtration processes , 2008, Appl. Soft Comput..

[20]  Ying Li,et al.  A soft computing method to predict sludge volume index based on a recurrent self-organizing neural network , 2016, Appl. Soft Comput..

[21]  Dae Sung Lee,et al.  Monitoring of sequencing batch reactor for nitrogen and phosphorus removal using neural networks , 2007 .

[22]  Miguel Ayala Botto,et al.  SCADA system with predictive controller applied to irrigation canals , 2013 .

[23]  Yongming Huang,et al.  A modified method for on-line determination of trace ammonium in seawater with a long-path liquid waveguide capillary cell and spectrophotometric detection , 2014 .

[24]  Yan Wang,et al.  A fuzzy neural network model for monitoring A2/O process using on-line monitoring parameters , 2012, Journal of environmental science and health. Part A, Toxic/hazardous substances & environmental engineering.

[25]  Jialin Liu Developing a soft sensor with online variable reselection for unobserved multi-mode operations , 2016 .

[26]  António E. Ruano,et al.  Soft-sensing estimation of plant effluent concentrations in a biological wastewater treatment plant using an optimal neural network , 2016, Expert Syst. Appl..

[27]  Xiaohong Chen,et al.  A sensor-software based on a genetic algorithm-based neural fuzzy system for modeling and simulating a wastewater treatment process , 2015, Appl. Soft Comput..

[28]  G. S. Mahapatra,et al.  Robust feedforward and recurrent neural network based dynamic weighted combination models for software reliability prediction , 2014, Appl. Soft Comput..

[29]  Zonghai Sun,et al.  A probabilistic self-validating soft-sensor with application to wastewater treatment , 2014, Comput. Chem. Eng..

[30]  Yong Zhu,et al.  A sensitive flow-batch system for on board determination of ultra-trace ammonium in seawater: Method development and shipboard application. , 2013, Analytica chimica acta.

[31]  Willi Gujer,et al.  Data-driven modeling approaches to support wastewater treatment plant operation , 2012, Environ. Model. Softw..

[32]  Francesco G. Gentili,et al.  Algal cultivation in urban wastewater: an efficient way to reduce pharmaceutical pollutants , 2016, Journal of Applied Phycology.

[33]  Witold Pedrycz,et al.  Robust Ultra-High Resolution Microwave Planar Sensor Using Fuzzy Neural Network Approach , 2017, IEEE Sensors Journal.

[34]  C K Yoo,et al.  A systematic approach to data-driven modeling and soft sensing in a full-scale plant. , 2009, Water science and technology : a journal of the International Association on Water Pollution Research.

[35]  Dexian Huang,et al.  Data-driven soft sensor development based on deep learning technique , 2014 .

[36]  Yan Wang,et al.  Prediction of effluent quality of a paper mill wastewater treatment using an adaptive network-based fuzzy inference system , 2011, Appl. Soft Comput..