System identification and real-time pattern recognition by neural networks for an activated sludge process (original) (raw)
Related papers
A Neural Network Model for Control of Wastewater Treatment Processes
IFAC Proceedings Volumes, 2007
This paper discusses the development of a neural network model for the prediction of the influent disturbances, which ultimately affect the activated sludge process. Neural networks are particularly suited to problems where there is no clear understanding of the processes and the complex interrelationship between variables. The historical data used for training and testing the neural network is actual plant data obtained from a municipal plant and weather data for the same time periods. The result of the predicted influent disturbance is used in the control of the dissolved oxygen (DO). The results are applied to a pilot wastewater treatment plant located at the Cape Peninsula University of Technology (CPUT). The number of and the type inputs are varied to find an optimal model in order to predict the Chemical Oxygen Demand (COD), Total Kjeldahl Nitrogen (TKN) and the flowrate. Three different dynamic multilayer perceptron (MLP) feed-forward neural network models are developed for the influent disturbances of COD, TKN and flowrate respectively.
Neural networks for prediction of wastewater treatment plant influent disturbances
AFRICON 2007, 2007
In order to develop an effective control strategy for the activated sludge process (ASP) of a wastewater treatment plant, an understanding of the nature of the influent load disturbances to the wastewater treatment plant is necessary. The wastewater treatment processes are dynamic and the interrelationships between variables are very complex. The values of the influent disturbances are usually measured off-line in a laboratory, as there are still no reliable on-line sensors available. This work proposes development of a neural network model for prediction of the values of the influent disturbances, which ultimately affect the activated sludge process. Three different dynamic multilayer perceptron feed-forward neural network models and three recurrent neural networks are developed for the prediction of the influent disturbances of Chemical Oxygen Demand (COD), Total Kjeldahl Nitrogen (TKN) and flowrate respectively. The predictive performance of the multi-layer perceptron is compared to that of the recurrent neural network.
Neural Network Identification of N-Removal Process in Waste Water Treatment Plants
Modelling, Identification and Control, 2014
A nonlinear model with neural networks structure is identified in this paper from input-output data of the activated-sludge process. The simulation protocol BSM1 is used as a benchmark to gather the operating data used for the neural networks training and validations. The neural model is constituted by two feed-forward neural networks to estimate oxygen and nitrates concentrations. The performance of each NN is assessed as a virtual sensor for variable estimation, or as a predictive model for process control purposes.
Elsevier, 2017
Chemical oxygen demand (COD) has been utilized to determine the content of organic matter of bath water, wastewater and natural water, due to the time consuming of biological oxygen demand (BOD) test, COD became an alternative in controlling the treatment process. For the oxidation of both organic and inorganic matter COD may be expressed as one of the demand parameters. In this paper, the Artificial neural network (ANNs) was employed to develop and estimate the effluent COD model from the wastewater treatment plant (WWTP), to evaluate the model, the daily recorded data sets were obtained from the new Nicosia WWT, the input parameters of ANNs are inlets COD, BOD, pH, Conductivity, Total Nitrogen (T-N), Total Phosphates (T-P), Total suspended solid (TSS), Suspended solid (SS) and the effluent COD were considered as an output neuron of ANN. The ANN performance has been evaluated using statistical techniques (Determination coefficient, RMSE, Correlations), the result of ANNs model was compared with the Multilinear regression analysis (MLR) and the efficiency revealed that ANNs model showed the prominent accuracy and better performance in predicting the effluent COD over the MLR model.
Forecasting Oxygen Demand in Treatment Plant Using Artificial Neural Networks
— Modeling the wastewater treatment plant is difficult due to nonlinear properties of most of its different processes. Due to the increasing concerns over environmental effects of treatment plants considering the poor operation, fluctuations in process variables and problems of linear analyses, algorithms developed using artificial intelligence methods such as artificial neural networks have attracted a great deal of attention. In this research, first using regression analysis, the parameters of biological oxygen demand, chemical oxygen demand, and pH of the input wastewater were chosen as input parameter among other different parameters. Next, using error analysis, the best topology of neural networks was chosen for prediction. The results revealed that multilayer perception network with the sigmoid tangent training function, with one hidden layer in the input and output as well as 10 training nodes with regression coefficient of 0.92 is the best choice. The regression coefficients obtained from the predictions indicate that neural networked are well able to predict the performance of the wastewater treatment plant in Yazd. Keywords—Yazd treatment plant, chemical oxygen demand, neural networks, sigmoid tangent.
CLEANSoil, Air, Water, 2008
A dynamic simulation model of the Ankara central wastewater treatment plant (ACWTP) was evaluated for the prediction of effluent COD concentrations. Firstly, a mechanistic model of the municipal wastewater treatment process was developed based on Activated Sludge Model No. 1 (ASM1) by using a GPS-X computer program. Then, the mechanistic model was combined with a feed-forward back-propagation neural network in parallel configuration. The appropriate architecture of the neural network models was determined through several iterative steps of training and testing of the models. Both models were run with the data obtained from the plant operation and laboratory analysis to predict the dynamic behavior of the process. Using these two models, effluent COD concentrations were predicted and the results were compared for the purpose of evaluation of treatment performance. It was observed that the ASM1 ANN model approach gave better results and better described the operational conditions of the plant than ASM1.
Due to changeable nature of the industrial wastewaters, proper operation of an industrial wastewater treatment plant is of prior importance in order to keep the process stability at the desired conditions. In this mean, simulation of the treatment system behavior using artificial neural network (ANN) can be an effective tool. This paper evaluates long term performance and process stability of a full-scale integrated industrial wastewater treatment system (Faraman's industrial estate, Kermanshah) in removing organic matter over a 2-year operation. The wastewater treatment system is composed of static screens, an equalization tank, an aerobic biological tower (TF) and an activated sludge (AS) reactor. Multilayer Feed-forward Networks of ANN was used to forecast the process performance of AS system. In this study, mixed liquor suspended solids (MLSS) (mg/l) and organic loading rate (OLR) (kg COD/m 3 .d) were selected as input parameters and TSS removal, COD removal and sludge volume index (SVI) as output parameters. The results showed a very good agreement between the actual and modeled data (R 2 > 0.9). The ANN models provided a robust tool for predicting the performance of wastewater treatment plants and as a result, the online monitoring parameters could be applied for prediction of effluent characteristics.
Neural Networks Identification of Wastewater Biodegradation Process
wseas.us
In this paper we present an algorithm for nonlinear continuous-time model of wastewater biodegradation process identification based on neural networks. The mathematical model of the nonlinear system of wastewater biodegradation process is developed. The topology of the neural network used for identification is presented. The described network is used to identify the wastewater biodegradation process where the unknown parameters appear in rational relations with measured variables. Some simulation results are presented.
KSOM and MLP neural networks for on-line estimating the efficiency of an activated sludge process
Chemical Engineering Journal, 2006
This work is devoted to the study of the Saint Cyprien (south of France) activated sludge WWTP process and to the on-line estimation of chemical parameters (influent and effluent chemical oxygen demand, ammonia and suspended solids) not easily measurable on-line. Their knowledge makes it possible to estimate the process efficiency and to provide reliable information for the plant monitoring. A tool including Kohonen's self-organizing maps and a multi level perceptron is used. The Kohonen's self organizing maps neural network is applied to analyze the multidimensional Saint Cyprien process data and to diagnose the interrelationship of the process variables in an activated sludge WWTP. The multi level perceptron is used as estimation tool. The obtained results are satisfactory. The information provided by the estimation procedure is sufficiently reliable and precise to be exploitable by operators in charge of the plant monitoring and maintenance. It allows understanding how the system is evolving. The whole procedure (Kohonen's self-organizing maps and multi level perceptron) uses tools which proved to be efficient and complementary.
Artificial Neural Network Based Model in Effluent Treatment Process
2011
During the past 30 years the industrial sector in India has quadrupled in size, thus it increases the pressure on wastewater treatment industries to produce higher quality treated water at a lower cost. The efficiency of a treatment process closely relates to the operation of the plant. To improve the operating performance, an Artificial Neural Network (ANN) paradigm has been applied to an effluent treatment plant. An ANN which is able to learn the non-linear performance relationships of historical data of a plant has been proved to be capable of providing operational guidance for plant operators. In this investigation the application of Artificial Neural Network (ANN) techniques are used to predict the Chemical Oxygen Demand for effluent treatment process. Sets of historical plant data of COD were collected from common effluent treatment plant at Govindpura, Bhopal (India). Data were collected over a period of 3 years from the influent and effluent streams of the station. Two ANN-b...