Application of artificial neural networks to estimate wastewater treatment plant inlet biochemical oxygen demand

Abstract

Biochemical oxygen demand (BOD) has been shown to be an important variable in water quality management and planning. However, BOD is difficult to measure and needs longer time periods (5 days) to get results. Artificial neural networks (ANNs) are being used increasingly to predict and forecast water resource variables. The objective of this research was to develop an ANNs model to estimate daily BOD in the inlet of wastewater biochemical treatment plants. The plantscale data set (364 daily records of the year 2005) was obtained from a local wastewater treatment plant. Various combinations of daily water quality data, namely chemical oxygen demand (COD), water discharge (Q w ), suspended solid (SS), total nitrogen (N), and total phosphorus (P) are used as inputs into the ANN so as to evaluate the degree of effect of each of these variables on the daily inlet BOD. The results of the ANN model are compared with the multiple linear regression model (MLR). Mean square error, average absolute relative error, and coefficient of determination statistics are used as comparison criteria for the evaluation of the model performance. The ANN technique whose inputs are COD, Q w , SS, N, and P gave mean square errors of 708.01, average absolute relative errors of 10.03%, and a coefficient of determination 0.919, respectively. On the basis of the comparisons, it was found that the ANN model could be employed successfully in estimating the daily BOD in the inlet of wastewater biochemical treatment plants.

Prediction of wastewater quality indicators at the inflow to the wastewater treatment plant using data mining methods

“…The accuracy of predictions is satisfactory, which is illustrated by the values of errors obtained (Tables 2-4). Although the parameters of computations fit to measurements (R, MAE, MAPE) received in this study were worse than those reported by Minsoo et al [5], Dogana et al [15], Verma and Kusiak [4] the models designed in this study can find practical applications. When the number of independent variables in the statistical models is limited to only wastewater inflow data, the models could be employed under failure conditions of the measurement system, or during the system overhaul.…”

“…To predict BOD5, Abyaneh [3] relied on temperature, pH of influent wastewater, and TSS. Dogan et al [15] received a better fit (R = 0.92) of BOD5 simulation results to measurements than Abyaneh [3]. Additionally, the values of MAPE computed for COD prediction model are greater than those (MAPE = 7.35%) obtained by Minsoo et al [5] with the k-NN method.…”

Fotovoltaik Hücrenin Verimliliğinin Yapay Sinir Ağı İle Tahmini

“…Determinasyon katsayısı (R 2 ), ölçüm değerleri ile model tahminleri arasında doğrusal bir iliĢki olup olmadığını belirlemek amacıyla kullanılır. R 2 değeri 0 ile 1 arasında değiĢmekte ve bu değerin 1'e yaklaĢması model tahminleri ile ölçüm değerleri arasındaki bağımlılığın kuvvetli olduğu anlamına gelmektedir [33].…”

Intelligent Multivariate Model for the Optical Detection of Total Organic Carbon

“…Moreover, the application of artificial neural network to spectrophotometric determination of challenging chemical substances is known to be very efficient [7]. The ANN model develops a mapping of the input and output variables, which can subsequently be used to predict as a function of suitable inputs making it very popular in handling various water quality problems [8][9][10][11][12][13][14][15][16][17].…”