Development and application of reduced‐order neural network model based on proper orthogonal decomposition for BOD5 monitoring: Active and online prediction

Abstract

This study aims at providing a reduced‐order neural network model (RONNM) based on proper orthogonal decomposition (POD) for online prediction of the 5 days biochemical oxygen demand (BOD5). To achieve this goal, the POD method is used to reduce the input vectors to neural network (NN) model. Evaluation of the selected RONNM and its comparison with the model fed with all input vectors (NN model) shows that it reduces not only the output error but also computational cost. Results depict that Pearson correlation coefficient (R) and root mean square error for the best fitted RONNM are 0.94 and 7.75, respectively. Furthermore, accuracy analysis of the output results of models based on developed discrepancy ratio statistic reveals that RONNM is superior. Thus, developed methodology can be considered as an effective tool to train the water resources managers for online evaluation of water quality related to BOD5. © 2011 American Institute of Chemical Engineers Environ Prog, 32: 120–127, 2013.

Simulation of Low TDS and Biological Units of Fajr Industrial Wastewater Treatment Plant Using Artificial Neural Network and Principal Component Analysis Hybrid Method

“…In order to improve models performance, the PCA technique was applied for data preprocessing. PCA seeks relevant directions for the input data that maximize variance [15].…”

Development and application of reduced‐order neural network model based on proper orthogonal decomposition for BOD5 monitoring in river systems: Uncertainty analysis

“…The NN and RONN models had been developed for the Sefidrood River Basin drained by the Sefidrood River and located in the northwest of Iran (Figure 1). As mentioned in Noori et al's [21] study, the dataset which was used to develop NN and RONN models was collected from 132 water quality monitoring stations along Sefidrood River and its reaches in spring, summer, autumn and winter seasons. The main branch of the Sefidrood River originates from the Zagros Mountains and flows down to the south of Caspian Sea.…”

“…Onkal-Engin et al [14] developed a relationship between sewage odor and BOD by NN model and reported that NN model can be used to classify the sewage samples collected from deferent 2013 American Institute of Chemical Engineers locations of a wastewater treatment plant. Because of the prediction capability of NN techniques strongly depends on the number of input vectors, Noori et al [21] suggested proper orthogonal decomposition (POD) method to reduce the input vector to NN model for BOD 5 prediction in the Sefidrood River Basin. Dogan et al [16] compared NN and multilinear regression models to estimate daily BOD in the inlet of wastewater biochemical treatment plants and suggested that NN model could be employed successfully in estimating the daily BOD in the inlet of wastewater biochemical treatment plants.…”

“…The one step of study is done by ''Noori et al [21].'' Thus in application of the results of these NN models, uncertainty analysis can be more effective.…”

Non‐intrusive reduced order modelling with least squares fitting on a sparse grid

“…Walton et al and Xiao et al proposed a NIROM using radial basis function (RBF) method and proper othogonal decomposition (POD) [28,29]. Noack [30] and Noori [31] used neural network to construct a NIROM. Xiao et.…”