Predicting flocculant dosage in the drinking water treatment process using Elman neural network

Wang, Dongsheng; Chang, Xuefeng; Ma, Kaiwei

doi:10.1007/s11356-021-16265-4

Cited by 12 publications

(4 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Wu 30 explored the effects of data normalization and inherent factors on the decision of optimal coagulant dosage in WWT by using the ANN algorithm. Wang 31 used the Elman neural network (ENN) to predict coagulant dosage in the DWTP. Although these models have achieved better results compared to ML algorithms in dealing with nonlinear problems, nevertheless, these models were used to treat original data as discrete data, the water quality parameters of the previous time sequence information were ignored and were not transformed into a time series prediction problem, resulting in the prediction accuracy being not satisfactory.…”

Section: Introductionmentioning

confidence: 99%

Exploring potential dual-stage attention based recurrent neural network machine learning application for dosage prediction in intelligent municipal management

Fang

Zang

Zhai

et al. 2023

Environ. Sci.: Water Res. Technol.

View full text Add to dashboard Cite

show abstract

Section: Introductionmentioning

confidence: 99%

Exploring potential dual-stage attention based recurrent neural network machine learning application for dosage prediction in intelligent municipal management

Fang

Zang

Zhai

et al. 2023

Environ. Sci.: Water Res. Technol.

View full text Add to dashboard Cite

show abstract

“…Finding the optimal hyperparameters for the model in the training and prediction process often requires a significant amount of resources. By using the SSA algorithm and setting the three hyperparameters as positive integers within the range of [1,20], [1,20], and [10,200], the SSA-SFA-CFBLS model can quickly and accurately determine the optimal hyperparameters, which greatly reduces the burden of training the model for researchers. Moreover, the SSA-SFA-CFBLS model has the characteristic of online learning.…”

Section: Resultsmentioning

confidence: 99%

“…The SSA-SFA-CFBLS parameters are chosen as follows. The population size is 50, the proportion of explorers is 20%, the maximum number of iterations is 5, and the range of CFBLS hyperparameters (number of feature groups, number of enhancement groups, number of nodes in each group) is [1,20], [1,20], [10,200], respectively.…”

Section: Hyperparameters and Evaluation Indicatorsmentioning

confidence: 99%

“…This method uses kernel technique [8] to process nonlinear data and solves the problem that the kernel function [9] of SVR is difficult to determine. Wang et al [10] proposed the use of elman neural network (ENN) as a method to predict the dosage of coagulant in the coagulation process. The method can capture the periodicity and time-variability of water quality data, as well as the mixture of long-term and short-term data [11].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Prediction of chlorine residual in effluent based on SSA-SFA-CFBLS for water treatment process parameters

Wang,

Han,

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

Accurate parameter prediction is necessary for nonlinear, long-delayed water treatment process to raise water quality. To improve the prediction model precision and computational efficiency, a cascade broad learning system based on the sparrow search algorithm and slow feature analysis is proposed in this paper. First, the slow feature analysis method is introduced to extract the essential characteristics of water monitoring data as the input of the prediction model. Then, a cascaded broad learning system is adopted to establish a prediction model for residual chlorine in water works effluent. The cascade broad learning can deal well with online prediction. Furthermore, the sparrow search algorithm is utilized to obtain the optimal hyperparameters of the established model, which can avoid the complex and time-consuming manual parameter tuning process. Finally, the comparison experiment with several methods is carried out. The experiment results show that the proposed method saves more computing resources and makes some improvements in prediction accuracy. Its prediction accuracy is much higher than majority traditional deep learning models such as LSTM, RNN, GRU.

show abstract

An effective dynamic immune optimization control for the wastewater treatment process

Wang

2021

Environ Sci Pollut Res

View full text Add to dashboard Cite

Aiming at the conflict of multiple performance indicators in the complex wastewater treatment process (WWTPs), an effective optimization control based on dynamic multi-objective immune (DMOIA-OC) is designed. This method first designs a dynamic optimization control scheme. It also divides the control process into a dynamic optimization layer and a tracking control layer. Secondly, based on analyzing the performance of WWTPs, the optimization layer establishes energy consumption and effluent quality models that adapt to the environment. Thirdly, an adaptive dynamic immune optimization algorithm is proposed to optimize complex and conflicting performance indicators. Besides, a suitable preference solution is selected from many Pareto solutions. It is to obtain the best set values of dissolved oxygen and nitrate nitrogen. Finally, the solution will be tested on the benchmark simulation platform (BSM1). The results show that the DMOIA-OC method can solve the complex optimization problem of multiple performance indicators in WWTPs. And it has a competitive advantage in the control effect.

show abstract

Predicting flocculant dosage in the drinking water treatment process using Elman neural network

Cited by 12 publications

References 41 publications

Exploring potential dual-stage attention based recurrent neural network machine learning application for dosage prediction in intelligent municipal management

Exploring potential dual-stage attention based recurrent neural network machine learning application for dosage prediction in intelligent municipal management

Prediction of chlorine residual in effluent based on SSA-SFA-CFBLS for water treatment process parameters

An effective dynamic immune optimization control for the wastewater treatment process

Contact Info

Product

Resources

About