Soft Sensor Modeling of Key Effluent Parameters in Wastewater Treatment Process Based on SAE-NN

Osman, Yousuf Babiker M.; Li, Wei

doi:10.1155/2020/6347625

Cited by 13 publications

(2 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The development of artificial neural network algorithms has been hot in recent years, and this approach is also widely used in soft sensor modeling. For example, artificial neural network (NN) and support vector regression (SVR), which are used extensively as baseline methods; , deep belief networks (DBN), which build a joint probability distribution between data and labels; , autoencoder networks (AE), which use input data for supervision to guide the network in learning mapping relationships; − ,, long- and short-term memory networks (LSTM), which can “remember” and can be applied to time series; ,− and convolutional neural networks (CNN), which is based on visual principles and pays more attention to local features. − For soft sensor modeling, neural networks extract useful features from many easily accessible auxiliary variables and then build a model between the key variables and the extracted features for prediction.…”

Section: Introductionmentioning

confidence: 99%

Horizontal Data Augmentation Strategy for Industrial Quality Prediction

et al. 2022

View full text Add to dashboard Cite

In recent years, neural network-based soft sensor technology has been widely used in industrial production processes and has excellent optimization, monitoring, and quality prediction performance. This paper proposes a horizontal data augmentation strategy to provide highly available data for subsequent prediction models, called the combined autoencoder data augmentation (CADA) strategy. This paper has developed a CADA-based convolutional neural network (CADA-CNN) soft sensor model and applied it to the process of industrial debutanizer and industrial steam volume. In terms of method validation, this paper compares the output data of the proposed CADA by the Spearman correlation coefficient to verify the strategy’s feasibility. Then, the output data of the CADA strategy is fed into the artificial neural network (NN), support vector regression (SVR), and convolutional neural network (CNN) for comparison experiments. The final experimental results show that our proposed CADA-CNN model has lower prediction error and better prediction error distribution.

show abstract

Section: Introductionmentioning

confidence: 99%

Horizontal Data Augmentation Strategy for Industrial Quality Prediction

et al. 2022

View full text Add to dashboard Cite

show abstract

“…For example, [2] and [17] used artificial neural network (ANN) for state estimation and effluent prediction. Also, effluent Biochemical Oxygen Demand (BOD) is estimated by a Stacked Autoencoder with Neural Network (SAE-NN) [20]. Nevertheless, the previous learning methods are static under the hypothesis of steady-state and static processes.…”

Section: Introductionmentioning

confidence: 99%

Adaptive Neural Network Based Monitoring of Wastewater Treatment Plants

Alharbi

Hong

Laleg‐Kirati

2022

2022 American Control Conference (ACC)

View full text Add to dashboard Cite

The quality of the treated wastewater is conditioned by the performance of wastewater treatment processes. However, real-time monitoring of non-easily measured quality variables in wastewater treatment plant (WWTP) is a challenging problem. In this paper, an adaptive online monitoring approach that is based on a long short term memory (LSTM) neural networks is proposed to estimate the bacterial concentration, mixed liquor suspended solids (MLSS) and mixed liquor volatile suspended solids (MLVSS) in WWTP. Due to lack of a large dataset and difficulties to experimentally measure quality variables, a Wasserstein generative adversarial network with gradient penalty (WGAN-GP) is designed to generate synthetic data for training. A tuned hyperparameters are obtained for the proposed method. In addition, the performance is compered with the traditional LSTM using two datasets. Finally, the results indicate that WGAN successfully generates realistic training samples and an quality variables are monitored with satisfactory performance.

show abstract