Missing data imputation and sensor self-validation towards a sustainable operation of wastewater treatment plants via deep variational residual autoencoders

Missing data imputation and automatic fault detection of wastewater treatment plant (WWTP) sensors are crucial for energy conservation and environmental protection. Given the dynamic and non-linear characteristics of WWTP measurements, the conventional diagnosis models are inefficient and ignore pot...

Full description

Saved in:
Bibliographic Details
Published in:Chemosphere (Oxford) Vol. 288; no. Pt 3; p. 132647
Main Authors: Ba-Alawi, Abdulrahman H., Loy-Benitez, Jorge, Kim, SangYun, Yoo, ChangKyoo
Format: Journal Article
Language:English
Published: England Elsevier Ltd 01.02.2022
Subjects:
Deep residual networks (ResNet)
electric energy consumption
energy conservation
environmental protection
Missing data imputation
probability distribution
Reproducibility of Results
risk
Sensor self-validation
Smart monitoring and management
Sustainable WWTP operation
Variational autoencoder (VAE)
wastewater treatment
Water Purification
Missing data imputation
Sensor self-validation
Variational autoencoder (VAE)
Deep residual networks (ResNet)
Sustainable WWTP operation
Smart monitoring and management
ISSN:0045-6535, 1879-1298, 1879-1298
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Missing data imputation and automatic fault detection of wastewater treatment plant (WWTP) sensors are crucial for energy conservation and environmental protection. Given the dynamic and non-linear characteristics of WWTP measurements, the conventional diagnosis models are inefficient and ignore potential valuable features in the offline modeling phase, leading to false alarms and inaccurate imputations. In this study, an inclusive framework for missing data imputation and sensor self-validation based on integrating variational autoencoders (VAE) with a deep residual network structure (ResNet-VAE) is proposed. This network structure can automatically extract complex features from WWTP data without the risk of vanishing gradients by learning the potential probability distribution of the input data. The proposed framework is intended to increase the reliability of faulty sensors by imputing missing data, detecting anomalies, identifying failure sources, and reconstructing faulty data to normal conditions. Several metrics were utilized to assess the performance of the suggested approach in comparison with other different methods. The VAE-ResNet approach showed superiority to detect (DRSPE = 100%), reconstruct faulty WWTP sensors (MAPE = 15.41%–5.68%) and impute the missing values (MAPE = 10.44%–3.98%). Lastly, the consequences of faulty data, missing data, reconstructed and imputed data were evaluated considering electricity consumption and resilience to demonstrate the ResNet-VAE model's superior performance for WWTP sustainability. [Display omitted] •The ResNet-VAE approach is proposed to improve the WWTP-MBR sensors' reliability.•The model is validated through faulty and missing intervals of WWTP-MBR data.•The ResNet-VAE method presented the highest fault detection rate of DRSPE = 100%.•The ResNet-VAE exhibits superior data imputation with a MAPE = 3.98%.•A sustainable smart monitoring system was achieved using ResNet-VAE method.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:0045-6535
1879-1298
1879-1298
DOI:10.1016/j.chemosphere.2021.132647