A Comparative Study to Detect Flowmeter Deviations Using One-Class Classifiers

Jove, Esteban; Casteleiro‐Roca, José‐Luis; Quintián, Héctor; Zayas‐Gato, Francisco; Nováis, Paulo; Méndez‐Pérez, Juan Albino; Calvo-Rolle, José Luís

doi:10.1007/978-3-030-57805-3_7

Cited by 2 publications

(2 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The use of DL aims to imitate the functioning of the human brain in data processing, learn without human supervision, and use unstructured and unlabeled data, following possible approaches, supervised and unsupervised. Autoencoders and generative modeling are examples of the unsupervised approach, while MultiLayer Perceptrons (MLP), RNNs or convolutional neural networks (CNNs) are examples of the supervised approach. ,, Considering the autoencoders, they reduce the dimensionality of the input through an encoder, reconstructing it again by a decoder. These models are evaluated by minimizing the reconstruction error .…”

Section: Wastewater Treatment Modeling Using Machine Learningmentioning

confidence: 99%

A Review of Computational Modeling in Wastewater Treatment Processes

Duarte,

Martins,

Oliveira

et al. 2023

ACS EST Water

Self Cite

View full text Add to dashboard Cite

Wastewater treatment companies are facing several challenges related to the optimization of energy efficiency, meeting more restricted water quality standards, and resource recovery potential. Over the past decades, computational models have gained recognition as effective tools for addressing some of these challenges, contributing to the economic and operational efficiencies of wastewater treatment plants (WWTPs). To predict the performance of WWTPs, numerous deterministic, stochastic, and time series-based models have been developed. Mechanistic models, incorporating physical and empirical knowledge, are dominant as predictive models. However, these models represent a simplification of reality, resulting in model structure uncertainty and a constant need for calibration. With the increasing amount of available data, data-driven models are becoming more attractive. The implementation of predictive models can revolutionize the way companies manage WWTPs by permitting the development of digital twins for process simulation in (near) real-time. In data-driven models, the structure is not explicitly specified but is instead determined by searching for relationships in the available data. Thus, the main objective of the present review is to discuss the implementation of machine learning models for the prediction of WWTP effluent characteristics and wastewater inflows as well as anomaly detection studies and energy consumption optimization in WWTPs. Furthermore, an overview considering the merging of both mechanistic and machine learning models resulting in hybrid models is presented as a promising approach. A critical assessment of the main gaps and future directions on the implementation of mathematical modeling in wastewater treatment processes is also presented, focusing on topics such as the explainability of data-driven models and the use of Transfer Learning processes.

show abstract

Section: Wastewater Treatment Modeling Using Machine Learningmentioning

confidence: 99%

A Review of Computational Modeling in Wastewater Treatment Processes

Duarte,

Martins,

Oliveira

et al. 2023

ACS EST Water

Self Cite

View full text Add to dashboard Cite

show abstract

“…Es por ello que, una alternativa interesante a los laboratorios reales son los laboratorios virtuales. Hoy en día, muchos de los sistemas basados en técnicas de inteligencia artificial como los que se explican en [31,1,9,17,39,7,28,26,33,13,45,29,36,40,44,34,27,4,47,4,16,14] se pueden verificar, en las primeras fases de diseño, mediante este tipo de laboratorios.…”

Section: Introductionunclassified

Implementación virtual de prácticas de asignaturas de control como alternativa a las prácticas de laboratorio presenciales

Michelena¹,

Zayas‐Gato²,

Jove³

et al. 2021

Xlii Jornadas De Automática : Libro De Actas

Self Cite

View full text Add to dashboard Cite

La enfermedad del coronavirus (COVID-19) ha provocado una grave crisis de salud con consecuencias socio-económicas sin precedentes. Desde la declaración de pandemia por parte de la Organización Mundial de la Salud, la mayoría de los gobiernos aplicaron políticas de control como el confinamiento, la restriccón de la movilidad, el distanciamiento social, etc. En este contexto, adaptar la planificación educativa a ese escenario conlleva un gran desafío para la comunidad educativa global. Además, dado que las prácticas presenciales de laboratorio en la educación superior fueron canceladas temporalmente, la creación de escenarios virtuales realistas mediante modernas aplicaciones software representa una alternativa interesante y necesaria. Este enfoque práctico se puede lograr mediante el uso de dos herramientas de software interesantes, como Node-RED y Factory I/O. En este trabajo se propone la implementación de una planta de laboratorio virtual utilizando las herramientas mencionadas anteriormente, con características muy similares a las plantas de laboratorio reales de la Facultad de Ingeniería de la Universidad de A Coruña.

show abstract

A Comparative Study to Detect Flowmeter Deviations Using One-Class Classifiers

Cited by 2 publications

References 20 publications

A Review of Computational Modeling in Wastewater Treatment Processes

A Review of Computational Modeling in Wastewater Treatment Processes

Implementación virtual de prácticas de asignaturas de control como alternativa a las prácticas de laboratorio presenciales

Contact Info

Product

Resources

About