Articles producció científica> Enginyeria Química

Robust data-driven soft sensors for online monitoring of volatile fatty acids in anaerobic digestion processes

  • Identification data

    Identifier: imarina:6112103
    Handle: http://hdl.handle.net/20.500.11797/imarina6112103
  • Authors:

    Kazemi P
    Steyer JP
    Bengoa C
    Font J
    Giralt J
  • Others:

    Author, as appears in the article.: Kazemi P; Steyer JP; Bengoa C; Font J; Giralt J
    Department: Enginyeria Química
    URV's Author/s: Bengoa, Christophe José / Font Capafons, José / Giralt Marcé, Jaume / KAZEMI, PEZHMAN
    Keywords: Waste-water treatment Unit Soft sensor Prediction Performance Optimization Operation Neural-network Neural network Genetic programming Data driven Benchmark simulation-model Anaerobic digestion
    Abstract: © 2019 by the authors. The concentration of volatile fatty acids (VFAs) is one of the most important measurements for evaluating the performance of anaerobic digestion (AD) processes. In real-time applications, VFAs can be measured by dedicated sensors, which are still currently expensive and very sensitive to harsh environmental conditions. Moreover, sensors usually have a delay that is undesirable for real-time monitoring. Due to these problems, data-driven soft sensors are very attractive alternatives. This study proposes different data-driven methods for estimating reliable VFA values. We evaluated random forest (RF), artificial neural network (ANN), extreme learning machine (ELM), support vector machine (SVM) and genetic programming (GP) based on synthetic data obtained fromthe international water association (IWA) Benchmark Simulation Model No. 2 (BSM2). The organic load to the AD in BSM2 was modified to simulate the behavior of an anaerobic co-digestion process. The prediction and generalization performances of the different models were also compared. This comparison showed that the GP soft sensor is more precise than the other soft sensors. In addition, the model robustness was assessed to determine the performance of each model under different process states. It is also shown that, in addition to their robustness, GP soft sensors are easy to implement and provide useful insights into the process by providing explicit equations.
    Thematic Areas: Process chemistry and technology Engineering, chemical Engenharias ii Ciências biológicas ii Chemical engineering (miscellaneous) Bioengineering
    licence for use: https://creativecommons.org/licenses/by/3.0/es/
    ISSN: 22279717
    Author's mail: jaume.giralt@urv.cat jose.font@urv.cat christophe.bengoa@urv.cat
    Author identifier: 0000-0001-5917-8741 0000-0002-4007-7905 0000-0001-9160-5010
    Record's date: 2023-02-22
    Papper version: info:eu-repo/semantics/publishedVersion
    Link to the original source: https://www.mdpi.com/2227-9717/8/1/67
    Licence document URL: http://repositori.urv.cat/ca/proteccio-de-dades/
    Papper original source: Processes. 8 (1):
    APA: Kazemi P; Steyer JP; Bengoa C; Font J; Giralt J (2020). Robust data-driven soft sensors for online monitoring of volatile fatty acids in anaerobic digestion processes. Processes, 8(1), -. DOI: 10.3390/pr8010067
    Article's DOI: 10.3390/pr8010067
    Entity: Universitat Rovira i Virgili
    Journal publication year: 2020
    Publication Type: Journal Publications
  • Keywords:

    Bioengineering,Chemical Engineering (Miscellaneous),Engineering, Chemical,Process Chemistry and Technology
    Waste-water treatment
    Unit
    Soft sensor
    Prediction
    Performance
    Optimization
    Operation
    Neural-network
    Neural network
    Genetic programming
    Data driven
    Benchmark simulation-model
    Anaerobic digestion
    Process chemistry and technology
    Engineering, chemical
    Engenharias ii
    Ciências biológicas ii
    Chemical engineering (miscellaneous)
    Bioengineering
  • Documents:

  • Cerca a google

    Search to google scholar