Determination of operating conditions in activated sludge process using fuzzy neural network and genetic algorithm

H. Yoshikawa, T. Hanai, Shuta Tomida, H. Honda, T. Kobayashi

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

In order to realize control of activated sludge process, a simulation model for effluent chemical oxygen demand (COD) was constructed using the time series data of three months. Here, the recursive fuzzy neural network (RFNN) was applied for the simulation. The simulation model could estimate effluent COD value with relatively high accuracy (average error: 0.68 mg/l). Next, to control effluent COD value to the desirable level, the search system for the values of the control variables, dissolved oxygen concentration (DO) and mixed liquor suspended solid (MLSS), was constructed using the genetic algorithm (GA) and GA with the reliability index (RI), called as RIGA. In search for DO and MLSS values, accuracy of GA search system was high (average error: 0.16 mg/l for DO and 214 mg/l for MLSS) and accuracy of RIGA search system was higher than GA (average error: 0.11 mg/l for DO and 144 mg/l for MLSS). Then, the search using RIGA was further extended for one-year data to check the ability of this system. As a result, the constructed system could search DO and MLSS values with the average errors of 0.10 mg/l and 162 mg/l, respectively.

Original languageEnglish
Pages (from-to)1033-1039
Number of pages7
JournalJournal of Chemical Engineering of Japan
Volume34
Issue number8
DOIs
Publication statusPublished - Aug 2001
Externally publishedYes

Fingerprint

Activated sludge process
Fuzzy neural networks
Dissolved oxygen
Genetic algorithms
Chemical oxygen demand
Effluents
Time series

Keywords

  • Activated sludge
  • Fuzzy neural network
  • Genetic algorithm
  • Reliability index
  • Simulation

ASJC Scopus subject areas

  • Chemical Engineering(all)

Cite this

Determination of operating conditions in activated sludge process using fuzzy neural network and genetic algorithm. / Yoshikawa, H.; Hanai, T.; Tomida, Shuta; Honda, H.; Kobayashi, T.

In: Journal of Chemical Engineering of Japan, Vol. 34, No. 8, 08.2001, p. 1033-1039.

Research output: Contribution to journalArticle

@article{9b5877e5712a408d9a237454756ac85d,
title = "Determination of operating conditions in activated sludge process using fuzzy neural network and genetic algorithm",
abstract = "In order to realize control of activated sludge process, a simulation model for effluent chemical oxygen demand (COD) was constructed using the time series data of three months. Here, the recursive fuzzy neural network (RFNN) was applied for the simulation. The simulation model could estimate effluent COD value with relatively high accuracy (average error: 0.68 mg/l). Next, to control effluent COD value to the desirable level, the search system for the values of the control variables, dissolved oxygen concentration (DO) and mixed liquor suspended solid (MLSS), was constructed using the genetic algorithm (GA) and GA with the reliability index (RI), called as RIGA. In search for DO and MLSS values, accuracy of GA search system was high (average error: 0.16 mg/l for DO and 214 mg/l for MLSS) and accuracy of RIGA search system was higher than GA (average error: 0.11 mg/l for DO and 144 mg/l for MLSS). Then, the search using RIGA was further extended for one-year data to check the ability of this system. As a result, the constructed system could search DO and MLSS values with the average errors of 0.10 mg/l and 162 mg/l, respectively.",
keywords = "Activated sludge, Fuzzy neural network, Genetic algorithm, Reliability index, Simulation",
author = "H. Yoshikawa and T. Hanai and Shuta Tomida and H. Honda and T. Kobayashi",
year = "2001",
month = "8",
doi = "10.1252/jcej.34.1033",
language = "English",
volume = "34",
pages = "1033--1039",
journal = "Journal of Chemical Engineering of Japan",
issn = "0021-9592",
publisher = "Society of Chemical Engineers, Japan",
number = "8",

}

TY - JOUR

T1 - Determination of operating conditions in activated sludge process using fuzzy neural network and genetic algorithm

AU - Yoshikawa, H.

AU - Hanai, T.

AU - Tomida, Shuta

AU - Honda, H.

AU - Kobayashi, T.

PY - 2001/8

Y1 - 2001/8

N2 - In order to realize control of activated sludge process, a simulation model for effluent chemical oxygen demand (COD) was constructed using the time series data of three months. Here, the recursive fuzzy neural network (RFNN) was applied for the simulation. The simulation model could estimate effluent COD value with relatively high accuracy (average error: 0.68 mg/l). Next, to control effluent COD value to the desirable level, the search system for the values of the control variables, dissolved oxygen concentration (DO) and mixed liquor suspended solid (MLSS), was constructed using the genetic algorithm (GA) and GA with the reliability index (RI), called as RIGA. In search for DO and MLSS values, accuracy of GA search system was high (average error: 0.16 mg/l for DO and 214 mg/l for MLSS) and accuracy of RIGA search system was higher than GA (average error: 0.11 mg/l for DO and 144 mg/l for MLSS). Then, the search using RIGA was further extended for one-year data to check the ability of this system. As a result, the constructed system could search DO and MLSS values with the average errors of 0.10 mg/l and 162 mg/l, respectively.

AB - In order to realize control of activated sludge process, a simulation model for effluent chemical oxygen demand (COD) was constructed using the time series data of three months. Here, the recursive fuzzy neural network (RFNN) was applied for the simulation. The simulation model could estimate effluent COD value with relatively high accuracy (average error: 0.68 mg/l). Next, to control effluent COD value to the desirable level, the search system for the values of the control variables, dissolved oxygen concentration (DO) and mixed liquor suspended solid (MLSS), was constructed using the genetic algorithm (GA) and GA with the reliability index (RI), called as RIGA. In search for DO and MLSS values, accuracy of GA search system was high (average error: 0.16 mg/l for DO and 214 mg/l for MLSS) and accuracy of RIGA search system was higher than GA (average error: 0.11 mg/l for DO and 144 mg/l for MLSS). Then, the search using RIGA was further extended for one-year data to check the ability of this system. As a result, the constructed system could search DO and MLSS values with the average errors of 0.10 mg/l and 162 mg/l, respectively.

KW - Activated sludge

KW - Fuzzy neural network

KW - Genetic algorithm

KW - Reliability index

KW - Simulation

UR - http://www.scopus.com/inward/record.url?scp=0035417171&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0035417171&partnerID=8YFLogxK

U2 - 10.1252/jcej.34.1033

DO - 10.1252/jcej.34.1033

M3 - Article

AN - SCOPUS:0035417171

VL - 34

SP - 1033

EP - 1039

JO - Journal of Chemical Engineering of Japan

JF - Journal of Chemical Engineering of Japan

SN - 0021-9592

IS - 8

ER -