ファジィニューラルネットワーク推論モデルを用いた吟醸もろみの発酵試験

Translated title of the contribution: Experimental Ginjo-Sake Brewing by Using Fuzzy Neural Network

西田 淑男, 花井 泰三, 片山 明美, 本多 裕之, 深谷 伊和男, 小林 猛

Research output: Contribution to journalArticle

Abstract

To examine applicability of a fuzzy neural network (FNN) to decision of <I>moromi</I> temperature in <I>ginjo</I>-sake brewing process, two kinds of <I>ginjo</I>-sake were made and compared. Temperature of the one moromi was calculated automatically by the FNN, while that of the other was manually managed by the <I>toji</I>, a sake-brew master. Baumé alcohol concentration and temperature from 25 kinds of <I>ginjo moromi</I> made in 17 sake breweries in Aichi prefecture from 1989 to 1991 were used to construct the FNN model for decision of <I>ginjo moromi</I> temperature.<BR>Each sake brewing employed 100 kg total Wakamizu rice polished to 50% and <I>sokujomoto</I> made by using a <I>ginjo</I>-sake yeast, <I>S. cerevisiae</I> FIA-2 strain. Temperatures during the first 11 days changedsimilarly for the both <I>moromi</I>. However, temperatures from 12 to 29 days in the case of the FNN control were 0.5-1.5°C lower than those of the manual control. Althoughthere were some differences in the concentrations of flavor components (<I>e. g.</I>, 4.20 ppm iso-amylacetate in the sake by the FNN control, 3.82 ppm by the manual control), the seven panelists judged that <I>ginjo</I> flavor of the two kinds of sake was similar. The concentrations of chemical components, physicalproperties and sensory evaluation had almost the same values in these sake, suggesting that <I>ginjo</I>-sake can be made under the FNN control with almost the same quality as that made under the manual control of the <I>toji</I>.
Original languageUndefined/Unknown
Pages (from-to)447-451
Number of pages5
Journal日本醸造協会誌
Volume92
Issue number6
DOIs
Publication statusPublished - 1997

Fingerprint

sake
brewing
neural networks
temperature
flavor
chemical concentration
brewing industry
sensory evaluation
alcohols
yeasts
rice

Cite this

ファジィニューラルネットワーク推論モデルを用いた吟醸もろみの発酵試験. / 西田淑男; 花井泰三; 片山明美; 本多裕之; 深谷伊和男; 小林猛.

In: 日本醸造協会誌, Vol. 92, No. 6, 1997, p. 447-451.

Research output: Contribution to journalArticle

西田淑男 ; 花井泰三 ; 片山明美 ; 本多裕之 ; 深谷伊和男 ; 小林猛. / ファジィニューラルネットワーク推論モデルを用いた吟醸もろみの発酵試験. In: 日本醸造協会誌. 1997 ; Vol. 92, No. 6. pp. 447-451.
@article{c42f2fccb91448a4ac2d5c4f4881a77c,
title = "ファジィニューラルネットワーク推論モデルを用いた吟醸もろみの発酵試験",
abstract = "To examine applicability of a fuzzy neural network (FNN) to decision of <I>moromi temperature in <I>ginjo-sake brewing process, two kinds of <I>ginjo-sake were made and compared. Temperature of the one moromi was calculated automatically by the FNN, while that of the other was manually managed by the <I>toji, a sake-brew master. Baum{\'e} alcohol concentration and temperature from 25 kinds of <I>ginjo moromi made in 17 sake breweries in Aichi prefecture from 1989 to 1991 were used to construct the FNN model for decision of <I>ginjo moromi temperature.<BR>Each sake brewing employed 100 kg total Wakamizu rice polished to 50{\%} and <I>sokujomoto made by using a <I>ginjo-sake yeast, <I>S. cerevisiae FIA-2 strain. Temperatures during the first 11 days changedsimilarly for the both <I>moromi. However, temperatures from 12 to 29 days in the case of the FNN control were 0.5-1.5°C lower than those of the manual control. Althoughthere were some differences in the concentrations of flavor components (<I>e. g., 4.20 ppm iso-amylacetate in the sake by the FNN control, 3.82 ppm by the manual control), the seven panelists judged that <I>ginjo flavor of the two kinds of sake was similar. The concentrations of chemical components, physicalproperties and sensory evaluation had almost the same values in these sake, suggesting that <I>ginjo-sake can be made under the FNN control with almost the same quality as that made under the manual control of the <I>toji.",
author = "淑男 西田 and 泰三 花井 and 明美 片山 and 裕之 本多 and 伊和男 深谷 and 猛 小林",
year = "1997",
doi = "10.6013/jbrewsocjapan1988.92.447",
language = "未定義",
volume = "92",
pages = "447--451",
journal = "日本醸造協会誌",
issn = "0914-7314",
publisher = "Brewing Society of Japan",
number = "6",

}

TY - JOUR

T1 - ファジィニューラルネットワーク推論モデルを用いた吟醸もろみの発酵試験

AU - 西田, 淑男

AU - 花井, 泰三

AU - 片山, 明美

AU - 本多, 裕之

AU - 深谷, 伊和男

AU - 小林, 猛

PY - 1997

Y1 - 1997

N2 - To examine applicability of a fuzzy neural network (FNN) to decision of <I>moromi temperature in <I>ginjo-sake brewing process, two kinds of <I>ginjo-sake were made and compared. Temperature of the one moromi was calculated automatically by the FNN, while that of the other was manually managed by the <I>toji, a sake-brew master. Baumé alcohol concentration and temperature from 25 kinds of <I>ginjo moromi made in 17 sake breweries in Aichi prefecture from 1989 to 1991 were used to construct the FNN model for decision of <I>ginjo moromi temperature.<BR>Each sake brewing employed 100 kg total Wakamizu rice polished to 50% and <I>sokujomoto made by using a <I>ginjo-sake yeast, <I>S. cerevisiae FIA-2 strain. Temperatures during the first 11 days changedsimilarly for the both <I>moromi. However, temperatures from 12 to 29 days in the case of the FNN control were 0.5-1.5°C lower than those of the manual control. Althoughthere were some differences in the concentrations of flavor components (<I>e. g., 4.20 ppm iso-amylacetate in the sake by the FNN control, 3.82 ppm by the manual control), the seven panelists judged that <I>ginjo flavor of the two kinds of sake was similar. The concentrations of chemical components, physicalproperties and sensory evaluation had almost the same values in these sake, suggesting that <I>ginjo-sake can be made under the FNN control with almost the same quality as that made under the manual control of the <I>toji.

AB - To examine applicability of a fuzzy neural network (FNN) to decision of <I>moromi temperature in <I>ginjo-sake brewing process, two kinds of <I>ginjo-sake were made and compared. Temperature of the one moromi was calculated automatically by the FNN, while that of the other was manually managed by the <I>toji, a sake-brew master. Baumé alcohol concentration and temperature from 25 kinds of <I>ginjo moromi made in 17 sake breweries in Aichi prefecture from 1989 to 1991 were used to construct the FNN model for decision of <I>ginjo moromi temperature.<BR>Each sake brewing employed 100 kg total Wakamizu rice polished to 50% and <I>sokujomoto made by using a <I>ginjo-sake yeast, <I>S. cerevisiae FIA-2 strain. Temperatures during the first 11 days changedsimilarly for the both <I>moromi. However, temperatures from 12 to 29 days in the case of the FNN control were 0.5-1.5°C lower than those of the manual control. Althoughthere were some differences in the concentrations of flavor components (<I>e. g., 4.20 ppm iso-amylacetate in the sake by the FNN control, 3.82 ppm by the manual control), the seven panelists judged that <I>ginjo flavor of the two kinds of sake was similar. The concentrations of chemical components, physicalproperties and sensory evaluation had almost the same values in these sake, suggesting that <I>ginjo-sake can be made under the FNN control with almost the same quality as that made under the manual control of the <I>toji.

U2 - 10.6013/jbrewsocjapan1988.92.447

DO - 10.6013/jbrewsocjapan1988.92.447

M3 - 記事

VL - 92

SP - 447

EP - 451

JO - 日本醸造協会誌

JF - 日本醸造協会誌

SN - 0914-7314

IS - 6

ER -