KR20210025832A - Rice Wine Quality Automatic Estimation System Using Artificial Intelligence - Google Patents
Rice Wine Quality Automatic Estimation System Using Artificial Intelligence Download PDFInfo
- Publication number
- KR20210025832A KR20210025832A KR1020190105664A KR20190105664A KR20210025832A KR 20210025832 A KR20210025832 A KR 20210025832A KR 1020190105664 A KR1020190105664 A KR 1020190105664A KR 20190105664 A KR20190105664 A KR 20190105664A KR 20210025832 A KR20210025832 A KR 20210025832A
- Authority
- KR
- South Korea
- Prior art keywords
- fermentation
- rice wine
- makgeolli
- raw rice
- fermentation tank
- Prior art date
Links
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 17
- 238000000855 fermentation Methods 0.000 claims abstract description 87
- 230000004151 fermentation Effects 0.000 claims abstract description 87
- 238000000034 method Methods 0.000 claims abstract description 17
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 7
- 238000013528 artificial neural network Methods 0.000 abstract description 8
- 238000012544 monitoring process Methods 0.000 abstract description 5
- 238000001816 cooling Methods 0.000 abstract description 4
- 238000005516 engineering process Methods 0.000 abstract description 4
- 235000019991 rice wine Nutrition 0.000 abstract 9
- 238000010438 heat treatment Methods 0.000 abstract 1
- LFQSCWFLJHTTHZ-UHFFFAOYSA-N Ethanol Chemical compound CCO LFQSCWFLJHTTHZ-UHFFFAOYSA-N 0.000 description 32
- 235000000346 sugar Nutrition 0.000 description 11
- 240000004808 Saccharomyces cerevisiae Species 0.000 description 8
- 230000010354 integration Effects 0.000 description 8
- 238000007654 immersion Methods 0.000 description 7
- 238000004519 manufacturing process Methods 0.000 description 7
- 239000002994 raw material Substances 0.000 description 7
- 238000013135 deep learning Methods 0.000 description 4
- JVTAAEKCZFNVCJ-UHFFFAOYSA-N lactic acid Chemical compound CC(O)C(O)=O JVTAAEKCZFNVCJ-UHFFFAOYSA-N 0.000 description 4
- 102000004190 Enzymes Human genes 0.000 description 3
- 108090000790 Enzymes Proteins 0.000 description 3
- 150000007524 organic acids Chemical class 0.000 description 3
- 238000005070 sampling Methods 0.000 description 3
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 description 2
- 238000004497 NIR spectroscopy Methods 0.000 description 2
- 239000002253 acid Substances 0.000 description 2
- 239000004310 lactic acid Substances 0.000 description 2
- 235000014655 lactic acid Nutrition 0.000 description 2
- 238000013178 mathematical model Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 244000005700 microbiome Species 0.000 description 2
- 235000005985 organic acids Nutrition 0.000 description 2
- 238000000611 regression analysis Methods 0.000 description 2
- 208000024891 symptom Diseases 0.000 description 2
- 241000894006 Bacteria Species 0.000 description 1
- 240000007594 Oryza sativa Species 0.000 description 1
- 235000007164 Oryza sativa Nutrition 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 150000001413 amino acids Chemical class 0.000 description 1
- 239000001569 carbon dioxide Substances 0.000 description 1
- 229910002092 carbon dioxide Inorganic materials 0.000 description 1
- 235000013339 cereals Nutrition 0.000 description 1
- 239000003795 chemical substances by application Substances 0.000 description 1
- 230000010485 coping Effects 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000012467 final product Substances 0.000 description 1
- 239000000796 flavoring agent Substances 0.000 description 1
- 235000019634 flavors Nutrition 0.000 description 1
- 239000003205 fragrance Substances 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000008571 general function Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000004321 preservation Methods 0.000 description 1
- 235000009566 rice Nutrition 0.000 description 1
- 238000002791 soaking Methods 0.000 description 1
- 235000014347 soups Nutrition 0.000 description 1
- 238000004611 spectroscopical analysis Methods 0.000 description 1
- 238000003756 stirring Methods 0.000 description 1
- 150000008163 sugars Chemical class 0.000 description 1
- 238000000411 transmission spectrum Methods 0.000 description 1
- 235000013311 vegetables Nutrition 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/04—Manufacturing
-
- C—CHEMISTRY; METALLURGY
- C12—BIOCHEMISTRY; BEER; SPIRITS; WINE; VINEGAR; MICROBIOLOGY; ENZYMOLOGY; MUTATION OR GENETIC ENGINEERING
- C12G—WINE; PREPARATION THEREOF; ALCOHOLIC BEVERAGES; PREPARATION OF ALCOHOLIC BEVERAGES NOT PROVIDED FOR IN SUBCLASSES C12C OR C12H
- C12G3/00—Preparation of other alcoholic beverages
- C12G3/02—Preparation of other alcoholic beverages by fermentation
- C12G3/021—Preparation of other alcoholic beverages by fermentation of botanical family Poaceae, e.g. wheat, millet, sorghum, barley, rye, or corn
- C12G3/022—Preparation of other alcoholic beverages by fermentation of botanical family Poaceae, e.g. wheat, millet, sorghum, barley, rye, or corn of botanical genus Oryza, e.g. rice
-
- C—CHEMISTRY; METALLURGY
- C12—BIOCHEMISTRY; BEER; SPIRITS; WINE; VINEGAR; MICROBIOLOGY; ENZYMOLOGY; MUTATION OR GENETIC ENGINEERING
- C12H—PASTEURISATION, STERILISATION, PRESERVATION, PURIFICATION, CLARIFICATION OR AGEING OF ALCOHOLIC BEVERAGES; METHODS FOR ALTERING THE ALCOHOL CONTENT OF FERMENTED SOLUTIONS OR ALCOHOLIC BEVERAGES
- C12H1/00—Pasteurisation, sterilisation, preservation, purification, clarification, or ageing of alcoholic beverages
- C12H1/12—Pasteurisation, sterilisation, preservation, purification, clarification, or ageing of alcoholic beverages without precipitation
- C12H1/16—Pasteurisation, sterilisation, preservation, purification, clarification, or ageing of alcoholic beverages without precipitation by physical means, e.g. irradiation
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01K—MEASURING TEMPERATURE; MEASURING QUANTITY OF HEAT; THERMALLY-SENSITIVE ELEMENTS NOT OTHERWISE PROVIDED FOR
- G01K3/00—Thermometers giving results other than momentary value of temperature
- G01K3/02—Thermometers giving results other than momentary value of temperature giving means values; giving integrated values
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
- G05B19/41875—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM] characterised by quality surveillance of production
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
- G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
- G05B23/0259—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterized by the response to fault detection
- G05B23/0283—Predictive maintenance, e.g. involving the monitoring of a system and, based on the monitoring results, taking decisions on the maintenance schedule of the monitored system; Estimating remaining useful life [RUL]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Chemical & Material Sciences (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Organic Chemistry (AREA)
- Theoretical Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Genetics & Genomics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Biochemistry (AREA)
- Wood Science & Technology (AREA)
- Zoology (AREA)
- Business, Economics & Management (AREA)
- Manufacturing & Machinery (AREA)
- Automation & Control Theory (AREA)
- Tourism & Hospitality (AREA)
- Biomedical Technology (AREA)
- Toxicology (AREA)
- Quality & Reliability (AREA)
- General Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Primary Health Care (AREA)
- Marketing (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Artificial Intelligence (AREA)
- Food Science & Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Apparatus Associated With Microorganisms And Enzymes (AREA)
- Alcoholic Beverages (AREA)
Abstract
Description
본 발명은 막걸리의 발효과정을 모니터링하고, 품질을 예측하여 발효과정을 제어하는 기술에 관한 발명이다. 좀 더 자세하게는 인공지능 학습방법을 이용하여 품질을 예측하는 기술과 품질을 제어하기 위한 제어 기술에 관한 것이다.The present invention relates to a technology for controlling the fermentation process by monitoring the fermentation process of makgeolli and predicting the quality. In more detail, it relates to a technology for predicting quality using an artificial intelligence learning method and a control technology for controlling the quality.
본 발명 이전의 선행기술로는 막걸리 품질 예측 분광분석 방법에 관한 것으로, 근적외선 분광기를 통해 막걸리의 투과 스펙트럼을 획득하고, 막걸리 품질인자의 예측 모델을 선정하여 발효조에서 발효되는 막걸리의 품질을 예측하며, 예측 결과를 이용해서 막걸리 발효 모니터링 시스템의 성능을 평가하고, 상기 품질인자는 알코올 함량, 환원당 함량 및 유기산에 의해 결정되는 적정산도 중에서 하나 이상을 포함하는 구성을 마련하여, 발효 중인 막걸리의 품질인자를 비파괴적으로 신속하게 측정할 수 있는 근적외선 분광분석 방법을 이용해서 품질예측 모델을 선정하고, 이를 통해 발효 중인 막걸리의 알코올 함량, 환원당 함량, 적정산도를 예측하는 발명이 개시되어 있으며, Prior art prior to the present invention relates to a spectroscopic analysis method for predicting makgeolli quality, obtaining a transmission spectrum of makgeolli through a near-infrared spectroscopy, and predicting the quality of makgeolli fermented in a fermenter by selecting a predictive model of makgeolli quality factor, The performance of the makgeolli fermentation monitoring system is evaluated using the predicted results, and the quality factor is prepared to include at least one of an alcohol content, a reducing sugar content, and an titratable acidity determined by an organic acid, and the quality factor of the makgeolli being fermented is determined. The invention is disclosed for selecting a quality prediction model using a near-infrared spectroscopy method that can be measured non-destructively and quickly, and predicting the alcohol content, reducing sugar content, and titratable acidity of makgeolli in fermentation through this,
또 다른 선행기술로는 담금조, 교반기 그리고 냉각 재킷을 포함하여 이루어지는 막걸리 제조장치에서 담금조의 내측으로는 막걸리 원료가 투입되면, 교반기는 담금조에 구비되어 투입된 막걸리 원료를 저속교반하고, 냉각 재킷은 담금조의 외측면에 밀착 구비되고, 담금조를 1차 냉각시킴으로써 2차로 담금조에 투입된 막걸리 원료의 온도를 낮추는 제조 장치를 제공한다.Another prior art is a makgeolli manufacturing apparatus comprising a immersion tank, a stirrer, and a cooling jacket, when the makgeolli raw material is introduced into the immersion tank, the stirrer is provided in the immersion tank and agitates the input makgeolli at low speed, and the cooling jacket is immersed It is provided in close contact with the outer surface of the bath, and provides a manufacturing apparatus for lowering the temperature of the raw material of makgeolli that is secondly introduced into the immersion bath by first cooling the immersion bath.
막걸리의 담금 과정은 환경과 날씨의 영향을 많이 받는 것이어서, 막걸리 양조에 노하우가 있는 기술자가 온도와 습도 등을 조절하며, 생산하여왔다. 특히 효모의 발효 기능이 중요하며, 발효 전체기간의 적산온도도 중요하다. 그러나 객관적인 자료가 없어 제조 기술자의 능력에 맛이 좌우되었다. The immersion process of makgeolli is highly influenced by the environment and the weather, so a technician with know-how in makgeolli brewing has been producing makgeolli by controlling the temperature and humidity. In particular, the fermentation function of yeast is important, and the accumulated temperature for the entire fermentation period is also important. However, since there was no objective data, the taste was influenced by the ability of the manufacturing engineer.
그동안에 여러 연구가 있었으나, 이러한 발효 과정에서 중요한 인자를 정의하고 이를 모니터링함으로써 최종 막걸리의 품질이 일정하도록 제어하는 장치가 없어왔다.There have been several studies in the meantime, but there has been no device to control the quality of the final makgeolli by defining and monitoring important factors in the fermentation process.
본 발명은 상기와 같은 문제를 해결하기 위하여,The present invention in order to solve the above problems,
발효조; 및 Fermentation tank; And
상기 발효조를 가열 또는 냉각하기 위해 상기 발효조 내부를 지나는 냉수관 및 온수관; 및 A cold water pipe and a hot water pipe passing through the fermentation tank to heat or cool the fermentation tank; And
상기 발효조 내부에 발효 중인 막걸리의 발효 상태를 확인하기위하여 발효조 온도센서를 구비하며, A fermentation tank temperature sensor is provided in the fermentation tank to check the fermentation status of makgeolli being fermented,
상기 발효조가 위치하는 공간의 온도를 측정하기 위한 실내온도센서를 구비하는 것을 특징으로 하는 인공지능기반 막걸리 품질 예측을 통한 자동제어시스템를 제공한다.It provides an automatic control system through artificial intelligence-based makgeolli quality prediction, characterized in that it comprises a room temperature sensor for measuring the temperature of the space in which the fermentation tank is located.
또한, 상기 발효조 온도센서 및 실내온도센서의 센싱 값과 상기 발효조 온도센서와 실내온도센서는 적산온도를 계산하여 저장하는 데이터 로거와 상기 데이터 로거의 측정값을 발효 일자별로 설정된 기준 값과 비교하여 기준 값을 벗어나는 경우 이를 사용자에게 알리거나, 이에 상응하는 대응을 할 수 있는 제어기를 더 포함하는 것을 특징으로 하는 인공지능기반 막걸리 품질 예측을 통한 자동제어시스템를 제공한다. In addition, the sensing value of the fermentation tank temperature sensor and the room temperature sensor, the fermentation tank temperature sensor and the room temperature sensor calculate and store the accumulated temperature, and compare the measured value of the data logger with a reference value set for each fermentation date. Provides an automatic control system through artificial intelligence-based makgeolli quality prediction, characterized in that it further comprises a controller capable of notifying a user of the value out of the value or responding corresponding thereto.
또한, 상기 제어기는 상기 발효조 온도, 실내온도, 발효조 온도 적산값, 실내온도 적산값을 입력으로 하여 출력값인 막걸리의 알콜농도를 현재까지의 입력 데이터로 예측하며, 그 예측값이 막걸리의 품질이 나쁜 결과이면, 발효 시작일로부터의 경과 시간과 이에 따른 제어수단을 사용자에게 알리는 것을 특징으로 하는 인공지능기반 막걸리 품질 예측을 통한 자동제어시스템를 제공한다. In addition, the controller predicts the alcohol concentration of makgeolli, which is an output value, as input data, by inputting the fermentation tank temperature, room temperature, fermentation tank temperature integration value, and room temperature integration value, and the predicted value is a result of poor quality of makgeolli. Then, it provides an automatic control system through artificial intelligence-based makgeolli quality prediction, characterized in that the elapsed time from the fermentation start date and the corresponding control means are notified to the user.
본 발명은 상기와 같은 구성에 의하여 기존에 인간의 경험적인 요소에 의하여 운영되는 막걸리 양조장의 담금 방법을 검토하여, 막걸리 발효의 주요 인자를 찾아내고 이를 장기간, 여러 환경조건에서 측정된 데이터를 모아, 빅 데이터를 구축하고, 이 빅 데이터를 이용하여 막걸리 품질을 예측할 수 있는 인공신경망 모델을 개발하였다. 상기 개발된 인공신경망 모델에 현재까지의 발효 조건을 입력하여 최적의 막걸리 품질이 나오기 위한 발효조 제어방법을 선택할 수 있도록 함으로써, 항상 최적의 품질을 가지는 막걸리가 생산될 수 있도록 하였다.The present invention examines the immersion method of a makgeolli brewery operated by human empirical factors by the above configuration, finds the main factors of makgeolli fermentation, and collects data measured under various environmental conditions for a long period of time, We built big data and developed an artificial neural network model that can predict the quality of makgeolli using this big data. By inputting the fermentation conditions up to now in the developed artificial neural network model, the fermentation tank control method for the optimal quality of makgeolli can be selected, so that makgeolli having the optimal quality can always be produced.
도1은 기존의 막걸리 제조공정을 도식화한 것이다.
도2는 본 발명의 막걸리 제조공정에 따른 기준 값과 이상시 대처방법이다.
도3은 본 발명의 발효상황에 따라 발효조의 제어를 다르게 하는 것을 보여주는 그래프이다.
도4는 본 발명의 알콜농도예측 그래프 이다.
도5는 본 발명의 발효조의 내부 모습이다.1 is a schematic diagram of an existing makgeolli manufacturing process.
2 is a reference value according to the makgeolli manufacturing process of the present invention and a coping method in case of abnormality.
Figure 3 is a graph showing the different control of the fermentation tank according to the fermentation situation of the present invention.
Figure 4 is an alcohol concentration prediction graph of the present invention.
5 is an internal view of the fermentation tank of the present invention.
본 발명의 작용효과를 도면을 이용하여 설명하면 하기와 같다. The operation and effect of the present invention will be described with reference to the drawings as follows.
막걸리는 전분질 원료(발아 곡류 제외)와 국(麴), 식물성 원료, 물 등을 원료로 하여 발효시킨 술덧을 혼탁하게 제성한 것 또는 제성 과정에 탄산가스 등을 첨가한 것을 말한다. 막걸리는 쌀을 원료로 하는 전통주로 누룩 곰팡이의 효소에 의해서 당화가 이루어지고 분해된 당은 효모에 의해 알코올로 전환되는 병행 복발효주로, 담금 후에도 누룩 미생물에 의한 지속적인 효소 작용으로 다량의 당분, 아미노산 및 유기산 등의 맛 성분과 효모, 젖산균 등의 미생물에 의한 알코올 발효로 휘발성 성분들이 생성된다. 막걸리의 품질은 알코올, pH, 총산, 휘발산, 총당 등의 일반적인 품질 특성과 유기산, 유리당, 향기 성분, 미량 알코올 성분 등의 미량 성분에 의하여 결정되며, 이러한 요인들은 전분질 원료, 발효 조건, 누룩 및 효모와 같은 발효제의 종류, 저장 조건에 따라 크게 달라진다. 이중 알코올은 막걸리의 보존성이나 향미에 영향을 주는 성분으로 알코올 발효가 진행됨에 따라 함량이 증가하며, 막걸리의 품질 중 가장 중요한 요소이다. 또한, 발효가 완료된 막걸리의 알콜농도가 일정하지 않으면 주류로써의 가치가 현저히 떨어지기 때문에 막걸지의 대표적인 품질 지표로 알콜농도를 사용하고 있다. Makgeolli refers to a mixture of starchy raw materials (excluding germinated grains), soup, vegetable raw materials, water, etc., and fermented mash to make it cloudy, or to add carbon dioxide gas during the making process. Makgeolli is a traditional liquor made from rice, which is saccharified by the enzymes of yeast fungi, and decomposed sugar is converted into alcohol by yeast. Even after soaking, it is a large amount of sugar and amino acids due to continuous enzyme action by yeast microorganisms. And volatile components are produced by alcohol fermentation by taste components such as organic acids and microorganisms such as yeast and lactic acid bacteria. The quality of makgeolli is determined by general quality characteristics such as alcohol, pH, total acid, volatile acid, total sugar, and trace components such as organic acids, free sugars, fragrance components, and trace alcohol components.These factors are starchy raw materials, fermentation conditions, yeast and It varies greatly depending on the type of fermenting agent such as yeast and storage conditions. Among them, alcohol is a component that affects the preservation and flavor of makgeolli, and its content increases as alcohol fermentation proceeds, and is the most important factor in the quality of makgeolli. In addition, if the alcohol concentration of makgeolli after fermentation is not constant, its value as a liquor decreases significantly, so alcohol concentration is used as a representative quality index of makgeolli.
도 1은 본 발명의 대상이 되는 막걸리 제조공정을 순차적으로 표현한 그래프이다. 상기 도1의 그래프로부터 각 단계별로 확인해야하는 품질인자와 그 품질 인자의 기준 값을 제시하고, 상기 품질인자가 상기 기준 값을 벗어난 경우에 조치방법을 제시하고 있다. 도3과 도4는 본 발명의 온도 모니터링을 통하여 발효조의 실시간 온도변화 그래프와 발효조의 적산온도 예측을 통한 막걸리의 알콜농도 예측 결과를 통하여 발효조에서 발효 중인 막걸리의 품질을 예측하고 이를 제어하기위한 방법에 관한 그래프이다. 1 is a graph sequentially representing the manufacturing process of makgeolli, which is an object of the present invention. From the graph of FIG. 1, a quality factor to be checked at each step and a reference value of the quality factor are presented, and a countermeasure method is suggested when the quality factor is out of the reference value. 3 and 4 are a method for predicting and controlling the quality of makgeolli fermenting in a fermenter through a graph of real-time temperature change of a fermenter through temperature monitoring of the present invention and an alcohol concentration prediction result of makgeolli through prediction of the accumulated temperature of the fermenter. It is a graph of.
도 2의 제어를 위하여 본 발명은 다음과 같은 구성을 구비한다. For the control of FIG. 2, the present invention has the following configuration.
발효조; 및 Fermentation tank; And
상기 발효조를 가열 또는 냉각하기 위해 상기 발효조 내부를 지나는 냉수관 및 온수관; 및 A cold water pipe and a hot water pipe passing through the fermentation tank to heat or cool the fermentation tank; And
상기 발효조 내부에 발효 중인 막걸리의 발효 상태를 확인하기위한 발효조 온도센서를 구비하며, A fermentation tank temperature sensor for checking a fermentation state of makgeolli in fermentation is provided inside the fermentation tank,
상기 발효조가 위치하는 공간의 온도를 측정하기 위한 실내온도센서를 구비하는 것을 특징으로 하는 인공지능기반 막걸리 품질 예측을 통한 자동제어시스템을 제공한다.It provides an automatic control system through artificial intelligence-based makgeolli quality prediction, characterized in that it comprises a room temperature sensor for measuring the temperature of the space in which the fermentation tank is located.
또한, 상기 발효조 온도센서 및 실내온도센서의 센싱값과 상기 발효조 온도센서와 실내온도센서는 적산온도를 계산하여 저장하는 데이터 로거와 In addition, the sensing values of the fermentation tank temperature sensor and the room temperature sensor, and the fermentation tank temperature sensor and the room temperature sensor include a data logger that calculates and stores the accumulated temperature.
상기 데이터 로거의 측정값을 발효 일자별로 설정된 기준 값과 비교하여 기준값을 벗어나는 경우 이를 사용자에게 알리거나, 이에 상응하는 대응을 할 수 있는 제어기를 더 포함하는 것을 특징으로 하는 인공지능기반 막걸리 품질 예측을 통한 자동제어시스템를 제공한다.An artificial intelligence-based makgeolli quality prediction, characterized in that it further comprises a controller capable of notifying a user of the reference value by comparing the measured value of the data logger with a reference value set for each fermentation date, or responding corresponding thereto. Provides an automatic control system through.
상기 제어기는 발효진행시간에 따른 상기 발효조 온도센서, 실내온도센서의 센싱값, 상기 발효조 온도센서의 적산값 및 상기 실내온도센서의 적산값과 입국조건으로 구성되는 발효조건과 및 최종 산물인 막걸리의 알콜농도를 입력으로하여 인공신경망 또는 다중회귀분석을 통한 수학적모델을 만들고, The controller includes a fermentation condition consisting of the fermentation tank temperature sensor, the sensing value of the indoor temperature sensor, the accumulated value of the fermentation tank temperature sensor, the accumulated value of the indoor temperature sensor, and the entry condition according to the fermentation progress time, and the final product of makgeolli. Create a mathematical model through artificial neural network or multiple regression analysis by inputting alcohol concentration,
상기 수학적모델을 이용하여, 상기 발효조건에 따라 결정되는 막걸리의 알콜농도를 예측하는 농도예측부를 더 구비하는 것을 특징으로 하는 인공지능기반 막걸리 품질 예측을 통한 자동제어시스템를 제공한다. Using the mathematical model, it provides an automatic control system through artificial intelligence-based makgeolli quality prediction, characterized in that it further comprises a concentration prediction unit for predicting the alcohol concentration of makgeolli determined according to the fermentation conditions.
[실시예 1][Example 1]
상기 제어기의 또 다른 실시예로 발효시작 3일차에 알콜농도 12 ~13%, 발효시작 4일차에 14% 이하, 발효시작 5일차에 15.5% 이하, 산도는 발효시작 3일차에 4.0ml 이상, 당도는 3일차에 7.0 Bx 이상, 실내온도는 20~23℃ 유지한 조건에서의 발효조 온도와 실내온도를 1분 내지 60분 간격으로 측정하고, 입국조건과 상기 발효조 온도의 적산값과 상기 실내온도의 적산값을 계산하여 입력으로하고, 최종 생산된 막걸리의 알콜농도를 출력값으로 하는 데이터 셋을 2개 이상 이용하여, 입력노드 5개, 출력노드 1개, 히든 레이어는 1 ~ 5개, 히든레이어의 노드수는 2 ~ 7개로 하여 역전파학습법으로 학습하여 학습오차 R2 = 0.9 이상, 추정오차 R2 = 0.8 이상인 학습모델을 제어기로 사용하는 것을 특징으로 하는 인공지능기반 막걸리 품질 예측을 통한 자동제어시스템를 제공한다.In another embodiment of the controller, the alcohol concentration is 12 to 13% on the 3rd day of fermentation start, 14% or less on the 4th day of fermentation start, 15.5% or less on the 5th day of fermentation start, and the acidity is 4.0ml or more on the 3rd day of fermentation start, and sugar content. The temperature of the fermentation tank and the room temperature were measured at intervals of 1 to 60 minutes under the condition that the temperature of the fermentation tank was maintained at 7.0 Bx or higher on the third day, and the room temperature was maintained at 20 to 23°C. Calculate the accumulated value as an input, and use two or more data sets with the alcohol concentration of the final produced makgeolli as an output value, and use 5 input nodes, 1 output node, 1 to 5 hidden layers, and Automatic control through artificial intelligence-based makgeolli quality prediction characterized by using a learning model with a learning error R 2 = 0.9 or more and an estimation error R 2 = 0.8 or more as a controller by learning by backpropagation learning with 2 to 7 nodes. System.
상기 농도예측부를 이용하여 발효단계에서 막걸리의 알콜 농도 15%를 맞출 수 없는 발효가 예상되는 경우 이를 상기 농도예측부에서 이상 징후로 포착하여, 사용자에게 알리거나 자동으로 조치를 취하는 것을 특징으로 하는 인공지능기반 막걸리 품질 예측을 통한 자동제어시스템를 제공한다. When fermentation that cannot meet the 15% alcohol concentration of makgeolli is expected in the fermentation step by using the concentration predictor, the concentration predictor detects this as an abnormal symptom, and informs the user or automatically takes action. It provides an automatic control system through intelligence-based makgeolli quality prediction.
상기 이상 징후는 발효조 적산온도가 발효에 적합한 적산온도를 유지하지 못하는 경우; 및 The above symptom is when the fermentation tank integration temperature fails to maintain an integration temperature suitable for fermentation; And
실내온도 적산온도가 발효에 적합한 적산온도를 유지하지 못하고 떨어지는 경우; 및When the indoor temperature integration temperature falls without maintaining the integration temperature suitable for fermentation; And
상기 알콜 농도가 발효진행을 따라 증가하지 못하는 경우인 것을 특징으로 하는 인공지능기반 막걸리 품질 예측을 통한 자동제어시스템를 제공한다.It provides an automatic control system through artificial intelligence-based makgeolli quality prediction, characterized in that the alcohol concentration does not increase according to the fermentation progress.
본 발명의 상기 제어기는 인공지능 방법 중에 하나인 인공신경망을 이용하는 것으로 더욱 자세하게는 역전파학습법을 이용하는 MLN(Multi Layer Neural Network) 또는 Deep Learning을 이용하는 인공지능일 수 있다. The controller of the present invention uses an artificial neural network, which is one of the artificial intelligence methods, and in more detail, may be a multi-layer neural network (MLN) using a backpropagation learning method or an artificial intelligence using deep learning.
학습목적은 2가지로 그 중하나는 발효진행시간별로 측정된 알콜농도 값, pH 값, 당도 값, 발효조 내부 온도와 적산값, 실내온도와 적산값과 발효의 결과인 최종 막걸리의 알콜 농도 값을 상기 MLN(Multi Layer Neural Network) 및/또는 Deep Learning으로 학습시켜, 발효진행시간에 따른 상기 측정된 알콜농도 값, pH 값, 당도 값, 발효조 내부 온도와 적산값, 실내온도와 적산값를 입력으로 하여 최종 막걸리의 품질을 예측하는 최종 막걸리 품질예측부를 구성한다. There are two learning objectives, one of which is to recall the alcohol concentration value, pH value, sugar content value, fermenter internal temperature and accumulated value, room temperature and accumulated value, and the alcohol concentration value of the final makgeolli as a result of fermentation. By learning with MLN (Multi Layer Neural Network) and/or Deep Learning, the measured alcohol concentration value, pH value, sugar content value, fermentation tank internal temperature and accumulated value, indoor temperature and accumulated value are input as input. Construct the final makgeolli quality prediction unit that predicts the quality of makgeolli.
또, 다른 목적은 발효진행시간별로 측정된 알콜농도 값, pH 값, 당도 값, 발효조 내부 온도와 적산값, 실내온도와 적산값과 발효의 결과인 최종 막걸리의 알콜 농도 값을 상기 MLN(Multi Layer Neural Network) 및/또는 Deep Learning으로 학습시켜, In addition, another purpose is to determine the alcohol concentration value, pH value, sugar content value, fermenter internal temperature and accumulated value, room temperature and accumulated value, and the alcohol concentration value of the final makgeolli, which is the result of fermentation, measured by fermentation progress time. Neural Network) and/or Deep Learning,
발효진행시간에 따른 상기 측정된 알콜농도 값, pH 값, 당도 값, 발효조 내부 온도와 적산값, 실내온도와 적산값를 입력으로 하여, 최종 막걸리 품질이 목표 품질이 나올 수 있도록 상기 알콜농도 값, pH 값, 당도 값, 발효조 내부 온도와 적산값, 실내온도와 적산값을 실내온도 조절, 발효조 온도 조절, 효모공급, 발효주공급, 젖산 공급, 정제효소 공급 및 교반을 실시하는 발효조 제어부를 구성하는 것이다.By inputting the measured alcohol concentration value, pH value, sugar content value, fermentation tank internal temperature and accumulated value, room temperature and accumulated value according to the fermentation progress time, the alcohol concentration value, pH, so that the final makgeolli quality can reach the target quality. It constitutes a fermenter control unit that controls the indoor temperature, fermenter temperature control, yeast supply, fermentation liquor supply, lactic acid supply, purified enzyme supply, and stirring.
상기 막걸리의 알콜농도 측정은 자동측정 장치에 의하여 진행할 수도 있고, 수동으로 시간을 정하여 샘플링하는 방법에 의하여서도 동일한 결과를 얻을 수 있음은 물론이다. It goes without saying that the measurement of the alcohol concentration of the makgeolli may be performed by an automatic measuring device, or the same result may be obtained by a method of manually setting a time and sampling.
또한, 본 발명의 인공지능기반 막걸리 품질 예측을 통한 자동제어시스템이 개발된 후에는 데이터의 측정을 이용하여 사용된 알콜농도센서를 제거하거나, 샘플링을 하지않고, 인공지능기반 막걸리 품질 예측을 통한 자동제어시스템을 구성할 수 있다. In addition, after the automatic control system through the artificial intelligence-based makgeolli quality prediction of the present invention is developed, the alcohol concentration sensor used is removed using the measurement of the data, or without sampling, the automatic control system is performed through artificial intelligence-based makgeolli quality prediction. You can configure the control system.
상기 농도예측부에 입력되는 알콜의 농도는 입국정보(초기에 투입되는 원재료의 정보로 역가, 산도, 수분을 의미)와 초기 샘플링을 통한 알콜농도 입력으로 알콜농도 예측결과의 정확성을 더 높이는 것도 가능하다. It is also possible to further increase the accuracy of the alcohol concentration prediction result by entering the alcohol concentration through entry information (information of the raw material input initially, meaning potency, acidity, and moisture) and the alcohol concentration through initial sampling. Do.
또한 상기 MLN 및/또는 Deep Learning은 일반적인 사용방법을 이용하는 것으로 상기 MLN은 입력레이어, 출력레이어, 히든레이어로 구성되며, 히든레이어의 수는 2내지 5일 수 있으며, 레이어 및 각 레이어의 노드수는 학습결과에 따라 변동된다. In addition, the MLN and/or Deep Learning uses a general usage method, and the MLN consists of an input layer, an output layer, and a hidden layer, and the number of hidden layers may be 2 to 5, and the number of layers and nodes of each layer is It fluctuates according to the learning outcome.
상기학습결과는 학습횟수, 학습률, 학습에 사용되는 data의 수에 따라 통상의 기술자가 선택할수 있는 것이다. The learning result can be selected by an ordinary technician according to the number of learning times, learning rate, and the number of data used for learning.
딥런닝의 경우 일반적인 함수를 사용하여 학습하고 이를 이용할 수 있으며, 학습의 수를 줄이기 위하여 상기 발효조 온도와 실내온도만을 입력으로 사용할 수 있다. In the case of deep running, it is possible to learn using a general function and use it. In order to reduce the number of learning, only the fermentation tank temperature and the room temperature can be used as inputs.
본 발명의 특징은 막걸리발효의 주요인자로, 막걸리 원료의 입국정보와 초기알콜농도, 발효조 내부온도, 실내온도, 발효조 적산온도, 실내적산온도, 발효시간을 이용하여, 막걸리 발효과정의 data를 수집하고, 이를 학습하여 막걸리 발효중에 최종막걸리의 품잘을 예측하는 모델을 만들고, 이를 이용하여 상기 막걸리 발효조와 실내온도를 제어하여 고품질의 막걸리를 제조하는 장치 및 방법에 관한것이다. Features of the present invention are major factors of makgeolli fermentation, and data of makgeolli fermentation process are collected using the entry information of makgeolli raw materials, initial alcohol concentration, fermentation tank internal temperature, room temperature, fermentation tank integration temperature, indoor integration temperature, and fermentation time. The present invention relates to an apparatus and method for producing a high-quality makgeolli by learning this to create a model for predicting the quality of the final makgeolli during makgeolli fermentation, and using this to control the makgeolli fermentation tank and the room temperature.
이외에도 다중회귀 분석을 통하여 상기 학습에 사용된 입력과 막걸리 농도와의 상관관계를 구하여 이를 이용할 수 있음은 물론이다.In addition, it is of course possible to obtain and use the correlation between the input used for the learning and the concentration of makgeolli through multiple regression analysis.
Claims (2)
상기 발효조를 가열 또는 냉각하기 위해 상기 발효조 내부를 지나는 냉수관 및 온수관; 및
상기 발효조 내부에 발효 중인 막걸리의 발효 상태를 확인하기위한 발효조 온도센서를 구비하며,
상기 발효조가 위치하는 공간의 온도를 측정하기 위한 실내온도센서를 구비하는 것을 특징으로 하는 인공지능기반 막걸리 품질 예측을 통한 자동제어시스템.Fermentation tank; And
A cold water pipe and a hot water pipe passing through the fermentation tank to heat or cool the fermentation tank; And
A fermentation tank temperature sensor for checking a fermentation state of makgeolli in fermentation is provided inside the fermentation tank,
An automatic control system through artificial intelligence-based makgeolli quality prediction, characterized in that comprising a room temperature sensor for measuring the temperature of the space in which the fermentation tank is located.
상기 발효조 온도센서 및 실내온도센서의 센싱값과 상기 발효조 온도센서와 실내온도센서는 적산온도를 계산하여 저장하는 데이터 로거와 상기 데이터 로거의 측정값을 발효 일자별로 설정된 기준 값과 비교하여 기준값을 벗어나는 경우 이를 사용자에게 알리거나, 이에 상응하는 대응을 할 수 있는 제어기를 더 포함하는 것을 특징으로 하는 인공지능기반 막걸리 품질 예측을 통한 자동제어시스템.
The method of claim 1,
The fermentation tank temperature sensor and the room temperature sensor sensing values, the fermentation tank temperature sensor and the room temperature sensor calculate and store the accumulated temperature and compare the measured values of the data logger with a reference value set for each fermentation date, and deviate from the reference value. In this case, the automatic control system through artificial intelligence-based makgeolli quality prediction, characterized in that it further comprises a controller capable of notifying a user or responding corresponding thereto.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| KR1020190105664A KR102290106B1 (en) | 2019-08-28 | 2019-08-28 | Rice Wine Quality Automatic Estimation System Using Artificial Intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| KR1020190105664A KR102290106B1 (en) | 2019-08-28 | 2019-08-28 | Rice Wine Quality Automatic Estimation System Using Artificial Intelligence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| KR20210025832A true KR20210025832A (en) | 2021-03-10 |
| KR102290106B1 KR102290106B1 (en) | 2021-08-17 |
Family
ID=75148145
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| KR1020190105664A KR102290106B1 (en) | 2019-08-28 | 2019-08-28 | Rice Wine Quality Automatic Estimation System Using Artificial Intelligence |
Country Status (1)
| Country | Link |
|---|---|
| KR (1) | KR102290106B1 (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115232694A (en) * | 2022-08-12 | 2022-10-25 | 余化伦 | Mechanical brewing process for Daqu crushed sand of solid-state white spirit |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20090119203A (en) * | 2008-05-15 | 2009-11-19 | 주식회사 나노엔텍 | System and method for monitoring temperature of food arrangements |
| KR101401650B1 (en) | 2012-11-05 | 2014-06-02 | 서울장수주식회사 | Apparatus, method for manufacturing rice wine |
| KR20140127780A (en) * | 2014-05-27 | 2014-11-04 | 김용완 | Manufacturing apparatus for korean traditional rice wine [Ｍａｋｅｏｌｉ] |
| KR101605995B1 (en) | 2015-08-18 | 2016-04-01 | 충남대학교산학협력단 | Makgeoli quality prediction spectroscopic analysis method |
| KR101916764B1 (en) * | 2018-04-18 | 2018-11-08 | 신우산기(주) | Solid fermentation device integration control system |
-
2019
- 2019-08-28 KR KR1020190105664A patent/KR102290106B1/en active IP Right Grant
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20090119203A (en) * | 2008-05-15 | 2009-11-19 | 주식회사 나노엔텍 | System and method for monitoring temperature of food arrangements |
| KR101401650B1 (en) | 2012-11-05 | 2014-06-02 | 서울장수주식회사 | Apparatus, method for manufacturing rice wine |
| KR20140127780A (en) * | 2014-05-27 | 2014-11-04 | 김용완 | Manufacturing apparatus for korean traditional rice wine [Ｍａｋｅｏｌｉ] |
| KR101605995B1 (en) | 2015-08-18 | 2016-04-01 | 충남대학교산학협력단 | Makgeoli quality prediction spectroscopic analysis method |
| KR101916764B1 (en) * | 2018-04-18 | 2018-11-08 | 신우산기(주) | Solid fermentation device integration control system |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115232694A (en) * | 2022-08-12 | 2022-10-25 | 余化伦 | Mechanical brewing process for Daqu crushed sand of solid-state white spirit |
Also Published As
| Publication number | Publication date |
|---|---|
| KR102290106B1 (en) | 2021-08-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112817354B (en) | Livestock and poultry house cultivation environment temperature prediction control system and regulation and control method thereof | |
| US20120269925A1 (en) | Automated winemaking system and winemaking method thereof | |
| Tosi et al. | Assessment of in‐line near‐infrared spectroscopy for continuous monitoring of fermentation processes | |
| Finn et al. | Near‐infrared spectroscopic monitoring of biomass, glucose, ethanol and protein content in a high cell density baker's yeast fed‐batch bioprocess | |
| CN113126490B (en) | Intelligent frequency conversion oxygenation control method and device | |
| CN104884938A (en) | Organic matter production method, organic matter production process monitoring method, and organic matter production process monitoring device | |
| KR102290106B1 (en) | Rice Wine Quality Automatic Estimation System Using Artificial Intelligence | |
| CN101995891B (en) | Method for online analysis of water content of solid master batch recovery system in aromatic acid production | |
| AU2020100377A4 (en) | Intelligent Solid-State Fermentation Method for Fermented Tea | |
| CN113393057A (en) | Wheat yield integrated prediction method based on deep fusion machine learning model | |
| Petersen et al. | In situ near infrared spectroscopy for analyte‐specific monitoring of glucose and ammonium in streptomyces coelicolor fermentations | |
| CN109858707B (en) | ABC-ANFIS-CTF-based intelligent coking diagnosis method for furnace tube of ethylene cracking furnace | |
| Zhao et al. | On-line monitoring of total sugar during kombucha fermentation process by near-infrared spectroscopy: Comparison of linear and non-linear multiple calibration methods | |
| CN107832582B (en) | Method for monitoring biological processes | |
| CN109497194A (en) | A kind of fermented tea intelligence process for solid state fermentation | |
| Birle et al. | On‐line yeast propagation process monitoring and control using an intelligent automatic control system | |
| CN116776252A (en) | Industrial process soft measurement method and system for improving Mallow's Cp variable selection | |
| KR20200046193A (en) | Makgeolli quality sensor | |
| WO1997005236A1 (en) | Method for controlling culture of lactic bacteria | |
| CN206303140U (en) | A kind of intelligent salted vegetables device | |
| Liu et al. | Near infrared spectroscopy coupled with radial basis function neural network for at-line monitoring of Lactococcus lactis subsp. fermentation | |
| AU2021100329A4 (en) | Intelligent Solid-State Fermentation Method For Fermented Tea | |
| Sakhamuri et al. | Simultaneous determination of multiple components in nisin fermentation using FTIR spectroscopy | |
| Kovačević et al. | Modelling the Fermentation Process in Winemaking using Temperature and Specific Gravity | |
| US20110269114A1 (en) | Yeast growth maximization with feedback for optimal control of filled batch fermentation in a biofuel manufacturing facility |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| E902 | Notification of reason for refusal | ||
| E701 | Decision to grant or registration of patent right | ||
| GRNT | Written decision to grant |