CN108121860A - A kind of biological yeast making process CPS modeling methods based on Multi-source Information Fusion - Google Patents
A kind of biological yeast making process CPS modeling methods based on Multi-source Information Fusion Download PDFInfo
- Publication number
- CN108121860A CN108121860A CN201711315323.XA CN201711315323A CN108121860A CN 108121860 A CN108121860 A CN 108121860A CN 201711315323 A CN201711315323 A CN 201711315323A CN 108121860 A CN108121860 A CN 108121860A
- Authority
- CN
- China
- Prior art keywords
- making
- koji
- biological
- factor
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Measuring Or Testing Involving Enzymes Or Micro-Organisms (AREA)
- Micro-Organisms Or Cultivation Processes Thereof (AREA)
Abstract
The invention discloses a kind of biological yeast making process CPS modeling methods based on Multi-source Information Fusion, are obtained including the crucial koji-making factor information under Multi-source Information Fusion, the koji-making result of decision that yeast making process CPS modelings, output based on deep learning optimize.It obtains first and merges the multi-source biology koji-making factor, build koji-making impact factor Decision-making structures;Factor Reduction obtains crucial koji-making factor information;Secondly resource data before record koji-making;Biological aspect data, koji-making resource data and koji-making task data and the mapping relations for establishing this three, the physical message emerging system model using the mapping relations as yeast making process are gathered, realizes the CPS modelings to yeast making process.Present method avoids the problems from complicated heat transfer agent and physical equipment Direct Modeling, by controlling koji-making resource data, formulating koji-making task data, biological aspect data in the biological yeast making process of observation, realize the modeling of the biological yeast-making technology state of Multi-source Information Fusion.
Description
Technical field
The present invention relates to a kind of Multi-source Information Fusions and the method for deep learning theoretical treatment biology koji-making information, especially relate to
And a kind of biological yeast making process CPS modeling methods based on Multi-source Information Fusion.
Background technology
Biological koji-making working environment is poor, and labor intensity is big, low production efficiency.Biological yeast-making technology include material storage,
Bent embryo forming, bent embryo fermentation, block ageing, block crush 5 steps, to obtain good koji-making effect, it is necessary to detect and control
System such as cultivation room and temperature, humidity, the oxygen content parameter for being aged room.It is currently the ginsengs such as detection temperature, humidity, oxygen content
Number, koji-making factory or workshop are equipped with respective sensor mostly, possess physical message fusion basis, but since the sensor having is non-certainly
Dynamic measurement can only detect, and can not be obtained more by suitable CPS models come active accommodation biology koji-making key factor information
Good output.This has become the factor for restricting biological koji-making downstream industry profit.Biology system of the structure based on Multi-source Information Fusion
Bent process CPS systems, it will help improve relevant industries and the benefit of enterprise.
The content of the invention:
The purpose of the present invention is improving Multi-source Information Fusion treatment effeciency, simplify biology yeast making process CPS modeling process, carry
A kind of biological yeast making process CPS modeling methods based on Multi-source Information Fusion are gone out.
To achieve these goals, the technical solution of present aspect is:A kind of biological koji-making mistake based on Multi-source Information Fusion
Journey CPS modeling methods, include the following steps:
Step 1:Crucial koji-making factor information under Multi-source Information Fusion obtains, and obtains the multi-source biology koji-making factor;It carries out
Factorial Design merges the biological koji-making factor;Reduce biological koji-making because of subnumber with latin square experiment method, obtain crucial koji-making factor letter
Breath builds koji-making impact factor Decision-making structures.
Step 2:Biological yeast making process CPS modelings based on deep learning, record resource data before biological koji-making;Acquisition life
Object status data, koji-making resource data and koji-making task data;With physical message emerging system (Cyber-Physical
Systems, CPS) system obtain big data by deep learning algorithm establish koji-making resource data, koji-making task data with
The mapping relations of biological aspect data, it is real using the mapping relations as the physical message emerging system model of biological yeast making process
Now the CPS of biological yeast making process is modeled.
Step 3:The biological koji-making result of decision of optimization is exported, by controlling crucial koji-making resource factor, in stable system
Under bent process conditions, the biological aspect data in biological yeast making process are observed.
The beneficial effects of the present invention are:Develop a kind of biological yeast making process CPS modelings based on Multi-source Information Fusion
Method, method of the invention screen the key organism koji-making factor by latin square experiment method, obtain the crucial koji-making factor, and keep away
The problem from complicated heat transfer agent and physical equipment Direct Modeling is exempted from, has been worked by controlling koji-making resource data, formulating koji-making
Task data, i.e. yeast-making technology data observe the biological aspect data in biological yeast making process, realize Multi-source Information Fusion
The modeling of biological yeast-making technology state.
Description of the drawings:
Fig. 1 is the biological yeast making process CPS modeling method flow charts based on Multi-source Information Fusion of the present invention.
Specific embodiment:
In conjunction with the drawings and specific embodiments, the invention will be further described.
As shown in Figure 1, the present invention provides a kind of biological yeast making process CPS modeling methods based on Multi-source Information Fusion,
This method comprises the following steps:
Step 1:Crucial koji-making factor information under Multi-source Information Fusion obtains, and obtains the multi-source biology koji-making factor;It carries out
Factorial Design merges the biological koji-making factor;Reduce biological koji-making because of subnumber with latin square experiment method, obtain crucial koji-making factor letter
Breath builds koji-making impact factor Decision-making structures.
With fiIt represents to influence to block disintegrating process process from raw material material storage, bent embryo forming, bent embryo fermentation, block ageing
The factor of biological koji-making effect, i=m, construction latin square are tested, and are reduced to the n factor, and wherein n is much smaller than m.
Step 2:Biological yeast making process CPS modelings based on deep learning, record resource data before biological koji-making;Acquisition life
Object status data Y, koji-making resource data YR and koji-making task data WD;With physical message emerging system (Cyber-
Physical Systems, CPS) system obtain big data by deep learning algorithm establish koji-making resource data, koji-making work
The mapping relations of task data and biological aspect data merge system using the physical message of the mapping relations as biological yeast making process
System model realizes the CPS modelings to biological yeast making process.
Because biological aspect data are obtained by sensor, this kind of data are stored as time series data collection form, use therefore
Recurrent neural network physical training condition data Y and koji-making resource data YR and koji-making task data WD in deep learning algorithm
Relation, realize
Y=f (YR, WD) maps, during wherein t=0, YR=YR0, WD=WD0
Step 3:The biological koji-making result of decision of optimization is exported, by controlling crucial koji-making resource factor, in stable system
Under bent process conditions, the biological aspect data in biological yeast making process are observed.
The beneficial effects of the present invention are:Develop a kind of biological yeast making process CPS modelings based on Multi-source Information Fusion
Method crosses the latin square experiment method screening key organism koji-making factor, obtains the crucial koji-making factor, and avoid and sensed from complexity
The problem of information and physical equipment Direct Modeling, by controlling koji-making resource data, formulating koji-making task data, i.e. koji-making
Process data observes the biological aspect data in biological yeast making process, realizes the biological yeast-making technology shape of Multi-source Information Fusion
The modeling of state.
The present invention can solve the problems, such as that CPS system modellings are difficult, the big data obtained with physical message emerging system CPS systems
The mapping relations of koji-making resource data, koji-making task data and biological aspect data are established by deep learning algorithm, with this
Physical message emerging system model of the mapping relations as biological yeast making process, efficiently realizes the CPS to biological yeast making process
Modeling.
The foregoing is merely presently preferred embodiments of the present invention, is not intended to limit the invention, it is all the present invention spirit and
All any modification, equivalent and improvement made within principle etc., should be included within the scope of the present invention.
Claims (4)
1. a kind of biological yeast making process CPS modeling methods based on Multi-source Information Fusion, including the key under Multi-source Information Fusion
The biological koji-making decision-making knot that koji-making factor information obtains, biological yeast making process CPS modelings, output based on deep learning optimize
Fruit;It is characterized in that:Obtain the multi-source biology koji-making factor;The biological koji-making factor of fusion, builds koji-making impact factor Decision-making structures;
Factor Reduction obtains crucial koji-making factor information;Resource data before the biological koji-making of record;Gather biological aspect data, koji-making money
Source data and koji-making task data;It is obtained with physical message emerging system (Cyber-Physical Systems, CPS) system
The big data obtained is established the mapping of koji-making resource data, koji-making task data and biological aspect data by deep learning algorithm
Relation using the mapping relations as the physical message emerging system model of biological yeast making process, is realized to biological yeast making process
CPS is modeled.
2. the biological yeast making process CPS modeling methods according to claim 1 based on Multi-source Information Fusion, feature exist
In:Crucial koji-making factor information under Multi-source Information Fusion obtains, and obtains the multi-source biology koji-making factor;Factorial Design is carried out, is melted
The symphysis object koji-making factor;Reduce biological koji-making because of subnumber with latin square experiment method, obtain crucial koji-making factor information, build koji-making
Impact factor Decision-making structures.
3. the biological yeast making process CPS modeling methods according to claim 1 based on Multi-source Information Fusion, feature exist
In:Biological yeast making process CPS modelings based on deep learning, record resource data before biological koji-making;Acquisition biological aspect data,
Koji-making resource data and koji-making task data;With physical message emerging system (Cyber-Physical Systems, CPS)
The big data that system obtains establishes koji-making resource data, koji-making task data and biological aspect data by deep learning algorithm
Mapping relations, using the mapping relations as the physical message emerging system model of biological yeast making process, realize to biological koji-making
The CPS modelings of process.
4. the biological yeast making process CPS modeling methods according to claim 1 based on Multi-source Information Fusion, feature exist
In:The biological koji-making result of decision of optimization is exported, by controlling crucial koji-making resource factor, in stable yeast-making technology condition
Under, observe the biological aspect data in biological yeast making process.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711315323.XA CN108121860A (en) | 2017-12-12 | 2017-12-12 | A kind of biological yeast making process CPS modeling methods based on Multi-source Information Fusion |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711315323.XA CN108121860A (en) | 2017-12-12 | 2017-12-12 | A kind of biological yeast making process CPS modeling methods based on Multi-source Information Fusion |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108121860A true CN108121860A (en) | 2018-06-05 |
Family
ID=62229029
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711315323.XA Pending CN108121860A (en) | 2017-12-12 | 2017-12-12 | A kind of biological yeast making process CPS modeling methods based on Multi-source Information Fusion |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108121860A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111553113A (en) * | 2020-03-30 | 2020-08-18 | 徐州徐工挖掘机械有限公司 | Factory production scene CPS modeling method based on multi-source information fusion |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1683254A (en) * | 2005-03-17 | 2005-10-19 | 哈尔滨工业大学 | Intelligent monitoring and control method for coagulation process based on multisource information fusion technology |
CN102819673A (en) * | 2012-07-26 | 2012-12-12 | 中国农业科学院农田灌溉研究所 | Multisource irrigation information fusion method and device |
CN104932421A (en) * | 2015-06-19 | 2015-09-23 | 华中科技大学 | Numerical control machine work process CPS modeling method based on instruction domain analysis |
CN106647629A (en) * | 2016-09-22 | 2017-05-10 | 华中科技大学 | Cutter breakage detection method based on internal data of numerical control system |
-
2017
- 2017-12-12 CN CN201711315323.XA patent/CN108121860A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1683254A (en) * | 2005-03-17 | 2005-10-19 | 哈尔滨工业大学 | Intelligent monitoring and control method for coagulation process based on multisource information fusion technology |
CN102819673A (en) * | 2012-07-26 | 2012-12-12 | 中国农业科学院农田灌溉研究所 | Multisource irrigation information fusion method and device |
CN104932421A (en) * | 2015-06-19 | 2015-09-23 | 华中科技大学 | Numerical control machine work process CPS modeling method based on instruction domain analysis |
CN106647629A (en) * | 2016-09-22 | 2017-05-10 | 华中科技大学 | Cutter breakage detection method based on internal data of numerical control system |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111553113A (en) * | 2020-03-30 | 2020-08-18 | 徐州徐工挖掘机械有限公司 | Factory production scene CPS modeling method based on multi-source information fusion |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108500498B (en) | Weld joint forming quality monitoring method | |
Chiroma et al. | A review of the applications of bio-inspired flower pollination algorithm | |
Wang et al. | Big data in cyber-physical systems, digital manufacturing and industry 4.0 | |
CN113325816A (en) | Industrial Internet-oriented digital twin body data management method | |
CN106897817A (en) | A kind of construction speed Visualized management system and method based on augmented reality | |
CN104112026B (en) | A kind of short message text sorting technique and system | |
CN103745271B (en) | Forecasting method for induction thermal deposition calcium-phosphate coating process on basis of neural network | |
CN113344875B (en) | Abnormal image detection method based on self-supervision learning | |
CN117389236B (en) | Propylene oxide production process optimization method and system | |
CN114418177B (en) | New product material distribution prediction method based on digital twin workshops for generating countermeasure network | |
Laktionov et al. | Planning of remote experimental research on effects of greenhouse microclimate parameters on vegetable crop-producing | |
CN115858940B (en) | Steel structure welding process quality management recommendation method based on big data processing | |
CN111402235B (en) | Growth recording method and device for colony image, electronic equipment and storage medium | |
CN108121860A (en) | A kind of biological yeast making process CPS modeling methods based on Multi-source Information Fusion | |
CN112184007B (en) | Workshop equipment remote diagnosis method based on digital twin | |
Hüsener et al. | The digital twin as a mediator for the digitalization and conservation of expert knowledge | |
CN116308128A (en) | Method, equipment and medium for green construction management of assembled building | |
CN102911852B (en) | Automatic screening apparatus and automatic screening method for clone bacterial strains | |
CN103439964A (en) | On-line updating system and method for OCSVM monitoring model | |
Romanov et al. | Wireless Sensor Networks for Digital Agriculture, Environmental Protection, and Healthcare | |
CN112231024A (en) | Shield main control room display interface optimization method based on attention distribution | |
Pradeep et al. | Smart Sensor-Based Smart Agriculture for Better Crop Production in This Smart Era | |
Singh et al. | Artificial internet of things (AIoT) and its momentous impact and challenges in modern agriculture | |
CN115983142B (en) | Regional population evolution model construction method based on depth generation countermeasure network | |
CN117372630B (en) | Data visualization system and method based on digital twin technology |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20180605 |
|
WD01 | Invention patent application deemed withdrawn after publication |