CN103500280A - Cell concentration online soft measurement method in glutamic acid fermentation process - Google Patents
Cell concentration online soft measurement method in glutamic acid fermentation process Download PDFInfo
- Publication number
- CN103500280A CN103500280A CN201310460718.4A CN201310460718A CN103500280A CN 103500280 A CN103500280 A CN 103500280A CN 201310460718 A CN201310460718 A CN 201310460718A CN 103500280 A CN103500280 A CN 103500280A
- Authority
- CN
- China
- Prior art keywords
- cell concentration
- soft
- glutamic acid
- acid fermentation
- soft measurement
- 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
Images
Landscapes
- Apparatus Associated With Microorganisms And Enzymes (AREA)
- Measuring Or Testing Involving Enzymes Or Micro-Organisms (AREA)
Abstract
The invention discloses a cell concentration online soft measurement method in the glutamic acid fermentation process, and relates to a cell measurement method. The cell concentration online soft measurement method comprises the steps that a soft measurement model is realized in a computer control system through a program, then real-time technology data in the glutamic acid fermentation process are collected through a computer, the cell concentration is calculated through the programmed soft measurement model, and finally online monitoring of the cell concentration is realized; the combination of a GA and a BP neural network is adopted to establish a GA-BP network soft measurement model in the glutamic acid fermentation process; the trained GA-BP soft measurement model is realized on the computer through a program, the estimation value of the cell concentration is worked out and real-time measurement on the cell concentration is realized. According to the cell concentration online soft measurement method, the trained GA-BP soft measurement model is realized in the computer control system through the program, parameters in four processes are collected in site in real time to be used as input of the soft measurement model and the cell concentration serves as output of the soft measurement model, so that online estimation of the cell concentration is realized, and therefore the yield is improved and the production cost is lowered.
Description
Technical field
The present invention relates to a kind of thalline measuring method, particularly relate to a kind of glutamic acid fermentation process cell concentration online soft sensor method.
Background technology
Soft-measuring technique is exactly to infer that according to the process variable that can detect some is difficult to the method for the technological parameter that detects or can't detect at all.Soft-measuring technique is widely used in process industrial now, and application comprises oil refining, petrochemical industry, polymerization, papermaking, mining, food, medicine, fine chemistry industry, semiconductor, weaving and microelectronic industry.Wherein, be widely used in chemical industry such as inferring the links such as senior control, FEEDBACK CONTROL, Operating Guideline, quality management, optimizing scheduling, decision support such as control.Chinese scholars started just soft-measuring technique have been carried out to large quantity research from the seventies in last century, and the middle and later periods eighties, it welcome the gold period of a development so far, and worldwide started the upsurge of one soft-measuring technique research.Because soft-measuring technique has very important impact and effect at industrial control field, so soft-measuring technique has obtained the development of advancing by leaps and bounds in recent years, it has related to the many key areas such as modeling, System Discrimination and data processing in Theory of Automatic Control, its research has been experienced from linearity to non-linear, from static state to dynamically, from without calibration function to the evolution that calibration function is arranged.At present, in the industrial processes such as oil refining, metallurgy, mining, fine chemistry industry and biochemical industry, successful application is arranged.As refinery sulfide catalytic cracking device is implemented soft-measuring technique, determine the operating parameters such as carbon, yield distribution, raw gasoline are done, light diesel fuel pour point in line computation cracking reaction heat, regeneration, complete the tasks such as the stablizing of sulfide catalytic cracking technological process, coordination, optimal control.In addition, also can be in line computation rectification column product component concentration and plate efficiency, reactant concentration and catalyst activity in chemical reactor, and the aspects such as biomass parameters in biological fermentation tank.Can predict, the soft-measuring technique that broad prospect of application is arranged, to become an emphasis direction of following process control field research, and the constantly perfect and development in theoretical research and practice along with it is bound to bring more satisfied economic and social benefit to Industry Control circle.
Summary of the invention
The object of the present invention is to provide a kind of glutamic acid fermentation process cell concentration online soft sensor method, the method realizes by program the GA-BP soft-sensing model trained in computer control system, input by field real-time acquisition Four processes parameter as soft-sensing model, and cell concentration is as output, the On-line Estimation of realization to cell concentration, thereby raising output, reduce production costs.
The objective of the invention is to be achieved through the following technical solutions:
A kind of glutamic acid fermentation process cell concentration online soft sensor method, described method comprises following process: soft-sensing model is realized in computer control system by program, then utilize the real-time process data of computer acquisition glutamic acid fermentation process, soft-sensing model by sequencing calculates cell concentration, finally realizes the on-line monitoring of cell concentration; Adopt the GA algorithm to be combined with the BP neural network, build GA-BP network glutamic acid fermentation process soft-sensing model; According to the GA-BP soft-sensing model trained, by program, realize in computing machine, then by field instrument gather sweat the pH value, mend sugared amount, temperature and ventilation parameter, as the input of soft-sensing model, calculate the estimated value of cell concentration, realize the online measurement to cell concentration.
The accompanying drawing explanation
The composition frame chart that Fig. 1 is glutamic acid fermentation process cell concentration online soft sensor system of the present invention;
Fig. 2 is the operation picture print schematic diagram of glutamic acid fermentation process cell concentration online soft sensor system of the present invention;
Fig. 3 is the test photo schematic diagram of glutamic acid fermentation process cell concentration online soft sensor system of the present invention.
Embodiment
Below in conjunction with the accompanying drawing illustrated embodiment, the invention will be further described.
Soft-measuring technique is to select and the one group measurable variable relevant by predictor, constructs certain and take measurable variable as input, mathematical model by predictor as exporting, realizes the estimation of significant process variable with computer software programming.This process comprises the selection of auxiliary variable, the acquisition and processing of data, foundation and the on-line correction of soft-sensing model.
(1) selection of auxiliary variable: the selection of auxiliary variable is generally according to process mechanism analysis (as material, energy balance relations), at measurable variable, concentrate, the original auxiliary variable that initial option is all with relevant by predictor, in these variablees, part may be correlated variables.Carry out on this basis selectedly, determine final auxiliary variable number.
(2) acquisition and processing of data: set up soft-sensing model, need to gather by the historical data of predictor and original auxiliary variable, the quantity of data is The more the better.The reliability of these data is most important for the success or not of soft measurement.Yet measurement data is generally all inevitably with error, sometimes even with the capital blunder error.Therefore, the processing of input data occupies very consequence in flexible measurement method.
(3) foundation of soft-sensing model: soft-sensing model is that the researcher is on the basis of going deep into understanding process mechanism, the model that is applicable to estimation of developing, it is the core of flexible measurement method, usually has based on process mechanism modeling and the method based on the process data modeling.
(4) on-line correction of soft-sensing model: due to the imperfection of the time variation of process, non-linear and model, must consider the on-line correction of model.The on-line correction of soft-sensing model can be expressed as the optimizing process of model structure and model parameter, and concrete grammar has adaptive method, method of addition and Multi-time Scale method.Due to a large amount of sample data of the correction needs of model structure and longer time, there is online real-time more difficult, therefore the thought that short-term study and Term Learning combine proposed.Short-term is only proofreaied and correct some parameter of model is adjusted, and does not even adjust parameter, only by some correction algorithms, calculates correction, directly output is compensated.Therefore its correction rate is fast, is suitable for the online real time correction of model.After long-term correction is suitable for the model work long period, operating mode and environmental interference have larger change, and model mismatch is more serious, and short-term is proofreaied and correct the situation that can't meet correction accuracy.Now often need a large amount of new datas again to train to determine new construction and parameter to model.Glutamic acid fermentation process cell concentration online soft sensor system, at first according to the glutamic acid fermentation technological process, find the Four processes parameter that cell concentration is had a direct impact, they are respectively pH value, temperature, ventilation and benefit sugar amount, then utilize soft-measuring technique to set up the cell concentration soft-sensing model.Wherein the core of soft-sensing model is the GA-BP network that combines with genetic algorithm with neural network and form, the GA-BP soft-sensing model trained is realized in computer control system by program, input by field real-time acquisition Four processes parameter as soft-sensing model, and cell concentration is as output, the On-line Estimation of realization to cell concentration, thereby can improve the output of monosodium glutamate, reduce the cost of glutamate production, improve Business Economic Benefit.
Fig. 1 comprises PH, temperature, benefit sugar amount and ventilation control; The GA-BP soft-sensing model; Sample training; Aminoglutaminic acid thalline concentration is calculated.Fig. 2 is the soft measuring system operation of glutamic acid fermentation process cell concentration picture; Fig. 3 is the soft measuring system test of glutamic acid fermentation process cell concentration
Embodiment:
Glutamic acid fermentation process cell concentration online soft sensor system is that the soft-sensing model will trained is realized in computer control system with computer program, then gather the parameter surveyed of glutamic acid fermentation process by field instrument, they are respectively pH value, temperature, ventilation and benefit sugar amount, input as soft-sensing model, and cell concentration is the output of soft measurement, just can online calculate the estimated value of cell concentration.The neural network of usining combines the GA-BP network that forms as soft-sensing model with genetic algorithm, the sample data of collection site operation is trained network model, as long as guarantee the accuracy of soft-sensing model, just can realize the online accurate monitoring to cell concentration.
Claims (1)
1. a glutamic acid fermentation process cell concentration online soft sensor method, it is characterized in that, described method comprises following process: soft-sensing model is realized in computer control system by program, then utilize the real-time process data of computer acquisition glutamic acid fermentation process, soft-sensing model by sequencing calculates cell concentration, finally realizes the on-line monitoring of cell concentration; Adopt the GA algorithm to be combined with the BP neural network, build GA-BP network glutamic acid fermentation process soft-sensing model; According to the GA-BP soft-sensing model trained, by program, realize in computing machine, then by field instrument gather sweat the pH value, mend sugared amount, temperature and ventilation parameter, as the input of soft-sensing model, calculate the estimated value of cell concentration, realize the online measurement to cell concentration.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310460718.4A CN103500280A (en) | 2013-09-30 | 2013-09-30 | Cell concentration online soft measurement method in glutamic acid fermentation process |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310460718.4A CN103500280A (en) | 2013-09-30 | 2013-09-30 | Cell concentration online soft measurement method in glutamic acid fermentation process |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103500280A true CN103500280A (en) | 2014-01-08 |
Family
ID=49865488
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310460718.4A Pending CN103500280A (en) | 2013-09-30 | 2013-09-30 | Cell concentration online soft measurement method in glutamic acid fermentation process |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103500280A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104503226A (en) * | 2014-11-06 | 2015-04-08 | 东华大学 | Wireless Wi-Fi remote monitoring system based on multi-sensor information fusion in fermentation chamber environment |
| CN105740622A (en) * | 2016-01-28 | 2016-07-06 | 浙江大学 | Method for selecting auxiliary variables of m-phenylene diamine rectifying tower soft measurement systems on basis of mixed integer programming |
| CN106444377A (en) * | 2016-10-09 | 2017-02-22 | 江苏大学 | Soft measuring method and system for key variables of lysine fermentation process based on PSO-FSVM |
| CN106802983A (en) * | 2016-12-30 | 2017-06-06 | 北京易沃特科技有限公司 | A kind of biogas output Modeling Calculation method and device of the BP neural network based on optimization |
| CN110161518A (en) * | 2019-05-29 | 2019-08-23 | 北京华电力拓能源科技有限公司 | A kind of volume measuring system and method for drag conveyor |
| CN111898301A (en) * | 2020-07-31 | 2020-11-06 | 上海应用技术大学 | Method for implementing soft measuring system |
| CN113805627A (en) * | 2021-09-24 | 2021-12-17 | 领先生物农业股份有限公司 | Nano-film aerobic composting Internet of things control method and device |
| CN115274004A (en) * | 2022-07-26 | 2022-11-01 | 江南大学 | Knowledge reuse-based fermentation process thallus concentration prediction method and system |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1529281A (en) * | 2003-10-21 | 2004-09-15 | 上海交通大学 | Neural network modelling method |
| US20090149981A1 (en) * | 2007-08-14 | 2009-06-11 | Wayne Errol Evans | System and methods for continuous, online monitoring of a chemical plant or refinery |
| CN102626557A (en) * | 2012-04-13 | 2012-08-08 | 长春工业大学 | Molecular distillation process parameter optimizing method based on GA-BP (Genetic Algorithm-Back Propagation) algorithm |
-
2013
- 2013-09-30 CN CN201310460718.4A patent/CN103500280A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1529281A (en) * | 2003-10-21 | 2004-09-15 | 上海交通大学 | Neural network modelling method |
| US20090149981A1 (en) * | 2007-08-14 | 2009-06-11 | Wayne Errol Evans | System and methods for continuous, online monitoring of a chemical plant or refinery |
| CN102626557A (en) * | 2012-04-13 | 2012-08-08 | 长春工业大学 | Molecular distillation process parameter optimizing method based on GA-BP (Genetic Algorithm-Back Propagation) algorithm |
Non-Patent Citations (4)
| Title |
|---|
| 姜长洪 等: "《谷氨酸发酵过程先进控制》", 《化工自动化及仪表》, no. 2, 30 April 2004 (2004-04-30) * |
| 孙蕾 王贵成 等: "《谷氨酸发酵过程菌体浓度的监测方法研究》", 《第六届全国信息获取与处理学术会议》, 6 August 2008 (2008-08-06) * |
| 王贵成 等: "《基于GA-BP网络软测量监测系统的研究》", 《中国化工学会化工自动化及仪表专委会2010年学术年会》, 12 April 2011 (2011-04-12) * |
| 王贵成 等: "《谷氨酸发酵过程计算机模拟仿真系统的设计》", 《计算机技术与应用进展--全国第17界计算机科学与技术应用（CACIS）学术会议论文集（上册）》, 1 July 2006 (2006-07-01) * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104503226A (en) * | 2014-11-06 | 2015-04-08 | 东华大学 | Wireless Wi-Fi remote monitoring system based on multi-sensor information fusion in fermentation chamber environment |
| CN105740622A (en) * | 2016-01-28 | 2016-07-06 | 浙江大学 | Method for selecting auxiliary variables of m-phenylene diamine rectifying tower soft measurement systems on basis of mixed integer programming |
| CN105740622B (en) * | 2016-01-28 | 2019-01-22 | 浙江大学 | The choosing auxiliary variables method of m-phenylene diamine (MPD) rectifying column hard measurement system based on mixed integer programming |
| CN106444377A (en) * | 2016-10-09 | 2017-02-22 | 江苏大学 | Soft measuring method and system for key variables of lysine fermentation process based on PSO-FSVM |
| CN106802983A (en) * | 2016-12-30 | 2017-06-06 | 北京易沃特科技有限公司 | A kind of biogas output Modeling Calculation method and device of the BP neural network based on optimization |
| CN106802983B (en) * | 2016-12-30 | 2020-02-18 | 北京易沃特科技有限公司 | Optimized BP neural network-based biogas yield modeling calculation method and device |
| CN110161518A (en) * | 2019-05-29 | 2019-08-23 | 北京华电力拓能源科技有限公司 | A kind of volume measuring system and method for drag conveyor |
| CN111898301A (en) * | 2020-07-31 | 2020-11-06 | 上海应用技术大学 | Method for implementing soft measuring system |
| CN113805627A (en) * | 2021-09-24 | 2021-12-17 | 领先生物农业股份有限公司 | Nano-film aerobic composting Internet of things control method and device |
| CN115274004A (en) * | 2022-07-26 | 2022-11-01 | 江南大学 | Knowledge reuse-based fermentation process thallus concentration prediction method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103500280A (en) | Cell concentration online soft measurement method in glutamic acid fermentation process | |
| Gnoth et al. | Process Analytical Technology (PAT): Batch-to-batch reproducibility of fermentation processes by robust process operational design and control | |
| Mears et al. | A review of control strategies for manipulating the feed rate in fed-batch fermentation processes | |
| Pawlowski et al. | Effective utilization of flue gases in raceway reactor with event-based pH control for microalgae culture | |
| US20200202051A1 (en) | Method for Predicting Outcome of an Modelling of a Process in a Bioreactor | |
| Komives et al. | Bioreactor state estimation and control | |
| CN108090500B (en) | Soft measurement method for key parameters in fermentation production process of edible fungi | |
| Urniezius et al. | Generic estimator of biomass concentration for Escherichia coli and Saccharomyces cerevisiae fed-batch cultures based on cumulative oxygen consumption rate | |
| Jin et al. | Hybrid intelligent control of substrate feeding for industrial fed-batch chlortetracycline fermentation process | |
| CN104765347A (en) | Yield real-time prediction method in residual oil delayed coking process | |
| CN101639902A (en) | Modeling method of support vector machine (SVM)-based software measurement instrument in biological fermentation process | |
| CN106022532A (en) | Glutamic acid product concentration online estimation method and device, and monitoring system | |
| CN106950824A (en) | Stalk fermentation alcohol fuel process feeding prediction control system and method based on fuzzy neural network | |
| CN104267600B (en) | Ladle refining furnace Electrode Computer Control System and control method thereof | |
| CN1261764C (en) | Off-line double correction method for assay value based on industrial soft measurement model | |
| Matveykin et al. | Problem of control of catalytic reforming and method of its solutions | |
| CN1597918A (en) | Process and apparatus for controlling temp. of edible mushroom liquid fermentation | |
| CN101419216B (en) | Fermentation pharmacy product quality soft measurement method based on GP learning model building | |
| CN103439964A (en) | On-line updating system and method for OCSVM monitoring model | |
| Vlasenko et al. | Neural network model for predicting the resource efficiency of the defecosaturation department of a sugar factory | |
| CN101339408A (en) | Sodium aluminate solution continuous carbonation decomposition course intelligence control system | |
| Lave et al. | Towards a Digital Twin: A validated Digital Model of a Pilot Scale Bioreactor producing Green Fluorescent Protein (GFP) | |
| EP2383621A1 (en) | Yeast growth maximization with feedback for optimal control of filled batch fermentation in a biofuel manufacturing facility | |
| EP4077693B1 (en) | Method and system for prediction of a performance of a strain in a plant | |
| Halme et al. | 091 Enhancing Fermentation Development Procedures Via Artificial Neural Networks J. Giassey, B. Kara, AC Ward, GA Montague, pp 147-152 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20140108 |