CN109060684B - Intelligent measurement method based on computer program microbial fermentation process - Google Patents
Intelligent measurement method based on computer program microbial fermentation process Download PDFInfo
- Publication number
- CN109060684B CN109060684B CN201810841989.7A CN201810841989A CN109060684B CN 109060684 B CN109060684 B CN 109060684B CN 201810841989 A CN201810841989 A CN 201810841989A CN 109060684 B CN109060684 B CN 109060684B
- Authority
- CN
- China
- Prior art keywords
- request
- test
- program
- fermentation process
- module
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
- G01N21/31—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
- G01N21/3103—Atomic absorption analysis
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N35/00—Automatic analysis not limited to methods or materials provided for in any single one of groups G01N1/00 - G01N33/00; Handling materials therefor
- G01N35/00584—Control arrangements for automatic analysers
Landscapes
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
- Measuring Or Testing Involving Enzymes Or Micro-Organisms (AREA)
Abstract
The invention discloses an intelligent measurement method based on a computer program microbial fermentation process, and belongs to the field of microbial fermentation process measurement. The invention provides an intelligent microorganism fermentation process measuring system, which comprises a test switch request and test result display module, a test request processing module and a test request corresponding module; the test switch request and test result display module comprises an electronic terminal, a request program and a display program which are stored in the electronic terminal; the request processing module comprises a request data processing program and a request response data processing program; the test request response module comprises a signal receiving module and an execution mechanism. The system can accurately measure the microbial fermentation process, the measurement result can be displayed on the electronic terminal in a natural data or icon form, and the measurement starting and finishing instructions are operated on the electronic terminal without manual control, so that the intellectualization is completely realized.
Description
Technical Field
The invention relates to an intelligent measurement method based on a computer program microbial fermentation process, and belongs to the field of microbial fermentation process measurement.
Background
The microbial fermentation process is a process of obtaining a target product by using the metabolic activity of microorganisms, and in order to control the fermentation process well, important parameters in the microbial fermentation process need to be rapidly monitored by using a real-time analysis tool. The united states food and drug administration recognizes that biosensors and spectroscopic instrumentation in combination with Process Analysis Technology (PAT) are effective tools for monitoring biological fermentation processes to monitor biological, chemical and physical variables in real time throughout the fermentation process. The biosensor has the advantages of small volume and convenient use as the fermentation process monitoring, but the application range of the biosensor is not as wide as that of a spectral instrument, and some biosensors are more expensive. The advantages of monitoring the fermentation process using spectroscopic techniques are speed, sensitivity and safety.
In recent years, quantitative and qualitative analysis by combining spectroscopic techniques with chemometrics has been widely used, and the main chemometrics include a Multiple Linear Regression (MLR) method, a principal component analysis (PCR) method, a Partial Least Squares (PLS) method, and the like, wherein PLS is most widely used as near infrared spectroscopic analysis, and necessary preprocessing is required for spectral data due to high dimensionality and strong correlation of spectra. The near-infrared spectrum model is generally established by removing singular samples, dividing a sample set, selecting an interval and establishing a model. Many scholars use the spectral analysis technology to combine with a plurality of measurement methods, compare and select the optimal model and apply to various fields. The scholars make outstanding contribution to the related fields by utilizing the near infrared spectrum analysis technology, but the near infrared spectrum analysis software matched with manufacturers (such as TQAnalyst spectrum analysis software matched with an Antaris near infrared spectrometer) is low in processing precision, low in processing speed, not intuitive in processing result display, low in intelligent degree and low in test starting and closing degree, and manual control is required by people.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides an intelligent measurement method based on a computer program microbial fermentation process. The method provided by the invention provides an intelligent microbial fermentation process measuring system, wherein the system comprises a test switch request and test result display module, a test request processing module and a test request corresponding module; the method has the advantages that the microbial fermentation process can be accurately measured, the measurement result can be displayed on the electronic terminal in a natural data or icon mode, the measurement starting and finishing instructions are operated on the electronic terminal, manual control is not needed, and the intellectualization is completely realized.
The invention is realized by the following technical scheme:
the invention relates to an intelligent measuring method based on a computer program microbial fermentation process, which provides an intelligent microbial fermentation process measuring system, wherein the system comprises a test switch request and test result display module, a test request processing module and a test request corresponding module; the test switch request and test result display module comprises an electronic terminal, a request program and a display program which are stored in the electronic terminal; the request processing module comprises a request data processing program and a request response data processing program; the test request response module comprises a signal receiving module and an execution mechanism.
The request program and the display program of the electronic terminal are APP or WEB applications installed on the electronic terminal; the test request program is embodied on the APP as a button which can trigger the request to start the test and request to close the test by clicking; the display program can request the test result data from the server, can display the test result data returned by the server, and can display the data returned by the server in an icon form.
Alternatively, the electronic terminal may be, but is not limited to, a Personal Computer (PC), a tablet personal computer (PDA), and a smart phone.
The test request processing module can judge whether the request is legal or not, and sends a signal to the test request response module according to the request combination rule; the signals are a test starting signal, a test closing signal and a system abnormal signal.
The request response data processing program comprises a spectrum data analyzing program and a spectrum data calculating program; the procedure of calculating the spectral data comprises the steps of removing abnormal samples, segmenting sample sets, selecting intervals and establishing a model.
The abnormal sample elimination is as follows: calling oushi (), mashi (), mtkl () to process spectral data, calling tiuchuyichang () to process the results returned by the oushi (), mashi (), mtkl (), calling the oushi () is a computer program written by java according to the idea of the European distance method, and calling the mashi () is a computer program written by java according to the idea of the European distance method; the mtkl () is a computer program written using java according to the monte carlo concept.
The code of the oushi () method is as follows:
the mashi () method code is:
the mtkl () method code is:
the processing flow of the segmentation sample set comprises the following steps: java file, execute getSpxy () function, return result; java is the getSpxy () method code used to partition the correction set and validation set samples is:
the processing flow of the selected interval is to read an AlgorithmsController. java file and execute a getSiPLS () function; returning to the interval range; the getSiPLS () function calls a SiPLS service written by python, the input of the SiPLS is all samples of a correction set, and the output is a joint interval with minimum self-correcting error, and the method comprises the following steps: firstly, dividing the characteristic wavelength of a sample into 5 equal parts, combining 2 equal parts to establish a partial least square model, wherein the partial least square model is PLSEGRESS of a python library function of skleern cross _ decomposition, judging whether the sample is good or bad by adopting self-correcting root mean square error, and selecting an optimal combined interval. The SiPLS () core code is as follows:
print ("best RMSECV ═ minresult [0]," interval: [ ", minresult [1],", ",", minresult [2], "]").
The method comprises the steps of reading an AlgorithmsController.java file, executing a getPLS () function, calling a PLS service written by python, inputting the function into a correction set and a verification set, and outputting the function as an optimal model.
The test request response module comprises a signal receiving module and an actuating mechanism; the signal receiving module can receive the signal sent by the signal request processing module and can control the actuating mechanism according to the signal sent by the signal request processing module; the actuating mechanism is a modified spectrometer, a switch part of the spectrometer is connected with a relay, and the relay is attracted and disconnected according to a signal sent by the signal receiving and receiving module, so that the spectrometer is controlled to start working and disconnect working.
Drawings
FIG. 1 is a block diagram of an intelligent measurement system for a microbial fermentation process.
FIG. 2 is a flow chart of an intelligent measurement system for microbial fermentation processes.
Fig. 3 is a flowchart of a request response data processing program.
Fig. 4 is a culling sample flow diagram.
Fig. 5 is an mtkl () function flowchart.
Fig. 6 is a flowchart of the getSpxy () function.
Figure 7 is a flowchart of the getSiPLS () function.
Fig. 8 is a getPLS () function flow diagram.
Fig. 9 is an electronic terminal display diagram.
Fig. 10 is a graph showing the result of data analysis by conventional software.
Detailed Description
The following detailed description of embodiments of the invention is provided in conjunction with the accompanying drawings: the present embodiment is implemented on the premise of the technical solution of the present invention, and a detailed implementation manner and a process are given, but the scope of the present invention is not limited to the following embodiments.
Example 1:
building system
As shown in FIG. 1, an intelligent measurement system for the microbial fermentation process is constructed. The stm32 is used as a main controller, and a peripheral circuit and a WIFI module form a signal receiving module (1); a spectrometer is used as an actuating mechanism (2), and a relay (3) is used for connecting the signal receiving module (1) and the actuating mechanism (2); the signal receiving module (1), the relay (3) and the actuating mechanism (2) form a test request response module; using the computer (4) to store a request processing module program and a request data response module program; the method comprises the steps that a smart phone is used as an electronic terminal (5), and a switch request and test result display module program is stored in the electronic terminal (5); the computer (4) is in contact with the test request response module through a WIFI wireless network; and the test switch request and the test result display module program stored on the electronic terminal are interacted with the request processing module program and the request data response module program through http.
Second, use the system test
Opening a test switch request program on a smart phone serving as an electronic terminal, and clicking to start testing; the test switch request program sends a request for starting a test, the request processing program receives the detected request information, analyzes the request information and verifies whether the request information is legal, if the request information is legal, a signal for starting the test is sent to the request response module, and after the signal receiving module of the request response module receives the signal for starting the test, a level signal is output to the relay, the relay is automatically closed, the spectrometer is opened, and scanning is carried out; and transmitting the scanned data to a computer (4) through WIFI, analyzing the returned data by a data response processing program stored in the computer (4), reading an ALMCONTROLLER.java file after analysis, and sequentially executing tihuyiichang (), getSpxy, getSiPLS and getPLS () in the ALMCONTROLLER.java file. When the tchuyichang () is executed, the method calls oushi (), mashi (), mtkl (), returns values of the three functions are transmitted to the tchuyichang (), a result returned after the tchuyichang () method is executed is transmitted to getSpxy () as a parameter, a result returned by the getSpxy () method is transmitted to getSiPLS () as a parameter, a result returned by the getSiPLS () is transmitted to getPLS () as a parameter, a result returned by the getPLS () function is stored, and when a test result display module program stored in the electronic terminal requests data from a data response program, the data is transmitted to a test result display module for display.
Thirdly, verifying the test result
In order to verify the effectiveness of the method, the root mean square error is adopted for comparison, the root mean square error reflects the error magnitude between the predicted value and the real value, and the smaller the root mean square error is, the closer the predicted result is to the real value is. For the same spectral sample data, the root mean square error of the spectral analysis software is much larger than that of the present invention. The verification steps are as follows: and taking the predicted values of the verification sets and the true values of the verification sets as input, calculating the difference values of the predicted values and the true values of all the verification sets, dividing the sum of squares by the number of the verification sets, and finally, forming a Root Mean Square Error (RMSE).
The root mean square error result obtained by the spectroscopy software was 5.32 as shown in figure 10, whereas the root mean square error result obtained by the present invention was 1.0526.
The invention provides an intelligent microorganism fermentation process measuring system, which comprises a test switch request and test result display module, a test request processing module and a test request corresponding module; the test switch request and test result display module comprises an electronic terminal, a request program and a display program which are stored in the electronic terminal; compared with the prior art, the technical scheme for testing the glucose concentration in the fermentation process by constructing an intelligent microorganism fermentation process measuring system has the beneficial effects that: the measurement result is more accurate, the measured data is more visual, the intelligent degree is high, and manual control is not needed.
Although the present invention has been described with reference to the preferred embodiments, it should be understood that various changes and modifications can be made therein by those skilled in the art without departing from the spirit and scope of the invention as defined in the appended claims.
Claims (5)
1. A method for measuring the fermentation process of microorganisms is characterized in that an intelligent system for measuring the fermentation process of microorganisms is provided to realize the automatic measurement of the fermentation process of the microorganisms, and the system comprises a test switch request and test result display module, a test request processing module and a test request response module; the test switch request and test result display module comprises an electronic terminal, a request program and a display program which are stored in the electronic terminal; the request processing module comprises a request data processing program and a request response data processing program; the test request response module comprises a signal receiving module and an actuating mechanism;
the signal receiving module can receive the signal sent by the signal request processing module and can control the actuating mechanism according to the signal sent by the signal request processing module; the actuating mechanism is a modified spectrometer, a switch part of the spectrometer is connected with a relay, and the relay is closed and opened according to a signal sent by the signal receiving module;
the request response data processing program comprises a spectrum data analyzing program and a spectrum data calculating program; the procedure of calculating the spectral data comprises the steps of removing abnormal samples, dividing sample sets, selecting intervals and establishing a model; the abnormal sample elimination is as follows: calling oushi (), mashi (), mtkl () to process spectral data, calling tiuchuyichang () to process the results returned by the oushi (), mashi (), mtkl (), calling the oushi () is a computer program written by java according to the idea of the European distance method, and calling the mashi () is a computer program written by java according to the idea of the European distance method; the mtkl () is a computer program written by python according to the Monte Carlo idea and then called by java;
the request program and the display program of the electronic terminal are APP or WEB applications installed on the electronic terminal; the test request program is embodied on the APP and can trigger a button for requesting to start the test and requesting to close the test by clicking; the display program can request the test result data from the server, can display the test result data returned by the server, and can display the data returned by the server in an icon form.
2. The method according to claim 1, wherein the electronic terminal is a Personal Computer (PC) or a tablet personal computer (PDA) or a smart phone.
3. The method of claim 1, wherein the split sample set processing procedure is: java file, execute getSpxy () function, return result; java is a correction set and a verification set for dividing samples, inputting all samples, gradually selecting the samples of the correction set by adopting an X-Y distance method, and outputting the selected correction set; the getSpxy () function is configured to pass the returned result as a parameter to a getSiPLS () function, where the getSiPLS () function calls python to write a SiPLS service, and the SiPLS input is all samples of the correction set and output is the union interval with the minimum self-correction error.
4. The method of claim 3, wherein the process flow of selecting the interval is reading an AlgorithmsController. java file, executing getSiPLS () function; returning to the interval range; the getSiPLS () function calls python to write the SiPLS service, the input of the SiPLS is all samples of the correction set, and the output is the joint interval with the minimum self-correcting error, and the steps are as follows: firstly, dividing the characteristic wavelength of a sample into 5 equal parts, establishing a partial least square model by combining 2 equal parts, wherein the partial least square model is PLSR (partial least squares) with a python library function of skleern. cross _ decomposition, judging an interval by adopting a self-correcting root mean square error, and selecting an interval range.
5. The method of claim 4, wherein the modeling comprises: java file is read, getPLS () function is executed, which is PLS service written by calling python, input is correction set and verification set, output is best model, including: and calling a PLSR regression library of python to establish a model for the correction set, performing model test on the verification set, and returning constant terms and coefficients in the model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810841989.7A CN109060684B (en) | 2018-07-27 | 2018-07-27 | Intelligent measurement method based on computer program microbial fermentation process |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810841989.7A CN109060684B (en) | 2018-07-27 | 2018-07-27 | Intelligent measurement method based on computer program microbial fermentation process |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109060684A CN109060684A (en) | 2018-12-21 |
| CN109060684B true CN109060684B (en) | 2020-11-06 |
Family
ID=64835817
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810841989.7A Active CN109060684B (en) | 2018-07-27 | 2018-07-27 | Intelligent measurement method based on computer program microbial fermentation process |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109060684B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105891146A (en) * | 2016-03-29 | 2016-08-24 | 电子科技大学 | Intelligent terminal for spectrum detection and detection method thereof |
| CN106130849A (en) * | 2016-02-01 | 2016-11-16 | 广州华睿电子科技有限公司 | A kind of intelligent switch control system |
| CN106775184A (en) * | 2015-11-25 | 2017-05-31 | 五八同城信息技术有限公司 | APP tabs exhibiting method and electronic equipment |
| CN107860473A (en) * | 2017-10-25 | 2018-03-30 | 暨南大学 | A kind of intelligent handhold spectrometer based on cloud data |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI446088B (en) * | 2010-03-25 | 2014-07-21 | Hon Hai Prec Ind Co Ltd | Device with lens switch function |
| WO2014043288A1 (en) * | 2012-09-12 | 2014-03-20 | Butamax Advanced Biofuels Llc | Processes and systems for the production of fermentation products |
| CN104062256B (en) * | 2013-04-15 | 2016-12-28 | 山东东阿阿胶股份有限公司 | A kind of flexible measurement method based near infrared spectrum |
| CN104034692A (en) * | 2014-05-16 | 2014-09-10 | 安徽农业大学 | Method for identifying quality of Congou black tea based on near infrared spectrum combined with catcchins analysis technology |
| CN105548064B (en) * | 2015-12-15 | 2019-04-30 | 驻马店华中正大有限公司 | The method for producing multiple nutritional components and titer of antibodies variation during antibiotic using near infrared ray microbial fermentation |
| CN106290240A (en) * | 2016-08-29 | 2017-01-04 | 江苏大学 | A kind of method based on near-infrared spectral analysis technology to Yeast Growth curve determination |
| CN106645009B (en) * | 2016-11-07 | 2019-08-09 | 江南大学 | Penicillin fermentation production process multi-model monitoring system based on near-infrared spectral analysis technology |
-
2018
- 2018-07-27 CN CN201810841989.7A patent/CN109060684B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106775184A (en) * | 2015-11-25 | 2017-05-31 | 五八同城信息技术有限公司 | APP tabs exhibiting method and electronic equipment |
| CN106130849A (en) * | 2016-02-01 | 2016-11-16 | 广州华睿电子科技有限公司 | A kind of intelligent switch control system |
| CN105891146A (en) * | 2016-03-29 | 2016-08-24 | 电子科技大学 | Intelligent terminal for spectrum detection and detection method thereof |
| CN107860473A (en) * | 2017-10-25 | 2018-03-30 | 暨南大学 | A kind of intelligent handhold spectrometer based on cloud data |
Non-Patent Citations (1)
| Title |
|---|
| Smartphone Spectrometers;Andrew J. S. McGonigle et al;《Sensors》;20180114;第18卷;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109060684A (en) | 2018-12-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105116156B (en) | A kind of biochemical detection methods of the suitable medical test of optimization | |
| CN110455722A (en) | Rubber tree blade phosphorus content EO-1 hyperion inversion method and system | |
| CN107703097B (en) | Method for constructing model for rapidly predicting crude oil property by using near-infrared spectrometer | |
| CN102590129B (en) | Method for detecting content of amino acid in peanuts by near infrared method | |
| CN101936912A (en) | Method and device for detecting freshness of fish based on olfaction visualization | |
| White et al. | Methodological tools | |
| CN105628644A (en) | Device and method for on-line monitoring of protein enzymolysis process based on in-situ real-time spectrum | |
| CN101206463A (en) | Method and system for on-line monitoring medicaments production mixing process | |
| CN106932360A (en) | Portable near infrared spectrum food science literature and modeling integral system and method | |
| CN105334185A (en) | Spectrum projection discrimination-based near infrared model maintenance method | |
| CN102876816A (en) | Fermentation process statue monitoring and controlling method based on multi-sensor information fusion | |
| Henriques et al. | Monitoring mammalian cell cultivations for monoclonal antibody production using near-infrared spectroscopy | |
| Xia et al. | Simultaneous, rapid and nondestructive determination of moisture, fat content and storage time in leisure dried tofu using LF-NMR | |
| CN112651173B (en) | Agricultural product quality nondestructive testing method based on cross-domain spectral information and generalizable system | |
| CN106814045A (en) | A kind of class PSE chicken decision methods based on near-infrared spectrum technique | |
| Reis et al. | Prediction of profiles in the process industries | |
| CN109060684B (en) | Intelligent measurement method based on computer program microbial fermentation process | |
| US7420170B2 (en) | Fourier transform infrared (FTIR) chemometric method to determine cetane number of diesel fuels containing fatty acid alkyl ester additives | |
| Cozzolino et al. | The use of correlation, association and regression to analyse processes and products | |
| CN111289459A (en) | Method, device, equipment and storage medium for detecting component concentration of mixed substance | |
| Gorla et al. | Process understanding and monitoring: A glimpse into data strategies for miniaturized NIR spectrometers | |
| Mei et al. | Study of an adaptable calibration model of near-infrared spectra based on KF-PLS | |
| CN113222268B (en) | Multi-mode reasoning-based tobacco baking quality prediction model establishment method | |
| JP2005127757A (en) | Automatic analyzer | |
| CN112257017B (en) | Unitary linear point-by-point analysis method, system and device for standardized residual error detection method |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |