CN103267740A - Straw fermentation process characteristic wave number soft instrument apparatus and construction method thereof - Google Patents
Straw fermentation process characteristic wave number soft instrument apparatus and construction method thereof Download PDFInfo
- Publication number
- CN103267740A CN103267740A CN2012105565555A CN201210556555A CN103267740A CN 103267740 A CN103267740 A CN 103267740A CN 2012105565555 A CN2012105565555 A CN 2012105565555A CN 201210556555 A CN201210556555 A CN 201210556555A CN 103267740 A CN103267740 A CN 103267740A
- Authority
- CN
- China
- Prior art keywords
- wave number
- sample
- stalk
- spectrometer
- soft instrument
- 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
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The present invention discloses a straw fermentation process characteristic wave number soft instrument construction method. Near infrared spectra and on-line instrument data for samples and experiment process are simultaneously acquired by a computer. By analyzing the characteristics of standard deviation of sample data, a sensitive wavelength for the sample to-be-tested is a characteristic wave number, a non-linear statistical model between the absorbance of the characteristic wave number in the fermentation process and process unavailable online testing data characteristics is established, and thus the soft instrument construction is realized. The invention also discloses an apparatus using the method, comprising a halogen light source, a Y-type fiber probe and a spectrometer. The light of the halogen light source is led out by Y-type optical fibers; the Y-type fiber probe is used for collecting diffuse reflection light in a timing used product sample in solid fermentation process and transmitting the light into the spectrometer; the spectrometer is used for analyzing received spectral signals, which are transferred into digital signals by A/D conversion and then transmitted into the computer by a data line. The invention is fast to select a characteristic wave number, has small number in characteristic wave number and is highly accurate in the soft instrument model.
Description
Technical field
The present invention relates to a kind of solid ferment process parameter soft instrument and building method thereof based near infrared spectrum, belong to solid ferment process detection technique field.
Background technology
Along with the development of agricultural biotechnologies, with biotechnology particularly the microbial fermentation means handle stalk, make it become feed stripped source, can not only promote China's Developing of Animal Industry, and can improve agroecological environment, and realize taking full advantage of of resource, turn waste into wealth.
Off-line chemical experiment method is generally all adopted in the detection of solid ferment process key parameter index, and key parameters such as the environment temperature in the solid ferment process, material moisture and pH value all are attempting the back and determine optimal conditions of fermentation through test of many times, then by each major parameter index of artificial experience control reactor.Though the result of chemical detection method is objective credible, in steps loaded down with trivial details, detection time shortcoming such as length, testing cost height, and off-line measurement has brought a lot of inconvenience for control and the optimization of Fermentation Engineering.Therefore, be unfavorable for realizing optimal control to whole fermentation process status information variable.
Near-infrared spectral analysis technology has fast, can't harm, accurately, polycomponent such as detects simultaneously at advantage, is to be suitable for one of mature technology that is implemented in line analysis and control in real time.But the application of near-infrared spectral analysis technology in solid ferment process is subjected to the influence of magnanimity spectroscopic data, seeks the feature wave number and has difficulties.
Summary of the invention
The objective of the invention is: the difficult problem for existing the spectral signature wave number to select in the stalk solid ferment process self-adaptation soft instrument that overcomes existing near infrared spectrum and the building method thereof provides a kind of stalk fermentation process feature wave number soft instrument device and building method thereof.
The objective of the invention is to realize in the following manner:
(1) physico-chemical analysis carries out the fixed cycle sampling to stalk solid ferment process sample, utilizes off-line physico-chemical analysis method to obtain the reference measurement values of sweat key parameter index, and sets up database;
(2) utilize diffuse reflection type near infrared spectrum system and device to come these samples are carried out the collection of near infrared spectrum data, computing machine carries out pre-service to the raw data that obtains, and utilizes the system of selection of variance wave number to select the feature wave number;
(3) the key parameter value measured in the corresponding absorbance of the feature wave number of extracting and the database of setting up is previously undertaken related by non-linear statistical models (as neural network etc.) method for building up, set up solid ferment process key parameter soft instrument model;
(4) for sweat product sample to be measured, by gathering spectroscopic data and the information extraction of feature wave number, utilize this soft instrument model to finish the real-time detection of sample to be tested key parameter.
The collection of described near infrared spectrum data specifically is stalk solid ferment process product sample to be taken by weighing put into sample cup (spectrometer standard fitting) about 40g, and places it on the objective table; Near infrared spectrometer is connected with objective table by y-type optical fiber, and the spectral signal of collection imports near infrared spectrometer into by y-type optical fiber, is being reached in the computing machine by the data line that is connected between computing machine and the spectrometer.
Described soft instrument model is the statistical models of the stalk solid ferment process product key parameter index of near infrared spectrum characteristic signal and timing sampling.The general process that model is set up is: at first collect the different fermentations process product sample of batch different fermentations time (generally greater than 80), with reference to the concerned countries standard, record the crucial ginseng value of the solid-state process product of stalk by off-line physico-chemical analysis method, gathering all then collects the near infrared spectrum of sample and it is carried out pre-service, extract the feature wave number according to above-mentioned variance wave number choosing method again, and set up statistical models between the reference value of the corresponding absorbances of these feature wave numbers and the solid-state process product key parameter of stalk index, utilization non-linear regression method (neural network etc.) is set up the soft-sensing model of the solid-state process product key parameter of stalk index.
Near infrared spectra collection device described above comprises halogen light source, y-type optical fiber probe and spectrometer etc., wherein:
Halogen light source, it is only drawn by y-type optical fiber, and it is shone on the surface of stalk solid ferment process product sample to be tested of timing sampling;
The y-type optical fiber probe is used for gathering the light that diffuse reflection is come out in the solid ferment process product sample that regularly adopts, and reaches spectrometer;
Spectrometer is used for the spectral signal that receives is analyzed, and changes it into electric signal, imports computing machine into by the data line that is connected between spectrometer and the computing machine again after being converted to digital signal by A/D then.
The invention has the beneficial effects as follows:
By gathering the near infrared spectrum data of sweat product sample, the original spectrum data of obtaining are carried out pre-service and passed through the variance wave number choosing method selected characteristic wave number of putting forward, set up the non-linear soft-sensing model of stalk solid ferment process key parameter index again in conjunction with off-line physico-chemical analysis methods and results.Sample to be tested extracts by corresponding spectrum data gathering, the pre-service of original spectrum data and characteristic information, and the soft instrument model that recycling has been set up is predicted the property value of this sample key parameter index.
The present invention compares with classic method, and the selected characteristic wavenumber velocity is fast, and characteristic wave keeps count of few, soft instrument model accuracy height.
Description of drawings
Fig. 1 is the synoptic diagram of stalk fermentation process feature wave number soft instrument building method technical scheme of the present invention;
Fig. 2 is stalk fermentation process feature wave number soft instrument schematic representation of apparatus of the present invention;
Among the figure: 1, sample cup; 2, objective table; 3, y-type optical fiber; 4, computing machine; 5, data line; 6, near infrared spectrometer.
Embodiment
The invention provides the system of selection of a kind of wave number of feature fast, and set up non-linear soft-sensing model based on such selection, thereby proposed corresponding building method.And corresponding non-linear soft-sensing model modeling method proposed.Gather the near infrared spectrum data of stalk solid ferment process product by diffuse reflection type near infrared spectrum system and device, the spectral signal of being gathered imports computing machine into by data line after the spectrometer analysis conversion, to the original spectrum data N lot sample basis that obtains, the corresponding absorbance of each wave number is done variance analysis, and then find out the maximum value of this variance curve, the wave number of this maximum value correspondence is the feature wave number; Be input with feature wave number absorbance again, physico-chemical analysis result (pH, biomass etc.) sets up non-linear soft instrument model for output.This feature wave number system of selection is called the system of selection of variance wave number hereinafter.
The present invention has versatility to the fast detecting of stalk solid ferment process key parameter.The present invention only lifts an embodiment that is used for stalk protein feed solid ferment process product pH fast detecting, and remaining can be with reference to the method for this embodiment.
Example performing step of the present invention is consulted Fig. 1, and the example implement device is consulted Fig. 2.At first, the stalk protein feed solid ferment process product sample (generally greater than 80) of collecting different fermentations batch, different fermentations time is used for setting up soft instrument, utilizes the near infrared spectra collection device that the sample of collecting is carried out the near infrared spectrum data collection; Secondly, with reference to the concerned countries standard, record the solid-state process product key parameter of stalk protein feed by the physico-chemical analysis method, as the reference measurement values of indexs such as protein content, pH value and humidity; Again, the original spectrum data of gathering are carried out the spectrum pre-service after, utilize above-mentioned variance wave number choosing method characteristic variable; At last, the corresponding absorbances of these characteristic variables and the reference measurement values of the solid-state process product key parameter of stalk protein feed index are carried out related, utilization non-linear regression method (neural network) is set up the soft instrument model of the solid-state process product key parameter of stalk protein feed index.
For the unknown stalk protein feed to be measured solid ferment process product sample, the sweat product that at every turn takes by weighing about 40g is put into sample cup (spectrometer standard fitting) 1, sample cup 1 is positioned on the objective table 2, the light that sends of Halogen lamp LED in the near infrared spectrometer 6 shines on the sweat product sample through y-type optical fiber 3 then, and in the inner formation of this sample diffuse reflection, the light that diffuse reflection is come out enters near infrared spectrometer 6 through y-type optical fiber 3 again, and the spectral signal that obtains imports computing machine 4 into by data line 5 after the spectrometer analysis conversion.Finishing pre-service and the feature wave number of original spectrum data in computing machine extracts, and the soft instrument model that the corresponding absorbance substitution of the feature wave number of extracting has been set up, corresponding key parameter value that just can the fast prediction sample to be tested, and be presented on the computer interface.So far key parameter value soft instrument that should the unknown sweat product to be measured sample is measured and is finished.
Claims (6)
1. stalk fermentation process feature wave number soft instrument building method, it is characterized in that: by computing machine sample and experimentation are gathered near infrared light spectral apparatus and in-line meter data simultaneously, by analyzing samples data standard difference feature, finding out the sample sensitive wave length is the feature wave number, set up sweat feature wave number absorbance and the process non-linear statistical models between can not online detection data characteristics, realize the structure of its soft instrument; Concrete steps are:
(1) physico-chemical analysis carries out the fixed cycle sampling to stalk solid ferment process sample, utilizes off-line physico-chemical analysis method to obtain the reference measurement values of sweat key parameter index, and sets up database;
(2) utilize diffuse reflection type near infrared spectrum system and device to come these samples are carried out the collection of near infrared spectrum data, computing machine carries out pre-service to the raw data that obtains, and utilizes the system of selection of variance wave number to select the feature wave number;
(3) the key parameter value of measuring in the corresponding absorbance of the feature wave number of extracting and the database of setting up is previously undertaken related by non-linear statistical models method for building up, set up solid ferment process key parameter soft instrument model;
(4) for sweat product sample to be measured, by gathering spectroscopic data and the information extraction of feature wave number, utilize this soft instrument model to finish the real-time detection of sample to be tested key parameter.
2. stalk fermentation process feature wave number soft instrument building method according to claim 1, it is characterized in that: the collection of the near infrared spectrum data in the described step (2), be stalk solid ferment process product sample to be taken by weighing put into sample cup about 40g, and place it on the objective table; Near infrared spectrometer is connected with objective table by y-type optical fiber, and the spectral signal of collection imports near infrared spectrometer into by y-type optical fiber, is reached in the computing machine by the data line that is connected between computing machine and the spectrometer again.
3. stalk fermentation process feature wave number soft instrument building method according to claim 2, it is characterized in that: described sample cup is the spectrometer standard fitting.
4. according to any described stalk fermentation process feature wave number soft instrument building method in the claim 1 to 3, it is characterized in that: described soft instrument model is the statistical models of the stalk solid ferment process product key parameter index of near infrared spectrum characteristic signal and timing sampling; Modeling process is:
(1) the process product sample of collection different fermentations batch different fermentations time with reference to the concerned countries standard, records the crucial ginseng value of the solid-state process product of stalk by off-line physico-chemical analysis method;
(2) gathering all collects the near infrared spectrum of sample and it is carried out pre-service;
(3) extract the feature wave number according to variance wave number choosing method, and set up statistical models between the reference value of the corresponding absorbances of these feature wave numbers and the solid-state process product key parameter of stalk index, the utilization non-linear regression method is set up the soft-sensing model of the solid-state process product key parameter of stalk index.
5. stalk fermentation process feature wave number soft instrument building method according to claim 4 is characterized in that: the feature wave number in the step (3) is the corresponding wave number of sample variance local maximum.
6. application rights requires the stalk fermentation process feature wave number soft instrument device of any described stalk fermentation process feature wave number soft instrument building method in 1 to 5, it is characterized in that: comprise halogen light source, y-type optical fiber probe and spectrometer, wherein:
Halogen light source, it is only drawn by y-type optical fiber, and it is shone on the surface of stalk solid ferment process product sample to be tested of timing sampling;
The y-type optical fiber probe is used for gathering the light that diffuse reflection is come out in the solid ferment process product sample that regularly adopts, and reaches spectrometer;
Spectrometer is used for the spectral signal that receives is analyzed, and changes it into electric signal, imports computing machine into by the data line that is connected between spectrometer and the computing machine again after being converted to digital signal by A/D then.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2012105565555A CN103267740A (en) | 2012-12-20 | 2012-12-20 | Straw fermentation process characteristic wave number soft instrument apparatus and construction method thereof |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2012105565555A CN103267740A (en) | 2012-12-20 | 2012-12-20 | Straw fermentation process characteristic wave number soft instrument apparatus and construction method thereof |
Publications (1)
Publication Number | Publication Date |
---|---|
CN103267740A true CN103267740A (en) | 2013-08-28 |
Family
ID=49011379
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN2012105565555A Pending CN103267740A (en) | 2012-12-20 | 2012-12-20 | Straw fermentation process characteristic wave number soft instrument apparatus and construction method thereof |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103267740A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103558406A (en) * | 2013-09-30 | 2014-02-05 | 江苏大学 | Measuring method for hammerhead speed of hydraulic forging hammer system based on soft instrument |
CN105092524A (en) * | 2015-08-31 | 2015-11-25 | 浙江大学 | System for detecting total solid content of fermentation liquid in mixed continuous anaerobic fermentation process of water hyacinths and rice straws |
CN105181635A (en) * | 2015-08-31 | 2015-12-23 | 浙江大学 | Detection system for volatile solid content in fermentation broth during Eichhornia crassipes and rice straw mixing continuous anaerobic fermentation process |
CN112444500A (en) * | 2020-11-11 | 2021-03-05 | 东北大学秦皇岛分校 | Alzheimer's disease intelligent detection device based on spectrum |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101419166A (en) * | 2008-11-18 | 2009-04-29 | 江苏大学 | Tea quality nondestructive detecting method and device based on near-infrared spectrum and machine vision technology |
CN101498667A (en) * | 2009-02-16 | 2009-08-05 | 浙江大学 | Method for detecting ethylene or ethylene propylene rubber content in ethylene-propylene copolymerization polypropylene |
CN102313713A (en) * | 2011-07-14 | 2012-01-11 | 浙江大学 | Rapid detection method of abundance of tracer isotope <15>N in plant based on midinfrared spectrum |
CN102539375A (en) * | 2012-01-10 | 2012-07-04 | 江苏大学 | Straw solid-state fermentation process parameter soft measurement method and device based on near infrared spectrum |
-
2012
- 2012-12-20 CN CN2012105565555A patent/CN103267740A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101419166A (en) * | 2008-11-18 | 2009-04-29 | 江苏大学 | Tea quality nondestructive detecting method and device based on near-infrared spectrum and machine vision technology |
CN101498667A (en) * | 2009-02-16 | 2009-08-05 | 浙江大学 | Method for detecting ethylene or ethylene propylene rubber content in ethylene-propylene copolymerization polypropylene |
CN102313713A (en) * | 2011-07-14 | 2012-01-11 | 浙江大学 | Rapid detection method of abundance of tracer isotope <15>N in plant based on midinfrared spectrum |
CN102539375A (en) * | 2012-01-10 | 2012-07-04 | 江苏大学 | Straw solid-state fermentation process parameter soft measurement method and device based on near infrared spectrum |
Non-Patent Citations (2)
Title |
---|
刘国海 等: "基于IRLS-ELM 生物发酵在线软测量建模方法", 《东南大学学报(自然科学版)》 * |
刘国海 等: "近红外光谱结合ELM快速检测固态发酵过程参数pH值", 《光谱学与光谱分析》 * |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103558406A (en) * | 2013-09-30 | 2014-02-05 | 江苏大学 | Measuring method for hammerhead speed of hydraulic forging hammer system based on soft instrument |
CN103558406B (en) * | 2013-09-30 | 2015-09-30 | 江苏大学 | A kind of hydraulic forging hammer system ram velocity measuring method based on soft instrument |
CN105092524A (en) * | 2015-08-31 | 2015-11-25 | 浙江大学 | System for detecting total solid content of fermentation liquid in mixed continuous anaerobic fermentation process of water hyacinths and rice straws |
CN105181635A (en) * | 2015-08-31 | 2015-12-23 | 浙江大学 | Detection system for volatile solid content in fermentation broth during Eichhornia crassipes and rice straw mixing continuous anaerobic fermentation process |
CN112444500A (en) * | 2020-11-11 | 2021-03-05 | 东北大学秦皇岛分校 | Alzheimer's disease intelligent detection device based on spectrum |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN101308086B (en) | Fruit internal quality on-line checking apparatus based on near infrared spectra technology | |
CN101620180B (en) | Method for rapidly detecting tea quality through near infrared technology | |
CN102539375A (en) | Straw solid-state fermentation process parameter soft measurement method and device based on near infrared spectrum | |
CN102590129B (en) | Method for detecting content of amino acid in peanuts by near infrared method | |
CN101210875A (en) | Damage-free measurement method for soil nutrient content based on near infrared spectra technology | |
CN101915738A (en) | Method and device for rapidly detecting nutritional information of tea tree based on hyperspectral imaging technique | |
CN104048939A (en) | Near infrared rapid detection method for blood sugar content in live pig blood | |
CN102252972B (en) | Near infrared spectrum based detection method for rapid discrimination of oil-tea camellia seed oil real property | |
CN103018181A (en) | Soft measurement method based on correlation analysis and ELM neural network | |
CN101059426A (en) | Method for non-destructive measurement for tea polyphenol content of tea based on near infrared spectrum technology | |
CN103411906B (en) | The near infrared spectrum qualitative identification method of pearl powder and oyster shell whiting | |
CN104111234A (en) | Method and device for online detection of biomass basic characteristics based on near infrared spectroscopy | |
CN101221125A (en) | Method for measuring eutrophication water body characteristic parameter by spectrum technology | |
CN106018332A (en) | Near-infrared-spectrum citrus yellow shoot disease field detection method | |
CN103645155A (en) | Quick nondestructive testing method for tenderness of fresh mutton | |
CN102288670A (en) | Method for detecting age of yellow wine | |
CN103267740A (en) | Straw fermentation process characteristic wave number soft instrument apparatus and construction method thereof | |
CN103808688A (en) | Rapid non-destructive detection on quality consistency of finished medicine product by using near-infrared spectroscopy | |
CN102393376A (en) | Support vector regression-based near infrared spectroscopy for detecting content of multiple components of fish ball | |
CN102876816A (en) | Fermentation process statue monitoring and controlling method based on multi-sensor information fusion | |
CN104034691A (en) | Rapid detection method for beta vulgaris quality | |
CN104568815A (en) | Method for quickly and nondestructively detecting content of volatile basic nitrogen in fresh beef | |
CN108827907A (en) | It is a kind of based near infrared spectrum to the rapid assay methods of color cotton coloration | |
CN104502307A (en) | Method for quickly detecting content of glycogen and protein of crassostrea gigas | |
CN103760130B (en) | The method of Tween-80 content near infrared ray compound Moschus injection |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C12 | Rejection of a patent application after its publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20130828 |