CN110749555B - Hyperspectral technology-based device and method for detecting internal fermentation state of white spirit koji - Google Patents
Hyperspectral technology-based device and method for detecting internal fermentation state of white spirit koji Download PDFInfo
- Publication number
- CN110749555B CN110749555B CN201911042816.XA CN201911042816A CN110749555B CN 110749555 B CN110749555 B CN 110749555B CN 201911042816 A CN201911042816 A CN 201911042816A CN 110749555 B CN110749555 B CN 110749555B
- Authority
- CN
- China
- Prior art keywords
- koji
- block
- hyperspectral
- hyperspectral data
- fermentation
- 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
- 238000000855 fermentation Methods 0.000 title claims abstract description 162
- 230000004151 fermentation Effects 0.000 title claims abstract description 162
- 238000000034 method Methods 0.000 title claims abstract description 36
- 238000005516 engineering process Methods 0.000 title claims abstract description 20
- 238000013178 mathematical model Methods 0.000 claims abstract description 28
- 238000012545 processing Methods 0.000 claims abstract description 23
- 230000003595 spectral effect Effects 0.000 claims abstract description 17
- 238000013135 deep learning Methods 0.000 claims abstract description 16
- 230000006870 function Effects 0.000 claims abstract description 10
- 238000001514 detection method Methods 0.000 claims description 57
- 230000033001 locomotion Effects 0.000 claims description 29
- 238000001228 spectrum Methods 0.000 claims description 24
- 239000000463 material Substances 0.000 claims description 20
- 230000005540 biological transmission Effects 0.000 claims description 17
- 230000008859 change Effects 0.000 claims description 10
- 238000004891 communication Methods 0.000 claims description 10
- 244000005700 microbiome Species 0.000 claims description 10
- 238000013499 data model Methods 0.000 claims description 7
- 238000003860 storage Methods 0.000 claims description 7
- 238000007789 sealing Methods 0.000 claims description 6
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Chemical compound O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 6
- 238000012937 correction Methods 0.000 claims description 5
- 238000003780 insertion Methods 0.000 claims description 5
- 230000037431 insertion Effects 0.000 claims description 5
- 238000012986 modification Methods 0.000 claims description 5
- 230000004048 modification Effects 0.000 claims description 5
- 239000000126 substance Substances 0.000 claims description 3
- 238000005452 bending Methods 0.000 claims 1
- 238000005259 measurement Methods 0.000 abstract description 9
- 239000007787 solid Substances 0.000 abstract description 3
- 240000004808 Saccharomyces cerevisiae Species 0.000 description 27
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 description 10
- 229910002092 carbon dioxide Inorganic materials 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 5
- 239000001569 carbon dioxide Substances 0.000 description 5
- 230000007613 environmental effect Effects 0.000 description 5
- 229910052760 oxygen Inorganic materials 0.000 description 5
- 239000001301 oxygen Substances 0.000 description 5
- 238000013480 data collection Methods 0.000 description 4
- 238000013124 brewing process Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000010563 solid-state fermentation Methods 0.000 description 3
- 239000007858 starting material Substances 0.000 description 3
- 230000015572 biosynthetic process Effects 0.000 description 2
- 238000012217 deletion Methods 0.000 description 2
- 230000037430 deletion Effects 0.000 description 2
- 229910052736 halogen Inorganic materials 0.000 description 2
- 150000002367 halogens Chemical class 0.000 description 2
- 230000010365 information processing Effects 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 239000003205 fragrance Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 238000010223 real-time analysis Methods 0.000 description 1
- 238000002310 reflectometry Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 239000000725 suspension Substances 0.000 description 1
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
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/70—Machine learning, data mining or chemometrics
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- Crystallography & Structural Chemistry (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Artificial Intelligence (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
- Measuring Or Testing Involving Enzymes Or Micro-Organisms (AREA)
Abstract
The invention discloses a device and a method for detecting the internal fermentation state of a white spirit koji block based on a hyperspectral technology. The method comprises the following steps: acquiring hyperspectral data of the surface of the koji block in real time, and taking the hyperspectral data of the surface as a basis for judging the internal and external fermentation states of the koji block; comprehensively processing the curved block image and the spectral information to obtain hyperspectral data of the curved block at a specific point; combining the hyperspectral data of the optimal curved block with the specific curved block in the database, and obtaining the hyperspectral data of the surface of the curved block with the specific wave band through deep learning; acquiring fermentation environment parameters of a koji room; judging whether the hyperspectral data on the surface of the curved block in the specific waveband is a new hyperspectral data type; if yes, updating the established optimal nonlinear prediction mathematical model in real time and storing data; if not, directly judging the internal fermentation state of the koji block according to the optimal nonlinear prediction mathematical model. The invention can realize the real-time measurement function of the solid fermentation of the koji blocks.
Description
Technical Field
The invention relates to the field of brewing solid state fermentation, in particular to a device and a method for detecting the internal fermentation state of a white spirit yeast block based on a hyperspectral technology.
Background
The white spirit is unique distilled spirit in China and has twelve major fragrance types at present. By virtue of the special brewing process, the method is popular with Chinese people. The yeast blocks are souls of the brewing process, are leavens for solid brewing, play a key role in the brewing and fermentation process, and directly influence the quality of the white spirit due to the quality of the yeast blocks. In the modern starter propagation process, the fermentation quality of the starter block is still judged according to manual experience, subjective influence exists, the manual intervention degree is high, the quality fluctuation is large, no quantitative standard exists, no data record for analyzing the starter block quality exists, and the labor cost is high; in order to solve the problems, the improvement of quality detection and nondestructive detection of fermented koji blocks becomes the development of the fermentation, but at present, research results and related patents in the aspect of online nondestructive detection of fermentation of white spirit koji blocks at home and abroad are not available, and particularly, in the aspect of rapid nondestructive detection of fermentation of hyperspectral white spirit koji blocks, a method for comprehensively detecting and controlling the fermentation state and quality in the koji blocks by applying a hyperspectral technology is not available according to the referred documents. Therefore, a device and a method for detecting the internal fermentation state of the white spirit koji block based on the hyperspectral technology are urgently needed to solve the problems.
Disclosure of Invention
The invention aims to provide a device and a method for detecting the internal fermentation state of a white spirit koji block based on a hyperspectral technology, which are used for detecting the internal fermentation state of the white spirit koji block according to surface information of the koji block, can quickly acquire surface hyperspectral data of the white spirit koji block fermented in different areas at different periods in real time on the premise of not influencing the fermentation environment of a koji room and not damaging the fermentation of the koji block, realize the real-time measurement function of the solid state fermentation of the white spirit koji block and provide important feedback information for controlling the fermentation quality of the koji block.
In order to achieve the purpose, the invention provides the following scheme:
the utility model provides an inside fermentation state detection device of bent piece of white spirit based on high spectrum technique, includes: the system comprises a motion control system, a koji block hyperspectral data acquisition system, a real-time transmission processing system, a sensor and a central control system, wherein the motion control system is used for sending the koji block hyperspectral data acquisition system and a manipulator to a designated position of a koji block to be detected, the koji block hyperspectral data acquisition system is connected with the motion control system, the koji block hyperspectral data acquisition system is used for acquiring hyperspectral data of various material components in the surface of a fermented koji block in real time, the real-time transmission processing system is respectively connected with the koji block hyperspectral data acquisition system and the central control system, the real-time transmission processing system is used for sending the hyperspectral data of various material components in the surface of the koji block acquired by the koji block hyperspectral data acquisition system to the central control system, and the central control system is used for receiving the spectrographic data of various materials, the sensor is used for collecting fermentation environment parameters of the koji room, the sensor is connected with the central control system, and the central control system is used for judging the internal fermentation state of the koji blocks according to various high spectrum data of the material components and the fermentation environment parameters of the koji room.
Optionally, the motion control system comprises a manipulator, a guide rail, a tractor, an embedded industrial personal computer and an industrial camera, the guide rail is arranged above the bent room, the tractor is located on the guide rail, the manipulator is arranged on the tractor, the embedded industrial personal computer is arranged on the acquisition system, the manipulator grabs the bent blocks of different layers of the bent frame to be detected in the bent room through the embedded industrial personal computer and places the bent blocks on a rotary sample stage of the bent block hyperspectral data acquisition system, the industrial camera is arranged at the tail end of the manipulator, the industrial camera is used for acquiring the distance between the tail end of the manipulator and the bent room in real time, the embedded industrial personal computer is respectively connected with the manipulator, the tractor and the industrial camera, and the embedded industrial personal computer is used for controlling the motion of the manipulator, controlling the motion of the tractor, And receiving the distance information between the tail end of the manipulator and the bent room.
Optionally, the curved block hyperspectral data acquisition system comprises a hyperspectral camera, a lead screw sliding table, a rotary sample table, a dehumidifying device, an embedded industrial personal computer, a 5G sending module and a motor, wherein the hyperspectral camera is arranged on the lead screw sliding table, and the lead screw sliding table is controlled by the motor to drive the hyperspectral camera to move; the rotating sample table is arranged below the hyperspectral camera and used for placing the manipulator to grab a curved block to be detected; the dehumidifying devices are arranged on two sides of the hyperspectral camera and are used for reducing the influence of water vapor on the hyperspectral camera lens and a precision instrument during data acquisition; the hyperspectral camera is connected with the embedded industrial personal computer, the embedded industrial personal computer is used for receiving hyperspectral data of various substance components on the surface of the curved block collected by the hyperspectral camera, the embedded industrial personal computer is connected with the 5G sending module, and the 5G sending module is connected with the real-time transmission processing system.
Optionally, the real-time transmission processing system adopts a 5G data communication system, the 5G data communication system is connected with the koji block hyperspectral data acquisition system, and the 5G data communication system is used for sending the koji block surface various substance component spectral data acquired by the koji block hyperspectral data acquisition system to the central control system.
A method for detecting the internal fermentation state of a white spirit koji block based on a hyperspectral technique introduces the hyperspectral technique into the online nondestructive detection of the internal fermentation state of the white spirit koji block, and obtains the hyperspectral data on the surface of the koji block of a specific waveband through deep learning to judge the internal and external fermentation states of the koji block, the detection method comprises the following steps:
acquiring surface hyperspectral data of the koji blocks fermented in different areas at different periods in real time, and taking the acquired surface hyperspectral data as a basis for judging the internal and external fermentation states of the koji blocks;
performing image processing and spectral information processing on the hyperspectral data on the surface of the curved block to obtain hyperspectral data of the curved block at a specific point;
acquiring optimal specific wave band curved block image data from a database;
combining the hyperspectral data of the specific-point curved block with the hyperspectral data of the optimal specific-wave-band curved block, and obtaining hyperspectral data of the surface of the specific-wave-band curved block by a deep learning method;
acquiring fermentation environment parameters of a koji room;
judging whether the hyperspectral data on the surface of the curved block with the specific waveband is a new hyperspectral data type;
if yes, updating the established optimal nonlinear prediction mathematical model in real time according to the high spectral data on the surface of the curved block with the specific wave band and the fermentation environment parameters of the curved house, and automatically storing the high spectral data on the surface of the curved block with the specific wave band into a database;
if not, not updating the data model, directly applying the established optimal nonlinear prediction mathematical model according to the hyperspectral data on the surface of the koji block with the specific wave band and the fermentation environment parameters of the koji chamber;
and judging the internal fermentation state of the koji block according to the optimal nonlinear predictive mathematical model, and controlling the fermentation environment parameters of the koji block according to the internal fermentation state of the koji block.
Optionally, the automatic storage of the hyperspectral data on the surface of the curved block with the specific waveband in the database specifically includes:
the database performs insertion and modification operations on the hyperspectral data on the surfaces of the koji blocks collected in real time through a relevant learning algorithm according to the growth change rule of microorganisms and the fermentation environment state of the koji room in the koji block fermentation process, so that online real-time intelligent storage of the hyperspectral data in a typical fermentation state is realized;
and storing hyperspectral data of a typical fermentation state according to the intelligence, and automatically updating database information of different types of material components in different koji rooms in the koji block fermentation process.
Optionally, the step of updating the established optimal nonlinear predictive mathematical model in real time specifically includes:
updating the established optimal nonlinear prediction mathematical model in real time according to the new curve block surface hyperspectral data; with the increase of detection time and the data of the detected koji blocks, the detection method has an online real-time learning function and can automatically optimize a prediction data model, and the intelligence of the detection system for the fermentation state in the koji blocks is gradually improved.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects:
the invention takes the hyperspectral data of the surface of the koji block collected in real time as the basis for judging the internal and external fermentation states of the koji block. The hyperspectral data of the koji blocks with the optimal specific wave bands obtained in the database are combined with the hyperspectral data of the specific points of the koji blocks collected in real time, and the hyperspectral data of the surfaces of the koji blocks with the specific wave bands are obtained through deep learning to judge the internal fermentation state of the koji blocks, so that the internal and external fermentation states and the quality of the koji blocks are comprehensively detected. The method for detecting the internal fermentation state of the white spirit koji block by the hyperspectral technology has an online real-time autonomous learning function, and has an intelligent database special for fermentation of solid brewing koji blocks, namely the database intelligently stores hyperspectral data of different types of koji block fermentation states by a related learning algorithm according to the growth change rule of microorganisms in the koji block fermentation process and the fermentation environment state of a koji room. With the increase of detection time and detection koji data, the detection method continuously updates the surface hyperspectral data of the koji fermentation state, updates the established optimal nonlinear mathematical model in real time according to the new koji hyperspectral data, automatically optimizes the prediction mathematical model, gradually improves the intelligence of the detection system of the koji internal fermentation state, and realizes the real-time online nondestructive detection of the internal fermentation state of the white spirit koji.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without inventive exercise.
FIG. 1 is a schematic diagram of a module of a device for detecting the internal fermentation state of a white spirit koji block based on a hyperspectral technology;
FIG. 2 is a front view of a device for detecting the internal fermentation state of a white spirit koji block by a hyperspectral technique;
FIG. 3 is a top view of a device for detecting the internal fermentation state of a white spirit koji block by a hyperspectral technique;
FIG. 4 is a partial schematic view of a koji fermentation detection system;
FIG. 5 is a first schematic view of a curved block hyperspectral data acquisition system;
FIG. 6 is a second schematic diagram of a curved block hyperspectral data acquisition system;
FIG. 7 is a flow chart of a method for detecting the internal fermentation state of a white spirit koji block based on the hyperspectral technology;
FIG. 8 is a block diagram of an embedded curved block hyperspectral measurement and control system;
FIG. 9 is a flow chart of the internal fermentation detection of the hyperspectral yeast blocks.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention aims to provide a device and a method for detecting the internal fermentation state of a white spirit koji block based on a hyperspectral technology, which are used for detecting the internal fermentation state of the white spirit koji block according to surface information of the koji block, can quickly acquire surface hyperspectral data of the white spirit koji block fermented in different areas at different periods in real time on the premise of not influencing the fermentation environment of a koji room and not damaging the fermentation of the koji block, realize the real-time measurement function of the solid state fermentation of the white spirit koji block and provide important feedback information for controlling the fermentation quality of the koji block.
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
FIG. 1 is a schematic diagram of a module of the device for detecting the internal fermentation state of the white spirit koji block based on the hyperspectral technology. As shown in fig. 1, a device for detecting the internal fermentation state of a white spirit koji block based on a hyperspectral technology comprises: the yeast fermentation system comprises a motion control system 1, a yeast high-spectrum data acquisition system 2, a real-time transmission processing system 3, a sensor 4 and a central control system 5, wherein the motion control system 1 is used for conveying the yeast high-spectrum data acquisition system 2 to a designated position of a yeast to be detected, the yeast high-spectrum data acquisition system 2 is connected with the motion control system 1, the yeast high-spectrum data acquisition system 2 is used for acquiring high-spectrum data of various material components in the surface of a fermented yeast in real time, the real-time transmission processing system 3 is respectively connected with the yeast high-spectrum data acquisition system 2 and the central control system 5, the real-time transmission processing system 3 is used for transmitting the high-spectrum data of various material components in the surface of the yeast collected by the yeast high-spectrum data acquisition system 2 to the central control system 5, the central control system 5 is used for receiving the high-spectrum data of various material components, and the sensor 4 is used for acquiring fermentation environment parameters of a yeast room, the sensor 4 is connected with a central control system 5, and the central control system 5 is used for judging the internal fermentation state of the koji blocks according to the hyperspectral data of various material components and the fermentation environment parameters of the koji room.
FIG. 2 is a front view of a device for detecting the internal fermentation state of a white spirit koji block by a hyperspectral technology. FIG. 3 is a top view of a device for detecting the internal fermentation state of a white spirit koji block by a hyperspectral technology. FIG. 4 is a partial schematic view of a koji fermentation detection system. Referring to fig. 2, 3 and 4, the motion control system 1 comprises a manipulator 11, a guide rail 12, a tractor 13 and an embedded industrial personal computer 26, the motion control system 1 is a motion system suitable for a curved house in a high-temperature and high-humidity environment, the guide rail 12 is arranged above the curved house, a label 6 is arranged on a door of the curved house, the tractor 13 is positioned on the guide rail 12, the manipulator 11 is arranged on the tractor 13, the embedded industrial personal computer 26 is arranged on the curved block hyperspectral data acquisition system 2, the manipulator 11 is used for grabbing curved blocks of different layers of curved frames to be detected in the curved house through the embedded industrial personal computer 26 and placing the curved blocks on a rotating sample table of the curved block hyperspectral data acquisition system 2, the embedded industrial personal computer 26 is respectively connected with the manipulator 11 and the tractor 13, and the embedded industrial personal computer 26 is used for controlling the motion of the manipulator 11 and the tractor 13.
The motion control system 1 further comprises a manipulator lifting platform 14, the manipulator lifting platform 14 is respectively connected with the tractor 13 and the manipulator 11, and the manipulator lifting platform 14 is used for controlling the motion of the manipulator 11.
The motion control system 1 further comprises an industrial camera 15, the industrial camera 15 is arranged at the tail end of the manipulator 11, and the industrial camera 15 is used for acquiring the tail end of the manipulator 11, the bent room distance and the bent block image information of the bent frame to be detected are acquired to realize accurate positioning and grabbing of the bent block to be detected.
The curved block hyperspectral data acquisition system 2 adopts a unique mobile suspension type curved block hyperspectral data acquisition system to be connected with the guide rail 12 through the tractor 13, so that the recognition rate and the detection precision of curved block states in different fermentation curved houses are improved. FIG. 5 is a first schematic diagram of a curved block hyperspectral data acquisition system. FIG. 6 is a second schematic diagram of a curved block hyperspectral data acquisition system. As shown in fig. 5 and 6, the curved block hyperspectral data acquisition system 2 comprises a hyperspectral camera 31, a rotary sample table 22, a screw sliding table and a motor, a 5G sending module 25, an embedded industrial personal computer 26, a light source 27 and a dehumidifying device 28, wherein the motor comprises a light source adjusting motor 241 and a screw sliding table motor 242, the hyperspectral camera 31 is installed on the screw sliding table through a connecting plate, the screw sliding table is controlled by the screw sliding table motor 242 to drive the hyperspectral camera 31 to move up and down and left and right, the object distance and the field angle are adjusted, and the omnidirectional spectral information acquisition of the curved block is realized. The rotating sample table 22 is arranged below the hyperspectral camera 31, the rotating sample table 22 is used for placing a curved block to be detected and captured by the manipulator 11, the hyperspectral camera 31 is connected with the embedded industrial personal computer 26, the embedded industrial personal computer 26 is used for receiving hyperspectral data of various material components on the surface of the collected fermented curved block in real time, the embedded industrial personal computer 26 is connected with the 5G sending module 25, and the 5G sending module 25 is connected with the real-time transmission processing system 3. The embedded industrial personal computer 26 used in the invention is an embedded industrial personal computer special for a bent house. The light source 27 is a halogen light source and is arranged on two sides of the hyperspectral camera 31, the light source 27 is connected with the light source adjusting motor 241, the intensity and the angle of the light source 27 are automatically adjusted through the light source adjusting motor 241, the optimal collection light inlet quantity is set, the interference of a koji room environment on koji block hyperspectral data collection is eliminated, the hyperspectral data of various material components in the surface of a fermented koji block are collected in real time, high-quality data is obtained, and the integration of a koji block surface data map is realized. The curved block hyperspectral data acquisition system 2 further comprises dehumidifying devices 28, the dehumidifying devices 28 are installed on two sides of the hyperspectral camera 31, and the dehumidifying devices 28 are used for reducing the influence of water vapor on a lens and a precision instrument of the hyperspectral camera 31 during data acquisition. The screw slide table includes a front-rear movement slide table 231, a left-right movement slide table 232, and an up-down movement slide table 233.
The central control system 5 establishes a relevant mathematical model according to a hyperspectral formation mechanism, the high-spectral data on the surface of the koji block and the koji room environment parameters, and judges the internal fermentation state of the koji block by acquiring the hyperspectral data on the surface of the koji block in a specific waveband through deep learning, so that the online nondestructive detection of the internal fermentation state of the hyperspectral koji block is realized.
The curved block hyperspectral data acquisition system 2 is core equipment of the device, and the guide rail 12 is a supporting structure of the whole system. When the device enters different curved houses, the motor drives the mechanical arm 11 to move vertically, the industrial camera 15 at the tail end of the mechanical arm 11 rotates and collects image information of the label 6 above the curved house door in the moving process, the distance between the mechanical arm 11 and the curved house door is continuously detected by processing the image information, when the specified distance is reached, the curved house door is automatically opened through signal control, and the curved block hyperspectral data collection system 2 and the mechanical arm 11 are automatically closed after entering the curved house to be detected. When the bent block is grabbed, the manipulator 11 moves horizontally, so that the industrial camera 15 acquires and processes the image information of the bent block, the bent block to be detected is accurately positioned, and the manipulator lifting platform 14 controls the manipulator 11 to effectively and accurately grab the bent block to be detected. The motion control system has the advantages of simple and reliable structure, accurate positioning and high accuracy.
The bent block hyperspectral data acquisition system 2 further comprises a sealing device, an automatic lifting door and a standard correction white board, wherein all the components of the bent block hyperspectral data acquisition system 2 are located inside the sealing device, so that the bent block hyperspectral data acquisition system 2 can be protected from being affected by high temperature and high humidity of a bent house, and the service life of the bent block hyperspectral data acquisition system is prolonged. When the curved block hyperspectral data acquisition system 2 acquires data, the rotary sample table 22 rotates by 90 degrees through the motor 30 in the base of the rotary sample table and moves to the outer side of the equipment, the manipulator 11 accurately places a curved block to be detected in a curved groove of the rotary sample table 22, the rotary sample table 22 rotates to an initial position at a speed of 40cm/s, and the automatic lifting door motor 33 controls the automatic lifting door 29 to be automatically closed after the sample table completely enters the sealing device within 1 ms. The dehumidifying devices 28 are arranged on two sides of the hyperspectral camera 31, water vapor in the sealing device is discharged, and the influence of the water vapor on the hyperspectral camera lens and a precision instrument can be reduced. The lead screw sliding table motor 242 controls the lead screw sliding table to move to complete the up-down and left-right movement of the hyperspectral camera 31, and the optimal object distance and the optimal field angle are adjusted, so that the lens can cover the whole sample table, and the omnibearing hyperspectral information acquisition of the curved block is realized. The standard correction white plate 32 is arranged below the lens, the angles between the two halogen lamps and the rotary sample table 22 are automatically adjusted through the light source adjusting motor 241, the optimal collection light inlet quantity is set, the reflectivity of each wave band reaches 80% -90% of the maximum dynamic range, sufficient light is ensured for measurement, and the phenomenon that the collected data is distorted due to the saturation of a white light reference point is avoided. The average resolution of the hyperspectral camera 31 is 8nm, the spectrum range is 300-1800nm, the sampling interval is set to 3.5nm, and 428 wave bands exist in the range. After the standard correction white board position and the collection area are set, the motor controls the screw rod sliding table to realize that the hyperspectral camera 31 moves from top to bottom in the direction vertical to the main shaft of the rotary sample table 22 at the speed of 15cm/s to collect the hyperspectral data of the bent block. The hyperspectral camera 31 points to the whiteboard first, and scans 100 lines of the whiteboard continuously to obtain a reference image of the average waveband of the correction light source. A narrow band of a parallel slit of a curved block object to be detected enters the hyperspectral camera 31 through the lens under the irradiation of a light source, is dispersed by the light splitting component and then is transmitted to the photosensitive element, so that hyperspectral data of the whole curved block to be detected in the sample stage are obtained, the embedded industrial personal computer 26 transmits a large amount of collected hyperspectral data to the central control system 5 at high speed through the 5G sending module 25, and the data receiving and processing are completed. The exposure time of the hyperspectral camera 31 is 11.5ms, and the acquisition power is 45 Hz. The device provided by the invention can be used for simply collecting the high spectrum of the white spirit yeast blocks and has high data quality.
After the collection of the koji block hyperspectral data collection system 2 is finished, a large amount of acquired koji block hyperspectral data are transmitted to the embedded industrial personal computer 26 for storage, and the real-time transmission processing system 3 realizes the high-speed transmission of a large amount of data to the central control system 5 by adopting a 5G wireless communication mode.
The central control system 5 adopts a large-scale server, the large-scale server establishes a correlation mathematical model according to a hyperspectral formation mechanism, koji surface hyperspectral data and koji environmental parameters (temperature, humidity, oxygen and carbon dioxide concentration), and judges the internal fermentation state of the koji through acquiring the specific waveband koji surface hyperspectral data through deep learning, so that the online nondestructive detection of the internal fermentation state of the hyperspectral koji is realized.
FIG. 7 is a flow chart of a method for detecting the internal fermentation state of a white spirit koji block based on a hyperspectral technology. As shown in FIG. 7, a method for detecting the internal fermentation state of a white spirit koji block based on a hyperspectral technology comprises the following steps:
step 101: acquiring surface hyperspectral data of yeast blocks fermented in different areas at different periods in real time;
the step 101 specifically includes:
acquiring image information and spectrum information of the curved block in real time through a curved block hyperspectral data acquisition system;
according to the image information and the spectrum information, the hyperspectral information of the surface of the koji block to be detected is obtained, the integration of the maps of fermentation state information of each stage of the koji block is realized, and the collected surface hyperspectral data is used as the basis for judging the internal and external fermentation states of the koji block.
Step 102: and performing image processing and spectral information processing on the hyperspectral data on the surface of the curved block to obtain the hyperspectral data of the curved block at the specific point.
Step 103: and acquiring the hyperspectral data of the optimal specific waveband curved block from the database.
Step 104: combining the hyperspectral data of the specific-point curved block with the hyperspectral data of the optimum specific-wave-band curved block, and obtaining the hyperspectral data of the surface of the specific-wave-band curved block by a deep learning method.
Step 105: obtaining fermentation environmental parameters of a koji room, which specifically comprises the following steps:
reasonably collecting fermentation environmental parameters of koji room by adopting sectional type collection mode according to growth change rule of microorganism in koji block fermentation process to obtain environmental temperature, humidity and O of koji room2Concentration, CO2Concentration, CO2Concentration by CO2Concentration sensor acquisition, O2Concentration through O2The concentration sensor collects, the temperature is collected through the temperature sensor, and the humidity is collected through the humidity sensor.
Step 106: and judging whether the hyperspectral data on the surface of the curved block with the specific wave band is a new hyperspectral data type.
Step 107: and if the type of the hyperspectral data is a new hyperspectral data type, updating the established optimal nonlinear prediction mathematical model in real time according to the hyperspectral data on the surface of the curved block with the specific wave band and the fermentation environment parameters of the curved house, and automatically storing the hyperspectral data on the surface of the curved block with the specific wave band into a database.
The database performs insertion and modification operations on the real-time collected high-spectrum data on the surfaces of the koji blocks through a relevant learning algorithm according to the growth change rule of microorganisms and the fermentation environment state of the koji chamber in the fermentation process of the koji blocks, so that the high-spectrum data in the typical fermentation state can be intelligently stored in real time on line;
and storing hyperspectral data of a typical fermentation state according to the intelligence, and automatically updating database information of different types of material components in different koji rooms in the koji block fermentation process.
The detection method has an online real-time learning function, and updates the established optimal nonlinear prediction mathematical model in real time according to the new curve block surface hyperspectral data; and increasing an automatic optimization prediction data model along with the detection time and the detected koji block data, and gradually improving the intelligence of the fermentation state detection system in the koji block.
Step 108: if the type of the hyperspectral data is not the new type of hyperspectral data, an optimal nonlinear prediction mathematical model is established by directly applying the hyperspectral data on the surface of the koji block in the specific waveband and the fermentation environment parameters of the koji chamber.
Step 109: and judging the internal fermentation state of the koji block according to the optimal nonlinear prediction mathematical model.
A suspended type koji block hyperspectral data acquisition system is adopted to enter different fermentation koji rooms, the hyperspectral data of the fermentation surfaces of koji blocks in different periods and different areas are acquired in real time, the image information and the spectral information of the fermentation state of the koji blocks are comprehensively processed, and the hyperspectral data of the koji blocks at specific points are acquired. And combining the hyperspectral data of the optimal curved block with the specific wave band obtained in the database with the hyperspectral data corresponding to the specific point of the curved block collected in real time, and obtaining the hyperspectral data of the surface of the curved block with the specific wave band through deep learning. According to the growth change rule of microorganisms in the fermentation of the koji blocks, a sectional type acquisition mode is adopted, fermentation environment parameters of the koji chamber are reasonably acquired, and an optimal nonlinear prediction mathematical model is established to judge the internal and external fermentation states of the koji blocks, wherein the parameters comprise the temperature, the humidity, the oxygen content, the carbon dioxide content and the like of the koji chamber and the hyperspectral data on the surface of the koji blocks in specific wave bands.
The koji block hyperspectral detection system has an autonomous learning function, discriminates and judges the collected hyperspectral data through the deep learning module, and if the collected data is determined to be a new koji block hyperspectral data type, the database implements insertion, query, deletion and modification operations on the real-time collected koji block hyperspectral data through a related algorithm according to the growth change rule of microorganisms and the fermentation environment state of a koji room in the koji block fermentation process, so that the hyperspectral data of a typical fermentation state can be intelligently stored, and the database information of different types of material components in different koji rooms in the koji block fermentation process can be automatically updated. Along with the increase of detection time and detection koji data, the detection system continuously updates the surface hyperspectral data of the koji fermentation state, updates the established optimal nonlinear mathematical model in real time according to the new koji hyperspectral data, automatically optimizes the prediction data model, gradually improves the intelligence of the detection system of the koji internal fermentation state, realizes the real-time online nondestructive detection of the internal fermentation state of the white spirit koji, reduces the interference of human factors and improves the detection precision. The method provided by the invention meets the requirements of rapid and real-time analysis of big data, and can improve the detection speed and precision. The invention has the following advantages:
(1) a hyperspectral technology is introduced into a method for detecting the fermentation state of the koji blocks of the white spirit on line, the hyperspectral data of the koji blocks with the optimal specific wave bands are combined with the hyperspectral data corresponding to specific points of the koji blocks collected in real time, and the fermentation state inside the koji blocks is judged according to the hyperspectral data on the surfaces of the koji blocks with the specific wave bands through deep learning, so that the fermentation state and the fermentation quality inside and outside the koji blocks are comprehensively detected, the precision and the accuracy of the quality judgment of the koji blocks are improved, and the real-time online nondestructive detection of the fermentation state and the quality of the koji blocks of the white spirit is realized.
(2) And (3) establishing a mathematical model of the yeast block hyperspectral data and yeast room environment parameters (temperature, humidity, oxygen and carbon dioxide concentration), and using the result to control the yeast block fermentation environment parameters to enable the yeast block fermentation environment parameters to be in the optimal fermentation state.
(3) A special mobile suspended type high-spectrum data acquisition system for the yeast blocks is adopted, so that the recognition rate and the detection precision of the yeast block state in the yeast fermentation room are improved. The bent block hyperspectral data acquisition system adopts a full-sealed mode, can protect the spectrum acquisition system from being influenced by high temperature and high humidity, and prolongs the service life of the bent block hyperspectral data acquisition system. The moisture extraction devices on the two sides of the hyperspectral core equipment can eliminate the influence of water vapor on the lens and the precision instrument, and avoid the interference of environmental factors on the collected hyperspectral data.
(4) The embedded koji block hyperspectral data acquisition system and the 5G data communication mode are adopted to transmit the acquired koji block hyperspectral data to the central control system in real time in a koji room, so that the automatic real-time acquisition of effective koji block hyperspectral information is realized, the fermentation state and quality detection of koji blocks are quickly realized, the hyperspectral data operation speed is improved, and the requirements of koji block production sites are met.
(5) The koji block hyperspectral detection system has an online real-time learning function, namely, the database can intelligently store typical fermentation state hyperspectral data online in real time through a relevant learning algorithm according to the growth change rule of microorganisms and the fermentation environment state of a koji room in the fermentation process of koji blocks. The method realizes that the hyperspectral data information of different types of curved blocks in different curved houses is automatically stored in an intelligent database, and the established optimal nonlinear mathematical model is updated in real time according to the hyperspectral data of the curved blocks of new types. An automatic optimization prediction data model is added along with the detection time and the detection koji block data, the intelligence of the fermentation state detection system in the koji block is gradually improved, and the detection and identification precision is enhanced.
Example (b):
FIG. 8 is a block diagram of an embedded curved block hyperspectral measurement and control system structure. The embedded type curved block hyperspectral measurement and control system is composed of an embedded type measurement and control system, a curved block hyperspectral data acquisition system, a 5G data communication module, a 5G sending module, a curved block hyperspectral data 5G receiving module and a high-performance server.
1) After the data is collected by the koji block hyperspectral collection system, a large amount of obtained koji block hyperspectral data are transmitted to the embedded koji block measurement and control system for storage.
2) And a 5G wireless communication mode is adopted, and high-speed transmission of a large amount of data is realized through a 5G sending module. And the bent block hyperspectral data 5G receiving module transmits the received data to a large server in real time for processing.
3) A large-scale system (server) establishes a correlation mathematical model according to the high spectrum data on the surface of the koji block and the koji room environment parameters (temperature, humidity, oxygen and carbon dioxide concentration), and judges the internal fermentation state of the koji block according to the high spectrum data on the surface of the koji block with the specific wave band through deep learning, so that the online detection of the internal fermentation state of the high spectrum koji block is realized.
FIG. 9 is a flow chart of the internal fermentation detection of the hyperspectral yeast blocks. As shown in fig. 9, the detection of the internal fermentation of the hyperspectral koji block comprises the following steps:
1) the koji block hyperspectral on-line acquisition system enters different fermentation koji rooms, collects the surface hyperspectral data of koji block fermentation in different areas and different periods in real time,
2) comprehensively processing image information and spectral information of the high spectral data on the surface of the yeast fermentation to obtain the high spectral data of the yeast fermentation at a specific point.
3) And combining the hyperspectral data of the optimal curved block with the specific wave band obtained in the database with the hyperspectral data corresponding to the specific point of the curved block collected in real time, and obtaining the hyperspectral data of the surface of the curved block with the specific wave band through deep learning.
4) According to the growth change rule of microorganisms in the fermentation of the koji blocks, a sectional type acquisition mode is adopted, fermentation environment parameters of the koji room are reasonably acquired, and the optimal nonlinear prediction mathematical model is established through deep learning to judge the fermentation state in the koji blocks, wherein the parameters comprise the parameters of the environment temperature, the humidity, the oxygen content, the carbon dioxide content and the like of the koji room and the data characteristics of the fermentation state in the koji blocks.
5) The koji block hyperspectral detection system has an online autonomous learning function, discriminates and judges the collected hyperspectral data through the deep learning module, and if the collected data is determined to be a new koji block hyperspectral data type, the database implements insertion, query, deletion and modification operations on real-time collected koji block surface hyperspectral data through a related algorithm according to the growth change rule of microorganisms and the fermentation environment state of a koji room in the koji block fermentation process, realizes intelligent storage of hyperspectral data in a typical fermentation state, and automatically updates database information of different types of material components in different koji rooms in the koji block fermentation process. Along with the increase of detection time and detection koji data, the detection system continuously adds surface hyperspectral data of koji fermentation states, updates the established optimal nonlinear mathematical model in real time according to new koji hyperspectral data, automatically optimizes a prediction data model, gradually improves the intelligence of the detection system of the koji fermentation states, realizes real-time online nondestructive detection of the internal fermentation states of the white spirit koji, reduces human factor interference, and improves the detection precision.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. Method and apparatus
The principles and embodiments of the present invention have been described herein using specific examples, which are provided only to help understand the method and the core concept of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, the specific embodiments and the application range may be changed. In view of the above, the present disclosure should not be construed as limiting the invention.
Claims (4)
1. The utility model provides an inside fermentation state detection device of bent piece of white spirit based on high spectrum technique which characterized in that includes: the system comprises a motion control system, a koji block hyperspectral data acquisition system, a real-time transmission processing system, a sensor and a central control system, wherein the motion control system is used for sending the koji block hyperspectral data acquisition system to a designated position of a koji block to be detected, the koji block hyperspectral data acquisition system is connected with the motion control system, the koji block hyperspectral data acquisition system is used for acquiring hyperspectral data of various material components in the surface of a fermented koji block in real time, the real-time transmission processing system is respectively connected with the koji block hyperspectral data acquisition system and the central control system, the real-time transmission processing system is used for sending the hyperspectral data of various material components in the surface of the koji block acquired by the koji block hyperspectral data acquisition system to the central control system, and the central control system is used for receiving the hyperspectral data of various material components, the sensor is used for collecting fermentation environment parameters of the koji room, the sensor is connected with the central control system, and the central control system is used for judging the internal fermentation state of the koji blocks according to the hyperspectral data of various material components and the fermentation environment parameters of the koji room;
the motion control system comprises a mechanical arm, a guide rail, a tractor, an embedded industrial personal computer and an industrial camera, wherein the guide rail is arranged above the bent room, the tractor is positioned on the guide rail, the mechanical arm is arranged on the tractor, the embedded industrial personal computer is arranged on the acquisition system, the mechanical arm grabs the bent blocks of different layers of bent frames to be detected in the bent room through the embedded industrial personal computer and places the bent blocks on a rotary sample table of the bent block hyperspectral data acquisition system, the industrial camera is arranged at the tail end of the mechanical arm and is used for acquiring the distance between the tail end of the mechanical arm and the bent room in real time, the embedded industrial personal computer is respectively connected with the mechanical arm, the tractor and the industrial camera, and the embedded industrial personal computer is used for controlling the motion of the mechanical arm, controlling the motion of the tractor, Receiving distance information between the tail end of the manipulator and the bending room;
the bent block hyperspectral data acquisition system comprises a hyperspectral camera, a lead screw sliding table, a rotary sample table, a dehumidifying device, an embedded industrial personal computer, a 5G sending module and a motor, wherein the hyperspectral camera is arranged on the lead screw sliding table, and the lead screw sliding table is controlled by the motor to drive the hyperspectral camera to move; the rotating sample table is arranged below the hyperspectral camera and used for placing the manipulator to grab a curved block to be detected; the dehumidifying devices are arranged on two sides of the hyperspectral camera and are used for reducing the influence of water vapor on the hyperspectral camera lens and a precision instrument during data acquisition; the hyperspectral camera is connected with the embedded industrial personal computer, the embedded industrial personal computer is used for receiving hyperspectral data of various substance components on the surface of the curved block collected by the hyperspectral camera, the embedded industrial personal computer is connected with the 5G sending module, and the 5G sending module is connected with the real-time transmission processing system;
the curved block hyperspectral data acquisition system further comprises a sealing device, an automatic lifting door and a standard correction white board, and all the components of the curved block hyperspectral data acquisition system are located inside the sealing device.
2. The device for detecting the internal fermentation state of the white spirit koji block based on the hyperspectral technology according to claim 1, wherein the real-time transmission processing system adopts a 5G data communication system, the 5G data communication system is connected with the koji block hyperspectral data acquisition system, and the 5G data communication system is used for sending hyperspectral data of various material components on the surface of the koji block acquired by the koji block hyperspectral data acquisition system to the central control system.
3. A method for detecting the internal fermentation state of a white spirit koji block based on a hyperspectral technique, which introduces the hyperspectral technique into an online nondestructive detection of the internal fermentation state of the white spirit koji block and obtains the hyperspectral data on the surface of the koji block of a specific waveband through deep learning to judge the internal and external fermentation states of the koji block, is applied to the hyperspectral technique-based detection device of the internal fermentation state of the white spirit koji block according to claim 1, and comprises the following steps:
collecting surface hyperspectral data of the koji blocks fermented in different areas at different periods in real time, and taking the surface hyperspectral data as a basis for judging the internal and external fermentation states of the koji blocks;
processing image and spectrum information of the hyperspectral data on the surface of the curved block to obtain hyperspectral data of the curved block at a specific point;
acquiring hyperspectral data of an optimal specific waveband curved block from a database;
combining the hyperspectral data of the specific-point curved block with the hyperspectral data of the optimal specific-wave-band curved block, and obtaining hyperspectral data of the surface of the specific-wave-band curved block by a deep learning method;
acquiring fermentation environment parameters of a koji room;
judging whether the hyperspectral data on the surface of the curved block with the specific waveband is a new hyperspectral data type;
if yes, updating the established optimal nonlinear prediction mathematical model in real time according to the high spectral data on the surface of the curved block with the specific wave band and the fermentation environment parameters of the curved chamber, and automatically storing the high spectral data on the surface of the curved block with the specific wave band into a database;
if not, the mathematical model is not updated, and an optimal nonlinear prediction mathematical model is established according to the hyperspectral data on the surface of the koji block of the specific waveband and the fermentation environment parameters of the koji chamber by direct application;
judging the internal fermentation state of the koji block according to the optimal nonlinear predictive mathematical model, and controlling the fermentation environment parameters of the koji block according to the internal fermentation state of the koji block;
the automatic storage of the hyperspectral data on the surface of the curved block with the specific waveband in a database specifically comprises the following steps:
the database performs insertion and modification operations on the hyperspectral data on the surfaces of the koji blocks collected in real time through a relevant learning algorithm according to the growth change rule of microorganisms and the fermentation environment state of the koji room in the koji block fermentation process, so that online real-time intelligent storage of the hyperspectral data in a typical fermentation state is realized;
and storing hyperspectral data of a typical fermentation state according to the intelligence, and automatically updating database information of different types of material components in different koji rooms in the koji block fermentation process.
4. The hyperspectral-technology-based detection method of the internal fermentation state of the white spirit koji blocks according to claim 3, wherein the real-time updating of the established optimal nonlinear predictive mathematical model specifically comprises:
updating the established optimal nonlinear prediction mathematical model in real time according to the new curve block surface hyperspectral data; with the increase of detection time and the data of the detected koji blocks, the detection method has an online real-time learning function and can automatically optimize a prediction data model, and the intelligence of the fermentation state detection system in the koji blocks is gradually improved.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911042816.XA CN110749555B (en) | 2019-10-30 | 2019-10-30 | Hyperspectral technology-based device and method for detecting internal fermentation state of white spirit koji |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911042816.XA CN110749555B (en) | 2019-10-30 | 2019-10-30 | Hyperspectral technology-based device and method for detecting internal fermentation state of white spirit koji |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110749555A CN110749555A (en) | 2020-02-04 |
| CN110749555B true CN110749555B (en) | 2022-05-31 |
Family
ID=69281102
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911042816.XA Active CN110749555B (en) | 2019-10-30 | 2019-10-30 | Hyperspectral technology-based device and method for detecting internal fermentation state of white spirit koji |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110749555B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112102898B (en) * | 2020-09-22 | 2022-09-23 | 安徽大学 | Method and system for identifying mode of spectrogram in solid fermentation process of vinegar grains |
| CN112652366B (en) * | 2020-12-14 | 2022-10-25 | 宜宾五粮液股份有限公司 | Embedded hyperspectral intelligent measurement and control system for quality detection of yeast for making hard liquor |
| CN112880734A (en) * | 2020-12-31 | 2021-06-01 | 中农新科(苏州)有机循环研究院有限公司 | Biological drying process digital monitoring system for reactor |
Citations (30)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101718683A (en) * | 2009-11-10 | 2010-06-02 | 中国农业大学 | Device for fast detection of chlorophyll content in leaf blades, modeling method and detection method |
| CN101806622A (en) * | 2010-03-22 | 2010-08-18 | 中国科学院遥感应用研究所 | Ground imaging spectral measurement system |
| CN102081039A (en) * | 2010-08-17 | 2011-06-01 | 江苏大学 | Environment-controllable hyperspectral image detecting device for crop nutrition and moisture |
| CN102507457A (en) * | 2011-11-18 | 2012-06-20 | 江苏大学 | Device and method for rapidly and nondestructively detecting crop nutrient elements |
| 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 |
| CN102539359A (en) * | 2011-12-30 | 2012-07-04 | 南京林业大学 | Meat quality visualization detection device based on static hyperspectral imaging system |
| CN102788794A (en) * | 2012-07-30 | 2012-11-21 | 江苏大学 | Device and method for detecting pesticide residues on leaves of leaf vegetables on basis of multi-sensed information fusion |
| CN103208011A (en) * | 2013-05-05 | 2013-07-17 | 西安电子科技大学 | Hyperspectral image space-spectral domain classification method based on mean value drifting and group sparse coding |
| CN103439264A (en) * | 2013-08-15 | 2013-12-11 | 湖南农业大学 | Device for data acquisition of fertility characteristics of tea tree living body based on online positioning |
| CN103616383A (en) * | 2013-12-02 | 2014-03-05 | 江苏大学 | Method for quantitatively detecting stability of flora structure in batch food fermentation process |
| CN103808669A (en) * | 2014-01-26 | 2014-05-21 | 沈阳农业大学 | Rapid nondestructive apple wormhole testing method based on hyperspectral imaging technology |
| CN104588334A (en) * | 2013-10-30 | 2015-05-06 | 邢玉明 | Way for adopting production line to sort miscellanies, sorting production line, and light spectrum parallel connection mechanical arm |
| CN104646310A (en) * | 2013-11-24 | 2015-05-27 | 邢玉明 | Sorting production line |
| CN104647351A (en) * | 2013-11-24 | 2015-05-27 | 邢玉明 | Parallel manipulator of spectral imager |
| CN105117734A (en) * | 2015-07-28 | 2015-12-02 | 江南大学 | Corn seed hyper-spectral image classification identification method based on model on-line updating |
| CN105158177A (en) * | 2015-09-30 | 2015-12-16 | 江苏大学 | Method for quantitatively detecting solid fermentation moisture distribution uniformity through hyper-spectral image technology |
| CN105203464A (en) * | 2015-08-28 | 2015-12-30 | 中国农业科学院农产品加工研究所 | Method for detecting oleic acid content distribution in peanuts based on hyperspectral imaging technology |
| CN105973839A (en) * | 2016-06-28 | 2016-09-28 | 江苏大学 | Hyperspectral batch-type nondestructive detection method and system for quality of agricultural and livestock products |
| CN106018292A (en) * | 2016-07-19 | 2016-10-12 | 华中农业大学 | Non-destructive testing device for protein conformation in egg white and method of non-destructive testing device |
| CN206178392U (en) * | 2016-10-21 | 2017-05-17 | 中国科学院南京土壤研究所 | Real -time reciprocity monitoring devices of greenhouse crop growth information |
| CN106791318A (en) * | 2016-12-30 | 2017-05-31 | 南京大学 | A kind of portable EO-1 hyperion video Real-time Collection and processing unit and its method |
| CN106841070A (en) * | 2017-03-09 | 2017-06-13 | 中国科学院遥感与数字地球研究所 | A kind of falsification of distilled spirit authentication method and device |
| CN107133976A (en) * | 2017-04-24 | 2017-09-05 | 浙江大学 | A kind of method and apparatus for obtaining three-dimensional hyperspectral information |
| CN107290293A (en) * | 2017-06-06 | 2017-10-24 | 浙江大学 | A kind of spectral imaging technology monitors the device of water planting heavy metal stress crop on-line |
| CN107999399A (en) * | 2017-12-27 | 2018-05-08 | 华侨大学 | Building waste on-line sorting system and method based on the detection of dot matrix EO-1 hyperion |
| CN108323295A (en) * | 2017-12-05 | 2018-07-27 | 江苏大学 | A kind of seedling stage crop liquid manure based on multiple dimensioned habitat information detects and controls method and device |
| CN208064001U (en) * | 2018-02-28 | 2018-11-09 | 北京农业信息技术研究中心 | One plant growth network push device |
| CN109855735A (en) * | 2019-02-20 | 2019-06-07 | 北京理工大学 | A kind of EO-1 hyperion calculating imaging method of synchronously control and acquisition |
| CN109884035A (en) * | 2019-02-25 | 2019-06-14 | 广东朗研科技有限公司 | A kind of detection device of sample to be tested, detection method and false-proof detection method |
| CN109916826A (en) * | 2019-02-20 | 2019-06-21 | 福建南方路面机械有限公司 | A kind of solid waste online recognition system and recognition methods based on EO-1 hyperion detection |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9002113B2 (en) * | 2006-03-01 | 2015-04-07 | Green Vision Systems Ltd. | Processing and analyzing hyper-spectral image data and information via dynamic database updating |
| US9996745B2 (en) * | 2012-11-19 | 2018-06-12 | Altria Client Services Llc | Blending of agricultural products via hyperspectral imaging and analysis |
-
2019
- 2019-10-30 CN CN201911042816.XA patent/CN110749555B/en active Active
Patent Citations (30)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101718683A (en) * | 2009-11-10 | 2010-06-02 | 中国农业大学 | Device for fast detection of chlorophyll content in leaf blades, modeling method and detection method |
| CN101806622A (en) * | 2010-03-22 | 2010-08-18 | 中国科学院遥感应用研究所 | Ground imaging spectral measurement system |
| CN102081039A (en) * | 2010-08-17 | 2011-06-01 | 江苏大学 | Environment-controllable hyperspectral image detecting device for crop nutrition and moisture |
| CN102507457A (en) * | 2011-11-18 | 2012-06-20 | 江苏大学 | Device and method for rapidly and nondestructively detecting crop nutrient elements |
| CN102539359A (en) * | 2011-12-30 | 2012-07-04 | 南京林业大学 | Meat quality visualization detection device based on static hyperspectral imaging system |
| 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 |
| CN102788794A (en) * | 2012-07-30 | 2012-11-21 | 江苏大学 | Device and method for detecting pesticide residues on leaves of leaf vegetables on basis of multi-sensed information fusion |
| CN103208011A (en) * | 2013-05-05 | 2013-07-17 | 西安电子科技大学 | Hyperspectral image space-spectral domain classification method based on mean value drifting and group sparse coding |
| CN103439264A (en) * | 2013-08-15 | 2013-12-11 | 湖南农业大学 | Device for data acquisition of fertility characteristics of tea tree living body based on online positioning |
| CN104588334A (en) * | 2013-10-30 | 2015-05-06 | 邢玉明 | Way for adopting production line to sort miscellanies, sorting production line, and light spectrum parallel connection mechanical arm |
| CN104646310A (en) * | 2013-11-24 | 2015-05-27 | 邢玉明 | Sorting production line |
| CN104647351A (en) * | 2013-11-24 | 2015-05-27 | 邢玉明 | Parallel manipulator of spectral imager |
| CN103616383A (en) * | 2013-12-02 | 2014-03-05 | 江苏大学 | Method for quantitatively detecting stability of flora structure in batch food fermentation process |
| CN103808669A (en) * | 2014-01-26 | 2014-05-21 | 沈阳农业大学 | Rapid nondestructive apple wormhole testing method based on hyperspectral imaging technology |
| CN105117734A (en) * | 2015-07-28 | 2015-12-02 | 江南大学 | Corn seed hyper-spectral image classification identification method based on model on-line updating |
| CN105203464A (en) * | 2015-08-28 | 2015-12-30 | 中国农业科学院农产品加工研究所 | Method for detecting oleic acid content distribution in peanuts based on hyperspectral imaging technology |
| CN105158177A (en) * | 2015-09-30 | 2015-12-16 | 江苏大学 | Method for quantitatively detecting solid fermentation moisture distribution uniformity through hyper-spectral image technology |
| CN105973839A (en) * | 2016-06-28 | 2016-09-28 | 江苏大学 | Hyperspectral batch-type nondestructive detection method and system for quality of agricultural and livestock products |
| CN106018292A (en) * | 2016-07-19 | 2016-10-12 | 华中农业大学 | Non-destructive testing device for protein conformation in egg white and method of non-destructive testing device |
| CN206178392U (en) * | 2016-10-21 | 2017-05-17 | 中国科学院南京土壤研究所 | Real -time reciprocity monitoring devices of greenhouse crop growth information |
| CN106791318A (en) * | 2016-12-30 | 2017-05-31 | 南京大学 | A kind of portable EO-1 hyperion video Real-time Collection and processing unit and its method |
| CN106841070A (en) * | 2017-03-09 | 2017-06-13 | 中国科学院遥感与数字地球研究所 | A kind of falsification of distilled spirit authentication method and device |
| CN107133976A (en) * | 2017-04-24 | 2017-09-05 | 浙江大学 | A kind of method and apparatus for obtaining three-dimensional hyperspectral information |
| CN107290293A (en) * | 2017-06-06 | 2017-10-24 | 浙江大学 | A kind of spectral imaging technology monitors the device of water planting heavy metal stress crop on-line |
| CN108323295A (en) * | 2017-12-05 | 2018-07-27 | 江苏大学 | A kind of seedling stage crop liquid manure based on multiple dimensioned habitat information detects and controls method and device |
| CN107999399A (en) * | 2017-12-27 | 2018-05-08 | 华侨大学 | Building waste on-line sorting system and method based on the detection of dot matrix EO-1 hyperion |
| CN208064001U (en) * | 2018-02-28 | 2018-11-09 | 北京农业信息技术研究中心 | One plant growth network push device |
| CN109855735A (en) * | 2019-02-20 | 2019-06-07 | 北京理工大学 | A kind of EO-1 hyperion calculating imaging method of synchronously control and acquisition |
| CN109916826A (en) * | 2019-02-20 | 2019-06-21 | 福建南方路面机械有限公司 | A kind of solid waste online recognition system and recognition methods based on EO-1 hyperion detection |
| CN109884035A (en) * | 2019-02-25 | 2019-06-14 | 广东朗研科技有限公司 | A kind of detection device of sample to be tested, detection method and false-proof detection method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110749555A (en) | 2020-02-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110749555B (en) | Hyperspectral technology-based device and method for detecting internal fermentation state of white spirit koji | |
| CN211503153U (en) | Indoor air quality cooperative monitoring and regulation system based on multiple targets | |
| CN103430858B (en) | Mobile remote pet feeding and monitoring system based on Internet | |
| CN210604434U (en) | Online detection device for typical defects of curved glass of mobile phone | |
| CN103392616A (en) | 3G (third generation telecommunication)-based mobile remote pet feeding and monitoring system | |
| CN210155031U (en) | Near-infrared fruit quality nondestructive testing device with illumination angle self-adaptive adjustment function | |
| CN104677827B (en) | A kind of deduction devices and methods therefor of the visible near-infrared diffusing reflection background signal based on portable fiber-optic spectrometer | |
| CN205333123U (en) | Farmland environment automatic monitoring device based on thing networking | |
| CN100357725C (en) | Method and device for rapidly detecting tenderness of beef utilizing near infrared technology | |
| CN113610935A (en) | Automatic fermentation monitoring system of black tea | |
| CN107764976A (en) | Soil nitrogen fast diagnosis method and on-line monitoring system | |
| CN112733958B (en) | Greenhouse ozone concentration control method and system | |
| CN203523512U (en) | Internet-based mobile remote pet nursing and monitor system | |
| CN109324051A (en) | A kind of plant moisture detection method and system | |
| CN102507457A (en) | Device and method for rapidly and nondestructively detecting crop nutrient elements | |
| CN115661057A (en) | Industrial nondestructive testing system and method based on cloud edge cooperation and deep learning | |
| CN104297136B (en) | A kind of method based on high spectrum image to pseudomonas aeruginosa growth prediction | |
| CN105352555B (en) | A kind of portable detector and application method of Rapid identification birds, beasts and eggs storage time | |
| CN105203467A (en) | Universal and nondestructive growth fitting method for fungi | |
| CN116389981B (en) | Power amplifier control system and method based on artificial intelligence | |
| CN111581602A (en) | Air quality index self-adaptive prediction voice system | |
| CN108414683A (en) | air pollution real-time monitoring system | |
| CN112033915A (en) | White spirit adulteration detection system based on portable spectrometer | |
| CN109392780B (en) | Method and device for predicting cold water fish migration under climate change | |
| KR102597253B1 (en) | Smart Farm System Through Video-based Crop Cultivation Growth Platform Construction |
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 |