CN111141836A - Pear early-stage internal disease nondestructive detection method and device based on information fusion of sound-vibration multi-domain spectrum and near infrared spectrum - Google Patents
Pear early-stage internal disease nondestructive detection method and device based on information fusion of sound-vibration multi-domain spectrum and near infrared spectrum Download PDFInfo
- Publication number
- CN111141836A CN111141836A CN202010033329.3A CN202010033329A CN111141836A CN 111141836 A CN111141836 A CN 111141836A CN 202010033329 A CN202010033329 A CN 202010033329A CN 111141836 A CN111141836 A CN 111141836A
- Authority
- CN
- China
- Prior art keywords
- spectrum
- domain
- information
- pear
- sound vibration
- 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.)
- Granted
Links
- 201000010099 disease Diseases 0.000 title claims abstract description 81
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 title claims abstract description 81
- 238000001228 spectrum Methods 0.000 title claims abstract description 54
- 238000001514 detection method Methods 0.000 title claims abstract description 52
- 230000004927 fusion Effects 0.000 title claims abstract description 33
- 238000002329 infrared spectrum Methods 0.000 title claims abstract description 23
- 235000014443 Pyrus communis Nutrition 0.000 title claims description 48
- 238000000034 method Methods 0.000 claims abstract description 53
- 235000021039 pomes Nutrition 0.000 claims abstract description 18
- 238000011161 development Methods 0.000 claims abstract description 6
- 235000013399 edible fruits Nutrition 0.000 claims description 21
- 238000004422 calculation algorithm Methods 0.000 claims description 18
- 238000012545 processing Methods 0.000 claims description 18
- 239000000523 sample Substances 0.000 claims description 18
- 238000005516 engineering process Methods 0.000 claims description 16
- 238000004458 analytical method Methods 0.000 claims description 13
- 238000004433 infrared transmission spectrum Methods 0.000 claims description 13
- 238000000411 transmission spectrum Methods 0.000 claims description 13
- 230000004044 response Effects 0.000 claims description 10
- 238000010801 machine learning Methods 0.000 claims description 9
- 238000013135 deep learning Methods 0.000 claims description 7
- 238000000605 extraction Methods 0.000 claims description 6
- 238000003909 pattern recognition Methods 0.000 claims description 6
- 238000007637 random forest analysis Methods 0.000 claims description 6
- 238000012706 support-vector machine Methods 0.000 claims description 6
- 239000000725 suspension Substances 0.000 claims description 5
- 241000228143 Penicillium Species 0.000 claims description 4
- 238000005520 cutting process Methods 0.000 claims description 4
- 238000007499 fusion processing Methods 0.000 claims description 4
- 241001164374 Calyx Species 0.000 claims description 3
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 230000005540 biological transmission Effects 0.000 claims description 3
- 210000004556 brain Anatomy 0.000 claims description 3
- 238000013527 convolutional neural network Methods 0.000 claims description 3
- 238000011081 inoculation Methods 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 239000013307 optical fiber Substances 0.000 claims description 3
- 238000002360 preparation method Methods 0.000 claims description 3
- 238000010183 spectrum analysis Methods 0.000 claims description 3
- 230000001133 acceleration Effects 0.000 claims description 2
- 238000002347 injection Methods 0.000 claims description 2
- 239000007924 injection Substances 0.000 claims description 2
- 230000001186 cumulative effect Effects 0.000 claims 1
- 238000012847 principal component analysis method Methods 0.000 claims 1
- 230000001737 promoting effect Effects 0.000 abstract description 2
- 241000220324 Pyrus Species 0.000 description 47
- 230000003595 spectral effect Effects 0.000 description 15
- 244000179970 Monarda didyma Species 0.000 description 12
- 235000010672 Monarda didyma Nutrition 0.000 description 12
- 241000220225 Malus Species 0.000 description 9
- 235000021017 pears Nutrition 0.000 description 8
- 230000008569 process Effects 0.000 description 7
- 238000010521 absorption reaction Methods 0.000 description 6
- 208000019622 heart disease Diseases 0.000 description 6
- 230000008901 benefit Effects 0.000 description 5
- 238000012937 correction Methods 0.000 description 5
- 238000011156 evaluation Methods 0.000 description 5
- 238000012360 testing method Methods 0.000 description 5
- 230000007547 defect Effects 0.000 description 4
- 230000018109 developmental process Effects 0.000 description 4
- 238000009826 distribution Methods 0.000 description 4
- 235000015203 fruit juice Nutrition 0.000 description 4
- 238000009659 non-destructive testing Methods 0.000 description 4
- 238000003860 storage Methods 0.000 description 4
- 239000003053 toxin Substances 0.000 description 4
- 231100000765 toxin Toxicity 0.000 description 4
- 108700012359 toxins Proteins 0.000 description 4
- 235000021016 apples Nutrition 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 238000010276 construction Methods 0.000 description 3
- 230000005284 excitation Effects 0.000 description 3
- 238000003384 imaging method Methods 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 239000011550 stock solution Substances 0.000 description 3
- 230000009466 transformation Effects 0.000 description 3
- 238000004497 NIR spectroscopy Methods 0.000 description 2
- 238000005481 NMR spectroscopy Methods 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 2
- 238000000149 argon plasma sintering Methods 0.000 description 2
- 230000002860 competitive effect Effects 0.000 description 2
- 238000012258 culturing Methods 0.000 description 2
- 238000000354 decomposition reaction Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000002068 genetic effect Effects 0.000 description 2
- 238000009499 grossing Methods 0.000 description 2
- 239000001963 growth medium Substances 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 239000008223 sterile water Substances 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Chemical compound O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- UFHFLCQGNIYNRP-UHFFFAOYSA-N Hydrogen Chemical compound [H][H] UFHFLCQGNIYNRP-UHFFFAOYSA-N 0.000 description 1
- 241001123663 Penicillium expansum Species 0.000 description 1
- 235000010724 Wisteria floribunda Nutrition 0.000 description 1
- 244000052616 bacterial pathogen Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000008280 blood Substances 0.000 description 1
- 210000004369 blood Anatomy 0.000 description 1
- 238000010835 comparative analysis Methods 0.000 description 1
- 238000007865 diluting Methods 0.000 description 1
- 238000010790 dilution Methods 0.000 description 1
- 239000012895 dilution Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 235000013569 fruit product Nutrition 0.000 description 1
- 235000019990 fruit wine Nutrition 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 229910052739 hydrogen Inorganic materials 0.000 description 1
- 239000001257 hydrogen Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000012535 impurity Substances 0.000 description 1
- 238000002188 infrared transmission spectroscopy Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000003902 lesion Effects 0.000 description 1
- 238000002156 mixing Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007500 overflow downdraw method Methods 0.000 description 1
- 235000010482 polyoxyethylene sorbitan monooleate Nutrition 0.000 description 1
- 229920000053 polysorbate 80 Polymers 0.000 description 1
- 238000010223 real-time analysis Methods 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000007790 scraping Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000007480 spreading Effects 0.000 description 1
- 238000003892 spreading Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 238000001845 vibrational spectrum Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N29/00—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object
- G01N29/44—Processing the detected response signal, e.g. electronic circuits specially adapted therefor
- G01N29/46—Processing the detected response signal, e.g. electronic circuits specially adapted therefor by spectral analysis, e.g. Fourier analysis or wavelet analysis
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
- G01N21/31—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
- G01N21/35—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light
- G01N21/359—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light using near infrared light
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N29/00—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object
- G01N29/44—Processing the detected response signal, e.g. electronic circuits specially adapted therefor
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N29/00—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object
- G01N29/44—Processing the detected response signal, e.g. electronic circuits specially adapted therefor
- G01N29/4481—Neural networks
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2291/00—Indexing codes associated with group G01N29/00
- G01N2291/02—Indexing codes associated with the analysed material
- G01N2291/023—Solids
Abstract
The invention discloses a nondestructive detection method and a nondestructive detection device for early internal diseases of pomes based on information fusion of acoustic vibration multi-domain spectrums and near infrared spectrums. By the method and the device, the pomes with early internal diseases can be quickly and accurately detected, the early detection of the internal diseases is realized as far as possible, and the method and the device have great significance for improving the commodity rate and market competitiveness of the pomes and promoting the quick and healthy development of the pome industry.
Description
Technical Field
The invention belongs to the technical field of rapid nondestructive testing of agricultural product quality, and particularly relates to a nondestructive testing method and device for early internal diseases of pomes based on information fusion of acoustic vibration multi-domain spectrum and near infrared spectrum.
Background
China is the biggest pear producing country in the world, Xinjiang is one of the main pear producing areas, the yields of Xinjiang bergamot pears and apples in 2017 are 123.09 ten thousand tons and 144.17 thousand tons respectively, and the Xinjiang bergamot pear and apple are important income-increasing and foreign exchange fruit products for Xinjiang fruit growers. The apple and the bergamot pear have internal diseases of different degrees, the mildew heart rate of the red Fuji apple is 27.78%, and the highest corer bergamot pear with the black heart disease in the storage period can reach 30%. When the lesion volume of the pome is less than 5%, the pulp is intact, the eating is not influenced, the pome still has commodity value, but the disease in the pome cannot be discovered as soon as possible due to the concealment of the disease in the pome, the pome is easy to rot and deteriorate, even the whole box of healthy fruits is infected, and serious economic loss is caused to fruit merchants and fruit fresh-keeping enterprises. In addition, the pulp of the diseased fruit is rich in a large amount of toxins, and the toxins are mixed in deep processing links such as fruit juice, fruit wine, fruit cans and the like, so that the toxins of the fruit juice exceed the standard (the Mmax of the toxins of the fruit juice is less than or equal to 50 mu g/Kg specified by the European Union standard), which not only seriously harms human health, but also extremely low the fruit juice outlet rate in China. Therefore, the nondestructive detection method for the internal diseases of the pomes is explored, the internal diseases are found as early as possible, and the nondestructive detection method has great significance for improving the commodity rate and market competitiveness of the pomes and promoting the rapid and healthy development of the pome industry.
In recent years, researchers at home and abroad try to develop a large amount of basic researches on the nondestructive detection problem of the internal diseases of the pomes based on different detection technologies. The nondestructive detection method for the internal diseases of the pomes mainly comprises an X-ray imaging method, a nuclear magnetic resonance technology, a near infrared spectrum analysis technology, an acoustic vibration technology and the like. According to the technical means, each method has certain limitations, and a nondestructive detection method which is high in detection accuracy and high in detection speed for early internal diseases of pomes does not exist so far. The X-ray imaging method has high requirements on safety protection, and is not favorable for popularization and application. The equipment adopted by the nuclear magnetic resonance technology is too expensive and has the defects of low imaging speed and complex detection and analysis process. Due to the interference of factors such as light scattering effect, spectral peak overlapping, baseline drift and the like, the near infrared spectroscopy limits the improvement of early slight disease identification precision. The sound vibration method is a traditional nondestructive detection method with lower technical equipment, the resonance frequency of the sound vibration method is used for carrying out discrimination research on the black heart disease of the bergamot pear by Xuehbo et al (2017) in the subject group, when the disease degree is higher, the resonance frequency difference between healthy fruits and diseased fruits is large, the detection accuracy rate of the black heart disease can reach 96.7%, and is higher than the identification accuracy rate of the Shenderey et al (2010) and Guo Shiming et al (2016) on the internal diseases of the apple approximation degree. However, when the degree of the defect is low, the difference in resonance frequency between the healthy fruit and the damaged fruit is small, and it is difficult to determine whether the change in resonance frequency is caused by the internal defect, and the accuracy of the determination of the blackheart disease is only 3%. Obviously, only extracting frequency domain characteristic parameters from the sound vibration response signals fails to fully mine other richer and more comprehensive potential information related to the internal diseases of pears, and is probably one of the reasons that the sound vibration method is low in detection accuracy of early internal disease pears. Since the multi-domain spectral characteristic parameters of the acoustic-vibration response signals are sensitive to the physical information change of the pear tissue, the near infrared spectrum is better than the method for acquiring the chemical characteristic information change of the hydrogen-containing groups of organic molecules of the pear tissue. If the sound vibration method is combined with the near infrared spectroscopy, the advantages of the two detection methods are fully utilized, the advantages are made full of the advantages, the physical and chemical information fusion of the internal diseases is realized, the development degree of the internal diseases of the pome can be more comprehensively understood, the detection precision of the internal diseases in the early stage of the pome is greatly improved, a new research trend for the rapid nondestructive detection of the internal diseases in the early stage of the pome is provided, the new idea is provided, and no related patent documents exist.
Disclosure of Invention
The invention mainly solves the technical problem of providing a nondestructive detection method and a nondestructive detection device for early internal diseases of pomes based on information fusion of a sound vibration multi-domain spectrum and a near infrared spectrum, particularly, different information fusion technologies are adopted to respectively construct a disease discrimination model fused with information of the sound vibration multi-domain spectrum and the near infrared transmission spectrum, so that accurate detection of early internal diseases of pomes can be realized, necessary scientific basis is provided for research and development of on-line detection technology for internal diseases of pomes in future, and the problem of low detection precision of early internal diseases of pomes in the current grading and storage processes of pomes is solved.
In order to solve the technical problems, the technical scheme adopted by the invention is as follows: comprises the following steps.
The method comprises the following steps: the preparation method of the disease pome sample comprises the following steps: firstly, adopting wound inoculation method to make the concentration be 1.0X 10 on the ultraclean bench by using microinjector10The cfu/mL penicillium spore suspension is injected into a pear kernel area along the calyx end of the pear, the pear sample after injection is transferred into a constant temperature and humidity box, and the internal disease development is carried out in the environment with the temperature of 25 ℃ and the relative humidity of 90%.
Step two: under the condition that the experimental device is stable and reliable, the time domain/frequency domain information and the spectrum information are collected by the acoustic vibration detection device and the near-infrared transmission spectrometer respectively.
Step three: after acquiring a multi-domain spectrum and a transmission spectrum of a sound vibration signal, cutting the pome from a central line part, photographing the cut section by using a Canon-EOS 750D digital camera at a focal length of 30-100 nm, processing the image by using a MatlabR2018a digital image processing tool box, and obtaining an internal disease degree index of the pome by adopting an iterative threshold segmentation method.
Step four: and respectively carrying out data processing on the acquired sound vibration multi-domain spectrum and spectrum information by utilizing a signal processing technology and a spectrum analysis technology, and respectively extracting sound vibration response signal multi-domain spectrum characteristics and transmission spectrum characteristics which can effectively represent the internal disease pome so as to establish a sound vibration multi-domain spectrum/transmission spectrum information characteristic set.
Step five: and constructing a prediction model for judging the internal diseases of the pome on the characteristic layer by utilizing a machine learning algorithm based on the established sound vibration multi-domain spectrum/transmission spectrum information characteristic set.
Step six: based on the single-source sound vibration signal multi-domain spectrum and near-infrared transmission spectrum information feature subset, a machine learning algorithm is utilized to construct a pear internal disease series discrimination analysis model, then a D-S evidence theory is utilized to fuse the probability outputs of the constructed independent series prediction models, and a disease pear discrimination model fused on a decision level is established.
The concentration in the step one is 1.0 multiplied by 1010The preparation method of the cfu/mL penicillium spore suspension comprises the following steps: cutting fruit pulp pieces 5 mm at rotten position of fructus Pyri with sterile knife at SW-CF-1F type superclean bench, mixing with appropriate amount of sterile water to obtain stock solution, sequentially diluting the stock solution to 10-1~10-6100 mu L of stock solution with each dilution factor is coated on a PDA culture medium and cultured in an intelligent constant temperature incubator at 25 ℃ for 7 d. Selecting different colonies, and repeatedly inoculating on a new PDA culture medium by using a plate streaking method until pure strains are obtained. Then inoculating the purified strain on a PDA test tube slant, culturing at 25 ℃ for 7 days, and preserving at low temperature. Inoculating Penicillium expansum to fresh PDA slant, culturing at 25 deg.C for 14 days, adding sterile water containing 0.05% Tween 80, scraping off spores on colony surface with inoculating loop, filtering with 4 layers of gauze to remove impurities such as hypha, observing with blood counting plate under DM2000 type optical microscope, and adjusting spore suspension concentration to 1.0 × 1010cfu/mL for standby.
The method for extracting the multi-domain spectral characteristic parameters of the acoustic vibration signals in the fourth step comprises the following steps: extracting common time-frequency domain statistical characteristic parameters such as mean value, root mean square value, variance, peak value, waveform index, pulse index, margin index, average frequency, center frequency, root mean square frequency and the like from time-frequency domain curves and frequency domain curves by adopting a time domain/frequency domain analysis method; and aiming at a time-frequency domain distribution image obtained by time-frequency analysis processing such as short-time Fourier transform (STFT), Continuous Wavelet Transform (CWT), S Transform (ST) and self-Adaptive Optimal Kernel (AOK), wavelet packet decomposition, integrated empirical mode analysis, a gray level co-occurrence matrix method and a local binary pattern method are adopted to extract characteristics such as time-frequency domain energy distribution, information entropy and image texture. In order to further select the characteristic parameters which are more sensitive to the early internal diseases of the pomes and eliminate irrelevant and redundant information, on the basis of the characteristic extraction, a popularity learning Method (ML), a distance evaluation method (DET) or a maximum correlation minimum redundancy method (mRMR) is adopted for characteristic evaluation so as to obtain a multi-domain spectrum characteristic subset of the vibro-acoustic response signals which has moderate dimensionality and is fully necessary for the fusion detection of the subsequent internal disease information.
In the fourth step, in order to eliminate influences from high-frequency random noise, baseline drift, light scattering, difference of component content information among samples and the like and improve convergence performance of the model, the original spectral data needs to be preprocessed, the scheme tries to process the spectral data by adopting various commonly used preprocessing methods such as vector normalization (Norm), standard normal variable transformation (SNV), Savitzky Golay convolution smoothing (SG-2-Der), Multivariate Scattering Correction (MSC) and the like on all the acquired original spectral variables of the samples, and then plans to adopt variable extraction methods such as a joint interval partial least squares method (is-PLS), a Genetic Algorithm (GA), a continuous projection method (SPA), a Wavelet Transformation (WT), a competitive adaptive reweighting algorithm (CARS) and the like, and the method is based on absorption frequency, absorption intensity, peak area, different waveband integral area and the like, And (3) revealing the difference of the transmission spectrum information of the diseased pomes with different disease degrees by using characteristic information such as absorption intensity ratios of different wavelengths, and finally forming a near-infrared transmission spectrum characteristic subset by optimally screening effective wavelength variables sensitive to the diseased pomes inside.
In the fifth step, a pear internal disease prediction model construction idea based on feature layer multi-source information fusion is that ① is used for constructing prediction models for distinguishing pear internal diseases in feature layers according to established traditional machine learning algorithms capable of effectively representing pear internal disease information feature sets, the BP neural network (BP-ANN), a Support Vector Machine (SVM), an Extreme Learning Machine (ELM), a Random Forest (RF) and the like are adopted, ② is used for self-adaptive extraction and self-learning of pear internal disease features by means of deep learning, deep learning algorithms such as a Deep Belief Network (DBN), a stacked automatic encoder (SDAE), a Deep Convolutional Neural Network (DCNN) and the like are adopted, an original multi-dimensional high-domain pear internal disease information data set is used as input, and detection models for distinguishing pear internal diseases are respectively constructed in the feature layers by adjusting parameters such as weight, hidden layer node number, learning rate, noise factors and the like.
① tries to extract characteristic information of a sound vibration method and a near infrared transmission spectroscopy method respectively by utilizing a D-S evidence theory to construct independent series of prediction model probability outputs for fusion, a disease pome distinguishing model ② fused on a decision level is established for a preliminary distinguishing result obtained by fusion of a heterogeneous information characteristic layer, and information fusion of the heterogeneous information multi-decision model is carried out by adopting a D-S evidence theory to obtain a disease pome distinguishing result fusing the multi-source information and the multi-source decision model.
And analyzing and comparing the prediction performance of the disease pome by the discrimination models constructed at different levels for each model established in the fifth step and the sixth step through the sample division verification set and the correction set, further adopting an ROC curve to perform comparative analysis on the accuracy of discrimination of the disease pome of each model, and finally determining an optimal model for qualitatively and quantitatively analyzing the existence of the internal diseases of the pome and grading the disease degree by using a multi-source information fusion technology to realize accurate detection of the internal diseases at the early stage of the pome.
The computer performs fusion and mode processing on the extracted characteristic signals, wherein the data fusion adopts a traditional machine learning algorithm and a modern deep learning algorithm to construct a high-precision real-time mode classification system to process the acoustic vibration and transmission spectrum data, and the high-precision real-time mode classification system is connected with a database to perform learning and training to obtain a knowledge base, so that the developed system can judge whether the detected sample is damaged or not.
The pear early internal disease nondestructive detection device based on the information fusion of the acoustic vibration multi-domain spectrum and the near infrared spectrum is composed of an acoustic vibration detection system, a near infrared spectrum system and a mode identification and data fusion processing system; the sound vibration detection system comprises a signal generator, a voltage amplifier, a piezoelectric beam type acceleration sensor, a VibPilot vibration control and dynamic signal acquisition Analyzer and SO Analyzer4.1 software matched with the VibPilot vibration control and dynamic signal acquisition Analyzer; the near-infrared transmission spectrum system comprises a spectrum acquisition instrument, an optical fiber probe, a detection table, a light source and a shading dark box; the spectrum acquisition instrument and the matched OceanView spectrum analysis software are respectively connected with a computer; the signal fusion and pattern recognition system in the computer simulates the human brain to perform fusion and pattern recognition processing on the near infrared spectrum data and the acoustic vibration multi-domain spectrum data, and finally the computer determines whether the disease of the pear to be detected exists or not.
The invention has the beneficial effects that: according to the sound vibration characteristics and the optical characteristics of the pear fruit with the internal disease, the sound vibration analysis technology and the spectrum analysis technology are organically combined, a multi-source information fusion processing method is adopted, sound vibration multi-domain spectrum information and near infrared transmission spectrum information are fused, a high-precision real-time mode classification system is used for processing the spectrum and the sound vibration data, the spectrum and the sound vibration data are compared and judged with information in a database established by learning, and the nondestructive detection is carried out on the existence of the internal disease of the pear fruit at the early stage.
The method is used for sorting the pear quality in a grading way and controlling the quality in the processing process, can accurately sort early-stage disease-causing pears in time before the apples are put in storage, prevents early-stage disease-causing pear germs from spreading and infecting healthy fruits in a large area, effectively reduces the morbidity of the fruits in the production, processing and storage periods, simultaneously assists and replaces professional detection personnel, liberates labor force, eliminates artificial subjective factors, improves the production efficiency, and can be popularized and applied to rapid nondestructive detection of internal diseases of other agricultural products.
The method applies the deep learning algorithm and the multi-source information fusion technology to the construction of the pear early internal disease detection model, fully exerts the advantage of self-extraction of features from original data in deep learning, better characterizes the internal information with rich data, can analyze the sound vibration and spectrum data fusion in a short time and then output the result, meets the requirements of rapid and real-time analysis of big data, realizes the intelligent grading treatment of pear early internal diseases, and provides necessary technical support for the construction of a modern intelligent forest fruit industry system.
Drawings
FIG. 1 is a flow chart of the method for fusing vibro-acoustic information and transmission spectrum information according to the present invention.
FIG. 2 is a flow chart of the fusion method of the vibroacoustic information and the transmission spectrum information (DBN is taken as an example).
FIG. 3 is a schematic diagram of the detection system apparatus of the present invention.
The parts in the drawings are numbered as follows: 1. a sound spectrum and spectrum test analysis and report software system; 2. a vibration control and dynamic signal acquisition analyzer; 3. a voltage amplifier; 4. a near infrared spectrum acquisition instrument; 5. and (4) a test platform.
FIG. 4 is a schematic diagram of the test platform structure of the present invention.
The parts in the drawings are numbered as follows: 1. a horizontal slide rail; 2. a horizontal slider; 3. a sensor and a support; 4. a ball screw; 5. a vertical sliding table; 6. a vertical slide rail; 7. fixing a nut; 8. a shading dark box; 9. a light source; 10. an apple sample; 11. a height adjustable stage; 12. a collimating mirror; 13. and a support table.
Detailed Description
The following detailed description of the preferred embodiments of the present invention, taken in conjunction with the accompanying drawings, will make the advantages and features of the invention easier to understand by those skilled in the art, and thus will clearly and clearly define the scope of the invention.
Implementation example steps referring to fig. 1-3, an example implementation apparatus referring to fig. 4, an embodiment of the present invention includes:
taking the bergamot pear blackheart disease as an example, the nondestructive testing of the internal diseases of other fruits can be carried out by referring to the method of the embodiment, and specifically, a new knowledge base is established according to the evaluation standard of the tested sample, so that the nondestructive testing can be carried out on the products.
The multi-source information fusion detection system for the internal diseases in the early stage of the pome consists of a sound vibration detection system, a near infrared spectrum system and a mode identification and data fusion processing system; the near-infrared transmission spectrum system comprises a spectrum acquisition instrument, an optical fiber probe, a detection table, a light source and a shading dark box; the spectrum acquisition instrument and the matched OceanView spectrum analysis software are respectively connected with a computer; the signal fusion and pattern recognition system in the computer simulates the human brain to perform fusion and pattern recognition processing on the near infrared spectrum data and the acoustic vibration multi-domain spectrum data, and finally the computer determines whether the disease of the pear to be detected exists or not. The method comprises the following specific steps.
Firstly, adopting wound inoculation method to make the concentration be 1.0X 10 on the ultraclean bench by using microinjector10Injecting cfu/mL penicillium spore suspension into a pear kernel area along the calyx end of a pear, transferring an injected pear sample into a constant temperature and humidity box, carrying out internal disease development in an environment with the temperature of 25 ℃ and the relative humidity of 90%, and carrying out backup test for 72 h.
Then the apple to be measured is placed on a height-adjustable objective table and is in effective contact with the two 2Q 220-A4-303YB type piezoelectric beam sensors on the two sides of the equator part which are opposite to each other (the middle part of the cantilever beam is 1/3). A semi-sinusoidal pulse signal with the peak voltage of 2.5V is linearly amplified into an excitation signal VA with the peak voltage of 80V through an HA-405 type voltage amplifier. The signal is input to an excitation end sensor in contact with the equator of the bergamot pear sample to vibrate the sample, and a cantilever beam of the sensor is in contact with the bergamot pear and deforms along with the vibration of the bergamot pear, so that a response signal V generated by the vibration of the sampleRE(equatorial response signal) and VRCThe (response signal of the sepal end) is received by the piezoelectric beam type sensor of the sensing end, then the excitation signal and the response signal are both collected by the VibPilot vibration control and dynamic signal collection Analyzer in a mode that the sampling frequency is 51200 Hz and the duration is 0.16 s, and finally the analysis processing is carried out through a software system SO Analyzer 4.1.
Meanwhile, in order to ensure the stability of the light source, the light source is turned on for preheating 15 min before the spectral data is acquired every time. As known from preliminary experiments, the distance between a light source and the surface of an objective table is 130 mm, the Spectrasuite software sets the integration time to be 100ms, the average scanning time is 10, the smoothness is 5, dark noise is removed, and the spectrum data acquired when nonlinear correction and stray light correction are added is optimal. When data are collected, the dark box door is kept in a closed state, the pear sample is placed on the height-adjustable objective table, and the axial direction of the fruit stem is perpendicular to the light source irradiation direction. And 3 points which are uniformly distributed and have no defects are selected at the equatorial plane of each sample to acquire spectral information, the positions of the points are 120 degrees, and finally the average value of the 3 times of data is taken as the spectral data of the sample. All spectrum of the diseased apples is collected under the same condition, and near-infrared transmission spectrum collection is immediately carried out after sound vibration multi-domain spectrum information collection of the diseased pears inside is completed.
After acquiring sound vibration multi-domain spectrum and near infrared spectrum data through a sound vibration detection system and a near infrared spectrum system, extracting common time-domain and frequency-domain statistical characteristic parameters such as a mean value, a root-mean-square value, a variance, a peak value, a waveform index, a pulse index, a margin index, an average frequency, a central frequency, a root-mean-square frequency and the like from time-domain and frequency-domain curves by adopting a time-domain/frequency-domain analysis method; and aiming at a time-frequency domain distribution image obtained by time-frequency analysis processing such as short-time Fourier transform (STFT), Continuous Wavelet Transform (CWT), S Transform (ST) and self-Adaptive Optimal Kernel (AOK), wavelet packet decomposition, integrated empirical mode analysis, a gray level co-occurrence matrix method and a local binary pattern method are adopted to extract characteristics such as time-frequency domain energy distribution, information entropy and image texture.
And performing feature evaluation by adopting a current learning Method (ML), a distance evaluation method (DET) or a maximum correlation minimum redundancy method (mRMR) to obtain a multi-domain spectral feature subset of the acoustic vibration response signal which has moderate dimensionality and is fully necessary for fusion detection of subsequent internal disease information. The spectral data is processed by a plurality of common preprocessing methods such as vector normalization (Norm), standard normal variable transformation (SNV), Savitzky Golay convolution smoothing (SG-2-Der) and Multivariate Scatter Correction (MSC), then, variable extraction methods such as a joint interval partial least square method (is-PLS), a Genetic Algorithm (GA), a continuous projection method (SPA), Wavelet Transform (WT), a competitive adaptive re-weighting algorithm (CARS) and the like are adopted, differences of transmission spectrum information of diseased pears with different disease degrees are revealed based on characteristic information such as absorption frequency, absorption intensity, peak area, integral areas of different wave bands, absorption intensity ratios of different wavelengths and the like, effective wavelength variables which are optimally screened and sensitive to the internally diseased pears form a near-infrared transmission spectrum characteristic subset, and finally a nondestructive detection database for early black heart disease of the bergamot pears is established.
By utilizing a multi-level fusion technology of vibro-acoustic multi-domain spectral information and near infrared spectral information, the vibro-acoustic and spectral information fusion is carried out by adopting methods such as traditional machine learning algorithms such as a BP neural network (BP-ANN), a Support Vector Machine (SVM), an Extreme Learning Machine (ELM), a Random Forest (RF) and the like, deep learning algorithms such as a Deep Belief Network (DBN), a stacked automatic encoder (SDAE), a Deep Convolutional Neural Network (DCNN) and the like, a high-precision real-time mode classification system is constructed to process vibro-acoustic and transmission spectral data and is linked with a database for learning and training to obtain a knowledge base, a discrimination model of the black heart disease bergamot pear fused on a characteristic layer/decision layer is established, and finally the discrimination of the existence of the early black heart disease bergamot pear is realized.
The above description is only an embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes performed by the present specification and drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (5)
1. A method and a device for nondestructive detection of early internal diseases of pomes based on information fusion of sound vibration multi-domain spectrums and near infrared spectrums are characterized by comprising the following steps:
the method comprises the following steps: the preparation method of the disease pome sample comprises the following steps: firstly, adopting wound inoculation method to make the concentration be 1.0X 10 on the ultraclean bench by using microinjector10Injecting cfu/mL penicillium spore suspension into a pear kernel area along the calyx end of a pear, transferring the pear sample after injection into a constant temperature and humidity box, and carrying out internal disease development in an environment with the temperature of 25 ℃ and the relative humidity of 90%;
step two: under the condition that an experimental device is stable and reliable, a sound vibration detection device and a near-infrared transmission spectrometer are respectively utilized to synchronously acquire time domain/frequency domain information and spectrum information;
step three: after acquiring a multi-domain spectrum and a transmission spectrum of a sound vibration signal, cutting a pear from a central line part, transversely cutting the pear along an equator part, shooting pulp by using an intelligent scanner ET18, and calculating the percentage of the area of rotten pulp in the image in the whole cross section area by using image processing software Photoshop;
step four: respectively utilizing a signal processing technology and a spectrum analysis technology to perform data processing on the obtained sound vibration multi-domain spectrum and spectrum information, and respectively extracting sound vibration response signal multi-domain spectrum characteristics and transmission spectrum characteristics which can effectively represent the internal disease pome to establish a sound vibration multi-domain spectrum/transmission spectrum information characteristic set;
step five: establishing a prediction model for judging the internal diseases of the pome in a feature layer by utilizing a machine learning algorithm based on the established sound vibration multi-domain spectrum/transmission spectrum information feature set;
step six: based on the single-source sound vibration signal multi-domain spectrum and near-infrared transmission spectrum information feature subset, a machine learning algorithm is utilized to construct a pear internal disease series discrimination analysis model, then a D-S evidence theory is utilized to fuse the probability outputs of the constructed independent series prediction models, and a disease pear discrimination model fused on a decision level is established.
2. The method and the device for nondestructive detection of the early internal diseases of the pome based on information fusion of the vibro-acoustic multi-domain spectrum and the near infrared spectrum according to claim 1, characterized in that: and repeating the steps to collect the information of the sound vibration multi-domain spectrum and the near infrared transmission spectrum of the healthy fruits according to the requirement that the number ratio of the diseased fruits to the healthy fruits is 1: 1.
3. The method and the device for nondestructive detection of the early internal diseases of the pome based on information fusion of the vibro-acoustic multi-domain spectrum and the near infrared spectrum according to claim 1, characterized in that: and in the fourth step, on the basis of completing the extraction of the multi-domain spectrum characteristic and the near-infrared transmission spectrum characteristic variable of the sound vibration signal, unifying the information dimensions of the multi-domain spectrum of the sound vibration signal and the near-infrared transmission spectrum and carrying out normalization processing, if information is repeatedly expressed in each characteristic parameter of the sound vibration multi-domain spectrum/near-infrared spectrum, reducing the dimensions by adopting a principal component analysis method, so that the selected principal components are not related to each other, the cumulative contribution rate of the variance reaches more than 80%, and finally constructing a multi-domain spectrum/spectrum information characteristic set capable of effectively representing internal diseases according to the number and the score condition of the selected principal components.
4. The method and the device for nondestructive detection of the early internal diseases of the pome based on information fusion of the vibro-acoustic multi-domain spectrum and the near infrared spectrum according to claim 1, characterized in that: the machine learning algorithm in the fifth step comprises traditional machine learning algorithms such as a BP neural network (BP-ANN), a Support Vector Machine (SVM), an Extreme Learning Machine (ELM), a Random Forest (RF) and the like, and deep learning algorithms such as a Deep Belief Network (DBN), a stacked automatic encoder (SDAE), a Deep Convolutional Neural Network (DCNN) and the like.
5. The device for realizing the method for nondestructively detecting the internal diseases in the early stage of the pome based on the information fusion of the acoustic vibration multi-domain spectrum and the near infrared spectrum is characterized by comprising an acoustic vibration detection system, a near infrared spectrum system and a mode identification and data fusion processing system; the sound vibration detection system comprises a signal generator, a voltage amplifier, a piezoelectric beam type acceleration sensor, a VibPilot vibration control and dynamic signal acquisition analyzer and SO Analyzer4.1 software matched with the VibPilot vibration control and dynamic signal acquisition analyzer; the near-infrared transmission spectrum system comprises a spectrum acquisition instrument, an optical fiber probe, a detection table, a light source and a shading dark box, wherein the spectrum acquisition instrument and the OceanView acquisition analyzer are respectively connected with a computer; the signal fusion and pattern recognition system in the computer simulates the human brain to perform fusion and pattern recognition processing on the near infrared spectrum data and the acoustic vibration multi-domain spectrum data, and finally the computer determines whether the disease of the pear to be detected exists or not.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010033329.3A CN111141836B (en) | 2020-01-13 | 2020-01-13 | Method and device for nondestructive detection of early internal diseases of pome based on fusion of sound vibration multi-domain spectrum and near infrared spectrum information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010033329.3A CN111141836B (en) | 2020-01-13 | 2020-01-13 | Method and device for nondestructive detection of early internal diseases of pome based on fusion of sound vibration multi-domain spectrum and near infrared spectrum information |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111141836A true CN111141836A (en) | 2020-05-12 |
| CN111141836B CN111141836B (en) | 2023-07-18 |
Family
ID=70524757
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010033329.3A Active CN111141836B (en) | 2020-01-13 | 2020-01-13 | Method and device for nondestructive detection of early internal diseases of pome based on fusion of sound vibration multi-domain spectrum and near infrared spectrum information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111141836B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111693488A (en) * | 2020-06-08 | 2020-09-22 | 济南大学 | Fruit grade classification method and system based on DS evidence theory fusion |
| CN111855800A (en) * | 2020-07-17 | 2020-10-30 | 西南科技大学 | Method for rapidly and nondestructively measuring shelf life or optimal edible period of fruit by acoustic vibration |
| CN113295674A (en) * | 2021-04-29 | 2021-08-24 | 中国科学院沈阳自动化研究所 | Laser-induced breakdown spectroscopy characteristic nonlinear processing method based on S transformation |
| CN113484738A (en) * | 2021-05-25 | 2021-10-08 | 北京航空航天大学 | Circuit fault diagnosis method based on multi-feature information fusion |
| CN114092710A (en) * | 2021-11-23 | 2022-02-25 | 沈阳农业大学 | Construction method of DCNN leaf blast classification model based on fusion characteristics |
| CN117807511A (en) * | 2024-02-29 | 2024-04-02 | 北京佳格天地科技有限公司 | Crop disease identification method based on spectral analysis and related device |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5402782A (en) * | 1993-03-05 | 1995-04-04 | University Of Kentucky Research Foundation | Apparatus and method for noninvasive chemical analysis |
| AU2002314969A1 (en) * | 2001-06-06 | 2002-12-16 | University Of Kentucky Research Foundation | Multimode structure for current measurement, ultrasonic and near-ir spectrum collection and processing |
| KR101228513B1 (en) * | 2012-11-29 | 2013-01-31 | 케이엔디이주식회사 | A system of non-destructive inspection |
| CN103063585A (en) * | 2013-01-05 | 2013-04-24 | 石河子大学 | Rapid nondestructive lemon and fruit maturity testing device and testing system establishment method |
| EP2913638A1 (en) * | 2014-02-28 | 2015-09-02 | Fuji Jukogyo Kabushiki Kaisha | Vibration detection apparatus and vibration detection method |
| US20170356842A1 (en) * | 2016-06-09 | 2017-12-14 | Adelphi University | Real-time trace gas sensor using a multi-mode diode laser and multiple line integrated cavity enhanced absorption spectroscopy |
| CN109100323A (en) * | 2018-08-20 | 2018-12-28 | 江苏大学 | A kind of transmitted spectrum harmless quantitative evaluation method of apple water core |
| CN109932333A (en) * | 2019-04-04 | 2019-06-25 | 浙江大学 | The fruit firmness measuring system and method for acoustic vibration and near infrared spectrum fusion |
| CN110376159A (en) * | 2019-08-22 | 2019-10-25 | 华东交通大学 | Yali pear black heart method for quick identification based on near-infrared diffusing transmission spectrum |
-
2020
- 2020-01-13 CN CN202010033329.3A patent/CN111141836B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5402782A (en) * | 1993-03-05 | 1995-04-04 | University Of Kentucky Research Foundation | Apparatus and method for noninvasive chemical analysis |
| AU2002314969A1 (en) * | 2001-06-06 | 2002-12-16 | University Of Kentucky Research Foundation | Multimode structure for current measurement, ultrasonic and near-ir spectrum collection and processing |
| KR101228513B1 (en) * | 2012-11-29 | 2013-01-31 | 케이엔디이주식회사 | A system of non-destructive inspection |
| CN103063585A (en) * | 2013-01-05 | 2013-04-24 | 石河子大学 | Rapid nondestructive lemon and fruit maturity testing device and testing system establishment method |
| EP2913638A1 (en) * | 2014-02-28 | 2015-09-02 | Fuji Jukogyo Kabushiki Kaisha | Vibration detection apparatus and vibration detection method |
| US20170356842A1 (en) * | 2016-06-09 | 2017-12-14 | Adelphi University | Real-time trace gas sensor using a multi-mode diode laser and multiple line integrated cavity enhanced absorption spectroscopy |
| CN109100323A (en) * | 2018-08-20 | 2018-12-28 | 江苏大学 | A kind of transmitted spectrum harmless quantitative evaluation method of apple water core |
| CN109932333A (en) * | 2019-04-04 | 2019-06-25 | 浙江大学 | The fruit firmness measuring system and method for acoustic vibration and near infrared spectrum fusion |
| CN110376159A (en) * | 2019-08-22 | 2019-10-25 | 华东交通大学 | Yali pear black heart method for quick identification based on near-infrared diffusing transmission spectrum |
Non-Patent Citations (3)
| Title |
|---|
| SIRINAD NOYPITAK 等: "Detection of cracked shell in intact aromatic young coconut using near infrared spectroscopy and acoustic response methods", vol. 13, pages 1991 - 1999, XP036860785, DOI: 10.1007/s11694-019-00119-2 * |
| 王志鹏 等: "基于声振频带幅值特性香梨硬度无损检测研究", vol. 32, no. 32, pages 343 - 349 * |
| 陆勇 等: "声学技术在西瓜品质无损检测中的应用", pages 77 - 81 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111693488A (en) * | 2020-06-08 | 2020-09-22 | 济南大学 | Fruit grade classification method and system based on DS evidence theory fusion |
| CN111693488B (en) * | 2020-06-08 | 2022-12-06 | 济南大学 | Fruit grade classification method and system based on DS evidence theory fusion |
| CN111855800A (en) * | 2020-07-17 | 2020-10-30 | 西南科技大学 | Method for rapidly and nondestructively measuring shelf life or optimal edible period of fruit by acoustic vibration |
| CN113295674A (en) * | 2021-04-29 | 2021-08-24 | 中国科学院沈阳自动化研究所 | Laser-induced breakdown spectroscopy characteristic nonlinear processing method based on S transformation |
| CN113484738A (en) * | 2021-05-25 | 2021-10-08 | 北京航空航天大学 | Circuit fault diagnosis method based on multi-feature information fusion |
| CN114092710A (en) * | 2021-11-23 | 2022-02-25 | 沈阳农业大学 | Construction method of DCNN leaf blast classification model based on fusion characteristics |
| CN117807511A (en) * | 2024-02-29 | 2024-04-02 | 北京佳格天地科技有限公司 | Crop disease identification method based on spectral analysis and related device |
| CN117807511B (en) * | 2024-02-29 | 2024-04-26 | 北京佳格天地科技有限公司 | Crop disease identification method based on spectral analysis and related device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111141836B (en) | 2023-07-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111141836B (en) | Method and device for nondestructive detection of early internal diseases of pome based on fusion of sound vibration multi-domain spectrum and near infrared spectrum information | |
| CN108663339B (en) | On-line detection method for mildewed corn based on spectrum and image information fusion | |
| CN101206463B (en) | Method and system for on-line monitoring medicaments production mixing process | |
| CN110907393B (en) | Method and device for detecting saline-alkali stress degree of plants | |
| CN107170445A (en) | The parkinsonism detection means preferably differentiated is cooperateed with based on voice mixing information characteristics | |
| CN105158186A (en) | Method for detecting black core of white radish based on hyperspectral image | |
| Zhao et al. | Early detection of moldy apple core based on time-frequency images of vibro-acoustic signals | |
| CN111157511A (en) | Egg freshness nondestructive testing method based on Raman spectrum technology | |
| CN108801971A (en) | Mould based on high light spectrum image-forming technology infects the detection method of Chinese chestnut | |
| Zhaoyong et al. | Detection of moldy core in apples and its symptom types using transmittance spectroscopy | |
| CN109541031A (en) | Fruit hardness detection method based on acoustics and vibration characteristics | |
| CN105911000A (en) | Characteristic wave band based blood spot egg on-line detection method | |
| Fu et al. | Discrimination of pear varieties using three classification methods based on near-infrared spectroscopy | |
| JP2002005827A (en) | Method for acquisition of information on specimen | |
| CN113030008B (en) | Near-infrared online quality detection method for cattail pollen charcoal processed product | |
| CN112086137B (en) | Method for quantitatively analyzing sorbose content in fermentation liquor | |
| Chu et al. | A Vis/NIR spectra-based approach for identifying bananas infected with Colletotrichum musae | |
| Hsieh et al. | Applied visible/near-infrared spectroscopy on detecting the sugar content and hardness of pearl guava | |
| CN114414521A (en) | Milk main component measuring method based on infrared multispectral sensor | |
| CN112801172A (en) | Chinese cabbage pesticide residue qualitative analysis method based on fuzzy pattern recognition | |
| CN112666110A (en) | Spectral identification model and method for milk and goat milk | |
| CN113628741A (en) | Health state identification method based on exhaled gas marker detection | |
| CN113418889B (en) | Real-time detection method for water content and total colony count of dried vegetables based on deep learning | |
| CN112067577A (en) | Method, device and equipment for identifying overproof cream pigment based on support vector machine | |
| CN100494982C (en) | Non-destructive detection method for quickly detecting inner quality of pear |
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 |