CN107202761A - The portable detection equipment and detection method of a kind of quick detection fruit internal quality - Google Patents

The portable detection equipment and detection method of a kind of quick detection fruit internal quality Download PDF

Info

Publication number
CN107202761A
CN107202761A CN201710434363.XA CN201710434363A CN107202761A CN 107202761 A CN107202761 A CN 107202761A CN 201710434363 A CN201710434363 A CN 201710434363A CN 107202761 A CN107202761 A CN 107202761A
Authority
CN
China
Prior art keywords
fruit
detection
light source
acidity
portable
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201710434363.XA
Other languages
Chinese (zh)
Inventor
肖建喜
武臣
路远
路小亮
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Gansu Danong Crafts Technology Co Ltd
Original Assignee
Gansu Danong Crafts Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Gansu Danong Crafts Technology Co Ltd filed Critical Gansu Danong Crafts Technology Co Ltd
Priority to CN201710434363.XA priority Critical patent/CN107202761A/en
Publication of CN107202761A publication Critical patent/CN107202761A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G01MEASURING; TESTING
    • G01NINVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/17Systems in which incident light is modified in accordance with the properties of the material investigated
    • G01N21/25Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01NINVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/17Systems in which incident light is modified in accordance with the properties of the material investigated
    • G01N21/25Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
    • G01N21/31Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
    • G01N21/35Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infra-red light
    • G01N21/3563Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infra-red light for analysing solids; Preparation of samples therefor
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01NINVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/17Systems in which incident light is modified in accordance with the properties of the material investigated
    • G01N21/25Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
    • G01N21/31Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
    • G01N21/35Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infra-red light
    • G01N21/359Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infra-red light using near infra-red light
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01NINVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/17Systems in which incident light is modified in accordance with the properties of the material investigated
    • G01N21/41Refractivity; Phase-affecting properties, e.g. optical path length
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01NINVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N33/00Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
    • G01N33/02Food
    • G01N33/025Fruits or vegetables

Abstract

The invention discloses a kind of portable detection equipment of quick detection fruit internal quality and detection method, including light source and detector module, governor circuit board component, shell, data wire, power supply module and display device;Bluetooth communication is carried out between the Bluetooth chip and display device of governor circuit board component;Detection method comprises the following steps, and spectra collection is carried out to fruit sample by portable detection equipment;Pol and acidity measurement are carried out to fruit sample;Build the forecast model of sugar degree;Build the forecast model of fruit acidity;Gather the spectral information of fruit to be measured and substitute into forecast model, obtain the pol of fruit to be measured and the predicted value of acidity.The present invention portable detection equipment have the advantages that small volume, can carry with, chargeable and endurance is strong.This detection method is destructive compared to traditional detection acidity of fruit confection to damage detection method, can carry out the pol and acidity two indices of the detection fruit of real non-destructive;It can be achieved to detect various fruits.

Description

The portable detection equipment and detection method of a kind of quick detection fruit internal quality
Technical field:
The invention belongs to fruit detection technique field, and in particular to a kind of portable inspection of quick detection fruit internal quality Measurement equipment and detection method.
Background technology:
Fruit industry significant, everyone daily life of fruit quality direct relation in Chinese national economy life It is living.Current China fruit commercialization level is still relatively low, and fruit quality is uneven, highly desired convenient convenient fruit detection And classification technique.The sugar and acid degree of fruit can represent the quality of fruit to a certain extent, at present to the detection of acidity of fruit confection Damage-type detection is depended on, i.e., the sugar content and pH value of the inside are detected by the way that fruit is squeezed the juice.This method needs pair Fruit is destroyed, and the detection for fruit quality can only be inspected by random samples, while adding cost, causes substantial amounts of waste. Its cumbersome sample preparation, prolonged detection process, are not used to the daily kind to fruit of consumer and detect.
Near infrared spectrum has abundant structure and composition information, suitable for the internal component such as pol of measurement, acidity.Near-infrared Spectral detection is as a kind of detection speed is fast, accuracy rate is high, safety and nondestructive detection technique receives much concern.Near infrared spectrum is detected Technology has obtained certain applications in the field of non destructive testing of fruit, and near infrared detection equipment also increasingly tends to miniaturization, facilitation. However, current near infrared detection equipment is required for external power supply, it is impossible to carry with, application scenarios are limited.Moreover, near-infrared Spectroscopic methodology is only used preliminarily for the detection of the pol and acidity of a few species fruit.In order to meet ordinary consumer to fruit quality Higher and higher to require, the real portable detection device of various fruits can be detected simultaneously by being badly in need of exploitation.
The content of the invention:
The technical problems to be solved by the invention are:There is provided that a kind of detection speed is fast, Detection accuracy is high and safety and nondestructive Be used for detect the portable detection equipment and detection method of fruit internal quality.
In order to solve the above-mentioned technical problem, the present invention is achieved by the following technical solutions:A kind of quick detection fruit The portable detection equipment of inside quality, including light source and detector module, governor circuit board component, shell, data wire, power supply Module and display device;
The light source and detector module are by light source module, detector, detector chip and data interface group into the inspection Survey device and detector chip is integrated on light source module, the data-interface is connected to detector chip by circuit;
The governor circuit board component includes being additionally provided with substrate and the main control chip being arranged on substrate, the substrate By circuit be connected to the signal acquisition amplifying circuit of main control chip, analog-to-digital conversion circuit, Bluetooth chip, power control circuit, Inner button and charging inlet;
The signal that the data-interface of the light source and detector module is connected to governor circuit board component by data wire is adopted Collect amplifying circuit, the power control circuit of the governor circuit board component is connected with power supply module by circuit;
Bluetooth communication is carried out between the Bluetooth chip and display device of the governor circuit board component;
The light source and detector module are arranged on the housing of shell, the governor circuit board component, data wire, power supply Module is arranged at enclosure interior.
As a kind of preferred technical scheme of portable detection equipment, the light source module is one wavelength range of transmitting 5 to 500 spot lights, the wavelength of spot light is in 500nm~1800nm is interval, the detection of the light source and detector module Device is photodiode, and light source module is integrated in a substrate from six pieces of LED chips and constitutes LED array, one piece of pole of photoelectricity two Pipe is integrated in the center of LED array, and the power supply module selects chargeable lithium cell.
As a kind of preferred technical scheme of portable detection equipment, the housing is divided into what is mutually fixed by fastener Upper shell and lower house, the governor circuit board component are fixed on inside lower house by screens, and the power supply module is arranged on On the substrate of governor circuit board component, it is provided with the top of the upper shell in circular hole, and circular hole and is provided with inner button control Component, the inner button control assembly includes spring, outer button and light guide ring, and the outer button and light guide ring are arranged on In the circular hole set at the top of upper shell, in the screens of the spring button mounted externally, the upper shell front end offer with Light source and detector module size identical window, the light source and detector module are placed in window, also set in the window The quartz glass plate for protecting light source and detector module is equipped with, the lower house rear end is further opened with keyhole.
The detection method of the portable detection equipment of quick detection fruit internal quality, it is characterised in that:Including following step Suddenly,
S1 spectra collection), is carried out to fruit sample by portable detection equipment, original spectrum is obtained;
S2 pol and acidity measurement), are carried out to fruit sample, and takes measured value as the observation of analysis forecast model;
S3 the forecast model of sugar degree), is built, passes through neural network algorithm, SVMs and particle cluster algorithm Classified and multiple authentication, the final forecast model for determining that sugar degree is optimal;
S4 the forecast model of fruit acidity), is built, passes through neural network algorithm, SVMs and particle cluster algorithm Classified and multiple authentication, the final forecast model for determining that fruit acidity is optimal;
S5), gather the spectral information of fruit to be measured and be updated in the forecast model that step D and step F is set up, treated Survey the pol of fruit and the predicted value of acidity.
As a kind of optimal technical scheme of detection method, the portable detection equipment in step A is anti-using overflowing The acquisition mode penetrated, the point randomly selected on the ring equatorial plane of each fruit carries out spectral scan.
As a kind of optimal technical scheme of detection method, the measuring method of sugar degree is in step B:First The prism of saccharimeter is cleaned up and cleans moisture post-equalization with distilled water and is returned to zero, then the fruit for having surveyed spectrum is cut And juice is extruded in being measured on the minute surface of refractive prism three times, average;The measuring method of fruit acidity is:With distillation Water cleaning hand-held pH meter front end, until pH value is shown as neutral, pH meter is inserted on the fruit ring equatorial plane, 6 positions are measured PH value, average.
As a kind of optimal technical scheme of detection method, the fruit based on BP networks in step S3 and step S4 Sorting algorithm includes BP neural network structure, BP neural network training and BP neural network three steps of classification.
As a kind of optimal technical scheme of detection method, SVMs study is calculated in step S3 and step S4 The kernel function of method includes linear kernel function, Polynomial kernel function, Radial basis kernel function and two layers of perceptron kernel function.
As a kind of optimal technical scheme of detection method, Particle Swarm Optimization described in step S3 and step S4 Method is by comparing fitness value and individual extreme value, fitness value more new individual extreme value Pbest and the group of colony's extreme value of new particle Body extreme value Gbest positions are set up.
As a kind of optimal technical scheme of detection method, the detectable fruit of detection method includes apple Really, strawberry, orange, grape, longan, orange, pears, Kiwi berry, banana, cherry tomato.
Compared with prior art, usefulness of the present invention is:
The present invention portable detection equipment have the advantages that small volume, can carry with, chargeable and endurance is strong.
This detection method is destructive compared to traditional detection acidity of fruit confection to damage detection method, can carry out in real time The pol and acidity two indices of lossless detection fruit, with low cost, nothing quick with simple, convenient directly perceived, detection The advantages of needing chemical reagent and be pollution-free, meets the daily detection requirement to fruit quality of ordinary consumer, and can be real Now various fruits are detected.
Brief description of the drawings:
The present invention is further described below in conjunction with the accompanying drawings.
Fig. 1 is the overall schematic of portable detection equipment;
Fig. 2 is the decomposition chart of portable detection equipment;
Fig. 3 is BP neural network algorithm flow;
Fig. 4 is the architecture of SVMs;
Fig. 5 is the pol and acidity distribution map of various fruits;
Fig. 6 is to optimize the mixed model constituted by particle cluster algorithm by BP neural network, SVMs to predict apple Pol and acidity prognostic chart;
Fig. 7 is the pol and acidity prognostic chart by BP neural network model prediction strawberry;
Fig. 8 is the pol and acidity prognostic chart by BP neural network model prediction orange;
Embodiment:
Below in conjunction with the accompanying drawings and embodiment the present invention will be described in detail:
A kind of portable detection equipment of quick detection fruit internal quality as depicted in figs. 1 and 2, including light source and inspection Survey device assembly 1, governor circuit board component 3, shell, data wire 12, power supply module 4 and display device;
The light source and detector module 1 by light source module, detector, detector chip and data interface group into, in order to Reduce equipment volume, the detector and detector chip are integrated on light source module, and the data-interface is connected by circuit It is connected to detector chip;
The governor circuit board component 3 includes also setting up on substrate and the main control chip being arranged on substrate, the substrate There are signal acquisition amplifying circuit, analog-to-digital conversion circuit, Bluetooth chip, the power supply electricity that main control chip is connected to by circuit Road, inner button and charging inlet;
The data-interface of the light source and detector module 1 is connected to the letter of governor circuit board component 3 by data wire 12 Number collection amplifying circuit, the power control circuit of the governor circuit board component 3 is connected with power supply module 4 by circuit, is examined The analog signalses of survey device output are transferred to the signal acquisition amplifying circuit on main control board 3 by flexible data line, afterwards Data enter main control chip by analog to digital conversion circuit again and carry out data processing, and the result after processing is carried out by Bluetooth chip Transmission, main control board 3 is except data acquisition, data processing, the function such as data are sent, also to light source module and power supply module 4 The inner button being powered on management, governor circuit board component 3 is the quick closing valve of integral device and the switch of detection control.
Bluetooth communication is carried out between the Bluetooth chip and display device of the governor circuit board component 3, testing result can show Show on the mobile phone A PP with this coordinative composition of equipments.
The light source and detector module 1 are arranged on the housing of shell, the governor circuit board component 3, data wire 12, Power supply module 4 is arranged at enclosure interior.
The light source module for one wavelength range of transmitting 5 to 500 spot lights, the wavelength of spot light 500nm~ In 1800nm is interval, the detector of the light source and detector module is photodiode, and the light source is not traditional halogen tungsten Lamp source, but the narrow LED/light source of small volume, wavelength;In order to further reduce the size of equipment, not using traditional LED Paster is encapsulated, but redesigns LED substrate, and light source module is integrated in a substrate from six pieces of LED chips and constitutes LED times Row, one piece of photodiode is integrated in the center of LED array, and such design reduces small product size to greatest extent, described Power supply module 4 selects chargeable lithium cell.
The housing is divided into the upper shell 6 and lower house 2 mutually fixed by fastener, and the governor circuit board component 3 leads to Cross screens to be fixed on inside lower house 2, the power supply module 4 is arranged on the substrate of governor circuit board component 3, the upper shell 6 tops, which are provided with circular hole, and circular hole, is provided with inner button control assembly, and the inner button control assembly includes spring 7th, outer button 8 and light guide ring 9, the outer button 8 and light guide ring 9 are arranged in the circular hole that the top of upper shell 6 is set, outside Button is surrounded by the guide-lighting groove for showing detection progress, in the screens of the button 8 mounted externally of spring 7, outside Button 8 is used as the inner button on control governor circuit board component 3, and spring 7 is upspring after being pressed as outer button 8, it is described The front end of upper shell 6 offer with light source and the size identical window of detector module 1, the light source and detector module 1 are placed in In window, the quartz glass plate 11 for protecting light source and detector module 1, the lower house 2 are additionally provided with the window Rear end is further opened with keyhole 5.
When detecting fruit, the APP supporting with present device is first turned on, and match somebody with somebody mobile phone with this equipment by bluetooth It is standby, the quartz glass plate 11 on this equipment top is then close to fruit surface, outer button 8 is pressed, when the surrounding of outer button 8 Guide-lighting groove is green by red change, represents that detection terminates, the numerical value of acidity of fruit confection now can be just seen on mobile phone A PP.
Embodiment one:
The sugar and acid degree of fruit is detected using above-mentioned portable detection equipment, choose first appearance not damaged, no disease and pests harm and Ten kinds of fresh fruit, its be respectively strawberry 68, orange 46, orange 76, pears 76, longan 55, Kiwi berry 30, Apple 366, grape 30, cherry tomato 60,38, persimmon and 26, banana, and to being numbered in every kind of fruit carry out group.
The collection of near infrared spectrum data uses irreflexive mode by portable detection equipment, obtains each fruit six Spectroscopic data under different wave length, data, the spectroscopic data that each sample collection is arrived are read by Bluetooth transmission to mobile phone A PP Data analysis for after.
The pol of each fruit sample is detected using handheld digital refractive power saccharimeter, first with distilled water by saccharimeter Prism is cleaned up and cleans moisture, correction zeroing, then the fruit knife for having surveyed spectrum is cut and juice is extruded in folding On the minute surface of light prism, measure three times, average.
The acidity of each fruit sample is detected using taper pen type pH meter, hand-held pH meter front end is cleaned with distilled water, directly It is neutrality to display pH, pH meter is inserted on the fruit ring equatorial plane, measures the pH value of 6 positions, average.
Because types of fruits is more, we are modeled using BP neural network respectively to every kind of fruit.Apple data volume It is larger, we using by BP neural network, SVMs and particle cluster algorithm optimize the mixed model that constitutes carry out pol, Acidity is predicted.
As shown in figure 3, BP neural network is a kind of multilayer feedforward neural network, the network be mainly characterized by before signal to Transmission, error back propagation.In forward direction transmission, input signal is successively handled from input layer through hidden layer, until output layer.Often One layer of neuron state under the influence of one layer of neuron state.If output layer cannot get desired output, reverse biography is transferred to Broadcast, network weight and threshold value are adjusted according to predicated error, so that BP neural network prediction output constantly approaches desired output.BP Training network is first had to before neural network prediction, makes network that there is associative memory and predictive ability by training.Based on BP networks Algorithm include BP neural network build, BP neural network training and BP neural network classify three steps.
SVMs (Support Vector Machine, SVM), as multi-Layer Perceptron Neural Network and Radial Basis Function Network Network is the same, available for pattern classification and nonlinear regression.SVMs is to set up an Optimal Separating Hyperplane as decision-making curved surface, So that the isolation edge between positive example and counter-example is maximized.The theoretical foundation of SVMs is statistical learning, is structure wind The approximate realization that danger is minimized.SVMs has advantages below:(1) versatility:Can be in very wide various collections of functions Constructed fuction;(2) robustness:It need not finely tune;(3) validity:Always belonged in solving practical problems the best way it One;(4) calculate simple:The realization of method only needs to utilize simple optimisation technique;(5) it is perfect in theory:Based on VC generalizations Theoretical framework.As shown in figure 4, inner product core between the vector x that " supporting vector " x (i) and the input space are extracted this without exception Thought is the key for constructing SVMs learning algorithm.SVMs is the small subset extracted by algorithm from training data Constitute.Wherein K is the kernel function of SVMs, and its species mainly has:Linear kernel function, Polynomial kernel function, radial direction base core Function and two layers of perceptron kernel function.
Particle swarm optimization algorithm (Particle Swarm Optimization, PSO) is a population in computational intelligence field The optimized algorithm of body intelligence.PSO algorithms come from the research to birds predation, and when birds prey on, every bird finds food most Simple effective method is exactly the peripheral region for searching the nearest bird of current distance food.PSO algorithms are from this biotic population Gained enlightenment in behavioural characteristic and for solving-optimizing problem, each particle represent a potential solution of problem in algorithm, The fitness value that each particle correspondence one is determined by fitness function.The speed of particle determine particle movement direction and away from Enter Mobile state with the mobile experience of itself and other particles from, speed to adjust, thus realize individual can be in solution space optimizing. PSO algorithms can initialize a group particle in solution space first, each particle represent one of extremal optimization problem it is potential most Excellent solution, with position, speed and the index expression of fitness value three particle characteristicses, fitness value is calculated by fitness function Arrive, the quality of its value represents the quality of particle.Particle is moved in solution space, by tracking individual extreme value Pbest and colony pole Value Gbest more new individual positions;Individual extreme value Pbest refers to that individual undergoes and the optimal position of obtained fitness value is calculated in position Put, colony fund-raising Gbest refers to the fitness optimal location that all particle search in population are arrived.Particle often updates once position Put, just calculate a fitness value, and by comparing fitness value and individual extreme value, the fitness of colony's extreme value of new particle It is worth more new individual extreme value Pbest and colony extreme value Gbest positions.
As shown in figure 5, we measure the pol and acidity of above-mentioned fruit, and make distribution map.
The pol of all kinds of fruit is respectively:Cherry tomato 8.0-4.2, strawberry 8.8-5.3, orange 15.2-7.8, pears 13.0-7.6, orange 13.7-8.6, persimmon 15.9-8.4, Kiwi berry 16.1-11.9, apple 20.7-10.5, grape 17.9- 14.5 and longan 23.0-17.4.
The acidity of all kinds of fruit is respectively:Strawberry 3.87-3.23, orange 4.03-3.08, grape 4.00-3.33, apple Fruit 4.54-3.51, orange 4.94-3.02, cherry tomato 4.55-3.69, pears 5.27-4.40, Kiwi berry 5.56-4.32 and persimmon 5.40-3.73。
It can be seen that, although the distributed area of the sugar of different fruit, acidity is overlapping, still there is obvious difference, it is different The distribution section of the corresponding different sugar and acid degree of the fruit of species.
As shown in fig. 6, analyzing BP neural network, SVMs, the mixed model pair of particle cluster algorithm optimization composition The prediction effect of apple sugar content and acidity.(A) test set triangle is pol actual value in Fig. 6, and square is glucose prediction value, (B) it is the percentage error of glucose prediction, the acidity actual value (triangle) and predicted value (square) of (C) test set, (D) acidity The percentage error of prediction.In glucose prediction model, predicted value is substantially identical with actual value, and percentage error is smaller, average exhausted It is 3.24% to percentage error.In acidity prediction, most of calculating value distribution is distributed in around actual value, and average absolute percentage is missed Difference is 13.49%.Therefore the mixed model set up can be very good to predict the pol and acidity of apple.
As shown in fig. 7, analyzing prediction effect of the BP neural network model to strawberry pol and acidity.(A) is tested in Fig. 7 Integrate triangle as pol actual value, square is glucose prediction value, and (B) is the percentage error of glucose prediction, the acid of (C) test set Spend actual value (triangle) and predicted value (square), the percentage error of (D) acidity prediction.In glucose prediction model, predicted value It is distributed in around actual value, mean absolute percentage error is 10.93%.In acidity prediction, predicted value largely compares actual value It is higher, but difference is less, and mean absolute percentage error is 4.59%.Therefore the BP models set up can be very good to predict strawberry Pol and acidity.
As shown in figure 8, analyzing prediction effect of the BP neural network model to orange pol and acidity.(A) is tested in Fig. 8 Integrate triangle as pol actual value, square is glucose prediction value, and (B) is the percentage error of glucose prediction, the acid of (C) test set Spend actual value (triangle) and predicted value (square), the percentage error of (D) acidity prediction.In glucose prediction model, predicted value Actual value both sides are distributed in, mean absolute percentage error is 9.33%.In acidity prediction, calculating value distribution is distributed in actual value two , there is identical trend side, preferably, mean absolute percentage error is 6.41% to prediction effect with actual value.Therefore the BP set up Model can be very good to predict the pol and acidity of orange.
It is obvious to a person skilled in the art that the invention is not restricted to the details of above-mentioned one exemplary embodiment, Er Qie In the case of without departing substantially from spirit or essential attributes of the invention, the present invention can be realized in other specific forms.Therefore, no matter From the point of view of which point, embodiment all should be regarded as exemplary, and be nonrestrictive, the scope of the present invention is by appended power Profit is required rather than described above is limited, it is intended that all in the implication and scope of the equivalency of claim by falling Change is included in the present invention.Any reference in claim should not be considered as to the claim involved by limitation.

Claims (10)

1. a kind of portable detection equipment of quick detection fruit internal quality, it is characterised in that:Including light source and detector group Part (1), governor circuit board component (3), shell, data wire (12), power supply module (4) and display device;
The light source and detector module (1) are by light source module, detector, detector chip and data interface group into the inspection Survey device and detector chip is integrated on light source module, the data-interface is connected to detector chip by circuit;
The governor circuit board component (3) includes being additionally provided with substrate and the main control chip being arranged on substrate, the substrate By circuit be connected to the signal acquisition amplifying circuit of main control chip, analog-to-digital conversion circuit, Bluetooth chip, power control circuit, Inner button and charging inlet;
The data-interface of the light source and detector module (1) is connected to governor circuit board component (3) by data wire (12) Signal acquisition amplifying circuit, the power control circuit of the governor circuit board component (3) is connected with power supply module (4) by circuit Connect;
Bluetooth communication is carried out between the Bluetooth chip and display device of the governor circuit board component (3);
The light source and detector module (1) are arranged on the housing of shell, the governor circuit board component (3), data wire (12), power supply module (4) is arranged at enclosure interior.
2. the portable detection equipment of quick detection fruit internal quality according to claim 1, its feature exists:In:Institute 5 to 500 spot lights of the light source module for one wavelength range of transmitting are stated, the wavelength of spot light is interval in 500nm~1800nm Interior, the detector of the light source and detector module is photodiode, and light source module is integrated in one from six pieces of LED chips Substrate constitutes LED array, and one piece of photodiode is integrated in the center of LED array, and the power supply module (4) selects chargeable lithium Battery.
3. the portable detection equipment of quick detection fruit internal quality according to claim 1, it is characterised in that:It is described Housing is divided into the upper shell (6) and lower house (2) mutually fixed by fastener, and the governor circuit board component (3) passes through screens Lower house (2) inside is fixed on, the power supply module (4) is arranged on the substrate of governor circuit board component (3), the upper shell (6) top, which is provided with circular hole, and circular hole, is provided with inner button control assembly, and the inner button control assembly includes bullet Spring (7), outer button (8) and light guide ring (9), the outer button (8) and light guide ring (9) are arranged at the top of upper shell (6) and set In the circular hole put, in the screens of the spring (7) button mounted externally (8), upper shell (6) front end is offered and light source And detector module (1) size identical window, the light source and detector module (1) are placed in window, gone back in the window The quartz glass plate (11) for protecting light source and detector module (1) is provided with, lower house (2) rear end is further opened with key Keyhole (5).
4. the detection side of the portable detection equipment of quick detection fruit internal quality according to claim 1-3 any one Method, it is characterised in that:Comprise the following steps,
S1 spectra collection), is carried out to fruit sample by portable detection equipment, original spectrum is obtained;
S2 pol and acidity measurement), are carried out to fruit sample, and takes measured value as the observation of analysis forecast model;
S3 the forecast model of sugar degree), is built, is carried out by neural network algorithm, SVMs and particle cluster algorithm Classification and multiple authentication, the final forecast model for determining that sugar degree is optimal;
S4 the forecast model of fruit acidity), is built, is carried out by neural network algorithm, SVMs and particle cluster algorithm Classification and multiple authentication, the final forecast model for determining that fruit acidity is optimal;
S5), gather the spectral information of fruit to be measured and be updated in the forecast model that step D and step F is set up, obtain water to be measured The pol of fruit and the predicted value of acidity.
5. the detection method of the portable detection equipment of quick detection fruit internal quality according to claim 4, it is special Levy and be:Portable detection equipment in step S1 uses irreflexive acquisition mode, randomly selects the ring equator of each fruit Point on face carries out spectral scan.
6. the detection method of the portable detection equipment of quick detection fruit internal quality according to claim 4, it is special Levy and be:The measuring method of sugar degree is in step S2:The prism of saccharimeter is cleaned up and cleaned with distilled water first Moisture post-equalization returns to zero, then cuts and extrude juice the fruit for having surveyed spectrum and measured on the minute surface of refractive prism Three times, average;The measuring method of fruit acidity is:Hand-held pH meter front end is cleaned with distilled water, until pH value is shown as Neutrality, pH meter is inserted on the fruit ring equatorial plane, is measured the pH value of 6 positions, is averaged.
7. the detection method of the portable detection equipment of quick detection fruit internal quality according to claim 4, it is special Levy and be:The fruit sorting algorithm based on BP networks includes BP neural network structure, BP neural network in step S3 and step S4 Training and BP neural network three steps of classification.
8. the detection method of the portable detection equipment of quick detection fruit internal quality according to claim 4, it is special Levy and be:In step S3 and step S4 the kernel function of SVMs learning algorithm include linear kernel function, Polynomial kernel function, Radial basis kernel function and two layers of perceptron kernel function.
9. the detection method of the portable detection equipment of quick detection fruit internal quality according to claim 4, it is special Levy and be:Particle swarm optimization algorithm described in step S3 and step S4 by compare new particle fitness value and individual extreme value, The fitness value of colony's extreme value more new individual extreme value Pbest and colony extreme value Gbest positions are set up.
10. the detection method of the portable detection equipment of quick detection fruit internal quality according to claim 4, it is special Levy and be:The detectable fruit of detection method includes apple, strawberry, orange, grape, longan, orange, pears, Kiwi berry, perfume (or spice) Any of several broadleaf plants, cherry tomato.
CN201710434363.XA 2017-06-09 2017-06-09 The portable detection equipment and detection method of a kind of quick detection fruit internal quality Pending CN107202761A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710434363.XA CN107202761A (en) 2017-06-09 2017-06-09 The portable detection equipment and detection method of a kind of quick detection fruit internal quality

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710434363.XA CN107202761A (en) 2017-06-09 2017-06-09 The portable detection equipment and detection method of a kind of quick detection fruit internal quality

Publications (1)

Publication Number Publication Date
CN107202761A true CN107202761A (en) 2017-09-26

Family

ID=59907837

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710434363.XA Pending CN107202761A (en) 2017-06-09 2017-06-09 The portable detection equipment and detection method of a kind of quick detection fruit internal quality

Country Status (1)

Country Link
CN (1) CN107202761A (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109100322A (en) * 2018-08-17 2018-12-28 江苏大学 Food near-infrared spectrum rapid detection method and portable detector based on temperature self-correcting
WO2020107965A1 (en) * 2018-11-27 2020-06-04 Oppo广东移动通信有限公司 Electronic device, information push method and related product
TWI712964B (en) * 2018-04-19 2020-12-11 行政院農業委員會農業試驗所 System and method of predicting fruit preference for consumer and data processing device thereof

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
TWI712964B (en) * 2018-04-19 2020-12-11 行政院農業委員會農業試驗所 System and method of predicting fruit preference for consumer and data processing device thereof
CN109100322A (en) * 2018-08-17 2018-12-28 江苏大学 Food near-infrared spectrum rapid detection method and portable detector based on temperature self-correcting
WO2020107965A1 (en) * 2018-11-27 2020-06-04 Oppo广东移动通信有限公司 Electronic device, information push method and related product

Similar Documents

Publication Publication Date Title
CN107202761A (en) The portable detection equipment and detection method of a kind of quick detection fruit internal quality
CN102818777B (en) Fruit maturity degree evaluation method based on spectrum and color measurement
CN107064047A (en) A kind of Fuji apple quality damage-free detection method based near infrared spectrum
CN106290238A (en) A kind of apple variety method for quick identification based on high light spectrum image-forming
CN205762405U (en) Sorting unit for online Non-Destructive Testing Apple Mould Core equipment
Matteoli et al. A spectroscopy-based approach for automated nondestructive maturity grading of peach fruits
CN106841103A (en) Near infrared spectrum detects fruit internal quality method and dedicated test system
CN108875913A (en) A kind of matsutake Fast nondestructive evaluation system and method based on convolutional neural networks
CN110411957A (en) The lossless method for quick predicting and device of fruit shelf life and freshness
CN103731440A (en) Near-infrared crop growth information real-time monitoring and crop disaster prediction wireless system
CN107796764A (en) A kind of construction method of the wheat leaf area index appraising model based on three wave band vegetation indexs
CN108663334A (en) The method for finding soil nutrient spectral signature wavelength based on multiple Classifiers Combination
CN103954582A (en) Apple cultivar near-infrared-spectrum sorting method based on hybrid K-harmonic means clustering
CN106706552A (en) Method for detecting wheat quality based on multiple-information integration
CN107290299A (en) A kind of pol and acidity real non-destructive detection method for peach
Sinambela et al. Application of an inductive sensor system for identifying ripeness and forecasting harvest time of oil palm
CN206450322U (en) A kind of spectral detection system based on micro spectrometer
CN105866050A (en) Low-cost lossless and fast detecting equipment for apple moldy core
CN105069504B (en) SCM Based BP neutral net Apple Mould Core discrimination model and method for building up thereof
CN107271372A (en) A kind of Apple Leaves chlorophyll remote sensing estimation method
CN205719951U (en) Detect black box and utilize the lossless quick detection equipment of Apple Mould Core of this detection black box
Shen et al. Feasibility of non-destructive internal quality analysis of pears by using near-infrared diffuse reflectance spectroscopy
CN206788033U (en) A kind of dedicated test system of near infrared spectrum detection fruit internal quality
CN109772730A (en) A kind of ellipse or round fruits and vegetables detection and classification mechanism
Liu et al. Diagnosis of Citrus Greening using Raman Spectroscopy-Based Pattern Recognition.

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