CN110583217A - Grain harvester cleaning loss rate detection device and detection method - Google Patents
Grain harvester cleaning loss rate detection device and detection method Download PDFInfo
- Publication number
- CN110583217A CN110583217A CN201911108900.7A CN201911108900A CN110583217A CN 110583217 A CN110583217 A CN 110583217A CN 201911108900 A CN201911108900 A CN 201911108900A CN 110583217 A CN110583217 A CN 110583217A
- Authority
- CN
- China
- Prior art keywords
- grain
- harvester
- image
- axis
- loss rate
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000004140 cleaning Methods 0.000 title claims abstract description 59
- 238000001514 detection method Methods 0.000 title claims abstract description 47
- 239000000463 material Substances 0.000 claims abstract description 30
- 238000012545 processing Methods 0.000 claims abstract description 23
- 238000012544 monitoring process Methods 0.000 claims abstract description 12
- 235000013339 cereals Nutrition 0.000 claims description 189
- 238000000034 method Methods 0.000 claims description 23
- 230000011218 segmentation Effects 0.000 claims description 12
- 238000005259 measurement Methods 0.000 claims description 11
- 238000009826 distribution Methods 0.000 claims description 8
- 238000012360 testing method Methods 0.000 claims description 8
- 230000006698 induction Effects 0.000 claims description 7
- 238000007781 pre-processing Methods 0.000 claims description 7
- 238000007599 discharging Methods 0.000 claims description 6
- 239000000919 ceramic Substances 0.000 claims description 5
- 238000005303 weighing Methods 0.000 claims description 5
- 239000000203 mixture Substances 0.000 claims description 4
- 238000010219 correlation analysis Methods 0.000 claims description 3
- 238000009990 desizing Methods 0.000 claims 1
- 238000013178 mathematical model Methods 0.000 abstract description 9
- 230000008859 change Effects 0.000 abstract description 7
- 238000005516 engineering process Methods 0.000 abstract description 7
- 238000003306 harvesting Methods 0.000 description 4
- 238000005520 cutting process Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000012535 impurity Substances 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 241001124569 Lycaenidae Species 0.000 description 1
- 239000006096 absorbing agent Substances 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000001035 drying Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 230000035939 shock Effects 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01D—HARVESTING; MOWING
- A01D41/00—Combines, i.e. harvesters or mowers combined with threshing devices
- A01D41/12—Details of combines
- A01D41/127—Control or measuring arrangements specially adapted for combines
- A01D41/1271—Control or measuring arrangements specially adapted for combines for measuring crop flow
- A01D41/1272—Control or measuring arrangements specially adapted for combines for measuring crop flow for measuring grain flow
- A01D41/1273—Control or measuring arrangements specially adapted for combines for measuring crop flow for measuring grain flow for measuring grain loss
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06M—COUNTING MECHANISMS; COUNTING OF OBJECTS NOT OTHERWISE PROVIDED FOR
- G06M1/00—Design features of general application
- G06M1/08—Design features of general application for actuating the drive
- G06M1/10—Design features of general application for actuating the drive by electric or magnetic means
- G06M1/102—Design features of general application for actuating the drive by electric or magnetic means by magnetic or electromagnetic means
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computational Mathematics (AREA)
- Mathematical Physics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Probability & Statistics with Applications (AREA)
- Operations Research (AREA)
- Algebra (AREA)
- Evolutionary Biology (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Environmental Sciences (AREA)
- Electromagnetism (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
A loss rate detection device and a detection method of a grain harvester are disclosed, the device comprises a feeding quality detection unit, a loss detection unit, a signal processing circuit and a secondary instrument; and acquiring the total loss amount and the feeding quality of the grains, and calculating the cleaning loss rate of the grain harvester. The invention is based on the sensor technology and the computer image processing technology, and combines a scientific mathematical model, thereby realizing the real-time monitoring of the cleaning loss rate, changing the traditional manual cleaning mode and saving a large amount of manpower and material resources. Meanwhile, the manipulator can reasonably change the operation parameters of the harvester according to the change rule of the loss rate, so that the operation performance and the working efficiency are improved.
Description
Technical Field
The invention relates to the technical field of agricultural machinery, in particular to a cleaning loss rate detection device and method for a grain harvester.
Background
With the popularization of grain combine harvesters and the continuous improvement of mechanization level in China, the automation and intellectualization of machinery become a great trend of mechanical development, wherein the cleaning loss rate is one of important indexes for measuring the operation performance of the combine harvester, so that the grain harvesting loss rate can be accurately monitored in real time, and the grain combine harvester has important significance for realizing accurate agriculture.
At present, the monitoring of the cleaning loss rate is mainly obtained by calculation after manual cleaning and separation, and although the monitoring result is more accurate, the detection efficiency is very low and the labor cost is high. Scholars at home and abroad have already made a lot of researches on the loss rate of the combine harvester, but the system can only display the change rule of the loss rate qualitatively, but can not display the current loss rate quantitatively. The research work of the loss rate of the grains is carried out in China, and some results are obtained, but the overall technology is still imperfect.
Disclosure of Invention
The invention aims to provide a device and a method for detecting the loss rate of a grain harvester, aiming at the defects of the prior art.
The technical scheme of the invention is as follows:
the invention provides a device for detecting the cleaning loss rate of a grain harvester, which comprises a feeding quality detection unit, a loss detection unit, a signal processing circuit and a secondary instrument, wherein the feeding quality detection unit is used for detecting the loss of the grain harvester;
the feeding quality detection unit comprises an image acquisition module, a magnet, a speed acquisition module and a distance measurement sensor, wherein the image acquisition module is arranged on the harvester and is used for shooting right above a plant to be harvested and acquiring the density of grains, the distance measurement sensor is arranged on two sides of a grain divider of the grain harvester and is used for acquiring the distance between the grain divider and the grains of the grain harvester, the speed acquisition module is arranged at the position of a wheel of the grain harvester and is used for acquiring the walking speed of the grain harvester, and detection signal output ends of the image acquisition module, the speed acquisition module and the distance measurement sensor are all connected with corresponding signal input ends of a secondary instrument;
the loss detection unit is arranged below the discharge position of the mixture at the tail of the sorting screen; the loss detection unit comprises two fixed plates, two sensitive plates and two supporting plates, wherein the two fixed plates are arranged on two sides of a box body at the tail part of a sorting screen of the grain harvester;
the piezoceramics sensor be used for acquireing cleaning sieve afterbody exhaust seed grain and miscellaneous residual impact pressure signal, piezoceramics sensor's detected signal output end links to each other with signal processing circuit's detected signal input, signal processing circuit's output links to each other with the signal input part of secondary instrument, acquires the loss rate of cleaning.
Further, the piezoelectric ceramic sensor is arranged in the middle position below the sensitive plate; the speed acquisition module includes magnetic induction counter and magnet, magnet install on the wheel, the magnetic induction counter is installed and is located at the bottom of grain harvester and aforementioned wheel correspondence.
Furthermore, rubber shock absorbers are arranged between the supporting plate and the two fixing plates.
Further, the signal processing circuit comprises a charge amplifier, a band-pass filter and a voltage comparator which are connected in sequence, the voltage comparator outputs a standard square wave signal to a secondary instrument, the secondary instrument comprises a single chip microcomputer, the single chip microcomputer counts the standard square wave signal output by the signal processing circuit, and cereal seeds in unit time are completedCounting grains, calculating actual grain weight obtained by the sensor according to thousand grain weight of the grainm c。
A method for detecting the cleaning loss rate of a grain harvester is applied to a cleaning loss rate detection device of the grain harvester, and the method comprises the following steps:
s1, establishing a probability model of the mass ratio of the lost grains along the X axis and the Y axis；
S2, establishing a grain feeding density detection model of the harvester；
S3, acquiring a proportion coefficient of the quality of the grains detected by a sensitive plate in a monitoring area to the total quality of the grains;
wherein:,the length start and stop horizontal coordinate value of the sensitive plate (2-2),，the longitudinal coordinate value of the width start and stop of the sensitive plate;
s4, calculating the total loss of the grains by adopting the following formulam s：
Wherein:m cindicating the fact of sensor acquisitionThe weight of the grain;
s5, respectively acquiring RGB images of the grain canopy, the distance between a divider and grains of the grain harvester by adopting the image acquisition module, the distance measurement sensor and the speed acquisition module, and the counting data of the magnetic induction counter, sending the counting data to the signal processing circuit, and acquiring the grain density of the grain harvesterActual swathl rAnd walking speedv m(ii) a Wherein: actual swathl rSubtracting the distance measured by the distance measuring sensors at the two sides from the width of the grain harvester;
s6, calculating the feed quality by adopting the following formulaM s：
Wherein:l ris the actual swath, in m;v mthe unit is m/s for the walking speed;tis the walking time, the unit is s;as grain density, the unit is kg/m2；
S7, calculating the cleaning loss rate P of the grain harvesterS：
。
Further, in step S1, a probability model of the mass ratio of the lost grains along the X axis and the Y axis is establishedThe method comprises the following specific steps:
s1-1, establishing a test bed, and selecting the same structural parameters as the grain harvester;
s1-2, setting a collecting surface of a grain harvester tail cleaning screen for discharging grains as an X axis along a grain discharging direction, setting a width of the cleaning screen as a Y axis and a coordinate origin O, placing m rectangular material receiving boxes along the X axis on the collecting surface, namely i =1, 2, 1.
S1-3, changing the rotating speed of the fan of the grain harvester, performing threshing, separating and cleaning tests at different rotating speeds of the fan, collecting cleaning discharge through the material receiving boxes, weighing the quality of grains in each material receiving boxm ij ；
S1-4, respectively accumulating the mass proportions of the grains in the material receiving boxes of each row along the Y-axis and X-axis directions to obtain mass proportions di and dj along the X-axis and Y-axis in the grain loss distribution range;
wherein i represents the number of the X-axis material receiving boxes, m represents the total number of the X-axis material receiving boxes, j represents the number of the Y-axis material receiving boxes, and n represents the total number of the Y-axis material receiving boxes;represents the total loss obtained by all the receiving boxes;
s1-5, acquiring accumulated numerical values of seed quality proportion in each material receiving box along the X-axis and Y-axis directions of seeds at the rotating speed of the corresponding fan (5), inputting the numerical values into a nonlinear fitting system for nonlinear fitting to obtain probability models of lost seed quality ratio along the X-axis and the Y-axis respectively。
Further, in step S2, a model for detecting the grain feeding density is establishedThe method comprises the following specific steps:
s2-1, shooting right above a plant to be harvested by adopting an image acquisition module, and acquiring RGB images of a cereal canopy;
s2-2, preprocessing the image, and utilizing a maximum inter-class variance method to obtain an optimal segmentation threshold value to segment the preprocessed cereal canopy gray level image to obtain a target area;
s2-3, extracting a pixel value x ʹ of a target area as a grain image density characteristic value, threshing and weighing plants with actual areas under the picture, repeating S2-1 to S2-3 times to obtain corresponding data, inputting DPS data processing software for correlation analysis according to the extracted density characteristic value and the actually measured grain density, and obtaining a harvester grain feeding density detection model:
wherein:denotes the feed density, unit: kg/m2(ii) a x ʹ represents the target area pixel value;
correspondingly, in step S5, the image acquisition module acquires the RGB images of the grain canopy and sends the RGB images to the signal processing circuit to acquire the grain density of the grain harvesterThe method comprises the following specific steps:
preprocessing the acquired image, and segmenting the image by using an optimal segmentation threshold value to obtain a target area; extracting a pixel value x ʹ ʹ of a current target area as a grain image density characteristic value, substituting the grain image density characteristic value into a grain feeding density detection model of the harvester to obtain the corresponding grain density。
Further, the preprocessing includes drying, restoration, and gradation conversion at step S2-2.
Further, in step S2-2, the step of obtaining the optimal segmentation threshold by using the maximum inter-class variance method specifically includes:
S2-2-A, dividing the gray of each pixel point of the image to be dividedThe value is recorded as f (m ʹ, n ʹ), and m ʹ represents the number of pixel columns; n ʹ represents the number of pixel lines, the gray level is L, the gray level range {0,1,2.., L-1} of the image, the threshold t ʹ divides the pixel points in the image into two types, C0 and C1, wherein C0 represents the background region, the gray level range {0,1,2.. once, t ʹ } and C1 represents the target region { t ʹ +1, t ʹ + 2.. once, L-1}, if f (m ʹ, n ʹ)<t, then (m ʹ, n ʹ)C0, if f (m ʹ, n ʹ)>t, then (m ʹ, n ʹ)C1, g (k) represents the sum of all pixels with the gray value k in the image, and p (k) represents the probability that the gray value of the pixel is k, then:
S2-2-B, setting a segmentation threshold t ʹ of the preprocessed cereal canopy gray level image, and respectively obtaining the probability of a target part and the probability of a background part：
Wherein,i' indicates the number of gradation values, p: (i') indicates a gray value ofi' probability, g: (i') indicates a gray scale value in the image ofi' the sum of all pixel points;
S2-2-C, calculating the pixel mean values of the target part and the background part respectively as；
S2-2-D, calculating the total mean value of the grain canopy gray level image pixelsComprises the following steps:
S2-2-E, obtaining the optimal division threshold T of the gray level:
in the invention, the threshold T divides the whole image into a target part and a background part, the maximum between-class variance means the maximum difference between the target and the background, the corresponding error rate is the minimum, and the optimal division threshold of the image is found. According to a color image acquired by a camera, a gray level image is obtained through direct graying, an optimal threshold value is found by utilizing a maximum inter-class variance method to segment the gray level image, plant valleys and leaves are separated from a background, a binary image containing the valleys, the leaves and the background is obtained, 0 represents the background, and 1 represents the plant valleys and the leaves. Therefore, the grain density characteristic of the area is represented by calculating the total pixel value of the valley and the leaf in the image.
The invention has the beneficial effects that:
the invention is based on the sensor technology and the computer image processing technology, and combines a scientific mathematical model, thereby realizing the real-time monitoring of the cleaning loss rate, changing the traditional manual cleaning mode and saving a large amount of manpower and material resources. Meanwhile, the manipulator can reasonably change the operation parameters of the harvester according to the change rule of the loss rate, so that the operation performance and the working efficiency are improved.
Additional features and advantages of the invention will be set forth in the detailed description which follows.
Drawings
The above and other objects, features and advantages of the present invention will become more apparent by describing in more detail exemplary embodiments thereof with reference to the attached drawings, in which like reference numerals generally represent like parts throughout.
Fig. 1 shows a schematic structural diagram of the present invention.
Fig. 2 shows a schematic configuration diagram of the loss amount detection unit of the present invention.
Detailed Description
Preferred embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While the preferred embodiments of the present invention are shown in the drawings, it should be understood that the present invention may be embodied in various forms and should not be limited to the embodiments set forth herein.
A grain harvester cleaning loss rate detection device comprises a feeding quality detection unit, a loss detection unit 2, a signal processing circuit 3 and a secondary instrument 4, wherein the feeding quality detection unit is used for detecting the loss of grain;
the feeding quality detection unit comprises an image acquisition module 6, a magnet, a speed acquisition module 7 and a distance measurement sensor 8, wherein the image acquisition module 6 is installed on the harvester and is used for shooting right above a plant to be harvested and acquiring grain density, the distance measurement sensor 8 is installed on two sides of a grain harvester divider and is used for acquiring the distance between the grain harvester divider and grains of the grain harvester, the speed acquisition module 7 is installed at the position of a wheel of the grain harvester and is used for acquiring the walking speed of the grain harvester, and detection signal output ends of the image acquisition module 6, the speed acquisition module 7 and the distance measurement sensor 8 are all connected with corresponding signal input ends of the secondary instrument 4;
the loss amount detection unit 2 is arranged below the discharge position of the mixture at the tail part of the sorting screen 1; the loss detection unit 2 comprises two fixed plates 2-1, two sensitive plates 2-2 and two support plates 2-3, the two fixed plates 2-1 are arranged on two sides of a box body at the tail part of a sorting screen 1 of the grain harvester, the support plates 2-3 are clamped between the two fixed plates 2-1, the sensitive plates 2-2 are fixed on the support plates 2-3, and piezoelectric ceramic sensors are arranged below the sensitive plates 2-2;
piezoceramics sensor be used for acquireing 1 afterbody exhaust seed grain of cleaning sieve and miscellaneous residual impact pressure signal, piezoceramics sensor's detected signal output end links to each other with signal processing circuit 3's detected signal input, signal processing circuit 3's output links to each other with secondary instrument 4's signal input part, acquires the loss rate of cleaning.
When the grains and the impurities discharged from the tail of the cleaning sieve impact on the sensitive plate, the piezoelectric ceramic sensor generates charge signals, the grains are separated from the impurities through the signal modulation circuit, the signal modulation circuit consists of a charge amplifier, a band-pass filter and a voltage comparator, and outputs standard square wave signals to the secondary instrument, the secondary instrument takes the single chip microcomputer as a core, counting is carried out by utilizing an external interruption falling edge triggering mode of the single chip microcomputer, counting of the grains in unit time is completed, the current total cleaning loss is calculated according to a relation model between the cleaning loss detected by the sensor and the total cleaning loss, and the total cleaning loss quality is calculated according to thousand seed weight.
The cleaning loss rate of the grain combine is the ratio of the total cleaning loss mass to the harvesting mass, and the harvesting mass of the combine is the product of the operation cutting range of the combine (the operation cutting range can be measured by a distance measuring sensor), the operation speed (measured by a speed sensor) and the grain mass per unit area. Considering the time difference between the harvested mass and the total loss amount, the method calculates the primary loss rate according to a certain harvesting area, so that the time difference can be ignored.
The mathematical model between the grain quantity detected by the monitoring area and the cleaning total loss is established through a bench test, and the bench test selects the structural parameters the same as those of the cleaning device of the corresponding combine harvester. Through changing parameters such as feeding amount, fan rotating speed and air outlet angle, the grains discharged from the tail of the sorting screen are averagely divided into a plurality of grid rectangular small areas, the grain distribution rule scattered on the ground is obtained by manually collecting the grain amount of each small area, and a mathematical model between the grain amount detected in the monitoring area and the sorting loss amount is established. The scheme is as follows:
firstly, establishing a mathematical model of the transverse distribution of the lost grains along the tail part of the cleaning sieve according to the distribution rule of a mixture discharged by the cleaning sieve; and then establishing a mathematical model of grain distribution along the longitudinal direction in the range of the installation position of the sensor, and establishing the mathematical models established in the transverse direction and the longitudinal direction to obtain the grain distribution proportion in the monitoring area of the sensor, thereby establishing the mathematical model between the monitoring value of the sensor and the actual cleaning loss.
The model establishment process is as follows:
s1, establishing a probability model of the mass ratio of the lost grains along the X axis and the Y axis；
S1-1, establishing a test bed, and selecting the same structural parameters as the grain harvester;
s1-2, setting a collecting surface of a grain harvester tail cleaning screen for discharging grains as an X axis along a grain discharging direction, setting a width of the cleaning screen as a Y axis and a coordinate origin O, placing m rectangular material receiving boxes along the X axis on the collecting surface, namely i =1, 2, 1.
S1-3, changing the rotating speed of a fan 5 of the grain harvester, performing threshing, separating and cleaning tests at different rotating speeds of the fan, collecting cleaning discharge through material receiving boxes, and weighing the quality of grains in each material receiving box；
S1-4, respectively accumulating the mass proportions of the grains in the material receiving boxes of each row along the Y-axis and X-axis directions to obtain mass proportions di and dj along the X-axis and Y-axis in the grain loss distribution range;
wherein i represents the number of the X-axis material receiving boxes, m represents the total number of the X-axis material receiving boxes, j represents the number of the Y-axis material receiving boxes, and n represents the total number of the Y-axis material receiving boxes;represents the total loss obtained by all the receiving boxes;
s1-5, acquiring accumulated numerical values of the seed quality proportion in each material receiving box along the X-axis direction and the Y-axis direction of the seeds at the rotating speed of the corresponding fan 5, inputting a nonlinear fitting system for nonlinear fitting as shown in the following table, and acquiring probability models of the lost seed quality ratio along the X-axis direction and the Y-axis direction, wherein the probability models are respectively。
S2, establishing a harvester grain feeding density detection model rho;
s2-1, shooting right above a plant to be harvested by adopting an image acquisition module 6, and acquiring RGB images of the grain canopy;
s2-2, preprocessing the image, and utilizing a maximum inter-class variance method to obtain an optimal segmentation threshold value to segment the preprocessed cereal canopy gray level image to obtain a target area;
the optimal segmentation threshold is obtained as follows:
S2-2-A, recording the gray value of each pixel point of the image to be segmented as f (m ʹ, n ʹ), wherein m ʹ represents the number of pixel point columns; n ʹ represents the number of pixel lines, the gray level is L, the gray level range {0,1,2.., L-1} of the image, the threshold t ʹ divides the pixel points in the image into two types, C0 and C1, wherein C0 represents the background region, the gray level range {0,1,2.. once, t ʹ } and C1 represents the target region { t ʹ +1, t ʹ + 2.. once, L-1}, if f (m ʹ, n ʹ)<t, then (m ʹ, n ʹ)C0, if f (m ʹ, n ʹ)>t, then (m ʹ, n ʹ)C1, g (k) represents the sum of all pixels with the gray value k in the image, and p (k) represents the probability that the gray value of the pixel is k, then:
S2-2-B, setting a segmentation threshold t ʹ of the preprocessed cereal canopy gray level image, and respectively obtaining the probability of a target part and the probability of a background part：
Wherein,i' indicates the number of gradation values, p: (i') indicates a gray value ofi' probability, g: (i') indicates a gray scale value in the image ofi' the sum of all pixel points;
S2-2-C, calculating the pixel mean values of the target part and the background part respectively as：
S2-2-D, calculating the total mean value of the grain canopy gray level image pixelsComprises the following steps:
S2-2-E, obtaining the optimal division threshold T of the gray level:
s2-3, extracting the pixel value x ʹ of the target area as the density characteristic value of the grain image, and threshing the plant with the actual area under the pictureWeighing, repeating S2-1 to S2-3 for multiple times to obtain corresponding data, inputting DPS data processing software for correlation analysis according to the extracted density characteristic value and the actually measured grain density, and obtaining a harvester grain feeding density detection model：
Wherein:denotes the feed density, unit: kg/m2(ii) a x ʹ represents the target area pixel value.
S3, acquiring the proportional coefficient of the mass of the grains below the monitoring area, namely the sensitive plate 2-2, to the total mass of the grains；
Wherein:,the length of the sensitive plate 2-2 is the initial and final horizontal coordinate value,，the longitudinal coordinate value of the width start and stop of the sensitive plate;
s4, calculating the total loss of the grains by adopting the following formulam s：
Wherein:m crepresenting the actual grain weight obtained by the sensor;
when seeds and sundries discharged from the tail of the sorting screen impact the sensitive plate, the piezoelectric ceramic sensor generates charge signals, the seeds are separated from the sundries through the signal modulation circuit, the signal modulation circuit consists of a charge amplifier, a band-pass filter and a voltage comparator, and outputs standard square wave signals to the secondary instrument, the secondary instrument takes the single chip microcomputer as a core, counting is carried out by utilizing an external interrupt falling edge triggering mode of the single chip microcomputer, counting of the grains in unit time is completed, and the actual grain weight obtained by the sensor is calculated according to the thousand grain weightm c；
S5, respectively acquiring RGB images of the grain canopy, the distance between a divider and grains of the grain harvester and counting data of a magnetic induction counter 7-1 by adopting the image acquisition module 6, the distance measurement sensor 8 and the speed acquisition module 7, sending the data to the signal processing circuit 3, and acquiring the grain density of the grain harvesterActual swathl rAnd walking speedv m(ii) a Wherein: actual swathl rSubtracting the distance measured by the distance measuring sensors 8 at the two sides from the width of the grain harvester;
density of grainThe acquisition steps are as follows: the image acquisition module 6 acquires RGB images of the cereal canopy and sends the RGB images to the signal processing circuit 3, the acquired images are preprocessed, and the images are segmented by using the optimal segmentation threshold value to obtain a target area; extracting a pixel value x ʹ ʹ of a current target area as a grain image density characteristic value, substituting the grain image density characteristic value into a grain feeding density detection model of the harvester to obtain the corresponding grain density；
S6, calculating the feed quality by adopting the following formulaM s：
Wherein:l ris the actual swath, in m;v mthe unit is m/s for the walking speed;tis the walking time, the unit is s;as grain density, the unit is kg/m2；
S7, calculating the cleaning loss rate P of the grain harvesterS：
。
The invention designs a set of grain harvester cleaning loss rate detection device based on sensor technology and computer image processing technology and combined with scientific mathematical model, realizes real-time monitoring of cleaning loss rate, changes the traditional manual cleaning mode and saves a large amount of manpower and material resources. Meanwhile, the manipulator can reasonably change the operation parameters of the harvester according to the change rule of the loss rate, so that the operation performance and the working efficiency are improved.
Having described embodiments of the present invention, the foregoing description is intended to be exemplary, not exhaustive, and not limited to the embodiments disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments.
Claims (9)
1. A grain harvester cleaning loss rate detection device is characterized by comprising a feeding quality detection unit, a loss detection unit (2), a signal processing circuit (3) and a secondary instrument (4);
the feeding quality detection unit comprises an image acquisition module (6), a magnet, a speed acquisition module (7) and a distance measurement sensor (8), wherein the image acquisition module (6) is installed on the harvester and is used for shooting right above a plant to be harvested and acquiring the density of grains, the distance measurement sensor (8) is installed on two sides of a grain divider of the grain harvester and is used for acquiring the distance between the grain divider and the grains of the grain harvester, the speed acquisition module (7) is installed at the position of wheels of the grain harvester and is used for acquiring the walking speed of the grain harvester, and detection signal output ends of the image acquisition module (6), the speed acquisition module (7) and the distance measurement sensor (8) are connected with corresponding signal input ends of the secondary instrument (4);
the loss detection unit (2) is arranged below the discharge position of the mixture at the tail of the sorting screen (1); the loss detection unit (2) comprises two fixing plates (2-1), two sensitive plates (2-2) and two supporting plates (2-3), the two fixing plates (2-1) are arranged on two sides of a box body at the tail part of a sorting screen (1) of the grain harvester, the supporting plates (2-3) are clamped between the two fixing plates (2-1), the sensitive plates (2-2) are fixed on the supporting plates (2-3), and piezoelectric ceramic sensors are arranged below the sensitive plates (2-2);
piezoceramics sensor be used for acquireing cleaning sieve (1) afterbody exhaust seed grain and miscellaneous surplus impact pressure signal, piezoceramics sensor's detected signal output end links to each other with the detected signal input part of signal processing circuit (3), the output of signal processing circuit (3) links to each other with the signal input part of secondary instrument (4), acquires and cleans the loss rate.
2. A cleaning loss rate detecting device of a grain harvester according to claim 1, characterized in that the piezoceramic sensor is installed at a middle position below the sensitive plate (2-2); the speed acquisition module (7) comprises a magnetic induction counter (7-1) and a magnet (7-2), the magnet (7-2) is installed on a wheel, and the magnetic induction counter (7-1) is installed at the bottom of the grain harvester and corresponds to the wheel.
3. The detecting device for cleaning loss rate of grain harvester according to claim 1, characterized in that a rubber damper (2-4) is installed between the supporting plate (2-3) and the two fixing plates (2-1).
4. The grain harvester cleaning loss rate detection device according to claim 1, wherein the signal processing circuit (3) comprises a charge amplifier, a band-pass filter and a voltage comparator which are connected in sequence, the voltage comparator outputs a standard square wave signal to the secondary instrument (4), the secondary instrument (4) comprises a single chip microcomputer, the single chip microcomputer counts the standard square wave signal output by the signal processing circuit (3), the counting of grain seeds in unit time is completed, and the actual grain weight obtained by the sensor is calculated according to the thousand grain weight of the grainm c。
5. A method for detecting cleaning loss rate of a grain harvester, which applies the cleaning loss rate detection device of the grain harvester according to one of claims 1 to 4, and is characterized by comprising the following steps:
s1, establishing a probability model of the mass ratio of the lost grains along the X axis and the Y axis；
S2, establishing a grain feeding density detection model of the harvester；
S3, acquiring the proportional coefficient of the mass of the grains detected by the monitoring area, namely the sensitive plate (2-2), to the total mass of the grains；
Wherein:,the length start and stop horizontal coordinate value of the sensitive plate (2-2),，the longitudinal coordinate value of the width start and stop of the sensitive plate;
s4, calculating the total loss of the grains by adopting the following formulam s：
Wherein:m crepresenting the actual grain weight obtained by the sensor;
s5, respectively acquiring RGB images of the grain canopy, the distance between a divider and grains of the grain harvester by adopting the image acquisition module (6), the distance measuring sensor (8) and the speed acquisition module (7) and counting data of the magnetic induction counter (7-1), sending the counting data to the signal processing circuit (3) to acquire the grain density of the grain harvesterActual swathl rAnd walking speedv m(ii) a Wherein: actual swathl rSubtracting the distance measured by the distance measuring sensors (8) at the two sides from the width of the grain harvester;
s6, calculating the feed quality by adopting the following formulaM s：
Wherein:l ris the actual swath, in m;v mthe unit is m/s for the walking speed;tis the walking time, the unit is s;as grain density, the unit is kg/m2；
S7, calculating the cleaning loss rate P of the grain harvesterS：
。
6. The method for detecting cleaning loss rate of grain harvester according to claim 5, wherein in step S1, a probability model of the mass ratio of the lost grains along X-axis and Y-axis is establishedThe method comprises the following specific steps:
s1-1, establishing a test bed, and selecting the same structural parameters as the grain harvester;
s1-2, setting a collecting surface of a grain discharging screen at the tail of the grain harvester (1) as an X axis along the grain discharging direction, setting the width of the cleaning screen (1) as a Y axis and a coordinate origin O, placing m rectangular material receiving boxes along the X axis on the collecting surface, namely i =1, 2, j.
S1-3, changing the rotating speed of a fan (5) of the grain harvester, performing threshing, separating and cleaning tests at different rotating speeds of the fan, collecting cleaning discharge through material receiving boxes, and weighing the quality of grains in each material receiving boxm ij ；
S1-4, respectively accumulating the mass proportions of the grains in the material receiving boxes of each row along the Y-axis and X-axis directions to obtain mass proportions di and dj along the X-axis and Y-axis in the grain loss distribution range;
wherein i represents the number of the X-axis material receiving boxes, m represents the total number of the X-axis material receiving boxes, j represents the number of the Y-axis material receiving boxes, and n represents the total number of the Y-axis material receiving boxes;represents the total loss obtained by all the receiving boxes;
s1-5, acquiring accumulated numerical values of seed quality proportion in each material receiving box along the X-axis and Y-axis directions of seeds at the rotating speed of the corresponding fan (5), inputting the numerical values into a nonlinear fitting system for nonlinear fitting to obtain probability models of lost seed quality ratio along the X-axis and the Y-axis respectively。
7. The method for detecting cleaning loss rate of grain harvester according to claim 5, wherein in step S2, a grain feeding density detection model is establishedThe method comprises the following specific steps:
s2-1, shooting right above a plant to be harvested by adopting an image acquisition module (6), and acquiring an RGB image of a cereal canopy;
s2-2, preprocessing the image, and utilizing a maximum inter-class variance method to obtain an optimal segmentation threshold value to segment the preprocessed cereal canopy gray level image to obtain a target area;
s2-3, extracting a pixel value x ʹ of a target area as a grain image density characteristic value, threshing and weighing plants with actual areas under the picture, repeating S2-1 to S2-3 times to obtain corresponding data, inputting DPS data processing software for correlation analysis according to the extracted density characteristic value and the actually measured grain density, and obtaining a harvester grain feeding density detection model:
wherein:denotes the feed density, unit: kg/m2(ii) a x ʹ represents the target area pixel value;
correspondingly, in step S5, the image acquisition module (6) acquires RGB images of the grain canopy and sends the RGB images to the signal processing circuit (3) to acquire grain density of the grain harvesterThe method comprises the following specific steps:
preprocessing the acquired image, and segmenting the image by using an optimal segmentation threshold value to obtain a target area; extracting a pixel value x ʹ ʹ of a current target area as a grain image density characteristic value, substituting the grain image density characteristic value into a grain feeding density detection model of the harvester to obtain the corresponding grain density。
8. The method for detecting cleaning loss rate of grain harvester according to claim 7, wherein the preprocessing includes desizing, restoring and gray-scale converting at step S2-2.
9. The method for detecting a cleaning loss rate of a grain harvester according to claim 7, wherein in the step S2-2, the step of obtaining the optimal segmentation threshold by using the maximum inter-class variance method specifically comprises the steps of:
S2-2-A, recording the gray value of each pixel point of the image to be segmented as f (m ʹ, n ʹ), wherein m ʹ represents the number of pixel point columns; n ʹ represents the number of pixel lines, the gray level is L, the gray level range {0,1,2., L-1} of the image, and the threshold t ʹ divides the pixel points in the image into two types, C0 and C1, wherein C0 represents the background area, and the gray level range is L{0,1,2., t ʹ }, C1 represents the target region { t ʹ +1, t ʹ + 2., L-1}, if f (m ʹ, n ʹ)<t, then (m ʹ, n ʹ)C0, if f (m ʹ, n ʹ)>t, then (m ʹ, n ʹ)C1, g (k) represents the sum of all pixels with the gray value k in the image, and p (k) represents the probability that the gray value of the pixel is k, then:
S2-2-B, setting a segmentation threshold t ʹ of the preprocessed cereal canopy gray level image, and respectively obtaining the probability of a target part and the probability of a background part：
Wherein,i' indicates the number of gradation values, p: (i') indicates a gray value ofi' probability, g: (i') indicates a gray scale value in the image ofi' the sum of all pixel points;
S2-2-C, calculating the pixel mean values of the target part and the background part respectively as；
S2-2-D, calculating the total mean value of the grain canopy gray level image pixelsComprises the following steps:
S2-2-E, obtaining the optimal division threshold T of the gray level:
。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911108900.7A CN110583217A (en) | 2019-11-13 | 2019-11-13 | Grain harvester cleaning loss rate detection device and detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911108900.7A CN110583217A (en) | 2019-11-13 | 2019-11-13 | Grain harvester cleaning loss rate detection device and detection method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110583217A true CN110583217A (en) | 2019-12-20 |
Family
ID=68852329
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911108900.7A Pending CN110583217A (en) | 2019-11-13 | 2019-11-13 | Grain harvester cleaning loss rate detection device and detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110583217A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112616425A (en) * | 2021-03-08 | 2021-04-09 | 农业农村部南京农业机械化研究所 | On-line detection method, system and device for operation performance of grain combine harvester |
| EP4029364A1 (en) * | 2021-01-18 | 2022-07-20 | CLAAS Selbstfahrende Erntemaschinen GmbH | Agricultural harvester comprising means for determining the thousand grain weight |
| CN114846991A (en) * | 2022-05-31 | 2022-08-05 | 江苏大学 | Cleaning load monitoring device and cleaning performance prediction method for combine harvester |
| CN115104425A (en) * | 2022-06-25 | 2022-09-27 | 农业农村部南京农业机械化研究所 | Cleaning control system and method for combine harvester integrating multi-source sensing information |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101743804A (en) * | 2009-12-29 | 2010-06-23 | 江苏大学 | Grain cleaning loss detection method for combined harvester and device thereof |
| CN102090207A (en) * | 2010-12-24 | 2011-06-15 | 江苏大学 | Method and device for detecting cleaning loss of grain combine |
| EP3284334A1 (en) * | 2016-08-17 | 2018-02-21 | CNH Industrial Belgium NV | Grain loss sensor array for crop harvesting machine |
| CN109566064A (en) * | 2018-12-11 | 2019-04-05 | 农业部南京农业机械化研究所 | A kind of grain harvesting machine loss amount detecting device and detection method |
-
2019
- 2019-11-13 CN CN201911108900.7A patent/CN110583217A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101743804A (en) * | 2009-12-29 | 2010-06-23 | 江苏大学 | Grain cleaning loss detection method for combined harvester and device thereof |
| CN102090207A (en) * | 2010-12-24 | 2011-06-15 | 江苏大学 | Method and device for detecting cleaning loss of grain combine |
| EP3284334A1 (en) * | 2016-08-17 | 2018-02-21 | CNH Industrial Belgium NV | Grain loss sensor array for crop harvesting machine |
| CN109566064A (en) * | 2018-12-11 | 2019-04-05 | 农业部南京农业机械化研究所 | A kind of grain harvesting machine loss amount detecting device and detection method |
Non-Patent Citations (3)
| Title |
|---|
| 刘仲鹏等: "基于改进算法的小麦收获机作物密度检测研究", 《农机化研究》 * |
| 张光跃等: "联合收割机清选损失率监测系统设计与实现", 《中国农机化学报》 * |
| 梁振伟等: "纵轴流联合收获机籽粒清选损失监测数学模型研究", 《农业机械学报》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP4029364A1 (en) * | 2021-01-18 | 2022-07-20 | CLAAS Selbstfahrende Erntemaschinen GmbH | Agricultural harvester comprising means for determining the thousand grain weight |
| CN112616425A (en) * | 2021-03-08 | 2021-04-09 | 农业农村部南京农业机械化研究所 | On-line detection method, system and device for operation performance of grain combine harvester |
| CN112616425B (en) * | 2021-03-08 | 2021-06-04 | 农业农村部南京农业机械化研究所 | On-line detection method, system and device for operation performance of grain combine harvester |
| CN114846991A (en) * | 2022-05-31 | 2022-08-05 | 江苏大学 | Cleaning load monitoring device and cleaning performance prediction method for combine harvester |
| CN114846991B (en) * | 2022-05-31 | 2023-10-10 | 江苏大学 | Cleaning load monitoring device and cleaning performance prediction method for combine harvester |
| CN115104425A (en) * | 2022-06-25 | 2022-09-27 | 农业农村部南京农业机械化研究所 | Cleaning control system and method for combine harvester integrating multi-source sensing information |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110583217A (en) | Grain harvester cleaning loss rate detection device and detection method | |
| CN101905215B (en) | Digitalized paddy rice seed testing machine | |
| CN108985260B (en) | Remote sensing and meteorological integrated rice yield estimation method | |
| Kataoka et al. | Crop growth estimation system using machine vision | |
| CN105741180B (en) | Grain yield graph drawing system of combined harvester | |
| CN102138383A (en) | Method and device for measuring grain loss spatial distribution of combine harvester | |
| CN103308430B (en) | A kind of method and device measuring thousand grain weigth | |
| CN109566064B (en) | Loss detection device and detection method for grain harvester | |
| US20160189007A1 (en) | Grain quality monitoring | |
| CN107185850B (en) | Corn seed activity detection device based on hyperspectral imaging and electrical impedance | |
| CN102090207A (en) | Method and device for detecting cleaning loss of grain combine | |
| CN104913797A (en) | Pointer type instrument number reading and recognition method and system | |
| CN114451132B (en) | Real-time monitoring device and monitoring method for corn cleaning loss | |
| CN100506013C (en) | Real time monitoring method for random loss rate of combine harvester | |
| CN103148791A (en) | Method for measuring cabo structure and distribution of cabo structure | |
| CN105009731B (en) | Corn seed investigating method and its system | |
| CN104198325A (en) | Method for measuring ratio of cut stem to cut tobacco based on computer vision | |
| WO2022049549A1 (en) | Artificial intelligence based tobacco particle measurement system | |
| CN114034826A (en) | Production environment monitoring system for freeze-drying cubilose process based on data analysis | |
| CN111881864A (en) | Wisdom farming crops growth full-period full-dynamic monitoring management system | |
| CN105405145B (en) | A kind of granule number grain method based on image Segmentation Technology | |
| CN202077389U (en) | Cleaning loss detection device of grain combine harvester | |
| CN112616425B (en) | On-line detection method, system and device for operation performance of grain combine harvester | |
| CN202918699U (en) | Real-time on-line monitoring device for sorting loss of grain combine | |
| CN102812825B (en) | Real-time online monitoring method and device for cleaning losses of grain combines |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191220 |
|
| RJ01 | Rejection of invention patent application after publication |