CN117829403A - Multi-sensor information fusion yield measurement method and device - Google Patents
Multi-sensor information fusion yield measurement method and device Download PDFInfo
- Publication number
- CN117829403A CN117829403A CN202311609976.4A CN202311609976A CN117829403A CN 117829403 A CN117829403 A CN 117829403A CN 202311609976 A CN202311609976 A CN 202311609976A CN 117829403 A CN117829403 A CN 117829403A
- Authority
- CN
- China
- Prior art keywords
- yield
- acceleration
- contact sensor
- yield measurement
- grain
- 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
- 230000004927 fusion Effects 0.000 title claims abstract description 23
- 238000000691 measurement method Methods 0.000 title claims abstract description 8
- 238000005259 measurement Methods 0.000 claims abstract description 143
- 230000001133 acceleration Effects 0.000 claims abstract description 119
- 238000012545 processing Methods 0.000 claims abstract description 15
- 238000000034 method Methods 0.000 claims description 65
- 230000007246 mechanism Effects 0.000 claims description 31
- 238000003860 storage Methods 0.000 claims description 10
- 238000004519 manufacturing process Methods 0.000 claims description 7
- 238000010276 construction Methods 0.000 claims description 5
- 235000013339 cereals Nutrition 0.000 description 63
- 238000010586 diagram Methods 0.000 description 6
- 230000000875 corresponding effect Effects 0.000 description 4
- 238000003306 harvesting Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 230000004720 fertilization Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000007790 scraping Methods 0.000 description 3
- 241001124569 Lycaenidae Species 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000010899 nucleation Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000035558 fertility Effects 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
- 239000002689 soil Substances 0.000 description 1
- 238000009331 sowing Methods 0.000 description 1
Landscapes
- Testing Or Calibration Of Command Recording Devices (AREA)
Abstract
The invention relates to a multi-sensor information fusion yield measurement method and device, comprising the following steps: the harvester is used for first time of yield measurement, and the sensors used in the first time of yield measurement comprise an acceleration sensor, a non-contact sensor and a contact sensor; acquiring and processing yield measurement data to obtain a first yield measurement value time sequence measured by a non-contact sensor, a second yield measurement value time sequence measured by a contact sensor, and measuring a first acceleration by an acceleration sensor while measuring the non-contact sensor, and measuring a second acceleration while measuring the contact sensor; constructing a time sequence prediction model according to the first yield measurement time sequence and the second yield measurement time sequence; and carrying out second time yield measurement on the grains to be measured, and selecting a non-contact sensor yield measurement mode, a contact sensor yield measurement mode and a time sequence prediction model yield measurement mode according to the comparison result of the first acceleration, the second acceleration and an acceleration threshold value.
Description
Technical Field
The invention relates to the technical fields of intelligent agriculture, agricultural sensing and informatization, in particular to a multi-sensor information fusion yield measuring method and device.
Background
The yield monitoring system installed on the grain combine harvester can accurately collect crop yield information while harvesting crops, draw a yield distribution diagram, and help farmland managers to reasonably formulate accurate planting production management schemes such as fertilization and sowing. The accurate measurement of crop yield is the core of all decisions of fertilization, seeding and the like based on yield, such as seeding and fertilizing decisions of a farmland fertility management area based on historical yield, soil measurement formula fertilization decisions of surrounding yield and the like, and the improvement of the measurement accuracy of a grain flow sensor is particularly important.
Because the impulse type grain flow sensor has the characteristics of simple structure, convenient installation, lower cost and the like, the impulse type grain flow sensor is the most widely applied method at present, and the most mature and most studied method of products. Most commercial yield monitoring systems abroad currently employ the cereal flow sensor. The photoelectric sensor calculates the volume of the grains by measuring the grain thickness on each scraper of the scraper type elevator, and is a non-contact grain flow measurement technology. The photoelectric sensor is convenient to install and calibrate, and is a commercial photoelectric yield measuring sensor which uses more volume flow sensors. However, under special working conditions such as jolt and inclination caused by the self-base vibration of the machine and uneven ground in the field, or turning around of the ground, emergency braking and the like, the vibration of the combine harvester has the most obvious influence on the two sensors, so that the measurement error of the sensors is increased.
Disclosure of Invention
In order to solve the problem of yield measurement error caused by the influence of vibration of a combine harvester on the measurement of a sensor under special working conditions such as jolt and inclination caused by uneven ground in a field, turning around, emergency braking and the like, the invention discloses a multi-sensor information fusion yield measurement method, which comprises the following steps:
the method comprises the steps that a harvester is used for first time yield measurement, and sensors used in the first time yield measurement comprise an acceleration sensor arranged on a body of the harvester, a non-contact sensor arranged at a first position of a grain conveying mechanism of the harvester and a contact sensor arranged at a second position of the grain conveying mechanism;
acquiring and processing the yield measurement data to obtain a time series of first yield measurements (p 1 ,p 2 ，…，p i …), a second time series of yield measurements (q 1 ,q 2 ,…,q i …), the acceleration sensor measuring a first acceleration while the non-contact sensor is measuring, and measuring a second acceleration while the contact sensor is measuring;
according to the first time series of yield measurements (p 1 ,p 2 ，…，p i …) and a second yield measurement time series (q 1 ,q 2 ,…,q i …) constructing a time sequence prediction model;
performing second time of yield measurement on the grain to be measured according to the first acceleration, the second acceleration and an acceleration threshold value a 0 And (3) selecting the non-contact sensor yield measurement mode, the contact sensor yield measurement mode and the time sequence prediction model yield measurement mode.
In one embodiment of the above method of the invention, the grain delivery mechanism employs a scraper elevator.
In one embodiment of the above method of the present invention, the first position of the grain delivery mechanism is the middle part of the scraper type elevator, and the second position of the grain delivery mechanism is the grain outlet of the scraper type elevator.
In one embodiment of the above method of the present invention, there are a plurality of squeegees between the non-contact sensor and the contact sensor, the first time series of yield measurements (p 1 ,p 2 ，…，p i …) of the first yield measurement p i Corresponds to the second time series of yield measurements (q 1 ,q 2 ,…,q i Second yield measurement q in …) n+i The first yield measurement p i Corresponding to a first acceleration a of the plurality of first accelerations i The second yield measurement q n+i Corresponding to a second acceleration a of the plurality of second accelerations n+i 。
In one embodiment of the above method of the present invention, the first yield measurement time series (p 1 ,p 2 ，…，p i …) and a second yield measurement time series (q 1 ,q 2 ,…,q i …) is when the acceleration is less than the acceleration threshold a 0 Measured at that time.
In one embodiment of the above method of the present invention, the step of constructing a time-series prediction model is based on constructing an autoregressive AR model.
In an embodiment of the above method of the present invention, the step of constructing an autoregressive AR model further includes:
the autoregressive AR model is:
wherein one of the scrapers has a grain yield valuei＝1,…,N
N is the length of the time series of first yield measurements, P is the model order,for model parameters, E n+1 Is the model residual.
In one embodiment of the above method of the present invention, the determining model parametersFurther comprising the steps of:
model parameters are calculated by least square methodLeast squares estimation of +.>Make model residual epsilon n+1 The sum of squares of (c) is minimal.
In an embodiment of the above method of the present invention, the step of determining the model order P further includes:
AIC(P)＝NInσ a 2 +2P
wherein sigma a 2 For passing model residual E n+1 The calculated variance of the discrete white noise, AIC (P) is a function of the model order P;
the model order P is obtained by minimizing the value of AIC (P).
In one embodiment of the above method of the present invention, the first acceleration, the second acceleration and an acceleration threshold value a are used 0 The step of selecting the non-contact sensor, the contact sensor and the time sequence prediction model production measurement mode further comprises the following steps:
when the harvester works stably, selecting the non-contact sensor and/or the contact sensor to measure the yield;
and when the operation of the harvester is not stable, selecting the time sequence prediction model yield measurement mode.
In an embodiment of the above method of the present invention, when the harvester is operating stably, the step of selecting the non-contact sensor and/or the contact sensor sensing method further includes:
when a first acceleration a i Acceleration threshold a is less than or equal to 0 < second acceleration a n+i When the grain yield value on the scraper, which is measured by the non-contact sensor, is selected as the grain yield value y of the scraper i I.e. y i ＝p i ；
When the second acceleration a n+i Acceleration threshold a is less than or equal to 0 < first acceleration a i When the grain yield value on the current scraper, which is measured by the contact sensor, is selected as a scraper grain yield value y i I.e. y i ＝q n+i ；
When a first acceleration a i Second acceleration a n+i Acceleration threshold a is less than or equal to 0 When the average value of the grain yield values on the current scraper, which are measured by the non-contact sensor and the contact sensor, is selected as a scraper grain yield value y i I.e.
In an embodiment of the above method of the present invention, when the operation of the harvester is unstable, the step of selecting the time series prediction model for measuring the yield further includes:
when a first acceleration a i Second acceleration a n+i >Acceleration threshold a 0 When the harvester operates stably, acquiring yield time sequence data f obtained by a yield measurement mode selected during the stable operation of the harvester i ；
Predicting the grain yield value on the current scraper by using the time sequence prediction model to obtain the scraper Gu Wuchan magnitude y i I.e.
In one embodiment of the method of the present invention, the time series prediction model is used to predict the grain yield value on the current screed to obtain the screed Gu Wuchan magnitude y i Further comprising the steps of:
current scraping using the time series prediction modelPredicting the grain yield value on the plate to obtain the magnitude y of the scraper Gu Wuchan i The yield timing data f may be added i The subsequent scraped grain yield was estimated.
In an embodiment of the above method of the present invention, the acquiring the yield measurement data and processing the yield measurement data further includes acquiring a plurality of location information for associating with the result of the second yield measurement to provide yield services and applications based on the location information.
In an embodiment of the above method of the present invention, the non-contact sensor is a photoelectric sensor, and the contact sensor is an impulse sensor.
The invention also discloses a multi-sensor information fusion yield measuring device, which is used for executing the steps of any one of the methods, and comprises the following steps:
the first yield measuring module is used for carrying out first yield measurement by using a harvester, and the sensor used in the first yield measurement comprises an acceleration sensor arranged on a body of the harvester, a non-contact sensor arranged at a first position of a grain conveying mechanism of the harvester and a contact sensor arranged at a second position of the grain conveying mechanism;
a yield measurement data acquisition and processing module for acquiring yield measurement data and processing the yield measurement data to obtain a first yield measurement value time sequence (p 1 ,p 2 ，…，p i …), a second time series of yield measurements (q 1 ,q 2 ,…,q i …), a first acceleration measured by the acceleration sensor while the non-contact sensor is measuring, and a second acceleration measured by the contact sensor while the non-contact sensor is measuring;
a time series prediction model construction module for constructing a time series (p) of the first yield measurement values 1 ,p 2 ，…，p i …) and a second yield measurement time series (q 1 ,q 2 ,…,q i …) constructing a time sequence prediction model;
a second yield measuring module for measuring the grain to be measuredPerforming second time of measurement of the yield according to the first acceleration, the second acceleration and an acceleration threshold value a 0 And (3) selecting the non-contact sensor yield measurement mode, the contact sensor yield measurement mode and the time sequence prediction model yield measurement mode.
The invention also comprises a multi-sensor information fusion yield measurement system, which comprises an acceleration sensor arranged on the harvester body, a non-contact sensor arranged on the grain conveying mechanism of the harvester, a contact sensor arranged on the grain conveying mechanism, a storage unit and a control unit, wherein the control unit is connected with the acceleration sensor, the non-contact sensor, the contact sensor and the storage unit, and the device connected with the control unit.
The invention also comprises a harvester, a yield measuring system and a system for measuring the yield of the multi-sensor information fusion, wherein the harvester comprises a vehicle body, a driving device and a grain conveying mechanism which are arranged on a chassis.
The present invention also includes a storage medium storing a computer control program for performing the steps of any of the methods described above.
Based on the above, the yield measuring method, the device, the yield measuring system and the harvester with the multi-sensor information fusion disclosed by the invention adopt the combination of the two yield measuring sensors to measure the yield at the same scraper at different moments, and select different scraper yield measuring methods according to the vibration amplitude of the harvester body, thereby overcoming the influence of the vibration increase of the harvester at a certain moment on the measuring precision of the yield measuring sensors and improving the yield measuring precision.
In addition, the yield service and the application based on the position information can be provided according to the position information acquired during the yield measurement and the yield measurement value. Meanwhile, the multi-sensor information fusion yield measuring method can be applied to various grain conveying mechanisms suitable for measuring by using photoelectric sensors and impulse sensors.
Drawings
FIG. 1 is a schematic block diagram of a multi-sensor information fusion yield measurement method according to an embodiment of the invention.
Fig. 2 is a schematic diagram of a grain delivery mechanism for measuring grain yield according to an embodiment of the present invention.
FIG. 3 is a schematic block diagram of a multi-sensor information fusion yield measurement device according to an embodiment of the present invention.
FIG. 4 is a schematic block diagram of a multi-sensor information fusion yield measurement system according to an embodiment of the present invention.
Fig. 5 is a schematic block diagram of a harvester in an embodiment of the invention.
Wherein, the reference numerals:
1: grain conveying mechanism
2: grain conveying direction
3: cereal to be tested
4: scraper blade
5: non-contact sensor
5': photoelectric sensor
6: contact sensor
6': impulse sensor
7: acceleration sensor
8: scraper type elevator
10: multi-sensor information fusion's survey device of producing
11: first yield measuring module
12: yield measurement data acquisition and processing module
13: time sequence prediction model construction module
14: second yield measuring module
100: multi-sensor information fusion yield measuring system
110: control unit
120: memory cell
200: harvester
210: chassis
220: vehicle body
230: driving device
Detailed Description
The following detailed description of the technical solution of the present invention will be provided with reference to the accompanying drawings and specific embodiments, so as to further understand the objects, the solutions and the advantageous technical effects of the present invention, and it is apparent that the described embodiments are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It should be noted that in this specification, relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
Certain terms are used throughout the description and following claims to refer to particular components or features, as one of ordinary skill in the art will appreciate that a technical user or manufacturer may refer to the same component or feature in different terms or terms. The present specification and the appended claims do not take the form of an element or component with differences in names, but rather take the form of functional differences in elements or components as criteria for distinction.
In the present invention, the terms "upper", "lower", "left", "right", "front", "rear", "top", "bottom", "inner", "outer", "middle", "vertical", "horizontal", "lateral", "longitudinal" and the like indicate an azimuth or a positional relationship based on that shown in the drawings. These terms are only used to better describe the present invention and its embodiments and are not intended to limit the scope of the indicated devices, elements or components to the particular orientations or to configure and operate in the particular orientations.
Also, some of the terms described above may be used to indicate other meanings in addition to orientation or positional relationships, for example, the term "upper" may also be used to indicate some sort of attachment or connection in some cases. The specific meaning of these terms in the present invention will be understood by those of ordinary skill in the art according to the specific circumstances.
Furthermore, the terms "mounted," "configured," "provided," "connected," and "connected" are to be construed broadly. For example, it may be a fixed connection, a removable connection, or a unitary construction; may be a mechanical connection, or an electrical connection; may be directly connected, or indirectly connected through intervening media, or may be in internal communication between two devices, elements, or components. The specific meaning of the above terms in the present invention can be understood by those of ordinary skill in the art according to the specific circumstances.
Referring to fig. 1 and 2, the invention discloses a multi-sensor information fusion yield measurement method, which comprises the following steps:
the method comprises the steps of carrying out first time yield measurement by using a harvester, wherein sensors used in the first time yield measurement comprise an acceleration sensor 7 arranged on a body of the harvester, a non-contact sensor 5 arranged at a first position of a grain conveying mechanism 1 of the harvester and a contact sensor 6 arranged at a second position of the grain conveying mechanism 1;
acquiring and processing the yield measurement data to obtain a time series (p 1 ,p 2 ，…，p i …), a second time series of yield measurements (q 1 ,q 2 ,…,q i …), the acceleration sensor 7 measures a first acceleration while the non-contact sensor 5 measures, and a second acceleration while the contact sensor 6 measures;
in addition, the position information of a plurality of harvesters during operation is acquired through a positioning antenna arranged at the center line position of the roof of the harvesters during first time of yield measurement.
According to the first time series of yield measurements (p 1 ,p 2 ，…，p i …) and a second yield measurement time series (q 1 ,q 2 ,…,q i …) constructing a time sequence prediction model;
performing second measurement of yield of the grain 3 to be measured according to the first acceleration, the second acceleration and an acceleration threshold value a 0 And (3) selecting the non-contact sensor 5 yield measurement mode, the contact sensor 6 yield measurement mode and the time sequence prediction model yield measurement mode.
In one embodiment of the method of the present invention, the non-contact sensor 5 is a photoelectric sensor 5', and the contact sensor 6 is an impulse sensor 6'.
In one embodiment of the above method according to the invention, the grain delivery means 1 is a scraper type elevator 8.
It will be appreciated by those skilled in the art that the scraper-type elevator described above is only an example of one of the grain delivery mechanisms 1 and that it may also be applied to other harvesting devices suitable for mounting the photoelectric sensor 5 'and the impulse sensor 6' for measuring.
In one embodiment of the method of the present invention, the first position of the grain conveying mechanism 1 is the middle part of the scraper type elevator 8, and the second position of the grain conveying mechanism 1 is the grain outlet of the scraper type elevator 8.
In one embodiment of the above method of the invention, there are a plurality of blades 4, e.g. n blades 4, between the non-contact sensor 5 and the contact sensor 6, the first time series of yield measurements (p 1 ,p 2 ，…，p i …) of the first yield measurement p i Corresponds to the second time series of yield measurements (q 1 ,q 2 ,…,q i Second yield measurement q in …) n+i The first yield measurement p i Corresponding to a first acceleration a of the plurality of first accelerations i The second yield measurement q n+i Corresponding to a second acceleration a of the plurality of second accelerations n+i 。
In one embodiment of the above method of the present invention, the first yield measurement time series (p 1 ,p 2 ，…，p i …) and a second yield measurement time series (q 1 ,q 2 ,…,q i …) is when the acceleration is less than the acceleration threshold a 0 Measured at that time.
In one embodiment of the above method of the present invention, the step of constructing a time-series prediction model is based on constructing an autoregressive AR model.
In an embodiment of the above method of the present invention, the step of constructing an autoregressive AR model further includes:
the autoregressive AR model is:
one of the blades 4 is provided with a grain yield valuei＝1,…,N
N is the length of the time series of first yield measurements, P is the model order,for model parameters, E n+1 As a model residual, the model residual is the difference between the real data and the predicted data.
That is, the time series prediction model expresses that the yield at the next time is related to the previous P yields, P is the model order, and the degree of the correlation is determined byIt is shown that the yield value at the next moment is predicted from the previous P correlated yield values.
In one embodiment of the above method of the present invention, the determining model parametersFurther comprising the steps of:
model parameters are calculated by least square methodLeast squares estimation of +.>Make model residual epsilon n+1 The sum of squares of (c) is minimal.
In an embodiment of the above method of the present invention, the step of determining the model order P further includes:
AIC(P)＝NInσ a 2 +2P
wherein sigma a 2 For passing model residual E n+1 The calculated variance of the discrete white noise, AIC (P) is a function of the model order P;
the model order P is obtained by minimizing the value of AIC (P).
In one embodiment of the above method of the present invention, the first acceleration, the second acceleration and an acceleration threshold value a are used 0 The step of selecting the non-contact sensor 5, the contact sensor 6 and the time series prediction model production measuring mode further comprises the following steps:
when the harvester works stably, selecting a yield measuring mode of the non-contact sensor 5 and/or the contact sensor 6;
and when the operation of the harvester is not stable, selecting the time sequence prediction model yield measurement mode.
In an embodiment of the above method of the present invention, when the harvester is operating stably, the step of selecting the non-contact sensor 5 and/or the contact sensor 6 for measuring the yield further includes:
when a first acceleration a i Acceleration threshold a is less than or equal to 0 < second acceleration a n+i At this time, the grain yield value on the scraper 4 currently measured by the non-contact sensor 5 is selected as the scraper grain yield value y i I.e. y i ＝p i ；
When the second acceleration a n+i Acceleration threshold a is less than or equal to 0 < first acceleration a i In this case, the grain yield value on the scraper 4 measured by the contact sensor 6 is selected as the scraper grain yield value y i I.e. y i ＝q n+i ；
When a first acceleration a i Second acceleration a n+i Acceleration threshold a is less than or equal to 0 When the average value of the current grain yield values of the scraping plate 4 measured by the non-contact sensor 5 and the contact sensor 6 is selected as a scraping plate grain yield value y i I.e.
In an embodiment of the above method of the present invention, when the operation of the harvester is unstable, the step of selecting the time series prediction model for measuring the yield further includes:
when a first acceleration a i Second acceleration a n+i >Acceleration threshold a 0 When the harvester operates stably, acquiring yield time sequence data f obtained by a yield measurement mode selected during the stable operation of the harvester i ；
Predicting grain yield value on the current scraper 4 by using the time series prediction model to obtain a scraper Gu Wuchan magnitude y i I.e.
In one embodiment of the method of the present invention, the time series prediction model is used to predict the grain yield value on the current screed 4 to obtain the screed Gu Wuchan magnitude y i Further comprising the steps of:
predicting grain yield value on the current scraper 4 by using the time series prediction model to obtain a scraper Gu Wuchan magnitude y i The yield timing data f may be added i The subsequent scraped grain yield was estimated.
Further, when determining the squeegee yield y i At the same time, the harvest position information at the moment is acquired,and obtaining the scraper blade output information at a certain position of the harvester at a certain moment so as to carry out subsequent application. For example, each yield data point corresponds to a location, and these yield data containing location information are used to obtain the yield of a certain area of the plot, to visualize the yield data containing geographic locations, and to further provide yield applications based on the geographic location services LBS.
As shown in fig. 3, the present invention further discloses a multi-sensor information fusion yield measurement device 10, which is configured to perform the steps of any one of the above methods, and includes:
the first yield measuring module 11 is used for measuring yield for the first time by using a harvester, and the sensors used in the first yield measuring process comprise an acceleration sensor 7 arranged on a body of the harvester, a non-contact sensor 5 arranged at a first position of a grain conveying mechanism 1 of the harvester and a contact sensor 6 arranged at a second position of the grain conveying mechanism 1;
a yield measurement data acquisition and processing module 12 for acquiring yield measurement data and processing the yield measurement data to obtain a first yield measurement time series (p 1 ,p 2 ，…，p i …), a second time series of yield measurements (q 1 ,q 2 ,…,q i …), a first acceleration measured by the acceleration sensor 7 while being measured by the non-contact sensor 5, and a second acceleration measured by the contact sensor 6;
a time series prediction model construction module 13 for constructing a time series (p 1 ,p 2 ，…，p i …) and a second yield measurement time series (q 1 ,q 2 ,…,q i …) constructing a time sequence prediction model;
a second yield measurement module 14 for performing a second yield measurement on the grain 3 to be measured according to the first acceleration, the second acceleration and an acceleration threshold value a 0 And (3) selecting the non-contact sensor 5 yield measurement mode, the contact sensor 6 yield measurement mode and the time sequence prediction model yield measurement mode.
As shown in fig. 4, the invention further comprises a multi-sensor information fusion yield measurement system 100, which comprises an acceleration sensor 7 installed on a harvester body, a non-contact sensor 5 installed on a grain conveying mechanism 1 of the harvester, a contact sensor 6 installed on the grain conveying mechanism 1, a storage unit 120 and a control unit 110, wherein the control unit 110 is connected with the acceleration sensor 7, the non-contact sensor 5, the contact sensor 6 and the storage unit, and the device connected with the control unit 110.
The control unit 110 described above may include a CPU (Central Processing Unit central processing unit), general purpose processor, DSP (Digital Signal Processor data signal processor), ASIC (Application SpecificIntegrated Circuit application specific integrated circuit), FPGA (Field Programmable Gate Array field programmable gate array) or other programmable logic device, transistor logic device, hardware components, or any combination thereof. Which may implement or perform the various exemplary logic blocks, modules, and circuits described in connection with this disclosure. The control unit 110 may also be a combination implementing computing functions, e.g. comprising one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.
As shown in fig. 5, the present invention further includes a harvester 200, including a body 220 mounted on a chassis 210, a driving device 230, and a grain delivery mechanism 1, and further includes the multi-sensor information fusion yield measurement system 100.
The present invention discloses a storage medium for storing a computer control program for executing the steps of any one of the methods described above.
The computer program executable by the processor may be disposed in Random Access Memory (RAM), memory, read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
Based on the above, the yield label extraction method, the yield label extraction device, the yield measurement system and the harvester based on the harvesting path disclosed by the invention adopt two yield measurement sensors to measure the yield of the same scraper blade 4 at different moments in combination, select different scraper blade 4 yield measurement methods according to the vibration amplitude of the harvester body, overcome the influence of the increase of the vibration of the harvester at a certain moment on the measurement precision of the yield measurement sensors, and improve the yield measurement precision.
In view of the foregoing, it will be evident to those skilled in the art that various modifications and changes may be made without departing from the broader spirit and scope of the invention.
Claims (19)
1. The multi-sensor information fusion yield measurement method is characterized by comprising the following steps of:
the method comprises the steps that a harvester is used for first time yield measurement, and sensors used in the first time yield measurement comprise an acceleration sensor arranged on a body of the harvester, a non-contact sensor arranged at a first position of a grain conveying mechanism of the harvester and a contact sensor arranged at a second position of the grain conveying mechanism;
acquiring and processing the yield measurement data to obtain a time series of first yield measurements (p 1 ,p 2 ，…，p i …), a second time series of yield measurements (q 1 ,q 2 ,…,q i …), the acceleration sensor measuring a first acceleration while the non-contact sensor is measuring, and measuring a second acceleration while the contact sensor is measuring;
according to the first time series of yield measurements (p 1 ,p 2 ，…，p i …) and a second yield measurement time series (q 1 ,q 2 ,…,q i …) constructing a time series prediction model;
performing second time of yield measurement on the grain to be measured according to the first acceleration, the second acceleration and an acceleration threshold value a 0 For the non-contact sensingAnd selecting a device yield measurement mode, a contact sensor yield measurement mode and a time sequence prediction model yield measurement mode.
2. The method of claim 1, wherein the grain delivery mechanism employs a scraper elevator.
3. A method as in claim 2 wherein the first position of the conveyor is a middle portion of the scraper elevator and the second position of the conveyor is a discharge of the scraper elevator.
4. A method according to claim 3, wherein there are a plurality of scrapers between the non-contact sensor and the contact sensor, the first time series of yield measurements (p 1 ,p 2 ，…，p i …) of the first yield measurement p i Corresponds to the second time series of yield measurements (q 1 ,q 2 ,…,q i Second yield measurement q in …) n+i The first yield measurement p i Corresponding to a first acceleration a of the plurality of first accelerations i The second yield measurement q n+i Corresponding to a second acceleration a of the plurality of second accelerations n+i 。
5. The method of claim 4, wherein said first time series of yield measurements (p 1 ,p 2 ，…，p i …) and a second yield measurement time series (q 1 ,q 2 ,…,q i …) is when the acceleration is less than the acceleration threshold a 0 Measured at that time.
6. The method of claim 5, wherein the step of constructing a time series prediction model is based on constructing an autoregressive AR model.
7. The method of claim 6, wherein the step of constructing an autoregressive AR model further comprises:
the autoregressive AR model is:
wherein one of the scrapers has a grain yield value
N is the length of the time series of first yield measurements, P is the model order,for model parameters, E n+1 Is the model residual.
8. The method of claim 7, wherein the determining model parametersFurther comprising the steps of:
model parameters are calculated by least square methodLeast squares estimation of +.>Make model residual epsilon n+1 The sum of squares of (c) is minimal.
9. The method of claim 8, wherein the step of determining the model order P further comprises:
AIC(P)＝NInσ a 2 +2P
wherein sigma a 2 For passing model residual E n+1 Calculated variance of discrete white noiseAIC (P) is a function of model order P;
the model order P is obtained by minimizing the value of AIC (P).
10. The method of claim 9, wherein the first acceleration, the second acceleration, and an acceleration threshold a are determined based on 0 The step of selecting the non-contact sensor, the contact sensor and the time sequence prediction model production measurement mode further comprises the following steps:
when the harvester works stably, selecting the non-contact sensor and/or the contact sensor to measure the yield;
and when the operation of the harvester is not stable, selecting the time sequence prediction model yield measurement mode.
11. The method of claim 10, wherein the step of selecting the non-contact sensor and/or the contact sensor sensing mode when the harvester is operating smoothly further comprises:
when a first acceleration a i Acceleration threshold a is less than or equal to 0 < second acceleration a n+i When the grain yield value on the scraper, which is measured by the non-contact sensor, is selected as the grain yield value y of the scraper i I.e. y i ＝p i ；
When the second acceleration a n+i Acceleration threshold a is less than or equal to 0 < first acceleration a i When the grain yield value on the current scraper, which is measured by the contact sensor, is selected as a scraper grain yield value y i I.e. y i ＝q n+i ；
When a first acceleration a i Second acceleration a n+i Acceleration threshold a is less than or equal to 0 When the average value of the grain yield values on the current scraper, which are measured by the non-contact sensor and the contact sensor, is selected as a scraper grain yield value y i I.e.
12. The method of claim 11, wherein the step of selecting the time series prediction model yield measurement mode when the harvester operation is not stationary further comprises:
when a first acceleration a i Second acceleration a n+i >Acceleration threshold a 0 When the harvester operates stably, acquiring yield time sequence data f obtained by a yield measurement mode selected during the stable operation of the harvester i ；
Predicting the grain yield value on the current scraper by using the time sequence prediction model to obtain the scraper Gu Wuchan magnitude y i I.e.
13. The method of claim 12 wherein the time series prediction model is used to predict the current grain yield value on the screed to yield a screed Gu Wuchan magnitude y i Further comprising the steps of:
predicting the grain yield value on the current scraper by using the time sequence prediction model to obtain the scraper Gu Wuchan magnitude y i The yield timing data f may be added i The subsequent scraped grain yield was estimated.
14. The method of claim 1, wherein the acquiring and processing the production testing data further comprises acquiring a plurality of location information for association with the results of the second production testing to provide location information based production services and applications.
15. The method of any one of claims 1 to 14, wherein the non-contact sensor is a photoelectric sensor and the contact sensor is an impulse sensor.
16. A multi-sensor information fusion yield measuring device for performing the steps of the method according to any one of claims 1 to 15, comprising:
the first yield measuring module is used for carrying out first yield measurement by using a harvester, and the sensor used in the first yield measurement comprises an acceleration sensor arranged on a body of the harvester, a non-contact sensor arranged at a first position of a grain conveying mechanism of the harvester and a contact sensor arranged at a second position of the grain conveying mechanism;
a yield measurement data acquisition and processing module for acquiring yield measurement data and processing the yield measurement data to obtain a first yield measurement value time sequence (p 1 ,p 2 ，…，p i …), a second time series of yield measurements (q 1 ,q 2 ,…,q i …), a first acceleration measured by the acceleration sensor while the non-contact sensor is measuring, and a second acceleration measured by the contact sensor while the non-contact sensor is measuring;
a time series prediction model construction module for constructing a time series (p) of the first yield measurement values 1 ,p 2 ，…，p i …) and a second yield measurement time series (q 1 ,q 2 ,…,q i …) constructing a time sequence prediction model;
the second yield measurement module is used for performing second yield measurement on the grains to be measured according to the first acceleration, the second acceleration and an acceleration threshold value a 0 And (3) selecting the non-contact sensor yield measurement mode, the contact sensor yield measurement mode and the time sequence prediction model yield measurement mode.
17. The multi-sensor information fusion yield measuring system comprises an acceleration sensor arranged on a harvester body, a non-contact sensor arranged on a grain conveying mechanism of the harvester, a contact sensor arranged on the grain conveying mechanism, a storage unit and a control unit, wherein the control unit is connected with the acceleration sensor, the non-contact sensor and the storage unit, and the device of claim 16 is connected with the control unit.
18. A harvester comprising a body mounted on a chassis, a drive, and a grain delivery mechanism, further comprising the multi-sensor information fusion yield measurement system of claim 17.
19. A storage medium storing a computer control program for performing the steps of the method according to any one of claims 1 to 15.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311609976.4A CN117829403A (en) | 2023-11-29 | 2023-11-29 | Multi-sensor information fusion yield measurement method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311609976.4A CN117829403A (en) | 2023-11-29 | 2023-11-29 | Multi-sensor information fusion yield measurement method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117829403A true CN117829403A (en) | 2024-04-05 |
Family
ID=90521739
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311609976.4A Pending CN117829403A (en) | 2023-11-29 | 2023-11-29 | Multi-sensor information fusion yield measurement method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117829403A (en) |
-
2023
- 2023-11-29 CN CN202311609976.4A patent/CN117829403A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105741180B (en) | Grain yield graph drawing system of combined harvester | |
| Pierce et al. | Yield mapping | |
| US11307074B2 (en) | Yield monitoring apparatus, systems, and methods | |
| Birrell et al. | Comparison of sensors and techniques for crop yield mapping | |
| US9693496B2 (en) | Agricultural planting depth sensor | |
| EP1361785B1 (en) | Improvements in mapping techniques | |
| UA125462C2 (en) | Systems, methods, and devices for monitoring weather and field conditions | |
| EP2030165A2 (en) | Method for determining field readiness using soil moisture modeling | |
| Murphy et al. | Yield mapping‐a guide to improved techniques and strategies | |
| CN103150615A (en) | Runoff predicting method | |
| Birrell et al. | Crop yield mapping: Comparison of yield monitors and mapping techniques | |
| Grisso et al. | Yield monitor accuracy: Successful farming magazine case study | |
| Fulton et al. | Grain yield monitor flow sensor accuracy for simulated varying field slopes | |
| CN108781657A (en) | A kind of Sowing machine for potatoes and its broadcast leakage detection method and detection device | |
| Liu et al. | Development and application experiments of a grain yield monitoring system | |
| CN117829403A (en) | Multi-sensor information fusion yield measurement method and device | |
| Semenov | Using weather generators in crop modelling | |
| JP2003000047A (en) | Method for measuring influent grain weight into combine tank and device therefor | |
| US20230073551A1 (en) | Row-by-row yield estimation system and related devices and methods | |
| Singh et al. | Precision in grain yield monitoring technologies: a review | |
| JP7284678B2 (en) | Virtual operating time calculator | |
| Dampney et al. | Precision Agriculture in England: Current Practice and Research‐Based Advice to Farmers | |
| CA3192803A1 (en) | Flow rate matching | |
| Van Bergeijk et al. | PA—Precision Agriculture: Dynamic Weighing for Accurate Fertilizer Application and Monitoring | |
| Purti et al. | Portable wireless yield monitoring system on conventional rice combine |
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 |