JP7321087B2 - Harvester management system, harvester, and harvester management method - Google Patents

Description

The present invention provides a harvester management system for managing harvest loss in a harvester comprising a harvesting section for harvesting crops in a field and a storage section for storing harvested materials harvested by the harvesting section. The present invention relates to a harvester equipped with a harvester management system and a harvester management method.

The combine harvests the planted culms, threshes the harvested culms, sorts the grain, and stores the sorted grain. The material threshed by the threshing body includes grains, stalks (grains with branches), waste straw, straw, etc. The grains selected from the threshed material by the sorting section It is transported to a tank and stored. Threshed products other than normal grains (branch stems, straw scraps, etc.) are collectively referred to as non-grains in this specification. Straw and straw waste are discharged from the rear part of the fuselage from the handling body or the sorting part. Ideally, it is preferable that only the threshed material other than the grains is discharged from the threshing barrel to the outside of the machine body, but the grains are also discharged together. Such grain loss is called barrel loss. Furthermore, the threshed material that falls from the threshing barrel to the sorting section contains not only grains but also defective grains such as branch stems and waste straw. Defective grains and straw scraps mixed in the sorting section are returned to the threshing process as the second crop. The occurrence of second products in such a sorting section is called a sorting loss. In this specification, the threshing loss is a collective term for the threshing loss and the sorting loss. In the combine, the operating equipment of the thresher is adjusted to reduce this threshing loss.

Patent Literature 1 discloses a combine harvester in which feedback control is performed based on the loss amount calculated by a handling cylinder loss sensor and a swing loss sensor, and the dust feed valve, chaff sieve, and vehicle speed are adjusted so that the loss amount falls within a target range. It is A threshing drum loss sensor, which senses the amount of grain by detecting the load caused by contact with the grain, detects the amount of grain falling from the terminal end of a receiving net laid below the threshing drum. The rocking loss sensor, which is a pressure sensor, detects the amount of grains falling from the rear part of the rocking sorting device toward the secondary collecting part.

In Patent Document 2, image processing is performed on the captured image of the grain stored in the grain tank to inspect the state of the grain and the contamination of foreign matter. A combine is disclosed in which the chaff sieve is adjusted.

JP 2017-176060 A JP 2013-027340 A

In the threshing control in Patent Document 1, a threshing loss sensor consisting of a threshing drum loss sensor and a rocking loss sensor measures the instantaneous threshing loss amount, and when the measured value deviates from the target range, the threshing device is adjusted. However, the amount of threshing processing changes from moment to moment. The problem arises that it is not controllable.

In the threshing control in Patent Literature 2, inspections such as the state of grains and the contamination of foreign matter are performed by image processing images captured by a camera. This threshing control has the advantage that the installation space of the camera is smaller than the installation space of the mechanically operated threshing loss sensor shown in Patent Document 1. However, the mixed amount of foreign matter to be inspected here is also detected as an instantaneous threshing loss amount, and has the same problem as in Patent Document 1.

In view of the above circumstances, an object of the present invention is to provide a harvester management system, a harvester, and a harvester management method for appropriately managing harvest loss.

A harvester management system according to the present invention for managing crop loss in a harvester comprising a harvesting unit for harvesting crops in a field and a storage unit for storing the harvested crops harvested by the harvesting unit,
a harvest amount measuring unit that measures the harvest amount of the harvested material; a loss amount calculation unit that calculates a loss amount indicating the amount of loss that occurs while the harvested material is transported from the harvesting section to the storage section; a loss rate calculation unit that calculates a loss rate, which is the loss amount per unit harvest amount, based on the harvest amount and the loss amount ;
The harvest amount measurement unit measures the yield, which is the amount of grain obtained from the harvested product, as the harvest amount,
The loss amount calculation unit calculates, as the loss amount, the amount of threshing loss in a threshing device provided in the harvester for threshing the harvested product.

According to this configuration, the harvest amount measured by the harvest amount measuring unit and the loss amount calculated by the loss amount calculating unit are provided to the loss rate calculating section. The loss rate calculator sequentially calculates a loss rate, which is the amount of loss per unit harvest amount during the harvesting operation. When the loss rate is sequentially calculated in this way, it becomes possible to control the harvester based on the loss rate. The loss rate is the value obtained by dividing the loss amount by the yield. less impact on As a result, harvester control based on loss rate eliminates problems that can arise in control based on instantaneous loss amount. In the threshing process, which is one of the harvested material processes in a harvester, harvested grain culms are separated into grains and straw while passing through a threshing drum. The threshed material such as grains dropped downward from the threshing drum is further sorted. Straw is delivered to the rear of the barrel and discharged from the rear of the fuselage. At that time, the amount of grains (actual harvest) mixed with the straw (pseudo-harvest) sent out of the machine from the rear of the threshing drum corresponds to the threshing drum loss. It means that the trunk loss is large. In addition, as a result of the sorting process, the threshed material that has fallen from the threshing drum is mixed with non-grains (pseudo-harvested material) such as straw scraps, and the amount of grain (real harvested material) that is discharged outside the machine is a sorting loss. Correspondingly, the larger the amount of grain discharged out of the machine, the larger the sorting loss. Sorting loss and handling drum loss are collectively referred to as threshing loss. Therefore, it is effective to use threshing loss as the amount of loss.

In one of the preferred embodiments of the present invention, the loss area in which the loss occurs is provided with a detection section for detecting the loss, and the loss amount calculation unit calculates the loss based on the detection result from the detection section. It is configured to output the amount of loss. In this configuration, a detection unit is provided for identifying a previously known loss area in which loss occurs while the harvested material is being conveyed from the harvesting unit to the storage unit, and for detecting loss in that loss area. Therefore, the detection unit can quickly detect the loss in the specific loss area with almost no adverse effects such as disturbance.

Conventionally, the threshing loss in the threshing apparatus was measured using an impact sensor, which has the drawback of requiring a large installation space. It is proposed to calculate the amount of loss using an image and a neural network, which is a machine learning unit. That is, in one of the preferred embodiments of the present invention, the detection unit is provided with a photographing unit that photographs the loss area where the loss occurs,
The loss amount calculation unit is configured as a neural network that outputs the loss amount based on image input data generated from the captured image from the imaging unit. This neural network is designed to output the amount of loss from the ratio of the actual harvest (e.g. grain) and pseudo-harvest (e.g. non-grains such as stalks and straw scraps) shown in the captured image. It is a trained machine learning model. At that time, in order to increase the reliability of the neural network, image input data obtained by performing preprocessing such as normalization on sequentially sent captured images is input as input data of the neural network. is preferred.

In one of the preferred embodiments of the present invention, the neural network includes learning image input data generated from learning captured images taken during harvesting by the harvester, and actual data obtained from the learning captured images. is learned using the estimated loss amount (estimated value by a harvest processing expert or expert) as learning data. That is, during learning, the learning image input data generated from the learning photographed image taken during the harvesting work is used as the input learning data, and the loss amount artificially estimated from the learning photographed image. is used as learning data for output (correct data). In this configuration, an image captured during an actual harvesting operation is used as a learning captured image, and an estimated loss amount actually estimated by a harvest processing expert or an expert from this learning captured image is used as correct data. Therefore, the threshing control based on the amount of loss output from the trained neural network is supported by the judgment of a harvest processing expert or an expert.

One of the loss areas suitable for confirmation of loss is the area where a small amount of pseudo-harvest is mixed with a large amount of real crop, and the other one is an area where a small amount of pseudo-harvest is mixed with a large amount of pseudo-harvest. This is an area where fruit crops are mixed. For this reason, if image input data based on captured images with two different fields of view as described above are used as inputs for the same neural network, it may be difficult to calculate the amount of loss. Accordingly, in one preferred embodiment of the present invention, the photographing unit includes a plurality of cameras having different photographing fields of view, and a plurality of cameras corresponding to the plurality of cameras, respectively. is provided, and the individual image input data corresponding to the captured images from the plurality of cameras are input to each of the neural networks corresponding to the cameras that are capturing sources. In this configuration, the loss amount in each area is output by a dedicated neural network configured to be suitable for each of the captured images in different areas. Since the loss amounts in different regions are calculated by using the optimum photographed image and a dedicated neural network, highly reliable loss amounts can be obtained.

When photographing a loss area where loss occurs, the amount of information obtained from the photographed image increases by photographing the harvested product in the area at various positions and in various photographing directions. Accordingly, in one of the preferred embodiments of the present invention, the photographing unit includes a plurality of cameras each having a different photographing field of view, and one neural network corresponds to each of the plurality of cameras. and all the image input data corresponding to the captured images from the plurality of cameras are input to the neural network. With this configuration, a more reliable amount of loss is output based on captured images of harvested crops captured from various positions and from various directions.

Sorting loss and handling drum loss have different definitions, so when calculating sorting loss and handling drum loss based on photographed images, photographed images taken in separate threshing areas (loss areas) is used. For this reason, in one preferred embodiment of the invention, the loss area in which said loss occurs includes the threshing cylinder end area and the sheave case rear end area, and in a further embodiment , the loss area in which the loss occurs includes a discharge section area for discharging non-grain (straw, straw waste, etc.) other than grain from the threshing device.

If the operating equipment of the harvester is automatically adjusted so that the loss rate calculated using the loss amount calculated by the neural network (sorting loss amount, handling cylinder loss amount, etc.) falls within the allowable range, the appropriate Harvester control is realized. For this reason, in one of the preferred embodiments of the present invention, a parameter determination unit is provided that determines control parameters for the harvester based on the loss amount. Of course, the parameter determination unit may be configured to determine the control parameters of the harvester based on a combination of the loss amount and the loss rate, or only on the loss rate.

The invention described above also applies to harvesters. Such a harvester includes a harvesting unit that harvests crops in a field, a storage unit that stores the harvested product harvested by the harvesting unit, a yield measurement unit that measures the yield of the harvested product, and the harvesting unit that measures the yield of the harvested product. a loss amount calculation unit that calculates a loss amount indicating the amount of loss that occurs while the material is being transported from the harvesting section to the storage section; and the loss per unit harvest amount based on the harvest amount and the loss amount. and a threshing device for threshing the harvested product . A certain yield is measured, and the loss amount calculation unit calculates the amount of threshing loss in the threshing device as the loss amount . The harvester according to the present invention can also obtain the various functions and effects described above.

In one preferred embodiment of the harvester according to the present invention, a traveling device and a conveying device for conveying the harvested material are provided, and based on the loss rate, the traveling device, the harvesting section, and the conveying device , and a parameter determination unit for determining at least one control parameter of the threshing device. With this configuration, the harvester can improve its harvesting performance by automatically adjusting each operating device so that the loss rate falls within the allowable range.

The present invention is also applied to the harvester management method employed in the harvester management system described above. In such a harvester management method, a harvester having a harvesting unit for harvesting crops in a field and a storage unit for storing the harvested product harvested by the harvesting unit performs a harvesting operation while harvesting the harvested product. while the harvesting work is being performed by the harvester, a loss amount indicating the amount of loss that occurs while the harvested material is being transported from the harvesting unit to the storage unit is calculated; While performing the harvesting work, the loss rate, which is the loss amount per unit harvest amount, is calculated based on the harvest amount and the loss amount , and the harvest amount is the amount of grain obtained from the harvest. The yield is measured, and the amount of threshing loss in a threshing device provided in the harvester for threshing the harvested product is calculated as the amount of loss. The harvester management method according to the present invention can also obtain the various functions and effects described above.

In one preferred embodiment of the harvester management method according to the present invention, a control parameter for the harvester is determined based on the loss rate while the harvester is performing the harvesting work. With this harvester management method, each operating device of the harvester is automatically adjusted so that the loss rate is within an acceptable range, thereby improving its harvesting performance.

1 is a side view of a combine with a threshing device; FIG. 1 is a plan view of a combine with a threshing device; FIG. It is a longitudinal side view of a threshing device. It is a schematic diagram which shows arrangement|positioning of a yield measuring instrument and a taste value measuring instrument in a grain tank. It is a functional block diagram of a control system of a combine. It is a block diagram of a threshing loss management unit. It is the schematic diagram by which the photography image of the threshing processed material was expanded. It is the schematic diagram by which the label image of the threshed material was expanded. It is a block diagram which shows another structure of a threshing loss management unit. It is a block diagram which shows another structure of a threshing loss management unit.

Preferred embodiments of the present invention will be described below with reference to the drawings. In this embodiment, the harvester is a combine that threshes harvested culms while traveling, and the harvester management system is a threshing management system provided in the combine.

FIG. 1 is a side view of a combine. FIG. 2 is a plan view of the combine. Moreover, FIG. 3 is sectional drawing of the threshing apparatus 1. As shown in FIG. In addition, below, although the combine of this embodiment is a normal type combine, of course, a self-threshing type combine may be used.

Here, for ease of understanding, in the present embodiment, unless otherwise specified, "front" (the direction of arrow F shown in FIG. 1) means forward in the longitudinal direction of the aircraft (running direction). "Rear" (the direction of arrow B shown in FIG. 1) means the rear in the longitudinal direction (running direction) of the aircraft. In addition, "up" (direction of arrow U shown in Figure 1) and "down" (direction of arrow D shown in Figure 1) is the positional relationship in the vertical direction (vertical direction) of the aircraft, and at ground level shall indicate the relationship. Furthermore, the left-right direction or the lateral direction is the fuselage transverse direction (body width direction) orthogonal to the fuselage longitudinal direction, that is, “left” (the direction of arrow L shown in FIG. 2) and “right” (the direction of arrow R shown in FIG. 2). direction) shall mean the left and right directions of the aircraft, respectively.

As shown in FIGS. 1 and 2 , the combine has a body frame 2 and a crawler travel device (an example of a travel device) 3 . A reaping section (an example of a harvesting section) 4 for reaping planted grain culms is provided in front of the traveling body 17 .

A threshing device 1 for threshing the harvested grain culms is provided behind the harvesting unit 4, and a feeder (conveying device example) 11 is provided. A grain tank (an example of a storage unit) 12 for storing grains after threshing processing is provided on the side of the threshing device 1 , and a straw shredding device 13 is provided behind the threshing device 1 .

A driving unit 9 covered with a cabin 10 is arranged on the right side of the front part of the traveling body 17 . An engine E is provided below the operating section 9 . The power of the engine E is transmitted to the crawler traveling device 3, the threshing device 1 and the like by a power transmission structure (not shown). Furthermore, a grain discharging device 14 for discharging the grains in the grain tank 12 to the outside is provided.

The grain discharging device 14 includes a vertical conveying portion 15 that conveys the grains in the grain tank 12 upward, and a horizontal conveying portion 16 that conveys the grains from the vertical conveying portion 15 toward the outside of the machine body. is provided. The grain discharging device 14 is configured to be rotatable around the axis of the vertical conveying section 15 . A lower end portion of the vertical conveying portion 15 is connected to the bottom portion of the grain tank 12 for communication. The end portion of the horizontal transport portion 16 on the side of the vertical transport portion 15 is connected to the upper end portion of the vertical transport portion 15 and is supported so as to be capable of swinging up and down.

As shown in FIG. 3 , the threshing device 1 includes a threshing drum section 41 for threshing harvested grain culms and a sorting section 42 . The threshing drum part 41 is arranged in the upper part of the threshing device 1 , and the sorting part 42 is arranged below the threshing drum part 41 . The sorting unit 42 includes a swing sorting mechanism 24 , a first product recovery unit 26 , a second product recovery unit 27 , and a second product return unit 32 .

The handling cylinder part 41 has a handling cylinder 22 housed in the handling chamber 21 and a receiving net 23 laid under the handling cylinder 22 . The handling chamber 21 is formed as a space surrounded by a front wall 51 on the front side, a rear wall 52 on the rear side, left and right side walls, and a top plate 53 covering the top. Below the front wall 51 of the handling chamber 21 is formed a supply port 54a through which harvested grain culms are supplied, and a guide bottom plate 59 is arranged under the supply port 54a. A dust outlet 54b is formed below the rear wall 52 of the handling chamber 21. As shown in FIG.

The handling cylinder 22 has a body 60 and a rotation support shaft 55 which are rotated integrally by the driving torque from the rotation drive mechanism 56 . The body 60 is integrally formed with a raking portion 57 at the front end and a handling portion 58 at the rear position of the raking portion 57 .

A plurality of plate-shaped dust valves 53a are provided on the inner surface (lower surface) of the top plate 53 at predetermined intervals along the front-rear direction. In the threshing chamber 21, the harvested culms rotating with the threshing cylinder 22 are subject to a rearward movement force. The plurality of dust valves 53a are configured to be able to adjust this rearward movement force.

The threshed material processed by the threshing drum section 41 includes grains, branches, straw scraps, and the like. In addition, the first product is a threshed product mainly containing grains, and the second product is a threshed product containing insufficiently single-grained grains, branches, straw scraps, and the like.

In the handling drum section 41, the harvested material from the feeder 11 is supplied to the handling chamber 21 through the supply port 54a. The harvested culms supplied are raked along the guide bottom plate 59 by the spiral blades of the raked portion 57 and threshed.

The grains obtained by the threshing process and short straw scraps and the like leak down the receiving net 23 and fall into the sorting section 42. - 特許庁On the other hand, processed materials (grain stalks, long straw scraps, etc.) that cannot flow down the receiving net 23 are discharged out of the processing chamber 21 through the dust outlet 54b.

The swing sorting mechanism 24 swings the frame-shaped sheave case 33 in the front-rear direction by an eccentric cam mechanism using an eccentric shaft or the like. A winnow 25 for generating a sorting wind from front to back is provided in the sorting section 42 . In an environment where sorting wind is supplied from the winnow 25, the sieve case 33 is shaken to sort out grains (first grains) from the threshed material. Further, a first product recovery section 26 and a second product recovery section 27 are arranged below the sieve case 33 .

The first product collected by the first product collecting unit 26 is conveyed upward toward the grain tank 12 by the first product collecting and conveying unit 29 (lifted). The first product transported by the first product collecting/transporting unit 29 is transported rightward by the storage screw 30 (see FIG. 1) and supplied to the grain tank 12 (see FIG. 1).

The second product recovery unit 27 is configured as a second product screw that transports the recovered second product in the horizontal direction. The second product recovered by the second product recovery unit 27 is conveyed obliquely forward and upward by the second product return unit 32 and returned above the sieve case 33 .

The sieve case 33 is provided with a first grain pan 34 , a plurality of first sieve lines 35 , a second sieve line 36 , a first chaff sieve 38 , a second chaff sieve 39 , a grain sieve 40 , an upper grain pan 61 and a lower grain pan 65 .

A first chaff sieve 38 having a plurality of chaff lip 38A is arranged behind the upper grain pan 61 , and a second chaff sieve 39 is arranged behind the first chaff sieve 38 . The plurality of chaflips 38A are arranged along the conveying direction (backward direction) in which the processed material is conveyed, and each of the plurality of chaflips 38A is arranged in a tilted posture obliquely upward toward the rear end side. The lower grain pan 65 is arranged below the front end portion of the first chaff sieve 38, and the grain sieve 40 made of a net-like body is arranged at a position connected to the rear thereof. The second chaff sieve 39 is arranged below the rear end of the first chaff sieve 38 and behind the grain sieve 40 . A discharge portion 28 is formed by the rear end portion (the right end portion in FIG. 3 ) of the sheave case 33 and the rear end portion of the receiving net 23 .

The first chaff sieve 38 conveys the threshed material to the rear side by wind sorting by a sorting wind and specific gravity sorting due to rocking, and at the same time, leaks the grains contained in the threshed material. The stalks such as straw scraps are transferred to the second chaff sieve 39, sent out from the rear end of the second chaff sieve 39 to the rear of the sieve case 33, and discharged from the discharging part 28 toward the discharged straw shredding device 13. be. The stems and culms discharged from the discharging part 28 are shredded by the straw shredding device 13 and discharged to the outside of the threshing device 1 . The grains directly leaking down to the second chaff sieve 39 through the receiving net 23 are sorted by the second chaff sieve 39 into grains and stalks such as straw scraps.

A processed material containing a large amount of grain is received on the upper surface of the grain sieve 40 . Since straw scraps and the like are sent rearward on the upper surface of the grain sieve 40, most of the threshed material leaking down the grain sieve 40 is grain, and is collected by flowing down to the first grain collecting section 26, where the first grain is collected. The grain tank 12 is stored by the transport unit 29 . Of the threshed material that did not leak through the grain sieve 40, straw waste is sent backward by the sorting wind.

On the other hand, the threshed material that has leaked down from the rear end portion of the grain sieve 40 or the threshed material that has fallen from the second chaff sieve 39 flows down to the secondary material recovery unit 27 and is recovered, and the secondary material is returned. By the portion 32, it is returned to the upstream side of the rocking sorting mechanism 24. As shown in FIG. Dust such as straw scraps generated by the sorting process is sent rearward from the rear end of the sheave case 33 and discharged from the discharging portion 28 to the discharged straw shredding device 13 .

The second item is returned to a position on the side of the receiving net 23 in the handling drum section 41 so as not to pass through the receiving net 23 . The second product discharge port 32A of the second product return unit 32 that returns the second product is provided at a radially outer position in the arc-shaped receiving net 23, and the second product is discharged at this position.

The sorting ability of sorting grains from the threshed material by the sorting unit 42 can be changed by adjusting the opening degree of each of the plurality of chaff lip 38A provided on the first chaff sieve 38 and adjusting the air volume of the winnow 25. . Further, in this embodiment, since the mounting angle of the dust valve 53a with respect to the top plate 53 is changeable, the sorting capability can be changed by adjusting the angle of the dust valve 53a. Furthermore, the change in the sorting ability by adjusting the opening degree of the chafflip 38A and the air volume of the winnow 25 is also related to the amount of threshed material and the amount of second harvest. If the amount of harvested culms is large, the amount of threshed material will be large, but if the condition of the crop is the same, the faster the vehicle speed, the greater the amount of harvested culms. From this, the opening degree of the chaflip 38A, the air volume of the winnow 25, the angle of the dust feed valve 53a, the reduction amount of the second product, the vehicle speed, etc. can be mentioned.

FIG. 4 shows a yield measurement for measuring the yield (harvest amount), which is the amount of grain that is put into the grain tank 12 from the threshing device 1 through the first product recovery conveying unit 29 (see FIG. 1) and the storage screw 30. A vessel M1 is shown as an example of a yield measuring unit. Furthermore, a taste value measuring instrument M2 for measuring the quality (moisture content, protein content, etc.) of the grain put into the grain tank 12 is also shown.

Yield measuring device M1 is incorporated in grain discharge device 30a provided at the end of storage screw 30. As shown in FIG. The grain discharging device 30a diffuses and discharges the conveyed grains into the grain tank 12 by means of a rotating plate. The yield measuring device M1 calculates the grain flow rate from the load cell signal that is distorted by the impact force of the grains that are diffused and released each time the rotating plate rotates. Furthermore, the yield measuring device M1 measures the yield per unit time (unit harvested amount ) is calculated.

The taste value measuring instrument M2 temporarily stores a portion of the grains diffusely released by the grain releasing device 30a, irradiates the stored grains with light, and returns through the grains. Spectroscopic analysis of light is used to measure the taste value (moisture and protein) of grains. Temporary storage and taste value measurement of such grains are performed periodically.

In this embodiment, the harvested product loss is the loss of grains, and particularly the threshing loss (amount of threshing loss) used as an index representing the threshing performance of the threshing device 1 is taken up. The threshing loss can be divided into a threshing cylinder loss and a sorting loss. In this embodiment, the handling drum loss amount is the amount of grain discharged from the rear end portion of the handling chamber 21 together with straw waste (discarded straw). The amount of threshing barrel loss includes the amount of grains discharged together with straw without threshing, and the amount of grains discharged from the rear end of the threshing chamber 21 together with straw scraps despite being threshed. be Furthermore, the amount of sorting loss is the amount of grains discharged from the rear end of the sorting unit 42 together with straw scraps despite being threshed and dropping into the sorting unit 42 . Such a threshing loss amount can be measured by a known impact detection sensor such as a pressure-sensitive sensor. be. Furthermore, using the calculated threshing loss amount and the yield measured by the yield measuring device M1, the threshing loss amount per unit harvest, that is, per unit yield is calculated.

For example, the ratio of the yield (unit yield) measured while a combine harvester is running for a predetermined time or distance during harvesting to the amount of threshing loss calculated during that run is calculated as the amount of loss per unit yield. A rate (loss rate in a unit run) is calculated. By assigning this loss rate to the travel locus, the loss rate in a predetermined area of the field and the loss rate of the entire field are calculated. In this embodiment, an imaging unit 80 that captures an image of the loss area is used as a detection unit that detects the loss in the loss area.

The photographed image for calculating the threshing loss amount is an image photographed by the photographing unit 80 having a photographing field of view of the loss area where the threshing loss occurs. In this embodiment, the loss area suitable for recognition of the handling cylinder loss is the rear end of the handling cylinder 22 or the rear of the handling cylinder 22, and the loss area suitable for recognition of the sorting loss is the sheave case 33. It is above the second chaff sheave 39 at the rear end. Of course, areas where other threshing losses can be recognized can be used as loss areas. Since the amount of grains mixed with the straw discharged from the vehicle body is also a kind of threshing loss, the cut behind the vehicle body may be used as the loss area.

FIG. 5 is a functional block diagram of the control system of the combine. FIG. 5 shows the control device 100, the imaging unit 80, the threshing loss management unit 7, the yield measuring device M1, the taste value measuring device M2, various sensors, and various operating devices. Here, a threshing loss management system is constructed by the imaging unit 80, the threshing loss management unit 7, and the yield measuring device M1.

The various motion devices include a traveling motion device D1, a reaping motion device D2, a threshing motion device D3, a discharge motion device D4, and the like. The traveling operation device D1 includes an engine operation device, a speed change operation device, and a steering operation device. The reaping motion device D2 includes a motion device that creates motion of the reaping unit 4 and the feeder 11 . The threshing motion device D3 includes motion devices such as the threshing cylinder 22, the rocking sorting mechanism 24, the chaflip 38A, the winnow 25, the dust-feeding valve 53a, the first product collecting and conveying unit 29, the second product returning unit 32, and the like. is included. Discharge action equipment D4 includes action equipment that creates movement of the grain discharge device 14 .

Of the various sensors, sensors that are particularly relevant to the present invention are the running state sensor S1 and the threshing state sensor S2. The running state sensor S1 detects the operating states of various running motion devices D1. The threshing state sensor S2 detects the operation states of the threshing cylinder 22, the rocking sorting mechanism 24, the chaflip 38A, the winnow 25, the first product collecting and conveying unit 29, the second product returning unit 32, and the like. In this embodiment, the running state sensor S1 includes a GNSS sensor having a satellite positioning function of receiving satellite radio waves and calculating position coordinates.

The control device 100 includes a running control unit RU, a reaping control unit CU, a threshing control unit TU, and a discharge control unit UU. The travel control unit RU generates a control signal for travel control and sends it to the travel action device D1 via the input/output signal processing unit IO to control travel of the travel body 17 . In this embodiment, the travel control unit RU has an own vehicle position calculation function for calculating the own vehicle position in the field based on the position coordinates output from the GNSS unit, and a travel trajectory function for calculating the travel trajectory from the own vehicle position over time. It also has a calculation function and an automatic driving function that automatically drives based on the position of the vehicle. The reaping control unit CU generates a control signal for reaping control and sends it to the reaping action device D2 via the input/output signal processing section IO to control the reaping operation.

The threshing control unit TU generates a control signal for threshing control and sends it to the threshing operation device D3 via the input/output signal processing unit IO to control the operation of the threshing work. The threshing control unit TU includes a chaff opening degree control section T1 that adjusts the opening degree of the chaff lip 38A, a winnow wind control section T2 that adjusts the wind force of the pickaxe 25, and a valve angle control section T3 that adjusts the valve angle of the dust feed valve 53a. and so on.

The discharge control unit UU generates a control signal related to discharge control for discharging grains from the grain tank 12, and sends it to the discharge operation device D4 via the input/output signal processing unit IO to perform the grain discharge operation. Control.

The above-described running state sensor S1 and threshing state sensor S2 also send signals and data to the control device 100 via the input/output signal processing unit IO.

The threshing loss management unit 7 receives the photographed image of the loss area sent from the photographing section 80 and outputs the loss rate, which is the amount of loss per unit yield. In this embodiment, the imaging section 80 has a first camera 81 and a second camera 82 . A lighting unit 84 is associated with each camera. The first camera 81 photographs the end region of the handling cylinder 22 (the end region including the rear of the handling cylinder 22), which is a loss area suitable for the handling cylinder loss. The second camera 82 photographs the rear end region of the sheave case 33 (the rear end region of the sheave case including the upper side of the second chaff sheave 39), which is a loss area suitable for sorting loss. Furthermore, it is also possible to prepare a plurality of first cameras 81, photograph the loss area suitable for the barrel loss at a plurality of photographing angles, and transmit photographed images of a plurality of different photographing fields. . Similarly, it is also possible to prepare a plurality of second cameras 82, photograph a loss area suitable for sorting loss at a plurality of photographing angles, and transmit photographed images of a plurality of different photographing fields. . The number of cameras is not limited.

The threshing loss management unit 7 includes a preprocessing section 71 , a loss amount neural network 72 as a loss amount calculation unit, and a loss rate calculation section 73 . The preprocessing unit 71 performs preprocessing such as trimming, color adjustment, and resolution change on the captured image from the imaging unit 80 . Furthermore, the threshing apparatus 1 is closed from the outside, and even if the inside of the threshing apparatus is illuminated, dust other than the grains is flying around, making it difficult to maintain constant photographing conditions. Therefore, the preprocessing unit 71 normalizes the captured image. The preprocessing unit 71 further converts the preprocessed captured image into data suitable for input to the neural network, and supplies the data to the loss amount neural network 72 as image input data.

As shown in FIG. 6, the loss amount neural network 72 is a convolutional neural network, preferably configured by deep learning, and includes multiple convolutional layers, multiple pooling layers, and one or more fully connected layers. An input layer is provided on the input side, and an output layer is provided on the output side. The convolutional and pooling layers are configured to repeat multiple times.

In the example of FIG. 6, a color photographed image (first photographed image) of the first camera 81 and a color photographed image (second photographed image) of the second camera 82 are used as the photographed images to simplify the explanation. It is assumed that The preprocessing unit 71 generates first image input data from the first captured image, and generates second image input data from the second captured image. A loss amount neural network 72 receives the first image input data and the second image data, and outputs a loss amount.

The construction of the loss amount neural network 72 is realized by supervised learning using a large number of learning samples (learning photographed images and their loss amounts) as learning data. A learning sample is composed of an actual photographed image and an estimated loss amount actually estimated by an expert from the photographed image. In a neural network such as deep learning, the more samples for learning, the higher the reliability of the output. For this reason, in order to increase the number of learning samples, it is necessary not only to use captured images for learning that are actually captured images as learning samples, but also to use images obtained by performing image processing such as rotation and translation on these learning samples. are used as additional training samples with the same estimated loss amount. It should be noted that what is actually input to the loss amount neural network 72 as learning data is learning image input data generated by the preprocessing unit 71 based on learning captured images.

Instead of inputting image input data and directly outputting the amount of loss, label images in which the threshed processed material in the photographed image is classified into grains and non-grains are output, and the amount of loss is calculated from this label image. form may be adopted. In such a form, the fully connected layers are divided, the former fully connected layer outputs the label image, and the latter fully connected layer outputs the loss amount from the label image. At that time, as the learning data, the actual photographed image and the loss amount calculated from the label image created based on the classification of the grain and the non-grain from the photographed image by the expert are used. good. FIG. 7 shows a partially enlarged schematic diagram of a photographed image of a threshed product in shades of gray. FIG. 8 is a label image corresponding to the partially enlarged portion of the photographed image shown in FIG. In the label image shown in FIG. 8, the grain is indicated by "1", the abnormal grain by "2", and the background by "0".
Grains indicate the unique shape and color of grains, and non-grains include not only branch stems and straw scraps, but also defective grains with irregular shapes and colors. ing. 7 and 8 are schematic diagrams for facilitating understanding, and are not based on actual conditions.

Further, instead of the loss amount output from the loss amount neural network 72, as the threshing processing state, normal distribution or Gaussian distribution parameters indicating the distribution of grains or non-grains in the threshed product are calculated, and from this distribution A configuration for calculating the loss amount may be employed. Alternatively, when the loss amount neural network 72 is configured as a semantic segmentation network, a label image is generated that indicates the degree of estimation of grains, non-grains, and background for each pixel, so the loss amount is calculated from the label image. to output.

Since most of the threshed material to be recognized in the photographed image is grain, the preprocessing unit 71 divides the photographed image into a plurality of areas (patch areas) in order to perform more precise recognition. , image input data may be generated for each region. Alternatively, the input layer of the loss amount neural network 72 may divide the image input data into a plurality of patches.

The loss rate calculator 73 is provided not only with the loss amount from the loss amount neural network 72 but also with the yield from the yield measuring device M1. Thereby, the loss rate calculation unit 73 calculates the loss rate, which is the amount of loss per unit yield. This loss rate includes the loss rate calculated from the yield per unit time, the loss rate calculated from the yield per unit run, and the loss rate calculated from the yield in the entire field. Furthermore, since the loss rate calculation unit 73 is also given the travel locus information from the travel control unit RU, it is possible to calculate the loss rate obtained from the yield in the predetermined area of the field. Such a loss rate can be linked to the travel trajectory calculated in the cruise control unit RU. As a result, the yield, taste value, and loss amount are recorded for each minute section of the field.

Since the loss rate is an important factor indicating the threshing performance, the parameter determining unit 74 determines the threshing performance of the threshing device 1 during the work travel based on the loss rate calculated during the work travel. Control parameters are determined and provided to the threshing control unit TU. The threshing control unit TU, for example, adjusts the opening degree of the chaff 38A, the wind power of the winnow 25, the vehicle speed, and the dust feed valve 53a so as to bring the received loss rate closer to the appropriate loss rate during work travel. , and so on. For this reason, the loss rate is calculated continuously or at predetermined repetition timings during the operation of the combine. In addition, the amount of loss and the loss rate obtained during work travel in one field are recorded together with travel information and work information of the combine harvester.

In the configuration of the loss amount neural network 72 shown in FIG. 6, the first input image data and the second input image data generated based on the first captured image and the second captured image are combined into one common loss amount neural network. It was input to the input layer of network 72 . Instead of this, as shown in FIG. 9, a first loss amount neural network 72A and a first loss amount neural network 72A and a second A two-loss neural network 72 B may be provided as the loss neural network 72 . In this configuration, first input image data based on the first captured image is input to the first loss amount neural network 72A, and second input image data based on the second captured image is input to the second loss amount neural network 72B. . As a result, the first loss amount neural network 72A calculates the handling cylinder loss amount, and the second loss amount neural network 72B calculates the sorting loss amount. The loss rate calculator 73 calculates a comprehensive loss rate based on the amount of loss of the handling cylinders and the amount of sorting loss. Also here, the first captured image and the second captured image may include captured images at different capturing angles and captured images at different capturing fields of view.

Furthermore, in the configuration shown in FIG. 10, a third camera 83 is prepared in addition to the first camera 81 and the second camera 82 shown in FIG. This third camera 83 is arranged at the discharge area where non-grain such as straw is discharged from the thresher 1 , for example at the entrance of the straw shredding device 13 . Alternatively, the third camera 83 may be arranged at a position for photographing the cut behind the vehicle body. Furthermore, the configuration shown in FIG. 10 includes a third loss amount neural network 72C.
This third loss amount neural network 72C is generated based on the image captured by the third camera 83 that captures the discharge area where non-grains such as straw are discharged from the threshing apparatus 1 or the cut behind the vehicle body. The third input image data is input to calculate a release loss amount that represents the amount of grains mixed in the discharged straw that is released from the vehicle body to the field. The loss rate calculator 73 calculates a loss rate from the amount of loss in the handling cylinder, the amount of sorting loss, the amount of release loss, and the yield. Of course, here as well, the loss rate calculator 73 can additionally obtain the release loss rate from the release loss amount and the yield. Here, too, the first captured image, the second captured image, and the third captured image may include captured images at different capturing angles or different capturing fields of view. Furthermore, a fourth camera, a fifth camera, and so on may be prepared, and the threshing loss management unit 7 may be provided with a corresponding number of loss amount neural network groups.

In the configurations shown in FIGS. 9 and 10, the loss rate calculator 73 calculates many kinds of loss rates. In order to determine the threshing control parameters of the threshing apparatus 1 based on such various types of loss rates, the parameter determining section 74 may be neural networkized. The neural network loss rate calculation unit 73 outputs threshing control parameters using loss rates in various areas as input data.

[Other embodiments]
In the above embodiment, the loss rate calculated by the loss rate calculator 73 is used to adjust the control parameters of the various control devices that make up the combine. Alternatively, the loss rate calculated by the loss rate calculator 73 during work is displayed on a meter panel or a display, and the driver can appropriately set the control parameters of various control devices while looking at the displayed loss rate. You may employ|adopt the structure which adjusts. In this case, it is more convenient if the loss rate is displayed together with an index indicating the running state such as engine speed and vehicle speed and an index indicating the working state such as mowing height.

In the above-described embodiment, the control parameters to be determined based on the loss rate are the adjustment amounts of various devices of the threshing device 1 (opening degree of chaflip 38A, air volume of winnow 25, angle of dust valve 53a, second thing reduction amount,) and travel control amount (vehicle speed) were taken up. In addition to these, the parameter determining unit 74 can also determine at least one control parameter of the crawler traveling device 3, the reaping unit 4, and various conveying devices.

In the above-described embodiment, the detection unit that detects the loss is the imaging unit 80 configured by a camera, and the captured image is used for calculating the amount of loss. The detection unit is not limited to the photographing unit 80, and various sensors provided in the constituent members of the combine such as the reaping unit 4, the feeder 11, the threshing device 1, and the first harvest conveying unit 29 detect function as a unit, and detection signals thereof as detection results of the detection unit may be used for calculating the amount of loss. Furthermore, the detection unit may be a combination of the photographing unit 80 and various sensors.

In the above embodiment, the loss amount calculation unit calculates the handling cylinder loss amount and the sorting loss amount. However, a loss also occurs, for example, when the culms are conveyed within the reaping unit 4 or when the culms are conveyed by the feeder 11 . Therefore, the loss amount calculation unit may calculate the loss amount in various conveying devices such as the reaping unit 4 or the feeder 11 and the first harvest conveying unit 29 . In that case, the threshing loss management unit 7 is configured as a harvester loss management unit, and the loss rate calculator 73 is also configured to calculate a loss rate corresponding to each loss amount. For example, the harvested grain culms and unhulled grains that are fed from the harvesting unit 4 to the threshing device 1 by the feeder 11 are regarded as the initial loss during the harvesting and conveying process, and the amount of this initial loss and its loss rate are calculated. It is also possible to employ a configuration for calculation.

In the above embodiment, the loss amount calculation unit is composed of a neural network, but instead of the neural network, an image that identifies grains and non-grains in a photographed image and calculates the loss amount from the identification information. A recognition unit may be used.

In the above-described embodiments, deep learning is used as the neural network with input image data based on a single photographed image or a plurality of simultaneously photographed images. Instead of this, a neural network that receives time-series input image data based on time-series captured images may be used.

Although the preprocessing unit 71 and the loss amount neural network 72 are configured separately in the above embodiment, the preprocessing unit 71 may be incorporated into the loss amount neural network 72 . Furthermore, the preprocessing unit 71, the loss amount neural network 72, and the loss rate calculation unit 73 may be configured integrally.

In the above embodiment, the threshing state management system has been described with the case where the threshing device 1 is mounted on a combine as an example. Alternatively, the threshing management system of the present invention can be mounted on a working vehicle whose threshing apparatus 1 is different from a combine harvester, or the threshing management system of the present invention can be incorporated into a stationary threshing apparatus 1 .

In the above embodiments, a combine harvester is used as a harvester, but the present invention is also applicable to other harvesters, such as harvesters for harvesting other agricultural products such as corn, potatoes, and carrots.

INDUSTRIAL APPLICABILITY The present invention can be applied to a harvester management system for a harvester that harvests agricultural products, a harvester equipped with such a harvester management system, and a harvester management method for such a harvester.

1: Threshing device 4: Reaping part (harvesting part)
12: grain tank (reservoir)
21 : Handling chamber 22 : Handling barrel 24 : Sieve case 40 : Glen sieve 41 : Handling barrel 42 : Sorting unit 43 : Swing sorting mechanism 53a : Dust feed valve 7 : Threshing loss management unit 71 : Pretreatment unit 72 : Loss amount Neural network 72A: First loss amount neural network 72B: Second loss amount neural network 72C: Third loss amount neural network 73: Loss rate calculation unit 74: Parameter determination unit 80: Imaging unit (detection unit)
81: first camera 82: second camera 83: third camera 100: control device CU: reaping control unit M1: yield measuring device

Claims (15)

A harvester management system for managing harvest loss in a harvester comprising a harvesting section for harvesting crops in a field and a storage section for storing harvested materials harvested by the harvesting section,
a yield measuring unit for measuring the yield of the harvest;
a loss amount calculation unit that calculates a loss amount indicating the amount of loss that occurs while the harvested product is being transported from the harvesting unit to the storage unit;
a loss rate calculation unit that calculates a loss rate, which is the loss amount per unit harvest amount, based on the harvest amount and the loss amount;
with
The harvest amount measurement unit measures the yield, which is the amount of grain obtained from the harvested product, as the harvest amount,
The harvester management system, wherein the loss amount calculation unit calculates, as the loss amount, the amount of threshing loss in a threshing device provided in the harvester for threshing the harvested product. A detection unit that detects the loss is provided in the loss area where the loss occurs,
The harvester management system according to claim 1, wherein the loss amount calculation unit is configured to output the loss amount based on the detection result from the detection section. A photographing unit for photographing the loss area where the loss occurs is provided as the detection unit,
3. The harvester management system according to claim 2, wherein the loss amount calculation unit is configured as a neural network that outputs the loss amount based on image input data generated from the photographed image from the photographing unit. The neural network uses learning image input data generated from learning captured images captured during harvesting by the harvester and an estimated loss amount actually estimated from the learning captured images as learning data. 4. The harvester management system of claim 3, wherein , is learned. The imaging unit includes a plurality of cameras each having a different imaging field of view, and a plurality of the neural networks are provided so as to correspond to the plurality of cameras,
5. The harvester management system according to claim 3 or 4, wherein the individual image input data corresponding to the captured images from the plurality of cameras are input to each of the neural networks corresponding to the cameras that are the sources of the images. . the imaging unit includes a plurality of cameras each having a different imaging field of view, and one neural network corresponds to each of the plurality of cameras,
5. The harvester management system according to claim 3, wherein all of the image input data corresponding to the captured images from the plurality of cameras are input to the neural network. 7. The harvester management system according to any one of claims 1 to 6 , wherein the loss region in which the loss occurs includes a threshing cylinder end region and a sheave case rear end region in the threshing device. 8. The harvester management system according to any one of claims 1 to 7, wherein the loss area in which the loss occurs includes a discharging section area for discharging non-grains other than grains from the threshing device. The harvester management system according to any one of claims 1 to 8 , further comprising a parameter determination unit that determines control parameters for the harvester based on the loss rate. a harvesting unit for harvesting crops in a field;
a storage unit that stores the harvested product harvested by the harvesting unit;
a yield measuring unit for measuring the yield of the harvest;
a loss amount calculation unit that calculates a loss amount indicating the amount of loss that occurs while the harvested product is being transported from the harvesting unit to the storage unit;
a loss rate calculation unit that calculates a loss rate, which is the loss amount per unit harvest amount, based on the harvest amount and the loss amount;
and a threshing device for threshing the harvested product ,
The harvest amount measurement unit measures the yield, which is the amount of grain obtained from the harvested product, as the harvest amount,
The said loss amount calculation unit is a harvester which calculates the amount of the threshing loss in the said threshing apparatus as said loss amount . A traveling device and a conveying device for conveying the harvested product are provided,
11. The harvesting machine according to claim 10 , further comprising a parameter determination unit that determines control parameters of at least one of the traveling device, the harvesting unit, the conveying device, and the threshing device based on the loss rate. . measuring the yield of the harvested material while performing a harvesting operation with a harvester having a harvesting unit for harvesting crops in a field and a storage unit for storing the harvested material harvested by the harvesting unit;
while performing the harvesting work by the harvester, calculating a loss amount indicating the amount of loss that occurs while the harvested material is transported from the harvesting unit to the storage unit;
A harvesting machine management method for calculating a loss rate, which is the loss amount per unit harvest amount, based on the harvest amount and the loss amount while performing the harvesting operation with the harvester, comprising:
As the harvested amount, the yield, which is the amount of grain obtained from the harvested product, is measured,
A harvesting machine management method, wherein an amount of threshing loss in a threshing device provided in the harvester for threshing the harvested product is calculated as the amount of loss. 13. The harvester management method according to claim 12 , wherein the control parameter of the harvester is determined based on the loss rate while the harvester is performing the harvesting work. A harvester management system for managing harvest loss in a harvester comprising a harvesting section for harvesting crops in a field and a storage section for storing harvested materials harvested by the harvesting section,
a yield measuring unit for measuring the yield of the harvest;
a loss amount calculation unit that calculates a loss amount indicating the amount of loss that occurs while the harvested product is being transported from the harvesting unit to the storage unit;
a loss rate calculation unit that calculates a loss rate, which is the loss amount per unit harvest amount, based on the harvest amount and the loss amount;
with
A detection unit that detects the loss is provided in the loss area where the loss occurs,
The loss amount calculation unit is configured to output the loss amount based on the detection result from the detection unit,
A photographing unit for photographing the loss area where the loss occurs is provided as the detection unit,
The loss amount calculation unit is configured as a neural network that outputs the loss amount based on image input data generated from the captured image from the imaging unit,
The neural network includes learning image input data generated from learning photographed images taken during actual harvesting work by the harvester, and an estimated loss amount actually artificially estimated from the learning photographed images. is learned as the correct answer data for the learning data of the harvester management system. A harvester management system for managing harvest loss in a harvester comprising a harvesting section for harvesting crops in a field and a storage section for storing harvested materials harvested by the harvesting section,
a yield measuring unit for measuring the yield of the harvest;
a loss amount calculation unit that calculates a loss amount indicating the amount of loss that occurs while the harvested product is being transported from the harvesting unit to the storage unit;
a loss rate calculation unit that calculates a loss rate, which is the loss amount per unit harvest amount, based on the harvest amount and the loss amount;
with
A detection unit that detects the loss is provided in the loss area where the loss occurs,
The loss amount calculation unit is configured to output the loss amount based on the detection result from the detection unit,
A photographing unit for photographing the loss area where the loss occurs is provided as the detection unit,
The loss amount calculation unit is configured as a neural network that outputs the loss amount based on image input data generated from the captured image from the imaging unit,
The imaging unit includes a plurality of cameras each having a different imaging field of view, and a plurality of the neural networks are provided so as to correspond to the plurality of cameras,
the individual image input data corresponding to the captured images from the plurality of cameras are input to each of the neural networks corresponding to the cameras from which the images were captured;
The harvester management system, wherein the loss rate calculation unit calculates the loss rate based on the loss amount and the harvest amount output from each of the neural networks.

Images