Residue collector

Patent metadata

Field	Value
Publication number	US-12588591-B2
Application number	US-202318093378-A
Country	US
Kind code	B2
Filing date	Jan 5, 2023
Priority date	Jan 14, 2022
Publication date	Mar 31, 2026
Grant date	Mar 31, 2026

Abstract

A residue collector is operable to receive residue from a combine harvester during a training harvesting operation. The residue collector includes a residue separator for separating the processed residue into a first portion and a second portion based on a property of the processed residue; one or more weight sensors for directly or indirectly determining the weight of the first portion and the second portion; and a controller configured to determine a quality factor for the processed residue based on the determined weight of the first portion in relation to the weight of the second portion.

First claim

What is claimed is:

1 . A residue collector that is separate from a combine harvester and operable to receive processed residue expelled from the combine harvester during a training harvesting operation, wherein the residue collector comprises:
a transfer system for transferring the processed residue expelled from the combine harvester to a residue separator of the residue collector, the residue separator being configured for receiving the processed residue received from the transfer system and separating the processed residue into a first portion and a second portion based on a property of the processed residue; one or more weight sensors for directly or indirectly determining a weight of the first portion and the second portion; and a controller configured to determine a quality factor for the processed residue based on the determined weight of the first portion in relation to the weight of the second portion.

2 . The residue collector of claim 1 , wherein the controller is configured to determine the quality factor during the training harvesting operation.

3 . The residue collector of claim 2 , wherein the controller is further configured to provide an indicator of the determined quality factor to an operator of the combine harvester during the training harvesting operation.

4 . The residue collector of claim 1 wherein:
the residue separator is configured for separating the processed residue into three or more portions based on one or more properties of the processed residue;
the one or more weight sensors are for directly or indirectly determining the weight of each portion; and
the controller is configured to determine the quality factor for the processed residue based on relative weights of the three or more portions.

5 . The residue collector of claim 1 , wherein the property of the residue that is used to separate the residue into the first portion and the second portion comprises one or more of:
a size of elements within the residue; a shape of elements within the residue; a density of elements within the residue; a moisture content of the residue; and a colour of the residue.

6 . The residue collector of claim 1 , wherein the residue collector comprises a trailer, which is configured to be pulled by the combine harvester when in use.

7 . The residue collector of claim 1 , wherein the residue collector has a residue collection configuration and a residue bypass configuration, wherein:
in the residue collection configuration, the residue collector is configured to transfer the residue to components of the residue collector for determining the quality factor for the residue; and in the residue bypass configuration, the residue collector is configured such that the residue bypasses or avoids the components of the residue collector for determining the quality factor for the residue.

8 . The residue collector of claim 1 , further comprising a residue selection component for selectively transferring only part of the received residue to the residue separator.

9 . The residue collector of claim 1 , wherein the controller is further configured to:
receive one or more sensor values from sensors that are associated with the combine harvester; and store the one or more sensor values and the quality factor as training data for a machine learning algorithm.

10 . The residue collector of claim 9 , wherein the controller is further configured to:
train a machine learning algorithm based on the training data, wherein the trained machine learning algorithm is for subsequent use during a harvesting operation.

11 . The residue collector of claim 5 , wherein the property of the residue that is used to separate the residue into the first portion and the second portion comprises the size of the elements within the residue.

12 . The residue collector of claim 5 , wherein the property of the residue that is used to separate the residue into the first portion and the second portion comprises the shape of the elements within the residue.

13 . The residue collector of claim 5 , wherein the property of the residue that is used to separate the residue into the first portion and the second portion comprises the density of the elements within the residue.

14 . The residue collector of claim 5 , wherein the property of the residue that is used to separate the residue into the first portion and the second portion comprises the moisture content of the residue.

15 . The residue collector of claim 5 , wherein the property of the residue that is used to separate the residue into the first portion and the second portion comprises the colour of the residue.

16 . A method of training a machine learning algorithm and operating a combine harvester using the trained machine algorithm, the method comprising the steps of:
training the machine learning algorithm by operating a residue collector, which is separate from the combine harvester, during a training harvesting operation, the step of operating the residue collector comprising (i) activating a transfer system of the residue collector to transfer processed residue expelled from the combine harvester to a residue separator of the residue collector, (ii) activating the residue separator to separate the processed residue into a first portion and a second portion based on a property of the processed residue, (iii) directly or indirectly determining a weight of the first portion and the second portion using one or more weight sensors, and (iv) determining a training quality factor for the processed residue based on the determined weight of the first portion in relation to the weight of the second portion; starting a harvesting operation following the training harvesting operation; receiving one or more sensor values from sensors that are associated with the combine harvester during the harvesting operation; using the trained machine learning algorithm to determine a calculated quality factor during the harvesting operation, the machine learning algorithm determining the calculated quality factor based on the training quality factor determined during the training step; and either presenting the calculated quality factor to an operator of the combine harvester during the harvesting operation or setting one or more operational parameters of the combine harvester during the harvesting operation based on the calculated quality factor.

17 . The method of claim 16 further comprising setting one or more operational parameters of the combine harvester during the harvesting operation based on the calculated quality factor and also based on a target quality factor.

18 . The method of claim 16 further comprising presenting the calculated quality factor to the operator of the combine harvester during the harvesting operation.

19 . The method of claim 16 , wherein the property of the residue that is used to separate the residue into the first portion and the second portion comprises one or more of:
a size of elements within the residue; a shape of elements within the residue; a density of elements within the residue; a moisture content of the residue; and a colour of the residue.

Assignees

• Cnh Ind America Llc

Inventors

• Deruyter Lucas
• Tallir Frederik
• Bonne Geert
• Leenknegt Arno
• Missotten Bart M A
• Jongmans Dré W J
• Vanlerberghe Jasper
• Van Overschelde Pieter
• Reubens Sam

Classifications

• G06Q50/02

  Agriculture; Fishing; Forestry; Mining · CPC title

• A01D43/07

  in or into a trailer (A01D43/077 takes precedence) · CPC title

• G06V10/774

  Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting · CPC title

• G06V10/82

  using neural networks · CPC title

• G06V10/764

  using classification, e.g. of video objects · CPC title