Near-infrared sensing was used to measure the characteristics of seed cotton.

Abstract

A system and method are provided for determining the characteristics of seed cotton based on measurements from near-infrared (NIR) sensors. The determined characteristics indicate the quality of the seed cotton. NIR sensors are mounted on harvesting equipment to acquire quality data during harvest. The quality data can be mapped to field locations and / or forwarded for further processing.

Description

[0001] Cross-references to related applications

[0002] This application claims the benefit and priority of U.S. Provisional Application No. 63 / 203,549, filed July 27, 2021. The entire contents of the aforementioned application are incorporated herein by reference. Background Technology

[0003] In many agricultural operations, farm operators expect to know information about their harvested crops (e.g., cotton). Many of these characteristics can affect the value of the cotton. Typically, seed cotton is harvested, bundled together, and then sent to a mill for further processing. At the regional grading office, several characteristics associated with the cotton being processed are measured by taking samples from each lint bale. Summary of the Invention

[0004] This summary is provided to illustrate the selection of concepts in a simplified form, which will be further described in the detailed description below. This summary is not intended to identify key elements or essential features of the claimed subject matter, nor is it intended to limit the scope of the claimed subject matter.

[0005] Certain aspects and features of this disclosure relate to the determination of seed cotton characteristics using a near-infrared (NIR) system including a NIR sensor. The NIR sensor can measure the wavelength profile of the seed cotton, and the NIR system can generate the wavelength profile of the seed cotton. The NIR system can use the wavelength profile to determine the characteristics of the seed cotton using one or more models (e.g., machine learning models). For example, the moisture content of the seed cotton, the seed protein or oil content of the seed cotton, or the turnout constituent present in the seed cotton can be determined.

[0006] In some examples, NIR sensors can be positioned near the field or at facilities outside the field to determine characteristics after the seed cotton has been removed from the harvester that collected it. Alternatively, NIR sensors can be mounted on the harvester to determine the characteristics of the seed cotton while it is being collected in the field.

[0007] In some examples, the identified characteristics can be correlated with the location where the seed cotton is collected, allowing the generation of a map indicating the characteristics of the seed cotton at different locations in the field. The characteristics of the seed cotton can be used, additionally or alternatively, to adjust variable parameters of the harvester, for example, to improve the harvester's performance.

[0008] To achieve the foregoing and related objectives, the following description and accompanying drawings illustrate certain illustrative aspects and embodiments. These indicate some of a variety of ways in which one or more aspects may be employed. Other aspects, advantages, and novel features of this disclosure will become apparent from the following detailed description when considered in conjunction with the accompanying drawings. Attached Figure Description

[0009] Various non-limiting embodiments are further described in the detailed description given below with reference to the accompanying drawings, which are incorporated in and form a part of this specification.

[0010] Figure 1 The diagram illustrates a component diagram of an exemplary harvester (e.g., a peeler) according to various aspects.

[0011] Figure 2 The illustration shows a partial cross-sectional view of a harvester (e.g., a picker) from one or more aspects.

[0012] Figure 3 The illustration shows a harvester including a near-infrared (NIR) system, based on various aspects.

[0013] Figure 4 The diagram illustrates how, based on certain aspects, it can be related to... Figure 1 An example of a delivery pipe that includes a (NIR) sensor and is used in conjunction with a harvester.

[0014] Figure 5 The diagram illustrates the various aspects that can be combined with Figure 1 An example of a cleaner used in conjunction with a harvester.

[0015] Figure 6 This is a flowchart illustrating the process of analyzing cotton based on several aspects.

[0016] Figure 7 The diagram is based on some aspects Figure 3 A simplified diagram illustrating the control aspects of an NIR system.

[0017] Figure 8 This is a schematic diagram of an exemplary, non-limiting implementation of a cotton analysis system based on one or more aspects.

[0018] Figure 9 This is a schematic diagram of an exemplary, non-limiting embodiment of a computing device for a cotton analysis system, based on various aspects.

[0019] Figure 10 This is a simplified schematic diagram of an exemplary implementation of cotton analysis based on one or more aspects.

[0020] Figure 11This is a flowchart of an exemplary, non-limiting process for analyzing cotton.

[0021] Figure 12 This is a flowchart of an exemplary, non-limiting process for controlling agricultural machinery based on cotton characteristics. Detailed Implementation

[0022] Certain aspects and features of this disclosure relate to a seed cotton measurement system that may include a near-infrared (NIR) sensor. The NIR sensor can emit light of wavelengths within a specified range toward a sample of seed cotton. The NIR sensor can detect which wavelengths of light are propagating through the sample and / or being reflected back from the sample, and send this data to a processor. The processor can generate wavelength properties of the seed cotton sample based on this data. One or more characteristics of the seed cotton sample can be determined using these wavelength properties.

[0023] In some examples, the processor can use a model such as a machine learning model to determine the characteristics of seed cotton based on wavelength attributes. For example, a neural network can receive at least a portion of the wavelength attributes as input and provide the characteristics of seed cotton as output. Examples of seed cotton characteristics may include seed cotton yield characteristics, seed characteristics, and moisture characteristics.

[0024] The turnout characteristics of seed cotton include its composition (e.g., the ratio of lint, seeds, and impurities in the material). Traditionally, turnout characteristics are measured by measuring the total weight of the seed cotton being fed into the cotton gin (i.e., the raw seed cotton including impurities) and the weight of the lint leaving the gin. However, conventional methods for measuring turnout characteristics only measure the lint and other components, which include the seeds and impurities of the seed cotton. Using a NIR system, turnout characteristics can be determined at a larger granular level to provide specific percentages of seeds, impurities, and lint. Furthermore, it is not necessary to wait for seed cotton processing to determine its turnout characteristics; at least a portion of the NIR system can be installed in the harvester, and turnout characteristics can be determined while cotton is being harvested from the field. For example, by using an NIR system to determine turnout characteristics while the seed cotton is being harvested, an estimate of the lint yield can be known before ginning, thereby generating a lint yield map based on the location of the field where the seed cotton was harvested.

[0025] NIR systems can additionally or alternatively determine seed characteristics of seed cotton. Seed characteristics indicate the protein components and other components of the seed. For example, an NIR system can determine wavelength attributes for the seed. At least a portion of the wavelength attributes can then be fed into a model as mentioned above to predict seed characteristics of the seed cotton. Similar to yield characteristics, seed characteristics of seed cotton can be stored in a database and used to generate a mapping that associates seed characteristics of the seed cotton with the location where the seed cotton was harvested.

[0026] NIR systems can additionally or alternatively determine the moisture content of seed cotton. Traditionally, the moisture content of seed cotton is measured some time after a large quantity of seed cotton has been bundled together in the harvester, using other sensing technologies. For example, the moisture content of an area can be measured together within a bale, but it is usually impossible to determine the moisture content of individual plants or rows. Some examples of this disclosure make it possible to determine the moisture content of seed cotton while it is being harvested. For example, the moisture content of individual rows of seed cotton can be determined. The moisture content of the seed cotton can then be correlated with the location where the seed cotton was harvested to create a moisture map. Furthermore, the moisture data can be stored in a database for later use.

[0027] In other examples, the NIR system can be used to determine a variety of other properties of seed cotton. For instance, for seed cotton, color grade, reflectance, yellowness, micronaire value, fiber length and staples, length uniformity, fiber strength, leaf grade, foreign matter, and impurities can be determined.

[0028] Any or all data associated with seed cotton (e.g., characteristics and location) can be stored in a database on the harvester or elsewhere, such as in the cloud. This data can be accessed and used through one or more systems. For example, the data can be used to establish settings for cotton gins, thereby improving their efficiency. The data can also be used, additionally or alternatively, to determine the classification of seed cotton for separation in the field or at the gin. Furthermore, the data can be used to classify the contents of lint in warehouses.

[0029] Some or all of the examples described in this article can be used in conjunction with agricultural equipment to measure the characteristics of seed cotton (e.g., virgin cotton) while it is being harvested. In conventional methods, certain characteristics of cotton are measured after it has been transported out of the field and undergone further processing. The examples described in this article differ from conventional methods, at least because these conventional methods cannot correlate these characteristics with the location where the seed cotton was harvested. Furthermore, some examples enable the measurement of seed cotton characteristics that are currently unmeasurable by conventional methods, and can provide higher accuracy than conventional methods.

[0030] These illustrative examples are given to introduce the general subject matter discussed herein and are not intended to limit the scope of the disclosed concepts. Various additional features and examples are described below with reference to the accompanying drawings, wherein the same reference numerals denote the same elements, but as with the illustrative examples, they should not be used to limit this disclosure.

[0031] Now for reference Figure 1 and Figure 2 The illustration depicts an exemplary harvester vehicle 100. In this example, the harvester 100 is a cotton harvester (e.g., a cotton picker, a cotton stripper), but other types of harvesters, such as combine harvesters, are also contemplated in this disclosure.

[0032] The harvester 100 includes a chassis 109 supported by front wheels 102 and rear wheels 104, but other support components, such as tracks, are also envisioned. The harvester 100 is adapted to move through fields to harvest crops (e.g., cotton, corn, straw, hay, wheat, alfalfa, etc.).

[0033] Operator station 107 is supported by chassis 109. Operator interface 105 is located in operator station 107. Power module 108, such as generator 106, can be supported under chassis 109. Water tank, lubricant tank, and fuel tank (not shown) can be supported in and on chassis 109.

[0034] The crop harvesting device 114 can be connected to the chassis 109. The crop harvesting device 114 can be configured to remove cotton from the field. The harvesting device 114 may include a cotton stripper header 112. Figure 1 ), one or more cotton picking units 116 ( Figure 2Alternatively, the harvesting device 114 may be configured to remove corn or other crops. The harvesting device 114 may have different configurations (e.g., size, specifications, etc.) depending on the type of crop being harvested and the method of removing the crop from the field. In some embodiments, the harvester vehicle 100 is a cotton stripper equipped with the crop harvesting device 114, which is adapted to remove or strip cotton from the plant.

[0035] In some embodiments, the harvester vehicle 100 includes a header system 110. The header system 110 may include a crop header component, a hydraulic or electric motor (not shown), and one or more sensors, which are capable of operatively harvesting crops from a target field. In some embodiments, the crop header component may include a header 112 (e.g., a cotton stripper) and a header system load monitor. For embodiments of the header system 110 that includes a hydraulic motor, a hydraulic pump on the harvester vehicle 100 may drive the hydraulic motor on the header 112. In these embodiments, the hydraulic motor may supply power to rotate the shafts of the individual harvesting units and the cross auger that feeds cotton to the harvester vehicle 100. In other embodiments, an electric motor may supply power to rotate the shafts of the individual harvesting units and the cross auger that feeds cotton to the harvester vehicle 100.

[0036] The one or more sensors may be configured to monitor or detect conditions indicating the power output of the hydraulic pump, hydraulic motor, or electric motor driving the header system 110. In some embodiments, the sensors are configured to monitor one or more of the following: hydraulic pressure at the hydraulic pump of the header system 110, current through the control solenoid of the hydraulic pump in the header system 110, and rotational speed of the shaft driving the harvesting unit in the header system 110. That is, for example, the sensors may detect conditions indicating pressure, current, and / or speed to monitor crop header components. In embodiments including an electric motor, the sensors may detect one or more power-related conditions, such as current and / or voltage. For embodiments including a hydraulic motor or an electric motor, the sensors may detect mechanical strain of the motor driving the crop header system 110.

[0037] In some embodiments, the harvester vehicle 100 includes an air system 120. The air system 120 may include: a crop conveyor component for conveying crops through the harvester vehicle 100, one or more sensors 160, 162, and crop conveyor devices (e.g., one or more air ducts and airflow generators). In some embodiments, the crop conveyor component may include one or more air ducts 122 and an air system load monitor, such as an airflow load monitor.

[0038] In some embodiments, the air system 120 may be operatively connected to and in communication with the header system 110. In these embodiments, the air duct 122 is connected to and aligned with the header 112 such that cotton stripped from the header 112 can be conveyed through the air duct 122 of the air system 120, powered by an airflow (e.g., an air generator), to the harvester vehicle 100 (e.g., a cleaner).

[0039] The one or more sensors 160, 162 may be configured to monitor airflow and / or crop material flow in the air duct 122 of the air system 120. In some embodiments, one or more sensors may be positioned within the air duct 122. As an example, a harvester 100, such as a cotton stripper, may include multiple material flow sensors 160 mounted across the width of the air duct 122, such as four cotton material flow sensors. In other embodiments, one or more sensors are positioned adjacent to the air duct 122. As an example, a harvester 200, such as a cotton picker, may include multiple material flow sensors 162 mounted behind the air duct 122, with one cotton material flow sensor mounted in each row of units. Various types of sensors can be used to monitor airflow and / or crop material flow, including, but not limited to, HDOC yield monitors, vacuum sensors, air velocity sensors, etc. As an example, an HDOC yield monitor is a microwave-based controller that bounces signals from flowing crop material to detect changes in speed, where a slowing crop material flow indicates that the air duct 122 is overloaded.

[0040] In some embodiments, the harvester vehicle 100 includes a cleaner system 130. The cleaner system 130 may include a crop cleaner component for operably cleaning the harvested crop, a hydraulic or electric motor (not shown), and one or more sensors. In some embodiments, the crop cleaner component may include a cleaner 132 and a cleaner system load monitor. The cleaner 132 may be configured to clean cotton from the cotton stripper header 112 by removing impurities and debris. For embodiments of the cleaner system 130 that include a hydraulic motor, a hydraulic pump on the harvester vehicle 100 may drive the hydraulic motor on the cleaner 132.

[0041] In some embodiments, the cleaner system 130 may be operatively connected to and in communication with the air system 120, and connected via the air system 120 to the header system 110. In these embodiments, the cleaner 132 is connected to and aligned with the air duct 122 such that cotton stripped from the header 112 can be conveyed through the air duct 122 of the air system 120, which is powered by an airflow, into the cleaner 132.

[0042] The one or more sensors may be configured to monitor or detect conditions indicating the power output of the hydraulic pump, hydraulic motor, or electric motor driving the cleaner system 130. In some embodiments, the sensors are configured to monitor one or more of the following: hydraulic pressure at the hydraulic pump of the cleaner system 130, current through the control solenoid of the hydraulic pump in the cleaner system 130, and rotational speed of the shaft of the cleaner 132 in the cleaner system 130. That is, for example, the sensors may detect conditions indicating pressure, current, and / or speed to monitor the crop cleaner components. In embodiments including an electric motor, the sensors may detect one or more power-related conditions, such as current and / or voltage. For embodiments including a hydraulic motor or an electric motor, the sensors may detect mechanical strain of the motor driving the crop cleaner system 130.

[0043] In some embodiments, the crop container 152 may be connected to the air duct system 120. In some embodiments, the crop container 152 is a module builder 150 having at least one baler strap 154. As an example, the module builder may be used to build modules of crops, such as bales of cotton or hay / straw. In other embodiments, the crops may be sprayed into an internal hopper by the air duct system 120 and / or sprayed from the harvester into an accompanying holding box.

[0044] Harvester vehicle 100 includes a accumulator system 140. The accumulator system 140 may include a crop accumulator component for temporarily storing harvested crops in an operable manner, and one or more sensors 124. In some embodiments, the crop accumulator component may include an accumulator 142 and an accumulator capacity monitor. The accumulator 142 is configured to receive harvested crops from the cotton stripper header 112 (… Figure 1 ) or cotton picking unit 116 ( Figure 2 The cotton or other crops harvested.

[0045] In some embodiments, the accumulator system 140 is operatively connected to and in communication with the cleaner system 130. In these embodiments, harvested crops can be transported from the cleaner 132 (e.g., powered by an airflow from an air generator) to the top of the accumulator 142 so that the accumulator 142 is filled from the bottom up.

[0046] refer to Figure 2 Sensor 124 or a feedback device may be connected to the accumulator 142 to monitor the accumulator fill level and provide an accumulator fill level signal indicating the fill level in the accumulator 142. In some embodiments, the accumulator 142 has a low-fill sensor 124a and a high-fill sensor 124b. When the high-fill sensor 124b indicates, a signal is provided to the accumulator 142 to empty its crop contents. That is, for example, when the high-fill sensor 124b detects that the accumulator fill level exceeds (e.g., rises above) a preset sensor threshold fill level, an accumulator emptying signal is propagated. In some embodiments, the high-fill sensor 124b may be configured to be triggered, for example, by its position in the accumulator 142, before the accumulator 142 is fully filled (e.g., with a built-in buffer having additional crop storage space). A triggering signal from the low-load sensor 124a (e.g., an IR sensor) indicates that the accumulator 142 has released sufficient crop load and that emptying its crop contents should cease. That is, for example, emptying of the accumulator 142 can be stopped when the low-load sensor 124a detects that the accumulator fill level has exceeded (e.g., decreased to below) a preset sensor threshold level. The low-load sensor 124a can be configured, for example, by its position within the accumulator 142, to slow the emptying of crops from the accumulator 142 to below a desired low load level.

[0047] In some embodiments, the accumulator system 140 may include additional sensors to determine the accumulator fill rate and / or fill capacity. In some embodiments, multiple sensors may be mounted at the inlet of the accumulator 142 to monitor the material flow rate (e.g., the flow of crop through the inlet or other part of the conveyor system) and the accumulator fill rate. These sensors may be configured to measure the material flow rate and to measure the time (e.g., the accumulator fill rate) for filling the accumulator 142 between the low-level sensor 124a and the high-level sensor 124b to determine yield.

[0048] In some embodiments, it is advantageous to determine the material in the accumulator 142 when the fill level is between the low-level sensor 124a and the high-level sensor 124b. In these embodiments, the sensors can monitor the flow of material into and out of the accumulator 142 (e.g., based on past accumulator cycles) and combine this data with additional timing data. As an example, the bundle diameter can be used to determine the bundle growth rate, and the bundle growth rate can be used to determine the amount of material based on the module diameter, thereby forming a better estimate of the material in the accumulator 142.

[0049] Continue to refer to Figure 2 The feeder 135 can be connected to the chassis 109. The feeder 135 can be configured to receive cotton or other crops from the accumulator 142. The feeder 135 may include a plurality of metering rollers 134 configured to compress the cotton or other crops and transfer them to the module builder 150 at a feeding rate. A first motor 125 is positioned to rotate the plurality of metering rollers 134. The first motor 125 may be hydraulic or electric.

[0050] Multiple agitator rollers 158 can be configured to cooperate with the multiple metering rollers 134 to transfer crops such as cotton to the module builder 150 at a feed rate. A second motor 159 can be positioned to rotate the multiple agitator rollers 158. The second motor 159 can be hydraulic or electric.

[0051] The feeder belt 156 can be configured to receive crops from the plurality of metering rollers 134 and the plurality of agitating rollers 158, and transfer the crops to the module builder 150 at a feeding rate. A third motor 157 is positioned to rotate the feeder belt 156. The third motor 157 can be hydraulic or electric.

[0052] Figure 3 The illustration shows a cotton harvester, for example... Figure 1 and Figure 2The harvester 100 can be used with the NIR system 111 to determine the characteristics of seed cotton 103. The cotton harvester 100 can be a cotton stripper or a cotton picker, or include both. The NIR system 111 may include an NIR sensor 113 for measuring the wavelength of the seed cotton 103, a processor 115 for determining the characteristics of the seed cotton, and a communication interface 117 for facilitating communication between the NIR sensor and the processor. Some or all of the NIR system 111 may be mounted on the harvester 100. For example, the NIR sensor 113 may be mounted on the harvester 100 at a location for measuring the wavelength characteristics of the seed cotton 103 being harvested. The NIR sensor 113 can measure the wavelength characteristics and transmit them to the processor 115 for determining certain other characteristics of the seed cotton 103. For example, processor 115 can determine the yield characteristics, seed characteristics, and moisture characteristics of seed cotton 103, at least in part, based on the wavelength characteristics of the seed cotton measured using NIR sensor 113, while the seed cotton is being harvested. Processor 115 can be mounted on cotton harvester 100 or located elsewhere, in which case NIR system 111 can include one or more communication interfaces 117 that facilitate information transfer between NIR sensor 113 and processor 115. For example, NIR sensor 113 can communicate with processor 115 via Bluetooth, Wi-Fi, or other radio interfaces. Additionally, NIR system 111 or harvester 100 can include a Global Positioning System (GPS) 118 for mapping the characteristics of seed cotton 103 to the location where the seed cotton 103 is being harvested. For example, yield characteristics, seed characteristics, or moisture characteristics can be mapped to the location associated with seed cotton 103 to create a “field” (e.g., real-time) map showing the various characteristics of the seed cotton being harvested. GPS 118 may include one or more communication interfaces 117 for communicating with NIR system 111. Data associated with seed cotton 103 may also be used to adjust components of cotton harvester 100 or to predict the seed cotton 103. These aspects are described in more detail below.

[0053] Figure 4 The diagram illustrates a transmission conduit 200 including an NIR sensor 113, which can be connected to... Figure 1 , Figure 2 or Figure 3The cotton harvester 100 (“harvester”) is used in conjunction with the cotton harvester. A NIR sensor 113 can be mounted in the conveyor duct 200 to measure the wavelength characteristics of the seed cotton while it is still on the harvester, which can then be used by a processor to determine the moisture content of the seed cotton. Traditionally, different measurement techniques are used on the harvester to measure only the moisture content of the seed cotton, and this measurement is taken after the seed cotton has traveled through the conveyor duct, been cleaned, and bundled together. Bundling the cotton together prevents conventional moisture sensing systems from generating a moisture map indicating the moisture content of the seed cotton at its harvesting location, because seed cotton from an entire field or multiple fields can be bundled together and measured at once. The NIR sensor 113, positioned in the conveyor duct 200, can measure the wavelength characteristics of the seed cotton immediately after harvesting and before it is bundled together. The NIR sensor 113 can measure the wavelength characteristics of the seed cotton and transmit this information to a processor, which can determine other characteristics of the seed cotton based on the wavelength characteristics and correlate these other characteristics with the location where the seed cotton was harvested. The associated locations can be used to generate one or more maps illustrating seed cotton characteristics and the location where the seed cotton containing those characteristics is harvested. For example, the processor can determine the moisture content of the seed cotton and generate a moisture map based on the wavelength profile of the seed cotton generated via NIR sensor 113. This moisture map can show how the moisture characteristics of the seed cotton change with the location of the seed cotton plant.

[0054] Measuring the characteristics of seed cotton in the conveying pipe 200 or elsewhere on the harvester (e.g., in a storage container) also allows for adjustments to harvester components based on the measured characteristics. For example, the characteristics of the seed cotton can be determined before cleaning, and these characteristics can be used to adjust the cleaner mounted on the harvester. In other embodiments, the characteristics of the seed cotton can be determined after the cotton has been cleaned by the harvester. This will be described further below.

[0055] Figure 5 The diagram shows what can be done with Figure 1 , Figure 2 or Figure 3An example of a cleaner 300 used with a cotton harvester 100. The cleaner 300 may include one or more rotating drums 302, one or more brushes 304, and one or more rods 306 positioned near the drums. A NIR system 111 may be used to determine the characteristics of the seed cotton 103 before it enters the cleaner 300. In other embodiments, the NIR system 111 may be used to determine the characteristics of the seed cotton as it leaves the cleaner 300. For example, the NIR system 111 may measure the yield characteristics or composition of the seed cotton 103. Based on one or more characteristics of the seed cotton 103, the NIR system 111 may (e.g., automatically) adjust components of the cleaner 300. The NIR system 111 may adjust the components by transmitting one or more control signals to the components or by actuators that control the position of the components. Adjusting the components of the cleaner 300 can improve the efficiency of the cleaner by reducing the amount of impurities allowed to remain in the seed cotton 103 after cleaning. For example, if the yield characteristics of seed cotton 103 are measured and show a high percentage of impurities, the NIR system can transmit a control signal to cause the rod 306 to move closer to the roller 302 to knock away more impurities. Conversely, if the yield characteristics show a high percentage of lint in the trash trail, the NIR system can transmit a control signal to cause the rod 306 to retract away from the roller 302, thereby preventing lint from being knocked away in the cleaner 300. Additionally, the NIR system 111 can use previously collected characteristics to optimize the cleaner 300. For example, if seed cotton 103 is measured and is similar to previously measured seed cotton, the NIR system can initially configure the components of the cleaner 300 with settings similar to those used for cleaning previous cotton, and the NIR system can further refine the settings based on the output of the cotton currently being cleaned.

[0056] In another example, the NIR system 111 can determine the characteristics before and after cleaning to improve control of the cleaner 300. For example, the yield characteristics of seed cotton 103 can be determined before and after the cleaner 300. By comparing the previous and subsequent yields, it can be determined how much impurity the cleaner 300 has removed. The control system associated with the cleaner 300 can use this information to control the operation of the cleaner 300. For example, the lever 306 can be moved toward or away from the roller 302 based on the yield comparison. It should be understood that, in addition to indicating how much impurity has been removed, measuring the yield before and after the cleaner 300 can also indicate how much lint has been lost through cleaning. Therefore, the control system can control the cleaner 300 to increase impurity removal while limiting the amount of lint loss.

[0057] According to another example, the NIR sensor 113 can be incorporated into the baler of the harvester 100. For example, the NIR sensor 113 can be located in the module builder 150, such as... Figure 2 As shown. At this location, the NIR sensor 113 can contact the seed cotton 103 to improve sensor readings. For example, in some embodiments, the NIR sensor 113 can be mounted to a movable arm and moved to contact the round bundle module to obtain a measurement result. In other examples, the NIR sensor 113 can be positioned at the bottom of the module builder 150 to measure the round bundle module at its outer periphery, regardless of the size of the round bundle module.

[0058] In other embodiments, an air gap may exist between the NIR sensor 113 and the seed cotton 103. That is, there is no direct contact. In such an arrangement, ambient light can be minimized to improve measurement quality. In this regard, the NIR sensor 113 can be positioned at virtually any location within the harvester 100. For example, in some examples, the NIR sensor 113 may be positioned on the harvesting device 114 (e.g., the cotton stripper header 112 or the cotton picking unit 116). More generally, virtually any dark area of ​​the harvester 100 can be a suitable location for the NIR sensor 113. Furthermore, since humidity is measured using the signal from the NIR sensor 113, the NIR sensor 113 can replace the humidity sensor included on the harvester 100.

[0059] The location mapping of seed cotton characteristics as described above can be performed in batches. For example, a round bale module created by module builder 150 can correspond to approximately one acre of seed cotton. Measurements can be acquired using NIR sensor 113 for each load from accumulator 140. For example, after adding seed cotton 103 from accumulator 140 to the round bale module being built, the most recently added seed cotton 103 is positioned towards the outer periphery of the round bale module. Thus, with the placement described above, once added to the round bale module, NIR sensor 113 can acquire readings of the accumulator load. These data can then be mapped to the corresponding area associated with the accumulator load.

[0060] While the round bundle module is stationary (e.g., between accumulator loads), further data resolution is enhanced by acquiring additional measurements. In some examples, the round bundle module can be micro-moved or rotated to acquire readings from multiple segments using the NIR sensor 113. Thus, the quality data acquired from the round bundle module can be coarsely mapped to acres, and the measurements of the accumulator load can be mapped to sub-segments of acres. Higher resolution location mapping is possible using further measurements at multiple locations on the round bundle module.

[0061] In another embodiment, using the aforementioned location mapping (e.g., from the baler module or its segments to the corresponding harvest location), additional data acquired after further processing can be linked back to the harvest location. For example, at the gin, the baler module can produce three or four lint bales. These three or four lint bales can be mapped to the corresponding baler module. Quality data associated with the lint bales can be associated with the baler module and, based on the mapping described above, further associated with the harvest location. Such quality data can be aggregated with other information associated with the harvest location to link, for example, the impact of agricultural operations on yield and / or quality.

[0062] In other examples, the mapped quality data are round bale modules according to the techniques described above. This mapping eliminates randomness in grouping modules (e.g., for ginning). Modules can be grouped based on quality data. For example, modules indicating higher quality can be grouped together and processed together to improve overall return. Higher quality can, in some respects, refer to seed cotton characteristics indicating higher lint yield. Certain thresholds or ranges can be predetermined for various characteristics. Specific measurements of these characteristics can be used individually or in combination as indicators of quality. Modules can be grouped based on these indicators.

[0063] Other grouping of modules can be based on the similarity of identified characteristics. This type of grouping allows gins to be configured to process similar modules, further increasing output more efficiently. For example, quality data for a module is forwarded to the gin before processing. This allows the gin to be configured accordingly. The grouping described above avoids configuring each module individually, which can be very time-consuming. Generally, forwarding quality data to the gin allows it to be optimized when processing related cotton to achieve maximum throughput and efficiency.

[0064] Data acquired at the cotton gin (e.g., categorical data) can be used to further enhance various aspects of this paper. For example, data from the cotton gin can be training data for a machine learning model that processes NIR sensor readings to determine seed cotton characteristics, and / or training data for a machine learning model that correlates the determined characteristics with estimates of lint yield.

[0065] Furthermore, quality data can be provided to the operator (e.g., via the operator interface 105 in operator station 107). The operator and / or harvester 100 can adjust settings based on the data to optimize the harvest.

[0066] In some implementations, data from the NIR sensor 113 can be combined with or supplemented by other sensors or imaging to improve measurement accuracy through data fusion. For example, data from one or more of the camera, yield monitor, humidity sensor, etc., can be combined with NIR data to improve measurement accuracy.

[0067] In addition to combined data, output data generated based on NIR data can also be input into the output monitor to provide more accurate real-time output estimates.

[0068] Turn now Figure 6 A flowchart illustrating a process 400 for analyzing cotton according to some aspects of this disclosure is shown. Process 400 begins at step 402, which involves harvesting seed cotton 103. This can be done by a harvester, for example, via... Figure 1 , Figure 2 and Figure 3 The harvester 100 discussed herein harvests seed cotton 103. Then, process 400 can continue to step 404, which may involve measuring the characteristics of the seed cotton 103. For example, the wavelength characteristics of the seed cotton 103 can be measured using an NIR sensor, for example, with NIR sensor 113 when a sample of seed cotton 103 is on the harvester 100. Depending on various examples, NIR sensor 113 can be an NIR camera, a multispectral camera, or a hyperspectral camera. For example, NIR sensor 113 can be a camera that captures both visible and non-visible spectra. Such a device can be used for data fusion, which will be described below.

[0069] The wavelength characteristics of seed cotton 103 can indicate one or more other characteristics of the seed cotton. Wavelength characteristics can include information about what wavelengths of light the seed cotton 103 absorbs. Process 400 can then proceed to step 406, which may involve the NIR sensor 113 transmitting the wavelength characteristics to a processor 115, which can determine various other characteristics of the seed cotton 103. For example, the processor 115 can determine yield characteristics, seed characteristics, or moisture characteristics of the seed cotton 103. In some examples, the processor can use one or more models to determine these characteristics, which are configured to receive wavelength characteristics (e.g., some or all wavelength attributes of the wavelength characteristics) as input and output characteristics as predictions. For example, a neural network can receive wavelength measurements associated with the seed cotton 103 measured by the NIR sensor 113 and map these wavelength measurements to various other characteristics of the seed cotton. The NIR system 111 can then use these characteristics in a variety of ways. Process 400 may also involve step 408, which may include the NIR system 111 using characteristics to update (e.g., retrain) one or more existing models. Additionally or alternatively, process 400 may involve step 410, which may include mapping characteristics of seed cotton 103 to the location where the seed cotton is harvested. Additionally or alternatively, process 400 may involve step 412, which may include automatic adjustments to components of the harvester 100. One or more steps 408 through 412 may be performed using a single set of data from seed cotton 103. For example, characteristics of seed cotton 103 may be used to refine existing models or create new models; characteristics may be mapped to locations to develop mappings of various cotton characteristics (e.g., mappings of yield characteristics); and characteristics may be used for adjustments to improve the efficiency of cleaners installed on the harvester.

[0070] Turn now Figure 7 The illustration shows Figure 3A simplified schematic diagram of the control aspects of the NIR system 111 is shown. The NIR system 111 may include a controller 502, which includes a memory 504 and a processor 115. The controller 502 may communicate with the NIR sensor 113, the harvester 100, and a database 506 via a communication interface 117. The NIR system 111 may include the NIR sensor 113 to measure the wavelength characteristics of the seed cotton 103 and transmit these wavelength characteristics to the processor 115. The processor 115 may execute instructions stored in the memory 504 to determine certain other characteristics of the seed cotton 103 based on the wavelength characteristics from the NIR sensor 113. The characteristics of the seed cotton 103 may be stored in the database 506 for use by the NIR system 111 or another system. Additionally or alternatively, the characteristics of the seed cotton 103 may be used by the controller 502 to determine whether to transmit control signals to components of the harvester 100. For example, controller 502 can transmit one or more control signals to cleaner 300 to actuate one or more components of the cleaner.

[0071] While the examples described above are generally about seed cotton, other examples can be implemented using lint. For example, NIR sensor 113 can determine the wavelength properties of the lint and transmit that information to a processor, which can then determine one or more characteristics of the lint based on the wavelength properties.

[0072] Now for reference Figure 8 This describes an agricultural system 800 for measuring one or more characteristics of seed cotton. In one example, system 800 may be partially or wholly included in or used by an agricultural vehicle 860, such as a harvester. Figure 8As shown, system 800 includes a cotton analysis system 810, and in some embodiments, system 800 may additionally include an agricultural machine 840 and a remote system 850. The cotton analysis system 810 includes one or more sensors 830 and a computing device 820. It should be understood that, in one example, the cotton analysis system 810 is capable of determining one or more characteristics of seed cotton based on data acquired by the sensors 830. In one example, the cotton analysis system 810 may determine cotton characteristics on an agricultural vehicle 860 and transmit the results to other devices, such as the remote system 850 and / or the agricultural machine 840 (e.g., a baler, cleaner, etc.). It should be understood that the agricultural machine 840 may be a component of the agricultural vehicle 860. For example, the agricultural machine 840 may be a baler or cleaner on a harvester (e.g., vehicle 860). In another example, the cotton analysis system 810 may jointly determine seed cotton characteristics with the assistance of the remote system 850. For example, data acquisition can be performed by the cotton analysis system 810 mounted on the agricultural vehicle 860, and data analysis can be performed by the remote system 850. Therefore, the determination of seed cotton characteristics can be performed by the cotton analysis system 810 and / or the remote system 850.

[0073] According to one aspect, sensor 830 can acquire data associated with seed cotton. This data can be acquired as an agricultural vehicle 860 passes through the field. For example, as described above, sensor 830 can acquire data while the cotton is being harvested. In some examples, sensor 830 may include a near-infrared sensor and / or an optical (e.g., RGB) sensor.

[0074] Data acquired by sensor 830 can be preprocessed to standardize or smooth the data. One or more models or analytical techniques can be used to analyze the preprocessed or unprocessed data to determine one or more characteristics of seed cotton. According to some examples, these models or techniques may include regression analysis (e.g., partial least squares or other regression analyses), component analysis, neural networks, classification analysis, other machine learning techniques, or a combination of one or more techniques / models. These techniques can be configured, updated, or optimized based on subsequent evaluations of the cotton measured using system 800. For example, information from the cotton gin or a USDA classifier can be used to adjust the data analysis.

[0075] Seed cotton characteristics can be transmitted to agricultural machinery 860 or remote system 850 for output to users. These characteristics can be transmitted to facilitate fleet management, ginning machine configuration, data mapping, etc. Seed cotton characteristics can also be used to configure or control agricultural machinery 140. In one example, a cleaner can be configured to improve impurity removal and / or limit lint loss.

[0076] In one example, computing device 820 can analyze sensor data to determine seed cotton characteristics. This analysis can alternatively be performed by remote system 850. For example, computing device 820 can collect sensor data and transmit that data to remote system 850 for processing. Furthermore, computing device 820 and remote system 850 can work jointly. For example, remote system 850 can provide storage, processing, and / or communication support to computing device 820. For example, remote system 850 can enable notifications to be transmitted to third parties, extend machine learning capabilities to computing device 820, and / or provide distributed computing resources to facilitate data processing across multiple nodes. Therefore, it should be understood that specific features, steps, or capabilities described in conjunction with computing device 820 can, in alternative scenarios, be performed by remote system 850.

[0077] Turning Figure 9 The illustration shows a schematic block diagram of an exemplary, non-limiting embodiment of a computing device 820. The computing device 820 includes a processor 902 configured to execute computer-executable instructions 906, such as instructions constituting sensor data analysis and cotton characteristic determination processes of an agricultural system 800. Such computer-executable instructions 906 may be stored on one or more computer-readable media, including non-transitory computer-readable storage media, such as memory 904. Memory 904 may also include other data (working data or variables) or portions thereof during the execution of instructions 906 by the processor 902.

[0078] The computing device 820 may also include a memory 908, which, according to one embodiment, may be a non-volatile storage device for persistently storing instructions 906, settings 910 (e.g., configuration settings) and / or data 912 (e.g., operation data, historical data, image data from sensor 830, learning models, etc.).

[0079] The computing device 820 may also include a user interface 916, which includes various elements for receiving user input and transmitting user output. For example, the user interface 916 may include a touchscreen display that can operate as both an input and output device. Additionally, the user interface 916 may include various buttons, switches, keys, etc., through which the user can input information into the computing device 820; and other displays, LED indicators, etc., through which other information can be output to the user. Furthermore, the user interface 916 may include input devices such as a keyboard, indicators, and a separate display.

[0080] The computing device 820 also includes a communication interface 914 for connecting the computing device 820 to various devices via a communication network. This communication interface 914 may include, but is not limited to, other computing devices 820, remote systems 850, agricultural machinery 840, agricultural vehicles 860, sensors 830, other controllers, servers, sensors, or internet-enabled devices (e.g., IoT sensors or devices). The communication interface 914 may be a wired or wireless interface, including but not limited to WiFi, Ethernet, Bluetooth, fiber optic, cellular radio, and satellite interfaces.

[0081] A component interface 918 is also provided to connect the computing device 820 to various components, such as sensor 830 and / or agricultural machinery 840. The component interface 918 may include multiple electrical connections on a circuit board or internal bus of the computing device 820, which is further connected to processor 902, memory 904, etc. In another embodiment, the component interface 918 may be an interface for a CAN bus for an agricultural vehicle 860. Furthermore, the component interface 918 can implement various wired or wireless interfaces, such as, but not limited to, USB interfaces, serial interfaces, WiFi interfaces, short-range RF interfaces (Bluetooth), infrared interfaces, near-field communication (NFC) interfaces, etc.

[0082] Turn now Figure 10 This diagram illustrates a simplified schematic of an exemplary embodiment of the cotton analysis system 1000. In some embodiments, the system 1000 may be integrated with an agricultural vehicle such as a harvester. In such embodiments, the system 1000 can operate simultaneously with the vehicle.

[0083] like Figure 10As shown, system 1000 may include an NIR sensor 1010 and an optical sensor 1020 (e.g., an RGB sensor or a camera). To improve measurement accuracy, data acquired by the NIR sensor 1010 and the optical sensor 1020 may be combined. It should be understood that additional sensors may also be utilized. Through data fusion, data acquired on a sample by multiple different sensors are combined and / or jointly analyzed.

[0084] Data acquired from NIR sensor 1010 and optical sensor 1020 (and any other sensors) can be input to preprocessor 1030 to smooth, standardize, or correlate the data (i.e., correlate data from one sensor with corresponding data from another sensor). After preprocessing by preprocessor 1030, or optionally without preprocessing, the data is input to analysis device 1040 to determine measurement result 1050. As described above, analysis device 1040 can utilize various models or techniques, such as, but not limited to, regression analysis (e.g., partial least squares or other regression analysis), component analysis, neural networks, classification analysis, other machine learning techniques, or a combination of one or more techniques / models.

[0085] Turning Figure 11 The flowchart depicts the process used to analyze cotton. Figure 11 The process can be implemented by the NIR system 111 and / or the cotton analysis system 810. At 1100, data related to seed cotton is acquired from one or more sensors. The one or more sensors may include optical sensors, NIR sensors, or both. In one aspect, the sensors may be mounted on or integrated with agricultural machinery such as a harvester. Therefore, data can be acquired while cotton is being actively harvested. In doing so, the NIR system 110 or the cotton analysis system 810 can control the machine to facilitate data acquisition or receive status signals from the machine to coordinate data acquisition. For example, if the sensors are mounted in association with a module builder, the system can stop the module's rotation to acquire data if static data is desired. Alternatively, for example, because an accumulator is being fed, the system can acquire such sensor readings when the module is not rotating. If continuous sensor readings are desired, the system can control data acquisition to occur while seed cotton is being conveyed to the module builder and therefore while the module is rotating.

[0086] At step 1102, the acquired data may optionally be preprocessed, and at step 1104, data fusion may be performed to correlate corresponding data from different sensors. At 1106, the acquired data is evaluated to determine at least one characteristic of the seed cotton. Data analysis may use one or more techniques or models to determine the at least one characteristic of the seed cotton. In one example, different models or techniques (or different sets of models and / or techniques) may be used to determine different characteristics. For example, a model or a set of models may be used to determine yield, and different techniques or different sets of techniques may be used to determine moisture characteristics. At 1108, the at least one characteristic is output to agricultural machinery, a cloud system, or a downstream processor (e.g., a cotton gin).

[0087] Figure 12 A flowchart depicts a process for controlling agricultural machinery based on cotton properties. At 1200, measurements of at least one property of the seed cotton are acquired. This can be based on... Figure 11 The process and / or the acquisition of measurement results via the NIR system 111 or cotton analysis system 810 described above. At 1202, a configuration change for the agricultural machinery is determined based on the measurement results. At 1204, a control signal is sent to the agricultural machinery to affect the configuration change. According to one example, measurements of the yield characteristics of seed cotton can be acquired. The measurement results may indicate a significant amount of impurities in the seed cotton. Therefore, a configuration change can be determined to increase the cleaning of seed cotton within the agricultural machinery (e.g., within the cleaner of a harvester). Similarly, if the measurement results indicate an increase in lint loss, a configuration change to reduce the cleaning intensity can be determined.

[0088] According to one aspect, an agricultural machine is described. The agricultural machine includes a sensor array and a computing device having a processor. The processor executes computer-readable instructions to: control the sensor array to measure seed cotton during harvesting by the agricultural machine to generate sensor readings; generate attributes of the seed cotton based on the sensor readings acquired from the sensor array; and determine one or more characteristics of the seed cotton based on the attributes.

[0089] According to one example, the agricultural machine also includes a baler, and the sensor array is mounted in the baler. Additionally, the computing device executes instructions to control the sensor array to measure the seed cotton when the bale in the baler is stationary. In another example, the computing device executes instructions to control the sensor array to measure the seed cotton when the baler is active. In yet another example, the computing device executes instructions to: rotate the bale when the seed cotton is not being fed to the baler; and control the sensor array to measure the seed cotton, thereby measuring the seed cotton while rotating.

[0090] In one example, the agricultural machine further includes a conveyor pipe, and the sensor array is mounted within the conveyor pipe. In another example, the agricultural machine includes a accumulator, and the sensor array is mounted within the accumulator.

[0091] In another example, the computing device also executes instructions to: determine the location of the seed cotton in the cotton field when it is harvested; and store the location in association with the determined one or more characteristics. Additionally, the computing device also executes instructions to adjust the settings of components of the agricultural machinery based on the one or more characteristics of the seed cotton.

[0092] Furthermore, in other examples, the computing device also executes instructions to determine one or more predictive characteristics of the seed cotton based on the one or more characteristics. The one or more predictive characteristics include estimates of the corresponding quantities of impurities, cotton fibers, and seeds present in the seed cotton. Additionally, the one or more characteristics of the seed cotton include at least one of the following: moisture level in the seed cotton, yield composition present in the seed cotton, seed protein level in the seed cotton, or oil content of the seed cotton.

[0093] According to other examples, the computing device also executes instructions to transmit quality data based at least in part on said one or more characteristics. The quality data may be transmitted to, for example, a cotton gin to establish settings associated with the quality data when processing the seed cotton.

[0094] In other examples, the sensor array includes at least a near-infrared (NIR) sensor. In another example, the sensor array also includes an optical sensor. Furthermore, the computing device is configured to combine data about the seed cotton acquired by the NIR sensor with data about the seed cotton acquired by the optical sensor, wherein the one or more characteristics of the seed cotton are determined based on the combined data.

[0095] In another example, a cotton analysis method is provided. The method includes acquiring sensor data related to the seed cotton via a sensor array while the seed cotton is being collected by agricultural machinery. The method further includes generating attributes of the seed cotton based on the sensor data acquired by the sensor array. The method also includes determining one or more characteristics of the seed cotton based on the attributes. Additionally, the method includes transmitting the one or more characteristics to a cotton gin to establish settings associated with the one or more characteristics when processing the seed cotton.

[0096] In one example, the method further includes adjusting the settings of components of the agricultural machine based on one or more characteristics of the seed cotton.

[0097] In another aspect, a non-transitory computer-readable storage medium is provided. The non-transitory computer-readable storage medium has computer-executable instructions stored thereon for a cotton analysis application. When executed by a processor, the cotton analysis application configures the processor to: acquire sensor data related to the seed cotton using a sensor array while the seed cotton is being collected by an agricultural machine; generate attributes of the seed cotton based on the sensor data acquired by the sensor array; determine one or more characteristics of the seed cotton based on the attributes; and adjust the settings of components of the agricultural machine based on the one or more characteristics of the seed cotton.

[0098] While this specification contains numerous details, these details should not be construed as limiting the scope of this disclosure, but rather as descriptions of specific features of particular aspects. Certain features described in the context of individual aspects in this specification may also be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment may also be implemented individually in multiple ways or in any suitable sub-combination. Furthermore, although features may be described above as functioning in certain combinations, in some cases one or more features from that combination may be removed, and the combination may be for sub-combinations or variations thereof. Thus, certain aspects have been described, but other aspects are also within the scope of this disclosure.

[0099] The word “exemplary” as used herein means serving as an example, instance, or illustration. Any aspect or design described herein as “exemplary” is not necessarily to be construed as superior to other aspects or designs. Rather, the use of the word “exemplary” is intended to present a concept in a specific manner. As used in this application, the term “or” is intended to mean an inclusive “or” rather than an exclusive “or.” That is, unless otherwise stated or clearly apparent from the context, “X adopts A or B” is intended to mean any natural inclusive arrangement. That is, “X adopts A or B” holds true in any of the foregoing cases if X adopts A; X adopts B; or X adopts both A and B. Furthermore, at least one of A and B and / or the like generally means A or B or both A and B. In addition, unless otherwise stated or clearly apparent from the context as to be directed to the singular form, the articles “a” and “an” as used in this application and the appended claims can generally be interpreted as meaning “one or more”.

[0100] Although the subject matter has been described in language specific to structural features and / or methodological actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. Rather, the specific features and actions described above are disclosed as exemplary forms for implementing the claims. Of course, those skilled in the art will recognize that many modifications can be made to this configuration without departing from the scope or spirit of the claimed subject matter.

[0101] Furthermore, while this disclosure has been shown and described with respect to one or more embodiments, equivalent changes and modifications will occur to those skilled in the art based on a reading and understanding of this specification and the accompanying drawings. This disclosure includes all such modifications and changes and is limited only by the scope of the appended claims. In particular, with respect to the various functions performed by the components described above (e.g., elements, resources, etc.), unless otherwise stated, the terminology used to describe these components is intended to correspond to any component that performs the specified function of the described component (e.g., functionally equivalent), even if structurally not equivalent to the disclosed structure that performs the function of the exemplary embodiments of this disclosure illustrated herein.

[0102] Furthermore, while specific features of this disclosure may have been disclosed with respect to only one of several embodiments, such features may be combined with one or more other features of other embodiments, which may be desirable and advantageous for any given or particular application. Additionally, the terms “comprising,” “including,” “having,” “with,” or variations thereof, as used in the detailed description or claims, are intended to be inclusive in a manner similar to the term “comprising.”

[0103] The embodiments have been described above. It will be apparent to those skilled in the art that the methods and apparatus described above may include variations and modifications without departing from the general scope of the invention. All such modifications and variations are intended to be included, provided they fall within the scope of the appended claims or their equivalents.

Claims

1. A cotton harvester (100, 860), comprising: Sensor arrays (113, 830); A module builder for constructing the seed cotton module; as well as Computing devices (502, 820) having processors (115, 902) that execute computer-readable instructions to: The sensor array (113, 830) is controlled to measure seed cotton (103) during harvesting by the cotton harvester (100, 860) to generate sensor readings; The wavelength properties of the seed cotton are generated based on sensor readings obtained from the sensor array (113, 830); Based on the wavelength attribute, one or more characteristics of the seed cotton are determined. The computing devices (502, 820) also execute instructions to adjust the settings of components of the cotton harvester (100, 860) based on one or more characteristics of the seed cotton (103), and The seed cotton modules are grouped based on the similarity of the aforementioned characteristics in order to establish settings that associate the cotton gin with the corresponding module groups.

2. The cotton harvester according to claim 1 further includes a baler (150), wherein, The sensor array (113, 830) is installed in the packing machine (150).

3. The cotton harvester according to claim 2, wherein, The computing devices (502, 820) execute instructions to control the sensor array (113, 830) to measure the seed cotton when the bundles in the baler (150) are stationary.

4. The cotton harvester according to claim 2, wherein, The computing devices (502, 820) execute instructions to control the sensor array (113, 830) to measure the seed cotton when the baler (150) is active.

5. The cotton harvester according to claim 2, wherein, The computing devices (502, 820) execute instructions to: When the seed cotton (103) is not conveyed to the baler (150), the baler's bales are rotated; and While the baler (150) is rotating, the sensor array (113, 830) is controlled to measure the seed cotton.

6. The cotton harvester according to claim 1 further includes a conveying pipe (200), wherein, The sensor array (113, 830) is installed inside the transmission pipe (200).

7. The cotton harvester according to claim 1 further includes a accumulator (140), wherein, The sensor array (113, 830) is installed in the storage device (140).

8. The cotton harvester according to claim 1, wherein, The computing devices (502, 820) also execute instructions to: Determine the location of the seed cotton (103) in the cotton field at the time of collection; and The location is stored in association with one or more of the determined characteristics.

9. The cotton harvester according to claim 1, wherein, The computing device (502, 820) also executes instructions to determine one or more predictive characteristics of the seed cotton based on the one or more characteristics; Wherein, the one or more characteristics of the seed cotton include at least one of the following: moisture level in the seed cotton, yield composition present in the seed cotton, seed protein level in the seed cotton, or oil content in the seed cotton; and The one or more predictive characteristics include estimates of the corresponding quantities of impurities, cotton, and seeds present in the seed cotton.

10. The cotton harvester according to claim 1, wherein, The sensor array (113, 830) includes at least a near-infrared sensor (1010).

11. The cotton harvester according to claim 10, wherein, The sensor array (113, 830) also includes an optical sensor (1020).

12. The cotton harvester according to claim 11, wherein, The computing device (502, 820) is further configured to combine data about the seed cotton acquired by the near-infrared sensor (1010) with data about the seed cotton acquired by the optical sensor (1020), wherein the one or more characteristics of the seed cotton are determined based on the combined data.

13. A cotton analysis method, comprising: While collecting seed cotton with a cotton harvester, a seed cotton module is constructed using a module builder, and sensor data related to the seed cotton is acquired through a sensor array. The wavelength properties of the seed cotton are generated based on the sensor data acquired by the sensor array; One or more characteristics of the seed cotton are determined based on the wavelength attribute; The one or more characteristics are transmitted to the cotton gin to establish settings associated with the one or more characteristics when processing the seed cotton; The settings of the components of the cotton harvester are adjusted based on one or more characteristics of the seed cotton, and The seed cotton modules are grouped based on the similarity of the aforementioned characteristics in order to establish a setting for the cotton gin associated with the corresponding module group.

Images