A combine that can accurately measure the weight of grain retained in a grain tank is provided. When a weight measurement signal is output from a measurement switch 66, a weight measurement decision unit 75 instructs a working state determination unit 71 to perform working state determination. If it is determined that the combine is in the working state, the weight measurement decision unit 75 does not instruct a load cell 39 to perform weight measurement.

A method and non-transitory computer-readable medium capture an image of bulk grain and apply a feature extractor to the image to determine a feature of the bulk grain in the image. For each of a plurality of different sampling locations in the image, based upon the feature of the bulk grain at the sampling location, a determination is made regarding a classification score for the presence of a classification of material at the sampling location. A quality of the bulk grain of the image is determined based upon an aggregation of the classification scores for the presence of the classification of material at the sampling locations.

A harvesting machine capable of automatic adjustment, comprising a plurality of acoustic material flow sensors, a control system, a processor, and application software, wherein the plurality of acoustic material flow sensors are mounted internal to the harvesting machine at points of crop material flow and are capable of sensing an amount of crop material passing by them. The control system operates in a cause-and-affect mode for interactively enabling manual or automatic responses to Mass Material Distribution (MMD) information and equipment-related performance parameters. An interactive combine control method is also provided.

A crop quality sensor, comprising an illumination source, an imaging device, and a processor executing application software. The illumination source is shone onto a crop sample, and an image is taken with the imaging device of the illuminated crop sample. The software executing on the processor is used to analyze the image to identify the outlines of individual kernels and to identify which of those outlines contain a specular highlight, indicative that the kernel is whole and unbroken, while the absence of such a specular highlight is indicative of a broken kernel.

Creating NIR sensor calibration models and their use in agricultural work machines is disclosed. A database structure, such as a database structure system, for creating calibration models for an NIR sensor system is used. The database structure includes raw data of the NIR spectra of one or both of plant material and other substances. The raw data are generated by one or more NIR sensor systems assigned to an agricultural work machine. The one or more NIR sensor systems transmit the raw data via an interface for the data traffic with at least one data processing unit external to the agricultural work machine. The database structure comprises one or more calibration models and the raw data, generates user-specific calibration models by using the saved raw data and/or calibration models, and provide user-specific calibration models to a user.

A system and method for determining a broken grain fraction of a quantity of grains is disclosed. The system includes at least one camera and a computing unit, with the camera configured to create an image of the quantity of grains, and with the computing unit configured to evaluate, using artificial intelligence, the image to determine broken grains in the image, and to determine, based on the broken grains, the broken grain fraction of the quantity of grains in the image.

An agricultural harvesting machine, with at least one work assembly and a monitoring assembly, is disclosed. The agricultural harvesting machine transports harvested material in a harvested material flow along a harvested material transport path. The monitoring assembly includes an optical measuring system positioned on the harvested material transport path and an evaluation device configured to determine at least one harvested material parameter. The optical measuring system includes a first optical sensor that senses spatially-resolved image data indicative of visible light in a first section and second optical sensor that senses image data indicative of invisible light in a second section that at least partly overlaps the first section. The evaluation device correlates the image data for the overlapping section from the first optical sensor and from the second optical sensor and determines, based on the correlation, at least one harvested material parameter.

A method and system for controlling the quality of harvested grains include capturing, by one or more image sensors, one or more images of material at a sampling location within a grain elevator of the combine harvester. The captured images are defined by a set of image pixels represented by image data and having a classification feature indicative of grain or non-grain material. One or more controllers receive the image data associated with the one or more images captured by the image sensor(s) and select a sample image defined by a subset of image pixels of the set of image pixels. The controller(s) apply a convolutional neural network (CNN) algorithm to the image data of the subset of image pixels of the selected sample image to determine the classification feature. The controller(s) analyze the determined classification feature to adjust an operational parameter of the combine harvester.

A controller for controlling a harvesting performance of an agricultural harvester. The controller receives automation settings, selected by an operator via a human-machine interface. The controller also receives data from on-board harvester sensors. The controller defines a target value for quality parameters based on the automation settings, and determines a current value of each of the quality parameters in dependence on the crop sensor data. The controller determines an actuator setting for actuators of the agricultural harvester when the current value of one or more of the plurality of quality parameters differs by greater than an acceptable amount from the associated target value. The actuator setting is determined in dependence on the automation settings and the target value. The controller controls the actuators to achieve the determined actuator setting.

Selectively removable nozzles for inclusion into a grain conveyor are disclosed. The nozzles may include a ramp and a sidewall coupled to the ramp. The ramp may conform to an inner surface of a conveyor housing and produce a constriction within the housing. The sidewall may also conform to the inner surface of the conveyor housing. The ramp may also include a recess that extends along the sidewall. The recess may receive a shaft of the conveyor. One nozzle may be replaced with another in order to accommodate different harvesting conditions. The ramp compresses grain traveling through the conveyor to provide a continuous flow of grain. The continuous flow of grain provides for accurate measurements of grain characteristics by a sensor located adjacent to the flow of grain.