Claas Selbstfahrende Erntemaschinen Gmbh

Claas E-systems Gmbh

Sven Carsten Belau

Frédéric Fischer

Christoph Heitmann

Ingo Bönig

Dennis Neitemeier

Daniel Irmer

Marvin Barther

Sebastian Spiekermann

Kristian Kirk

Johann Witte

Andreas Skiba

Jannik Redenius

Maik Heufekes

René Middelberg

Jan Meyer Zu Hörste

Christoffer Rasmussen

Thomas B Moeslund

A method and a system for determining an indicator of processing quality of an agricultural harvested material using a mobile device is disclosed. A computing unit analyzes image data of a prepared sample of harvested material containing grain components and non-grain components in an analytical routine to determine the indicator of the processing quality of the agricultural harvested material. Further, the computing unit uses a trained machine learning model in the analytical routine to perform at least one step of determining the indicator of the processing quality of the agricultural harvested material.

System and method for determining an indicator of processing quality of an agricultural harvested material

A method and system for identifying, using a computing unit, lengths of a particle in a material flow is disclosed. The computing unit is configured to analyze images of the material flow () in an analytical routine and to derive particle lengths of particles of the material flow contained in the images. The particle length derived in the analytical routine may comprise an excess length, with the analytical routine being based on a machine learning method trained to find or identify particles with the excess length.

System and method for identifying lengths of harvested particles

A forage harvester. The forage harvester has a work assembly for harvesting a crop and for processing harvested material of the crop, which includes grain components and non-grain components. In operation, the harvested material is transported in a harvested material flow along a harvested material transport path through the harvesting machine. The forage harvester also has a control assembly that includes an optical measuring system arranged on the harvested material transport path. The optical measuring system has a camera for recording image data of the harvested material of the harvested material flow. The control assembly, using an image recognition routine, determines image regions assigned to a non-grain component in the image data, determines geometric properties of the assigned non-grain components based on the image regions, and determines an indicator of a structural percentage of the harvested material from the geometric properties.

Forage harvester

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 measuring system positioned on the harvested material transport path and an evaluation device configured to determine at least one harvested material parameter. The measuring system includes a first passive optical sensor that senses image data indicative of visible light in a first section and a second non-passive non-optical sensor that senses data 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 the data from the second optical sensor and determines, based on the correlation, at least one harvested material parameter.

Agricultural harvesting machine with a monitoring assembly to sense harvested material flow in the agricultural harvesting machine

A forage harvester with at least one work assembly is disclosed. The forage harvester has a corn cracker to process grain components and a driver assistance system. The driver assistance system controls the corn cracker by adjusting the machine parameters of the corn cracker. In particular, the driver assistance system has an optimization model which includes a multidimensional characteristic map that represents a relationship between a processing quality of the grain components and at least three parameters that comprise an input parameter representing a current harvesting process state and at least one machine parameter of the corn cracker as an output parameter. Thus, the driver assistance system determines the output parameter in the control routine during the harvesting process based on the varying input parameter from the optimization model and adjusts it in the corn cracker to achieve a uniform given processing quality of the grain components during the harvesting process.

A method and a system for determining an indicator of processing quality of an agricultural harvested material using a mobile device is disclosed. A computing unit analyzes image data of a prepared sample of harvested material containing grain components and non-grain components in an analytical routine to determine the indicator of the processing quality of the agricultural harvested material. Further, the computing unit uses a trained machine learning model in the analytical routine to perform at least one step of determining the indicator of the processing quality of the agricultural harvested material and that the computing unit adjusts at least one machine parameter of the forage harvester based on the indicator of processing quality.

A method for the evaluation of signals of a rangefinder having at least one sensor point involves carrying out measurements cyclically, wherein the rangefinder emits a plurality of measurement points that indicate a distance from the sensor point. The rangefinder measures distances in a plurality of directions, and a horizontal angle is associated with each measurement point. The measurement points are differentiated into useful signals and interfering signals based on the distance. Measurement points with a distance below a first limiting value are identified as interfering signals, and measurement points above the first limiting value are identified as useful signals. Useful signals are associated with a first measurement area when they satisfy a predetermined condition for distance and horizontal angle. The quantity of useful signals in the first measurement area is determined, and a warning signal is emitted when the quantity of useful signals lies below a first threshold value.

Growing community of inventors

Guetersloh, Germany

Sven Carsten Belau