Abstract: A pickup reel assembly that includes a hub and multiple bat assemblies where each bat assembly rotates through a functional area where it moves crop material into a harvester, and a non-functional area where it does not move crop material into the harvester. Each bat assembly rotates at a first speed through the functional area and at a second speed through the non-functional area, where the second speed is greater than the first speed. A nominal speed shaft can rotate at the first speed, and an increased speed shaft can rotate at the second speed. Cogs can couple the bat assembly to the increased speed shaft when it is in the non-functional area. The cogs can also couple the bat assembly to the nominal speed shaft when it is in the functional area.

Abstract: A pickup reel assembly that includes a hub and multiple bat assemblies where each bat assembly rotates through a functional area where it moves crop material into a harvester, and a non-functional area where it does not move crop material into the harvester. Each bat assembly rotates at a first speed through the functional area and at a second speed through the non-functional area, where the second speed is greater than the first speed. A nominal speed shaft can rotate at the first speed, and an increased speed shaft can rotate at the second speed. Cogs can couple the bat assembly to the increased speed shaft when it is in the non-functional area. The cogs can also couple the bat assembly to the nominal speed shaft when it is in the functional area.

Abstract: Some embodiments of the present application include obtaining a trained machine learning model that was trained using training data. Production data may be obtained from a data feed selected based on the trained machine learning model. In some embodiments, feature sets and observed results may be extracted from data output from the data feed, and one or more features or results may be masked to generate the production data. Predicted results data may be generated with the trained machine learning model based on the production data and an accuracy score for the trained machine learning model may be determined based on the predicted results data. If the accuracy score satisfies a threshold accuracy condition, the trained machine learning model may be caused to be rebuilt or the training data may be caused to be updated.