Tech’s Perspective: Closeout to #Harvest2017

As the harvest season comes to a close, a quick look at Twitter gives us some insights into how things went. Many had great shots of harvesters and grain carts with the next generation driving them, which was amazing to see. Several growers also highlighted the success they had thanks to data solutions.

 

MORE BY TIM MARQUIS

Twitter also gave us a window into recurring problems every harvest season that threaten success: downtime and preventable problems. When it comes to not having a harvester in the field due to maintenance, that can significantly impact a grower’s revenue. But losing a harvester due to a fire caused by mechanical issues, like what happened to Tim Penner’s uncle, that’s a catastrophic problem.

Growers have lost their entire fields, hundreds of thousands of dollars in equipment and, for some, their lives due to these fires.

Harvester fires, train derailments, high winds in Nebraska, and recent snow in Minnesota and Iowa are just some of the struggles growers needlessly continue to face between planting and harvesting. Machines being down due to maintenance and fleet management can lead to catastrophic delays that allow weather to reduced yield, burned fuel, and put critical schedules at risk. Such misfortune fell upon Jeff Theis and the Scotts family farm this year:

But it doesn’t have to be this way. Unexpected downtime and combine fires should be a thing of the past. By leveraging telematics to not only track all equipment — combines, carts, trucks, and semis — but also to seek to increase their uptime and efficiency, we can aim to get the harvest out of the ground as fast as possible.

Utilizing machine learning we can figure out the least amount of machine downtime so that growers get the crop out expediently. Utilizing the sensor data from the CAN-BUS, we can perform data analytics on the onboard sensors to find the subtle precursors which cause combine fires.

Not all of these misfortunes can be prevented, especially when it comes to the weather. However, many can be predicted, and we at Uptake are looking forward to realizing that technology for next planting season.

0

Leave a Reply

[…] “Utilizing machine learning we can figure out the least amount of machine downtime so that growers get the crop out expediently. Utilizing the sensor data from the [Controller Area Network] CAN-BUS, we can perform data analytics on the onboard sensors to find the subtle precursors which cause combine fires,” wrote Tim Marquis, agriculture lead for Uptake in PrecisionAg. […]

[…] “Utilizing machine learning we can figure out the least amount of machine downtime so that growers get the crop out expediently. Utilizing the sensor data from the [Controller Area Network] CAN-BUS, we can perform data analytics on the onboard sensors to find the subtle precursors which cause combine fires,” wrote Tim Marquis, agriculture lead for Uptake in PrecisionAg. […]