Real-Time Prediction of Efficient Operating Points in Quasi-Stationary Agricultural Processes with Hydraulic Implements

Agriculture is a critical industry that relies on the use of mobile machinery with high energy demands. Currently, the efficiency optimization of agricultural machinery is limited by the targets set by the human operator. Manual adjustments of the targets are challenging since the operator does not know the optimization strategy of the internal control systems of the machines, and therefore cannot fully exploit all degrees of freedom for efficiency optimization, including the operating speed.
While some agricultural processes only require draft power, others depend on additional power transmission. Compared to the use of mechanical PTO shafts to provide energy for power-intensive functions of agricultural implements, the use of hydraulics offers the possibility of variable adjustment of the transmitted power as it is independent of the engine speed.
In this paper, an algorithm for the prediction of the best operating point is proposed based on an interaction model of a machine-implement combination with the environment and a neural network for the prediction of the system efficiency.
Simulations demonstrate that the system can propose advantageous operating points.