Design of an Adaptive Neuro-Fuzzy Inference System (ANFIS) for tractor-implement tillage depth control

During ploughing operations, variations in soil conditions cause ploughing depth errors. This chapter presents the designed of a neuro-fuzzy controller to decrease tractors ploughing depth errors. The tractor’s electrohydraulic lifting system consisting of pump, valves and cylinders, position and force sensors, and the neuro-fuzzy controller, is modeled using MATLAB software. The aim of this study is to control the draft force and the position of the lifting mechanism using a controller based on the Adaptive Neuro-fuzzy Inference System (ANFIS). After several simulations, the performance of the proposed controller is analysed and compared with that of a Proportional Integral Derivative (PID) controller and a fuzzy logic controller. The performance index based on the Integral Time Absolute value Error (ITAE) criterion indicates a value of 0.32 in the case of the neuro-fuzzy controller; this is almost half the value of the PID controller, which is 0.76. In addition, the values of the standard deviations on the desired depth for the proposed controller are lower than those obtained by the PID controller and those of the fuzzy controller. The results obtained show that the neuro-fuzzy controller adapts perfectly to the dynamics of the system with rejection of disturbances.