Position Control of Magnetic Levitation Ball Based on an Improved Adagrad Algorithm and Deep Neural Network Feedforward Compensation Control

<table class="table-group" id="tab6"><tr><td><table class="table"><tr><td class="thead-hr" colspan="3"><hr/></td></tr><tr class="thead"><td class="align_left">Controller</td><td class="align_center">Sinusoidal signal (mm)</td><td class="align_center">Trapezium signal (mm)</td></tr><tr><td class="thead-hr" colspan="3"><hr/></td></tr><tr><td class="align_left">PID</td><td class="align_center">[−0.45, 0.45]</td><td class="align_center">[−0.50, 0.50]</td></tr><tr><td class="align_left">ANNC</td><td class="align_center">[−0.38, 0.38]</td><td class="align_center">[−0.39, 0.43]</td></tr><tr><td class="align_left">IANNC</td><td class="align_center">[−0.10, 0.10]</td><td class="align_center">[−0.09, 0.09]</td></tr><tr class="table-tr"><td colspan="3"><hr class="tbody-hr"/></td></tr></table></td></tr></table>

<div>Comparison of the experimental results for error range.</div>

Mathematical Problems in Engineering

tab6

Table 6

Table 6: Position Control of Magnetic Levitation Ball Based on an Improved Adagrad Algorithm and Deep Neural Network Feedforward Compensation Control 

Table 6 | Position Control of Magnetic Levitation Ball Based on an Improved Adagrad Algorithm and Deep Neural Network Feedforward Compensation Control 