Research Article

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

Table 4

Iterative results of two optimization algorithms.

No.MinAdagrad iteration resultsImproved Adagrad iteration results

101.06480.2806
200.34420.2813
303.51840.4130
4āˆ’1.031632.1352āˆ’0.2115
503.60490.0001