Optimization of Emotional Learning Approach to Control Systems with Unstable Equilibrium - Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing - page 50

4

actual position desired position

2

0

−2

−4

0 50 100 150 200 250 300

0.04

0.02

0

−0.02

0 50 100 150 200 250 300

time (second)

Fig. 4 Results of proposed controller in first disturbance test

3

actual position desired position

2

1

0

−1

−2

0 50 100 150 200 250 300

0.04

0.02

0

−0.02

0 50 100 150 200 250 300

time (second)

Fig. 5 Results of proposed controller in second disturbance test

Ta b l e 1 Evaluation measures without disturbance

Controller IAE p IAE a IACF IADCF

Proposed controller 2.16 0.28 7.74 6.91

Double PID 2.73 0.39 11.02 11.81

Ta b l e 2 Evaluation measures of first disturbance test

Controller IAE p IAE a IACF IADCF

μ σ μ σ μ σ μ σ

Proposed controller 5.73 0.71 0.38 0.11 55.18 2.02 94.08 5.96

Double PID 14.91 3.26 1.96 0.40 73.60 2.96 126.03 5.83

than basic controller is found in time 100.2 and the optimization is continued to
217.4. In the second disturbance test a random voltage produced by a Gaussain
distribution with zero mean and 0.05 of variance is applied to desired cart position
in optimization phase. The better candidate solution for stress generation is found in
100.2 as same as previous test, and the optimization is continued to 217.4 too. As it