An Output-Recurrent-Neural-Network-Based Iterative Learning Control for Unknown Nonlinear Dynamic Plants

Figure 3

(a) max_{𝑡∈{1,…,200}}|𝑒^𝑗𝑐(𝑡)| versus control iteration 𝑗. (b) max_{𝑡∈{0,…,200}}|𝑒^𝐼10,𝑘(𝑡)| versus identification process 𝑘 at the 10th control iteration. (c) 𝑦¹⁰(𝑡) (dotted line) and 𝑦_𝑑(𝑡) (solid line) versus time 𝑡 at the 10th control iteration. (d) 𝑦̂¹⁰(𝑡) (dotted line) and 𝑦¹⁰(𝑡) (solid line) versus time 𝑡 at the 10th control iteration. (e) 𝑢¹⁰(𝑡) at the 10th control iteration versus time 𝑡.

(a)

(b)

(c)

(d)

(e)