Figure 9 - uploaded by Fatma Ezzahra Rhili
Content may be subject to copyright.
Source publication
In this study, an adaptive control based on fuzzy adapting rate for neural emulator of nonlinear systems having unknown dynamics is proposed. The indirect adaptive control scheme is composed by the neural emulator and the neural controller which are connected by an autonomous algorithm inspired from the real-time recurrent learning. In order to ens...
Contexts in source publication
Context 1
... oscillations are noted during the starting phase and when perturbations occur (Figure 8). The tracking error resulting from the fuzzy controller (Figure 9) is always larger than the tracking error resulting from the proposed controller (Figure 12) which guarantees the systems stability. Figure 10 indicates that the perturbations affect the emulation system performances and lead to large variance of the neural emulator output. ...
Context 2
... oscillations are noted during the starting phase and when perturbations occur (Figure 8). The tracking error resulting from the fuzzy controller (Figure 9) is always larger than the tracking error resulting from the proposed controller (Figure 12) which guarantees the systems stability. Figure 10 indicates that the perturbations affect the emulation system performances and lead to large variance of the neural emulator output. ...
Context 3
... oscillations are noted during the starting phase and when perturbations occur (Figure 8). The tracking error resulting from the fuzzy controller (Figure 9) is always larger than the tracking error resulting from the proposed controller (Figure 12) which guarantees the systems stability. Figure 10 indicates that the perturbations affect the emulation system performances and lead to large variance of the neural emulator output. ...
Citations
... In this context, to avoid the problem linked to the Lyapunov constant parameter, authors in (Rhili et al., 2021) proposed a new NC adaptive rate ensuring stability and faster convergence in the sense of the continuous Lyapunov stability method. The main drawback of this method is the requirement of some stability conditions. ...
... To evaluate the performance of the proposed algorithm, comparative studies with the method proposed in Rhili et al., 2021 are elaborated. The obtained results are illustrated in Figure 9. ...
... In the initialization phase [0, 25s], this error takes low values with the developed method compared to conventional NC, and the decrease in the error can reach 57%. In the regulation phase [200s, 400s], we note a diminution around 36% of the tracking relative error for the proposed method compared to the method suggested by (Rhili et al., 2021). With reference to the results, we can conclude that the proposed strategy is more efficient than the one used in (Rhili et al., 2021), in terms of precision, speed of convergence, and robustness during the tracking and regulation phases. ...
An arbitrary choice of the neural controller adaptive rate can have a negative effect on the performance of the closed-loop system. In this study, we propose a novel methodology for neural controller adaptive rate using Particle Swarm Optimization algorithm. The developed control scheme is composed of a recurrent neural networks emulator and controller with decoupled adaptive rates. Constraints on the adaptive rate are derived from the Lyapunov stability method. Particle Swarm Optimization is proposed as a mechanism to optimize the adaptive rate of the NC to improve the closed-loop performances. The advantages of the proposed new control algorithm are as follows: (1) online optimal choice of adaptive rate, which reduces the effort for searching an adequate neural controller adaptive rate when considering the conventional methods and (2) ensuring stability, faster convergence, disturbance rejection, and good tracking. The efficiency of the proposed PSO adaptive rate is demonstrated with numerical control of SISO nonlinear system. The obtained results prove the efficiency of the proposed NC compared to those obtained with existing methods. An application of the developed approach on a semi-batch reactor is presented to validate simulations results.
