Figure 2 - uploaded by Fatma Ezzahra Rhili
Content may be subject to copyright.
Source publication
This paper deals with a new fuzzy adapting rate for a neural emulator of nonlinear systems with unknown dynamics. This method is based on an online intelligent adaptation by using a fuzzy supervisor. The satisfactory obtained simulation results are compared with those registered in the case of the classical choice of adapting rate and show very goo...
Contexts in source publication
Context 1
... choice of the constant value of the adapting rate h ec leads to bad results in terms of emulation performances. For example, the choice of h ec = 2 can affect the emulation results (Figure 2). This figure shows that NE adapts itself to the variation of the plant output with a relatively important emulation error. ...
Context 2
... get rid of problems caused by the choice of the starting term e e and the constant value of NE adaptive rate h ec , a NE based on the fuzzy adapting rate is considered. A comparative study with the NE based on a constant value of adaptive rate ( Rhili et al., 2018), given by Figures 11 and 12, shows the contribution in precision of the new proposed method. We remark that the NE output, based on the fuzzy adapting rate, follows the real output with relative precision. ...
Similar publications
Motion control is essential to industrial machinery and production systems. In this paper, the
Adaptive Fuzzy controller is proposed to optimize the velocity and vibration during the two-axis motion of the automatic guided vehicle (AGV). Theoretical analysis, as well as simulation, shows that, during the simultaneous motion of two axes of the AGV,...
Citations
... However, a bad choice of this parameter can affect the system performances. In order to resolve this problem, a fuzzy adapting rate for NE of nonlinear systems is presented in [14]. Using a fuzzy adapting rate, the effort required for searching an optimal NE adapting rate can be avoided since the used fuzzy supervisor does not need any initialization parameter. ...
... Researchers had considered different strategies. Among them, we can cite the proposition of Neural emulators based on Real-Time Recurrecnt Learnning algorithm, Uncoupled multimodel emulators, emulators based on fuzzy logic... [12,14,22]. However, these strategies present some disadvantages which are mentioned previously. ...
... In order to demonstrate the effectiveness of the proposed PSONE strategy, a comparative study with the method based on fuzzy adapting rate for NE presented in [14], carried on. The obtained results with the fuzzy supervision of the adaptive rate are given in Fig. 9. ...
Searching an optimal value of the neural emulator adaptive rate presents a great problem. Indeed, a new scheme of neural emulators based on the Particle Swarm Optimization (PSO) algorithm for nonlinear systems is adopted in this paper. The main goal of this approach consists in adjusting effectively the neural emulator adaptive rate in order to accelerate the convergence speed and to improve the precision degree. The obtained results are compared with those reached with an intelligent tuning strategy. An experimental validation of the new emulator adaptation is carried on chemical reactor. Efficiency of the proposed method is proved according to the obtained performances.
... In Rhili et al. [15], [16], the authors have presented a fuzzy supervisor for neural emulator of nonlinear processes. The fuzzy logic is one possible solution to adjust the learning rate of neural emulator. ...
... We can observe that the neural emulator learning rate takes different values which guarantee the good precision and faster convergence. To demonstrate the importance of the designed NE, a comparative study with an existing approach using fuzzy supervision is given [15], [16]. The major drawback of fuzzy logic is the non possibilty of an optimal selection of the universes of discourse, membership functions, number of fuzzy sets, inference , and defuzzyfication method. ...
... The online neural emulation and control need an important computing load to obtain good performances. In order to overcome the neural emulation problem, authors proposed a fuzzy adapting rate for the neural emulator of nonlinear systems [15], [16]. The basic advantage of this approach is to avoid the effort required for searching optimal choice of the neural emulator adapting rate. ...
... Indeed, an intuitive and bad choice of the emulator term η e (t) can affect the open loop performance. So, to overcome this problem, we proposed in [15] a method which is using a neural emulator fuzzy adapting rate ( Figure 2). The mean value of the emulation error E(t) and its variation ∆Ē(t) are the supervisor inputs. ...
... In order to overcome the neural emulation problem, the authors proposed a fuzzy adapting rate for the neural emulator of nonlinear systems. 31 The basic advantage of this approach is to avoid the effort required for searching optimal choice of the neural emulator adapting rate. This type of fuzzy supervisor does not require any initialization parameter. ...
... So, to overcome this problem, the authors have proposed a method which is based on a fuzzy adapting rate for the neural emulator. 31 Then, a fuzzy supervisor is considered for the online adjustment of h e (t) ( Figure 4). ...
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 ensure stability and faster convergence, a neural controller adapting rate is established in the sense of the continuous Lyapunov stability method. Numerical simulations are included to illustrate the effectiveness of the proposed method. The performance of the proposed control strategy is also demonstrated through an experimental simulation.
... In order to overcome this limitation, an adapting rate for Neural Emulator (NE) is proposed in [14] based on fuzzy logic. This strategy is based on online adjustment of the emulator adaptive rate by using a fuzzy supervisor. ...
... By minimizing a cost function generated by error obtained between the real process and the NE output, the adjustment constraints of the learning rate for neural emulator are derived to guarantee precision and faster convergence in system emulation area. Efficiency of the developed learning rate for NE is illustrated by two exemples of nonlinear systems simulations and compared with previous work [14]. ...
... Let consider, firstly, a SISO nonlinear system (18) [4], [13], [14]: ...
... It used the gradient back-propagation learning algorithm in real time. The use of the RTRL for real-time applications was one of the advantages [12]- [14]. ...
... Indeed, the open-loop performance depend on the intuitive and the non systematic choice of the emulator parameter. We presented in [12], to overcome this problem, the use of fuzzy adaptive parameter of neural emulator for SISO nonlinear processes. The applying of the fuzzy adaptive parameter facilitate the search of the optimal choice of the neural emulator adaptive parameter. ...
This paper proposes an indirect adaptive control method based on recurrent neural networks. To achieve satisfactory closed-loop performances, a neural emulator (NE) and a neural controller (NC) adapting rates are established using the multiobjective particle swarm optimization (MOPSO) algorithm. The proposed MOPSO algorithm has been designed to minimize, simultaneously, two separated objective functions: the emulation and the tracking errors. The proposed approach guarantees that the NE tracks the system dynamics within a short time window. Consequently, it provides for the suggested control structure useful information to synthesize optimal adaptive rates of the NE and NC. To validate the effectiveness of the proposed MOPSO algorithm, a numerical example and an experimental validation on a chemical reactor are proposed.
In this paper, a stability analysis strategy of nonlinear control systems is proposed. An adaptive neural control scheme composed of an emulator, and a controller with decoupled adaptive rates is considered. A Lyapunov function based on tracking error dynamic is retained and an online adjusting technique of the neural controller adaptive rate is adopted to improve the closed loop performance in terms of stability, rapidity and precision. Comparative studies and an experimental validation on a semi-batch reactor are realized to prove the efficiency of the developed strategy.
