Modelling of a Flexible Manoeuvring System Using ANFIS Techniques

Aldebrez

Proceedings of the Institution of Mechanical Engineers, Part G:

et al. 2012

This article addresses the input tracking control problem of a highly nonlinear flexible system namely a twin-rotor multi-input multi-output system in the vertical plane motion. The twin-rotor multi-input multi-output system can be considered as an aerodynamic experimental model, representing the control challenges of complex air vehicles. A hybrid control scheme comprising a fuzzy proportional–derivative-like control and a conventional integrator is developed by adding the outputs of both control actions. To satisfy the tracking characteristics of the manoeuvring system, an efficient combination of the control actions is developed using a smooth nonlinear activation function which continuously regulates contribution of the integral term in the controller output. The effect of the activation function greatly reduces overshoots when the system is exposed to abrupt changes during its manoeuvre. The control system performance is tested in simulations and experimentally in real-time situations. Robustness and stability of the controller are also investigated. The obtained results prove the efficiency of the proposed scheme in terms of time-domain performance specifications of the system.

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Hybrid intelligent control for set-point tracking of a flexible manoeuvring system using sigmoid activation function

Aldebrez

Proceedings of the Institution of Mechanical Engineers, Part G:

et al. 2012

“…Various neuro-fuzzy control structures have been applied to helicopter models. ANFIS modelling for vertical motion of the TRMS has been reported in reference [31,32], where the effectiveness of ANFIS approaches in modelling the TRMS has been demonstrated. In reference [33], neuro-fuzzy-based fuzzy subtractive clustering method has been used to control the TRMS in both vertical and horizontal planes.…”

Section: Introductionmentioning

confidence: 99%

Dynamic modelling and control of a twin-rotor system using adaptive neuro-fuzzy inference system techniques

Proceedings of the Institution of Mechanical Engineers, Part G:

Tokhi

2011

This article presents an online non-linear dynamic modelling and control approach based on adaptive neuro-fuzzy inference system (ANFIS) for a twin-rotor multi-input multi-output system (TRMS), in the vertical plane motion. The TRMS can be considered as a flexible aerodynamic test rig that resembles the behaviour of a helicopter. The TRMS and similar manoeuvring systems are often subjected to random disturbances arising from various sources such as driving motors and external environmental sources. For such highly non-linear systems with varying operating conditions, adaptive control approaches are suitable tools to cope with plant uncertainties. An inverse-model control of the TRMS is developed using online ANFIS learning algorithm. The consequent and antecedent parameters of a Takagi–Sugeno fuzzy inference system are optimized online using recursive least squares and gradient descent algorithms, respectively. In order to reduce the computation complexity, the training process is minimized based on global system error tolerance. The optimal initialization of the ANFIS parameters is achieved through an off-line training process. The developed strategy is compared to other control laws in terms of tracking performance, disturbance rejection, and response to external noise. The obtained simulation results demonstrate the efficiency of the online inverse control scheme.

“…Therefore, adaptive control approaches are preferred for highly nonlinear systems such as flexible manoeuvring systems [1].…”

Section: Introductionmentioning

confidence: 99%

“…ANFIS modelling for vertical motion of the TRMS has been reported in [1,3], where the effectiveness of ANFIS approaches in modelling the TRMS has been demonstrated. In [4] Neuro-fuzzy based fuzzy subtractive clustering method has been used to control the TRMS in both vertical and horizontal planes.…”

Section: Introductionmentioning

confidence: 99%

An on-line approach for ANFIS modelling and control of a flexible manoeuvring system

Mohamad

2011 IEEE International Conference on Mechatronics

et al. 2011

Self Cite

This paper presents an on-line nonlinear dynamic modelling and control approach based on adaptive neuro-fuzzy inference system (ANFIS) for a twin rotor multi-input multi output system (TRMS), in the vertical plane motion. The TRMS can be considered as a flexible aerodynamic test rig that resembles the behaviour of a helicopter in hovering mode. The TRMS and similar manoeuvring systems are often subjected to random disturbances arising from various sources such as driving motors and external environmental sources. For such highly nonlinear systems with varying operating conditions, adaptive control approaches are suitable tools to cope with plant uncertainties. A model inverse control of the TRMS is developed using on-line ANFIS learning algorithm. The consequent and antecedent parameters of a fI rst order Takagi-Sugeno fuzzy inference system are optimised on-line using recursive least squares and gradient descent algorithms, respectively. The optimal initialization of the ANFIS parameters is achieved through an off-line training process. The developed strategy is compared to other control laws in terms of tracking performance and disturbance rejection. The obtained simulation results demonstrate the efficiency of the on-line control scheme.