Abstract
This paper is concerned with the identification of linear parameter varying (LPV) systems by utilizing a multimodel structure. To improve the approximation capability of the LPV model, asymmetric Gaussian weighting functions are introduced and compared with commonly used symmetric Gaussian functions. By this mean, locations of operating points can be selected freely. It has been demonstrated through simulations with a high purity distillation column that the identified models provide more satisfactory approximation. Moreover, an experiment is performed on real HVAC (heating, ventilation, and air-conditioning) to further validate the effectiveness of the proposed approach.
Highlights
In nonlinear system identification, numerous black box modeling structures have been developed in pieces of literature
Block-oriented nonlinear models such as Hammerstein models and Wiener models consisting of linear time invariant (LTI) dynamics and static nonlinearities have been studied widely
Subspace approaches are studied by Verdult and Verhaegen [3, 4] and Felici et al [5]; orthonormal basis related functions are used by Toth et al [6]; transfer function linear parameter varying (LPV) models are discussed by Bamieh and Giarre [7], Previdi and Lovera [8], Wei [9], Butcher et al [10], and Laurain et al [1]
Summary
Numerous black box modeling structures have been developed in pieces of literature. The input excitation signal for this representation results in too much upset, which can be costly or even unrealistic in practice [13] To circumvent these difficulties, Zhu and Xu [12] proposed a multimodel LPV model based on Journal of Applied Mathematics blended linear models. This paper aims at improving the performance in identifying multimodel LPV models by adopting the asymmetric Gaussian weighing function, such that multilocal models can be smoothly interpolated to approximate the global dynamical behaviors of the process. This means that the locations of the operating points can be freely selected.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
