Uncertain nonlinear system identification using Jaya-based adaptive neural network
- PDF / 1,159,539 Bytes
- 10 Pages / 595.276 x 790.866 pts Page_size
- 31 Downloads / 207 Views
(0123456789().,-volV)(0123456789(). ,- volV)
METHODOLOGIES AND APPLICATION
Uncertain nonlinear system identification using Jaya-based adaptive neural network Nguyen Ngoc Son1 • Tran Minh Chinh1 • Ho Pham Huy Anh2
Ó Springer-Verlag GmbH Germany, part of Springer Nature 2020
Abstract The piezoelectric actuator has been receiving tremendous interest in the past decade, due to its broad applications in areas of micro-robotics, neurosurgical robot, MEMS, exoskeleton, medical applications, and other applications. However, the hysteresis nonlinearity widely existing in smart materials yields undesirable responses, which make the hysteresis control problem even more challenging. Therefore, many studies based on artificial neural networks have been developed to cope with the hysteresis nonlinearity. However, the back-propagation algorithm which is popular in training a neural network model often performs local optima with stagnation and slow convergence speed. To overcome these drawbacks, this paper proposes a new training algorithm based on the Jaya algorithm to optimize the weights of the neural NARX model (called Jaya-NNARX). The performance and efficiency of the proposed method are tested on identifying two typical nonlinear benchmark test functions and are compared with those of a classical BP algorithm, particle swarm optimization algorithm, and differential evolution algorithm. Forwardly, the proposed Jaya-NNARX method is applied to identify the nonlinear hysteresis behavior of the piezoelectric actuator. The identification results demonstrate that the proposed algorithm can successfully identify the highly uncertain nonlinear system with perfect precision. Keywords Neural nonlinear auto-regressive exogenous (NNARX) model Jaya algorithm Nonlinear system identification Piezoelectric actuator Nonlinear benchmark test function
1 Introduction Micro-positioning stages using a piezoelectric (PZT) actuator are widely used in a variety of applications such as microgripper (Nah and Zhong 2007), MEMs (Nguyen et al. 2018a, b), micro-robotics (Mu et al. 2019) and microscopy (Kariya et al. 2019) because of a higher displacement accuracy, larger generation force and higher response speed. However, the nonlinearities hysteresis behavior of the piezoelectric actuator can greatly degrade the positioning accuracy of micro-positioning systems. To cancel out the hysteresis behavior, there are existed different
Communicated by V. Loia. & Ho Pham Huy Anh [email protected] 1
Faculty of Electronics Technology, Industrial University of Ho Chi Minh City, Ho Chi Minh City, Vietnam
2
FEEE, HCM City University of Technology - VNU HCM, Ho Chi Minh City, Vietnam
models for describing the characteristic of hysteresis based on phenomenological or mathematical analysis, gray-box and black-box modeling approaches. The kind of models based on phenomenological or mathematical analysis approach were considered such as Preisach model (Iyer et al. 2005), Krasnosel’skii-Pokrovskii (KP) model (Xu and Zhou 2017), Prandtl–Ishlinskii (PI) op
Data Loading...
