An efficient recursive identification algorithm for multilinear systems based on tensor decomposition

2021 ◽  
Author(s):  
Yanjiao Wang ◽  
Ling Yang
Keyword(s):  
Tensor Decomposition ◽  
Recursive Identification ◽  
Identification Algorithm

scholarly journals Nonsmooth Recursive Identification of Sandwich Systems with Backlash-Like Hysteresis

2012 ◽  
Vol 2012 ◽  
pp. 1-16 ◽  
Author(s):  
Ruili Dong ◽  
Yonghong Tan ◽  
Hui Chen ◽  
Yangqiu Xie
Keyword(s):  
Estimation Algorithm ◽  
Dynamic Parameter ◽  
Bundle Method ◽  
Recursive Identification ◽  
Identification Algorithm ◽  
Nonsmooth Problem ◽  
Positioning Stage ◽  
Dynamic Parameter Estimation ◽  
Estimation Scheme ◽  
Sandwich System

A recursive gradient identification algorithm based on the bundle method for sandwich systems with backlash-like hysteresis is presented in this paper. In this method, a dynamic parameter estimation scheme based on a subgradient is developed to handle the nonsmooth problem caused by the backlash embedded in the system. The search direction of the algorithm is estimated based on the so-called bundle method. Then, the convergence of the algorithm is discussed. After that, simulation results on a nonsmooth sandwich system are presented to validate the proposed estimation algorithm. Finally, the application of the proposed method to anX-Ymoving positioning stage is illustrated.

Developing data fusion and recursive estimation methods for online identification of dive plane dynamics of an autonomous underwater vehicle

2019 ◽  
Vol 234 (2) ◽  
pp. 520-533
Author(s):  
Seid Farhad Abtahi ◽  
Mohammad Mehdi Alishahi ◽  
Ehsan Azadi Yazdi
Keyword(s):  
Autonomous Underwater Vehicle ◽  
Unscented Kalman Filter ◽  
Underwater Vehicle ◽  
Recursive Estimation ◽  
High Rate ◽  
Pole Placement ◽  
Estimation Methods ◽  
Recursive Identification ◽  
Identification Algorithm ◽  
Hydrodynamic Coefficients

The purpose of this article is to develop an online method to identify the hydrodynamic coefficients of pitch plane of an autonomous underwater vehicle. To obtain necessary data for the identification, the dive plane dynamics should be excited through diving maneuvers. Hence, a controller is needed whose performance and stability are appropriate. To design such a controller, first, hydrodynamic coefficients are approximated using semi-empirical methods. Based on these approximated coefficients, a classic controller is designed at the next step. Since the estimation of these coefficients is uncertain, µ-analysis is employed to verify the robustness of stability and performance of the controller. Using the verified robust controller, some oscillating maneuvers are carried out that excite the dive plane dynamics. Using sensor fusion and unscented Kalman filter, smooth and high-rate data of depth is provided for the depth controller. A recursive identification algorithm is developed to identify the hydrodynamic coefficients of heave and pitch motions. It turns out that some inputs required by the identification are not measured directly by the sensors. But the devised fusion algorithm is able to provide the necessary data for identification. Finally, using the identified coefficients and employing pole placement method, a new controller with better performance is synthesized online. To evaluate the performance of the identification and fusion algorithms, a 6-degree-of-freedom simulation of an autonomous underwater vehicle is carried out.

Recursive identification algorithm for parity space based fault detection systems

2009 ◽  
Vol 42 (8) ◽  
pp. 312-317
Author(s):  
Amol S. Naik ◽  
Shen Yin ◽  
Steven X. Ding ◽  
Torsten Jeinsch
Keyword(s):  
Fault Detection ◽  
Recursive Identification ◽  
Identification Algorithm ◽  
Detection Systems ◽  
Parity Space
Sign in / Sign up

Export Citation Format

Share Document