Auxiliary model multiinnovation stochastic gradient parameter estimation methods for nonlinear sandwich systems

Abstract

This article studies the identification problem of the nonlinear sandwich systems. For the sandwich system, because there are inner variables which cannot be measured in the information vector of the identification models, it is difficult to identify the nonlinear sandwich systems. In order to overcome the difficulty, an auxiliary model is built to predict the estimates of inner variables by means of the output of the auxiliary model. For the purpose of employing the real-time observed data, a cost function with dynamical data is constructed to capture on-line information of the nonlinear sandwich system. On this basis, an auxiliary model stochastic gradient identification approach is proposed based on the gradient optimization. Moreover, an auxiliary model multiinnovation stochastic gradient estimation method is developed, which tends to enhance estimation accuracy by introducing more observed data dynamically. The numerical simulation is provided and the simulation results show that the proposed auxiliary model identification method is effective for the nonlinear sandwich systems.

Fault Detection and Identification Method for Quadcopter Based on Airframe Vibration Signals

“…Additionally, more fault modes, such as sensor fault, are expected to be incorporated into the established model. The proposed method in this paper can combine the iterative schemes [ 48 , 49 , 50 , 51 , 52 , 53 ] and recursive schemes [ 54 , 55 , 56 , 57 , 58 , 59 , 60 , 61 , 62 ] to study the parameter identification problems of linear and nonlinear stochastic systems with colored noises [ 63 , 64 , 65 , 66 , 67 , 68 , 69 , 70 , 71 ] and to present highly efficient fault detection methods that can also be applied to the literature.…”

Recursive least squares estimation methods for a class of nonlinear systems based on non‐uniform sampling

“…Remark Differently from the methods in Reference 89, this article focuses on the Hammerstein‐Wiener nonlinear system rather than the Hammerstein nonlinear system. In addition, to enhance the computational efficiency of the auxiliary model‐based recursive least‐squares algorithm, this article uses the hierarchical identification principle to decompose the Hammerstein‐Wiener system into four sub‐systems and to estimate the parameters of the four sub‐systems, respectively.…”

Iterative parameter and order identification for fractional‐order nonlinear finite impulse response systems using the key term separation

“…The multiinnovation identification theory is an important branch of the system identification 35‐38 . The innovation is the useful information to improve the parameter estimation accuracy 39‐42 .…”