System identification

About: System identification is a research topic. Over the lifetime, 21291 publications have been published within this topic receiving 439142 citations.

A signal processing framework based on dynamic neural networks with application to problems in adaptation, filtering, and classification

Abstract: We present a coherent neural net based framework for solving various signal processing problems. It relies on the assertion that time-lagged recurrent networks possess the necessary representational capabilities to act as universal approximators of nonlinear dynamical systems. This applies to system identification, time-series prediction, nonlinear filtering, adaptive filtering, and temporal pattern classification. We address the development of models of nonlinear dynamical systems, in the form of time-lagged recurrent neural nets, which can be used without further training. We employ a weight update procedure based on the extended Kalman filter (EKF). Against the tendency for a net to forget earlier learning as it processes new examples, we develop a technique called multistream training. We demonstrate our framework by applying it to 4 problems. First, we show that a single time-lagged recurrent net can be trained to produce excellent one-time-step predictions for two different time series and also to be robust to severe errors in the input sequence. Second, we model stably a complex system containing significant process noise. The remaining two problems are drawn from real-world automotive applications. One involves input-output modeling of the dynamic behavior of a catalyst-sensor system which is exposed to an operating engine's exhaust stream, the other the real-time and continuous detection of engine misfire.

Combined Design of Disturbance Model and Observer for Offset-Free Model Predictive Control

Abstract: This note presents a method for the combined design of an integrating disturbance model and of the observer (for the augmented system) to be used in offset-free model predictive controllers. A dynamic observer is designed for the original (nonaugmented) system by solving an Hprop control problem aimed at minimizing the effect of unmeasured disturbances and plant/model mismatch on the output prediction error. It is shown that, when offset-free control is sought, the dynamic observer is equivalent to choosing an integrating disturbance model and an observer for the augmented system. An example of a chemical reactor shows the main features and benefits of the proposed method.

Integrated System Identification and State-of-Charge Estimation of Battery Systems

Abstract: Accurate estimation of the state of charge in battery systems is of essential importance for battery system management. Due to nonlinearity, high sensitivity of the inverse mapping from external measurements, and measurement errors, SOC estimation has remained a challenging task. This is further compounded by the fact that battery characteristic model parameters change with time and operating conditions. This paper introduces an adaptive nonlinear observer design that compensates nonlinearity and achieves better estimation accuracy. A two-time-scale signal processing method is employed to attenuate the effects of measurement noises on SOC estimates. The results are further expanded to derive an integrated algorithm to identify model parameters and initial SOC jointly. Simulations were performed to illustrate the capability and utility of the algorithms. Experimental verifications are conducted on Li-ion battery packs of different capacities under different load profiles.

Optimum approximation for residual stiffness in linear system identification

Abstract: A new method of system identification uti 1 i zes projector m atrix theory and the MoorePenrose generalized inverse to derive an analytical stiffness matrix which, when combined with the analytical mass matrix, will more closely p redict modal test results. Weighting matrices a re used to enforce connectivity and make weighted corrections to the original analytical stiffness matrix. A simple and straightforward mathematical formulation is obtained. The method is compared and contrasted with other methods found in the literature, and a simple numerical example is presented.