An Extended Linearized Neural State Space Based Modeling and Control

نویسندگان

  • Qing WU
  • Yongji WANG
  • Hong WANG
چکیده

In this paper, an extended linearized neural state space (ELNSS) topology is proposed, where an ELNSS based modeling and cont rol strategy for a class of nonlinear systems is presented. In terms of the modeling, the extended Kalman filter (EKF) algorithm is used to train the parameters inside the ELNSS model, where a high order correlation method is applied to validate the estimated model. This is then followed by the design of a one-step-ahead predictive controller for affine nonlinear systems. The stability of the so-formed closed loop control system is investigated, and several sufficient conditions that guarantee the local asymptotic stability are established. Two simulation examples are used to demonstrate the proposed algorithm and desired results have been obtained. Copyright © 2002 IFAC

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Modeling of Nanofiltration for ‎Concentrated Electrolyte Solutions using ‎Linearized Transport Pore Model

   In this study, linearized transport pore model (LTPM) is applied for modeling nanofiltration (NF) membrane separation process. This modeling approach is based on the modified extended Nernst-Planck equation enhanced by Debye-Huckel theory to take into account the variations of activity coefficient especially at high salt concentrations. Rejection of single-salt (NaCl) electrolyte is inve...

متن کامل

Dynamic Analysis of Multi-Directional Functionally Graded Panels and Comparative Modeling by ANN

In this paper dynamic analysis of multi-directional functionally graded panel is studied using a semi-analytical numerical method entitled the state-space based differential method (SSDQM) and comparative behavior modeling by artificial neural network (ANN) for different parameters. A semi-analytical approach which makes use the three-dimensional elastic theory and assuming the material propert...

متن کامل

Modeling of Nonlinear Systems with Friction Structure Using Multivariable Taylor Series Expansion

The major aim of this article is modeling of nonlinear systems with friction structure that, thismethod is essentially extended based on taylore expansion polynomial. So in this study, thetaylore expansion was extended in the generalized form for the differential equations of the statespaceform. The proposed structure is based on multi independent variables taylore extended.According to the pro...

متن کامل

Development of an in-cylinder processes model of a CVVT gasoline engine using artificial neural network

Today, employing model based design approach in powertrain development is being paid more attention. Precise, meanwhile fast to run models are required for applying model based techniques in powertrain control design and engine calibration. In this paper, an in-cylinder process model of a CVVT gasoline engine is developed to be employed in extended mean valve control oriented model and also mod...

متن کامل

Time Delay and Data Dropout Compensation in Networked Control Systems Using Extended Kalman Filter

In networked control systems, time delay and data dropout can degrade the performance of the control system and even destabilize the system. In the present paper, the Extended Kalman filter is employed to compensate the effects of time delay and data dropout in feedforward and feedback paths of networked control systems. In the proposed method, the extended Kalman filter is used as an observer ...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2002