Structured model identification algorithm based on constrained optimisation

Background: Despite the recent advancements in the modeling of glycemic dynamics for type 1 diabetes mellitus, automatically considering unannounced meals and exercise without manual user inputs remains challenging. Method: An adaptive model identification technique that incorporates exercise information and estimates of the effects of unannounced meals obtained automatically without user input is proposed in this work. The effects of the unknown consumed carbohydrates are estimated using an individualized unscented Kalman filtering algorithm employing an augmented glucose-insulin dynamic model, and exercise information is acquired from noninvasive physiological measurements. The additional information on meals and exercise is incorporated with personalized estimates of plasma insulin concentration and glucose measurement data in an adaptive model identification algorithm. Results: The efficacy of the proposed personalized and adaptive modeling algorithm is demonstrated using clinical data involving closed-loop experiments of the artificial pancreas system, and the results demonstrate accurate glycemic modeling with the average root-mean-square error (mean absolute error) of 25.50 mg/dL (18.18 mg/dL) for six-step (30 minutes ahead) predictions. Conclusions: The approach presented is able to identify reliable time-varying individualized glucose-insulin models.

Download Full-text

A New Integrated Algorithm of Structure Determination and Parameter Estimation for Nonlinear Systems Identification

Volume 7B: 17th Biennial Conference on Mechanical Vibration and Noise ◽

10.1115/detc99/vib-8393 ◽

1999 ◽

Author(s):

Wang Xiao Wang ◽

Jianyin Xie

Keyword(s):

Parameter Estimation ◽

Nonlinear Systems ◽

Structure Determination ◽

Model Identification ◽

Identification Algorithm ◽

Householder Transformation ◽

Systems Identification ◽

Value Decomposition ◽

Svd Method ◽

Nonlinear Systems Identification

Abstract A new integrated algorithm of structure determination and parameter estimation is proposed for nonlinear systems identification in this paper, which is based on the Householder Transformation (HT), Givens and Modified Gram-Schmidt (MGS) algorithms. While being used for the polynomial and rational NARMAX model identification, it can select the model terms while deleting the unimportant ones from the assumed full model, avoiding the storage difficulty as the CGS identification algorithm does which is proposed by Billings et. al., and is numerically more stable. Combining the H algorithm with the modified bidiagonalization least squares (MBLS) algorithm and the singular value decomposition (SVD) method respectively, two algorithms referred to as the MBLSHT and SVDHT ones are proposed for the polynomial and rational NARMAX model identification. They are all numerically more stable than the HT or Givens or MGS algorithm given in this paper, and the MBLSHT algorithm has the best performance. A higher precision for the parameter estimation can thus be obtained by them, as supported b simulation results.

Download Full-text

Dynamic Model Identification for 6-DOF Industrial Robots

Journal of Robotics ◽

10.1155/2015/471478 ◽

2015 ◽

Vol 2015 ◽

pp. 1-9 ◽

Cited By ~ 12

Author(s):

Li Ding ◽

Hongtao Wu ◽

Yu Yao ◽

Yuxuan Yang

Keyword(s):

Robot Manipulator ◽

Industrial Robot ◽

Model Identification ◽

Friction Model ◽

Industrial Robots ◽

Parameters Identification ◽

Identification Algorithm ◽

Unknown Parameters ◽

Joint Friction ◽

Dynamical Parameters

A complete and systematic procedure for the dynamical parameters identification of industrial robot manipulator is presented. The system model of robot including joint friction model is linear with respect to the dynamical parameters. Identification experiments are carried out for a 6-degree-of-freedom (DOF) ER-16 robot. Relevant data is sampled while the robot is tracking optimal trajectories that excite the system. The artificial bee colony algorithm is introduced to estimate the unknown parameters. And we validate the dynamical model according to torque prediction accuracy. All the results are presented to demonstrate the efficiency of our proposed identification algorithm and the accuracy of the identified robot model.

Download Full-text

Recursive Subspace Identification Algorithm using the Propagator Based Method

Indonesian Journal of Electrical Engineering and Computer Science ◽

10.11591/ijeecs.v6.i1.pp172-179 ◽

2017 ◽

Vol 6 (1) ◽

pp. 172 ◽

Cited By ~ 2

Author(s):

Irma Wani Jamaludin Wani Jamaludin ◽

Norhaliza Abdul Wahab

Keyword(s):

State Space ◽

Model Identification ◽

Industrial Applications ◽

Dynamic State ◽

Subspace Identification ◽

Identification Algorithm ◽

Online Application ◽

Subspace Algorithms ◽

State Space System ◽

Value Decomposition

<p>Subspace model identification (SMI) method is the effective method in identifying dynamic state space linear multivariable systems and it can be obtained directly from the input and output data. Basically, subspace identifications are based on algorithms from numerical algebras which are the QR decomposition and Singular Value Decomposition (SVD). In industrial applications, it is essential to have online recursive subspace algorithms for model identification where the parameters can vary in time. However, because of the SVD computational complexity that involved in the algorithm, the classical SMI algorithms are not suitable for online application. Hence, it is essential to discover the alternative algorithms in order to apply the concept of subspace identification recursively. In this paper, the recursive subspace identification algorithm based on the propagator method which avoids the SVD computation is proposed. The output from Numerical Subspace State Space System Identification (N4SID) and Multivariable Output Error State Space (MOESP) methods are also included in this paper.</p>

Download Full-text

Fault diagnosis for flight control systems using subspace method and adaptive two-stage Kalman filter

Transactions of the Institute of Measurement and Control ◽

10.1177/0142331215596805 ◽

2016 ◽

Vol 38 (12) ◽

pp. 1480-1490 ◽

Cited By ~ 3

Author(s):

Jianchen Wang ◽

Xiaohui Qi

Keyword(s):

Kalman Filter ◽

Fault Diagnosis ◽

Control Systems ◽

Linear Model ◽

Flight Control ◽

Model Identification ◽

Identification Algorithm ◽

Actuator Fault ◽

Two Stage ◽

Non Linear

Model-based fault diagnosis has attracted considerable attention from researchers and developers of flight control systems, thanks to its hardware simplicity and cost-effectiveness. However, the airplane model, which is adopted commonly in fault diagnosis, only exists theoretically and is linearized in approximation. For this reason, uncertainties such as system non-linearity and subjectivity will degrade the fault diagnosis results. In this paper, we propose a novel actuator fault diagnosis scheme for flight control systems based on model identification techniques. With this scheme, system identification can be achieved with a linear model that uses a closed-loop subspace model identification algorithm, and a non-linear model that uses an extended state observer and neural networks. On this basis, the current actuator fault is estimated using an adaptive two-stage Kalman filter. Finally, the non-linear six-degree-of-freedom model of a B747 airplane is simulated in the Matlab/Simulink environment, where the effectiveness of the proposed scheme is verified from fault diagnosis tests.

Download Full-text

Multi-Rate Generalized Predictive Control for Multi-Variable Systems

Proceedings of the Institution of Mechanical Engineers Part I Journal of Systems and Control Engineering ◽

10.1243/pime_proc_1993_207_347_02 ◽

1993 ◽

Vol 207 (4) ◽

pp. 253-260

Author(s):

I O Park ◽

J H Oh

Keyword(s):

Process Control ◽

Predictive Control ◽

Control Algorithm ◽

Model Identification ◽

Measurement Noise ◽

Noise Model ◽

Generalized Predictive Control ◽

Identification Algorithm ◽

Stochastic Framework ◽

And Control

The purpose of this paper is to drive the adaptive multi-rate generalized predictive control for multi-variable systems in a stochastic framework. Modelling disturbances as white noise is inadequate for process control because most disturbances encountered in process control are coloured or non-stationary in nature. For that reason a stochastic parallel model identification algorithm for a multi-rate-sampled system is proposed. No attempt is made to identify the noise model. Hence the algorithm is applicable to any measurement noise case. The measurement noise can be arbitrary (for example coloured or non-stationary noise), except for the assumption that it and control inputs are stochastically uncorrelated. Then the control algorithm based on the generalized predictive control is proposed. In order to demonstrate the effectiveness of the proposed control algorithm a simulation study is carried out. The closed-loop performances are excellent.

Download Full-text