Wyniki wyszukiwania - BazTech

1

Model parameter on-line identification with nonlinear parametrization – manipulator model

Cedro Leszek

Technical Transactions

|

2022

|

Vol. 119, iss. 1

art. no. e2022007

EN

This paper presents an example of solving the parameter identification problem in the case of a robot with two degrees of freedom. In this study, a weighted recursive least squares algorithm was generalised to a case of nonlinear parameterisation in which the identified parameters did not satisfy the linear model. The generalisation involved linearising the model in the neighbourhood of current values of the parameter estimates. It was assumed that the estimates were updated every N steps of signal sampling. This method of identification can be applied whenever the parameters concerning a model need to be determined at the time of measurement. This is particularly useful in adaptive control when the plant parameters vary over time.

2

The identification method of the coal mill motor power model with the use of machine learning techniques

Łabęda-Grudziak Zofia Magdalena, Lipiński Mariusz

Bulletin of the Polish Academy of Sciences. Technical Sciences

|

2021

|

Vol. 69, nr 1

art. no. e135842

EN

The article presents an identification method of the model of the ball-and-race coal mill motor power signal with the use of machine learning techniques. The stages of preparing training data for model parameters identification purposes are described, as well as these aimed at verifying the quality of the evaluated model. In order to meet the tasks of machine learning, additive regression model was applied. Identification of the additive model parameters was performed on the basis of iterative backfitting algorithm combined with nonparametric estimation techniques. The proposed models have predictive nature and are aimed at simulation of the motor power signal of a coal mill during its regular operation, startup and shutdown. A comparative analysis has been performed of the models structured differently in terms of identification quality and sensitivity to the existence of an exemplary disturbance in the form of overhangs in the coal bunker. Tests carried out on the basis of real measuring data registered in the Polish power unit with a capacity of 200 MW confirm the effectiveness of the method.

3

New methods for the identification of nonlinear model structures based upon genetic programming techniques

Winkler S., Affenzeller M., Wagner S.

Systems Science

|

2005

|

Vol. 31, no 1

5-13

EN

Identifying nonlinear model structures as a part of analyzing a physical system means trying to generate an algebraic expression as a part of an equation that describes the physical representation of a dynamic system. Many existing system identification methods are based on parameter identification. In this paper, we describe a method using genetic programming to evolve an algebraic representation of measured input-output response data. The main advantage of the presented approach is that unlike many other identification methods, it does not restrict the set of models that can be identified but can be applied to any kind of data sets representing a system's observed or simulated input and output signals. This paper describes research that was done for the project "Specification, Design and Implementation of a Genetic Programming Approach for Identifying Nonlinear Models of Mechatronic Systems". The goal of the project is to find models for mechatronic systems; our task was to examine whether the methods of Genetic Programming are suitable for determining the structures of physical systems by analyzing a system's measured behaviour or not.