Abstract
An identification method is presented to deal with practical identification difficulties often encountered in plant testing, such as unsteady initial states and unknown load disturbances. A linear regression equation for step testing is first derived via integrating the differential system equation multiple times. A rectangular-pulse input is then considered as a combination of two step inputs. Based on the pulse response, the so-called two-stage least-squares algorithm is developed to overcome those identification difficulties and yield accurate estimates of the model parameters in a sequential manner. The method provides a convenient way to estimate the delay along with other model parameters. Furthermore, it is robust with respect to noise and model structure mismatch.
Original language | English |
---|---|
Article number | 412-116 |
Pages (from-to) | 79-84 |
Number of pages | 6 |
Journal | Proceedings of the IASTED International Conference on Modelling, Identification and Control |
Volume | 23 |
Publication status | Published - 2004 Dec 1 |
Event | Proceedings of the 23rd IASTED International Conference on Modelling, Identification, and Control - Grindelwald, Switzerland Duration: 2004 Feb 23 → 2004 Feb 25 |
All Science Journal Classification (ASJC) codes
- Software
- Modelling and Simulation
- Computer Science Applications