Abstract
In general, structure of a system to be identified is unknown for users a priori. This makes the model complex and high order structure. In this paper, we introduce the asymptotic method (ASYM) to deal with the problem. ASYM calculates a high-order model using the well-known least squares method, then reduces the identified model to a simple one. For this model reduction, various model reduction techniques such as balanced realization and output error reduction were developed. In this paper, a new method to reduce the high-order model using the particle swarm optimization in the frequency domain is proposed. Effectiveness of the proposed method is examined through numerical examples.
| Original language | English |
|---|---|
| Title of host publication | ICCAS-SICE 2009 - ICROS-SICE International Joint Conference 2009, Proceedings |
| Pages | 4499-4502 |
| Number of pages | 4 |
| Publication status | Published - 2009 |
| Event | ICROS-SICE International Joint Conference 2009, ICCAS-SICE 2009 - Fukuoka, Japan Duration: 2009 Aug 18 → 2009 Aug 21 |
Other
| Other | ICROS-SICE International Joint Conference 2009, ICCAS-SICE 2009 |
|---|---|
| Country | Japan |
| City | Fukuoka |
| Period | 09/8/18 → 09/8/21 |
Fingerprint
Keywords
- Asymptotic method
- Curve fitting
- High-order estimation
- Model reduction
- Particle swarm optimization
- System identification
ASJC Scopus subject areas
- Information Systems
- Control and Systems Engineering
- Industrial and Manufacturing Engineering
Cite this
Asymptotic system identification method based on particle swarm optimization. / Muroi, Hideo; Adachi, Shuichi.
ICCAS-SICE 2009 - ICROS-SICE International Joint Conference 2009, Proceedings. 2009. p. 4499-4502 5333057.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Asymptotic system identification method based on particle swarm optimization
AU - Muroi, Hideo
AU - Adachi, Shuichi
PY - 2009
Y1 - 2009
N2 - In general, structure of a system to be identified is unknown for users a priori. This makes the model complex and high order structure. In this paper, we introduce the asymptotic method (ASYM) to deal with the problem. ASYM calculates a high-order model using the well-known least squares method, then reduces the identified model to a simple one. For this model reduction, various model reduction techniques such as balanced realization and output error reduction were developed. In this paper, a new method to reduce the high-order model using the particle swarm optimization in the frequency domain is proposed. Effectiveness of the proposed method is examined through numerical examples.
AB - In general, structure of a system to be identified is unknown for users a priori. This makes the model complex and high order structure. In this paper, we introduce the asymptotic method (ASYM) to deal with the problem. ASYM calculates a high-order model using the well-known least squares method, then reduces the identified model to a simple one. For this model reduction, various model reduction techniques such as balanced realization and output error reduction were developed. In this paper, a new method to reduce the high-order model using the particle swarm optimization in the frequency domain is proposed. Effectiveness of the proposed method is examined through numerical examples.
KW - Asymptotic method
KW - Curve fitting
KW - High-order estimation
KW - Model reduction
KW - Particle swarm optimization
KW - System identification
UR - http://www.scopus.com/inward/record.url?scp=77951142581&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=77951142581&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:77951142581
SN - 9784907764333
SP - 4499
EP - 4502
BT - ICCAS-SICE 2009 - ICROS-SICE International Joint Conference 2009, Proceedings
ER -