Abstract
The unbiased finite impulse response (UFIR) filter has strong engineering features for industrial applications, because it does not require the noise statistics and initial values. This filter minimizes the mean square error (MSE) on the optimal horizon of Nopt points and the real-time determination of <formula><tex>$N_\mathrm{opt}$</tex></formula> is an important issue. In this paper, a new strategy is proposed to adaptively estimate <formula><tex>$N_\mathrm{opt}$</tex></formula> in real time. A concept of the maximum allowed horizon is introduced referring to the fact that the current iteration with large horizon contains data from the previous iterations with small horizons. That allows selecting the target horizon in a single cycle of iterations and design the adaptive-horizon UFIR (AUFIR) filter. The proposed AUFIR filter is tested by a rotary pendulum system and a three degree-of-freedom helicopter system. Higher accuracy and robustness of the AUFIR filter are demonstrated in a comparison with the Kalman filter (KF), adaptive KF, and UFIR filter.
| Original language | English |
|---|---|
| Journal | IEEE Transactions on Industrial Electronics |
| DOIs | |
| Publication status | Accepted/In press - 2017 Dec 15 |
Fingerprint
Keywords
- Covariance matrices
- Estimation
- Indexes
- Iterative algorithms
- Kalman filter
- Kalman filters
- mean square error
- Mean square error methods
- optimal horizon
- Robustness
- robustness
- Unbiased FIR filter
ASJC Scopus subject areas
- Control and Systems Engineering
- Electrical and Electronic Engineering
Cite this
Adaptive-Horizon Iterative UFIR Filtering Algorithm with Applications. / Zhao, Shunyi; Shmaliy, Yuriy S.; Ahn, Choon Ki; Liu, Fei.
In: IEEE Transactions on Industrial Electronics, 15.12.2017.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - Adaptive-Horizon Iterative UFIR Filtering Algorithm with Applications
AU - Zhao, Shunyi
AU - Shmaliy, Yuriy S.
AU - Ahn, Choon Ki
AU - Liu, Fei
PY - 2017/12/15
Y1 - 2017/12/15
N2 - The unbiased finite impulse response (UFIR) filter has strong engineering features for industrial applications, because it does not require the noise statistics and initial values. This filter minimizes the mean square error (MSE) on the optimal horizon of Nopt points and the real-time determination of $N_\mathrm{opt}$ is an important issue. In this paper, a new strategy is proposed to adaptively estimate $N_\mathrm{opt}$ in real time. A concept of the maximum allowed horizon is introduced referring to the fact that the current iteration with large horizon contains data from the previous iterations with small horizons. That allows selecting the target horizon in a single cycle of iterations and design the adaptive-horizon UFIR (AUFIR) filter. The proposed AUFIR filter is tested by a rotary pendulum system and a three degree-of-freedom helicopter system. Higher accuracy and robustness of the AUFIR filter are demonstrated in a comparison with the Kalman filter (KF), adaptive KF, and UFIR filter.
AB - The unbiased finite impulse response (UFIR) filter has strong engineering features for industrial applications, because it does not require the noise statistics and initial values. This filter minimizes the mean square error (MSE) on the optimal horizon of Nopt points and the real-time determination of $N_\mathrm{opt}$ is an important issue. In this paper, a new strategy is proposed to adaptively estimate $N_\mathrm{opt}$ in real time. A concept of the maximum allowed horizon is introduced referring to the fact that the current iteration with large horizon contains data from the previous iterations with small horizons. That allows selecting the target horizon in a single cycle of iterations and design the adaptive-horizon UFIR (AUFIR) filter. The proposed AUFIR filter is tested by a rotary pendulum system and a three degree-of-freedom helicopter system. Higher accuracy and robustness of the AUFIR filter are demonstrated in a comparison with the Kalman filter (KF), adaptive KF, and UFIR filter.
KW - Covariance matrices
KW - Estimation
KW - Indexes
KW - Iterative algorithms
KW - Kalman filter
KW - Kalman filters
KW - mean square error
KW - Mean square error methods
KW - optimal horizon
KW - Robustness
KW - robustness
KW - Unbiased FIR filter
UR - http://www.scopus.com/inward/record.url?scp=85039761474&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85039761474&partnerID=8YFLogxK
U2 - 10.1109/TIE.2017.2784405
DO - 10.1109/TIE.2017.2784405
M3 - Article
AN - SCOPUS:85039761474
JO - IEEE Transactions on Industrial Electronics
JF - IEEE Transactions on Industrial Electronics
SN - 0278-0046
ER -