2017
DOI: 10.1007/s11768-017-6003-7
|View full text |Cite
|
Sign up to set email alerts
|

Orthogonal projection based subspace identification against colored noise

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
5
0

Year Published

2019
2019
2024
2024

Publication Types

Select...
6

Relationship

2
4

Authors

Journals

citations
Cited by 9 publications
(5 citation statements)
references
References 21 publications
0
5
0
Order By: Relevance
“…The initial input parameters of the proposed algorithm are set as follows: the length of the past horizon is p = 10, the length of the future horizon is f = 10, and the number of total samples is N = 2000. In order to verify the effectiveness of the proposed algorithm further, several existing off-line subspace identification algorithms (MOESP [17], N4SID [18], 2ORT-SIM [19]) and the on-line subspace identification algorithm (OSIMPCA-E [24]) are introduced as the comparison. Here, the 1200 sets of sample data in the identification set are used for the relevant training.…”
Section: Identification Results and Validation Analysismentioning
confidence: 99%
See 2 more Smart Citations
“…The initial input parameters of the proposed algorithm are set as follows: the length of the past horizon is p = 10, the length of the future horizon is f = 10, and the number of total samples is N = 2000. In order to verify the effectiveness of the proposed algorithm further, several existing off-line subspace identification algorithms (MOESP [17], N4SID [18], 2ORT-SIM [19]) and the on-line subspace identification algorithm (OSIMPCA-E [24]) are introduced as the comparison. Here, the 1200 sets of sample data in the identification set are used for the relevant training.…”
Section: Identification Results and Validation Analysismentioning
confidence: 99%
“…Here, the proof of Equation ( 15) can be found in reference [19] and the relevant contents are omitted here for brevity. Then, Equation ( 14) can be transformed into…”
Section: Matrix Definitionmentioning
confidence: 99%
See 1 more Smart Citation
“…Estimate Afalse^, Bfalse^, and Cfalse^ from (48)–(50). Remark 4 Since θ^1 and θ^2 are consistent (see Remark 1 and Theorem 1), the retrieved system matrices (Afalse^,Bfalse^,Cfalse^) are also consistent (see [51, 53]. Remark 5 In the OPM‐like SIMs, the parameters of Bwnx×r are obtained before estimating Bnx×1 and w1×r, which will result in a dimension problem (the number of parameters for the former is rnx which is much larger than nx+r).…”
Section: Proposed Methodsmentioning
confidence: 99%
“…The main proponents of these methods are MOESP (Multivariate Output Error State-space) proposed in [4], N4SID (Numerical algorithms for State-space Sub-Space IDentification) in [5], and CVA (Canonical Variate Analysis) in [6]. The statistical properties of these methods are fairly well established in a series of papers [7][8][9][10]. The above-mentioned methods estimate the extended observability matrix or state from a signal subspace of certain noise-free matrix, then retrieve the system matrices based on the above intermediate results.…”
Section: Introductionmentioning
confidence: 99%