TY - JOUR
T1 - Tensor networks for MIMO LPV system identification
AU - Gunes, Bilal
AU - van Wingerden, Jan Willem
AU - Verhaegen, Michel
PY - 2018
Y1 - 2018
N2 - In this paper, we present a novel multiple input multiple output (MIMO) linear parameter varying (LPV) state-space refinement system identification algorithm that uses tensor networks. Its novelty mainly lies in representing the LPV sub-Markov parameters, data and state-revealing matrix condensely and in exact manner using specific tensor networks. These representations circumvent the ‘curse-of-dimensionality’ as they inherit the properties of tensor trains. The proposed algorithm is ‘curse-of-dimensionality’-free in memory and computation and has conditioning guarantees. Its performance is illustrated using simulation cases and additionally compared with existing methods.
AB - In this paper, we present a novel multiple input multiple output (MIMO) linear parameter varying (LPV) state-space refinement system identification algorithm that uses tensor networks. Its novelty mainly lies in representing the LPV sub-Markov parameters, data and state-revealing matrix condensely and in exact manner using specific tensor networks. These representations circumvent the ‘curse-of-dimensionality’ as they inherit the properties of tensor trains. The proposed algorithm is ‘curse-of-dimensionality’-free in memory and computation and has conditioning guarantees. Its performance is illustrated using simulation cases and additionally compared with existing methods.
KW - closed-loop identification
KW - Identification
KW - LPV systems
KW - subspace methods
KW - tensor trains
KW - time-varying systems
UR - http://resolver.tudelft.nl/uuid:9b81f383-1c36-4c9d-a91b-d28e32ff2625
UR - http://www.scopus.com/inward/record.url?scp=85050984979&partnerID=8YFLogxK
U2 - 10.1080/00207179.2018.1501515
DO - 10.1080/00207179.2018.1501515
M3 - Article
AN - SCOPUS:85050984979
SN - 0020-7179
VL - 93 (2020)
SP - 797
EP - 811
JO - International Journal of Control
JF - International Journal of Control
IS - 4
ER -