TY - JOUR
T1 - Internal state identification for black box systems
AU - De Jesús Medel Juárez, José
AU - Álvarez, María Teresa Zagaceta
PY - 2014
Y1 - 2014
N2 - In digital filter theory, the identification process describes internal dynamic states based on a reference system, commonly known as a black box. The identification process as a function of: a) transition function, b) identified delayed states, c) gain function which depends on convergence correlation error, and d) an innovation process based on the error described by the differences between the output reference system and the identification result. Unfortunately, in the black box concept, the exponential transition function considers the unknown internal parameters. This means that the identification process does not operate correctly because its transition function has no access to the internal dynamic gain. An approximation for solving this problem includes the estimation in the identification technique. This paper presents an estimation for a "single input single output" (SISO) system with stationary properties applied to internal state identification.
AB - In digital filter theory, the identification process describes internal dynamic states based on a reference system, commonly known as a black box. The identification process as a function of: a) transition function, b) identified delayed states, c) gain function which depends on convergence correlation error, and d) an innovation process based on the error described by the differences between the output reference system and the identification result. Unfortunately, in the black box concept, the exponential transition function considers the unknown internal parameters. This means that the identification process does not operate correctly because its transition function has no access to the internal dynamic gain. An approximation for solving this problem includes the estimation in the identification technique. This paper presents an estimation for a "single input single output" (SISO) system with stationary properties applied to internal state identification.
KW - Digital filter
KW - Estimation
KW - Functional error
KW - Identification
KW - Reference model
KW - Stochastic gradient
UR - http://www.scopus.com/inward/record.url?scp=84903998356&partnerID=8YFLogxK
U2 - 10.13053/CyS-18-2-2014-039
DO - 10.13053/CyS-18-2-2014-039
M3 - Artículo
SN - 1405-5546
VL - 18
SP - 391
EP - 398
JO - Computacion y Sistemas
JF - Computacion y Sistemas
IS - 2
ER -