作者: L. Glielmo , R. Setola , F. Vasca
DOI: 10.1109/9.780418
关键词:
摘要: An estimation algorithm for a class of discrete time nonlinear systems is proposed. The system structure we deal with partitionable into in subsystems, each affine w.r.t. the corresponding part state vector. consists bank m interlaced Kalman filters, and them estimates state, considering remaining parts as known time-varying parameters whose values are evaluated by other filters at previous step. procedure neglects subsystem coupling terms covariance matrix error counteracts errors so introduced suitably "increasing" noise matrices. Comparisons through numerical simulations extended filter its modified versions proposed literature illustrate good trade-off provided between reduction computational load accuracy.