2020/01/17 by Diganta Bhattacharjee, Bhattacharjee, Diganta, Kamesh Subbarao +1
Computer Science · Engineering · #Control Systems and Identification #FOS: Electrical engineering #FOS: Mathematics #Fault Detection and Control Systems #Optimization and Control (math.OC) #Systems and Control (eess.SY) #Target Tracking and Data Fusion in Sensor Networks #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2001.06562
openalex publication_date 2020/01/17 · openalex created_date 2022/07/26 · openalex updated_date 2026/07/28
In this technical note, a recursive set-membership filtering algorithm for\ndiscrete-time nonlinear dynamical systems subject to unknown but bounded\nprocess and measurement noises is proposed. The nonlinear dynamics is\nrepresented in a pseudo-linear form using the state dependent coefficient (SDC)\nparameterization. Matrix Taylor expansions are utilized to expand the state\ndependent matrices about the state estimates. Upper bounds on the norms of\nremainders in the matrix Taylor expansions are calculated on-line using a\nnon-adaptive random search algorithm at each time step. Utilizing these upper\nbounds and the ellipsoidal set description of the uncertainties, a two-step\nfilter is derived that utilizes the `correction-prediction' structure of the\nstandard Kalman Filter variants. At each time step, correction and prediction\nellipsoids are constructed that contain the true state of the system by solving\nthe corresponding semi-definite programs (SDPs). Finally, a simulation example\nis included to illustrate the effectiveness of the proposed approach.\n