Hatun, Metin2024-10-302024-10-302023-01-011392-1215https://doi.org/10.5755/j02.eie.35119https://hdl.handle.net/11452/47159https://eejournal.ktu.lt/index.php/elt/article/view/35119The Recursive Gauss-Seidel (RGS) algorithm is presented that is implemented in a one-step Gauss-Seidel iteration for the identification of Wiener output error systems. The RGS algorithm has lower processing intensity than the popular Recursive Least Squares (RLS) algorithm due to its implementation using one-step Gauss-Seidel iteration in a sampling interval. The noise-free output samples in the data vector used for implementation of the RGS algorithm are estimated using an auxiliary model. Also, a stochastic convergence analysis is presented, and it is shown that the presented auxiliary model-based RGS algorithm gives unbiased parameter estimates even if the measurement noise is coloured. Finally, the effectiveness of the RGS algorithm is verified and compared with the equivalent RLS algorithm by computer simulations.eninfo:eu-repo/semantics/closedAccessSquares parameter-estimationModel-predictive controlNonlinear-systemsIterative identificationAdaptive-controlStochastic gradientAuxiliary modelGauss-seidelRecursive estimationSystem identificationWiener systemScience & technologyTechnologyEngineering, electrical & electronicEngineeringArticle00111154860000941029510.5755/j02.eie.35119