Errors-in-variables identification of dynamic bilinear systems in the case of coloured output noise

An approach for the identification of single-input single-output dynamic errors-in-variables bilinear system models for the case of white input noise and coloured output noise is proposed. The algorithm is based on the extension of the bias compensation technique for bilinear systems that is applied to a set of overdetermined normal equations. The separable nonlinear least squares method is used, subsequently, to determine the model parameters together with the auto-correlation elements of the input/output noise sequences. A numerical Monte-Carlo simulation demonstrates the appropriateness and the robustness against noise of the proposed approach.