A New Algorithm for Blind Separation of Post-Nonlinear Mixture A new algorithm for blind separation of post-nonlinear mixture is proposed in this paper.The extra information on source signals is required and blind separation becomes half-blind separation for the post-nonlinear mixture in the most of the existing algorithms.So whole-blind separation algorithm without any extra information is proposed.Firstly,the model of post-nonlinear mixture is transformed into the model like the instantaneous linear mixture by the differential transformation,which makes the nonlinear problem simplified largely.Then it is proofed that the differential of source signals conserves the same statistical characters as the source signals.Secondly,the correlation characters of signals are utilized to construct separation criterion function and iterative equation,then LMS algorithm is utilized to make criterion function minimized for blind source separation.Lastly,the numerical computer simulations are performed to illustrate the validity and feasibility of our algorithm.Compared with the existing algorithms,our algorithm possesses some good excellences like low computational complexity,rapid convergence,well real-time processing and whole-blind source separation.