Abstract
NARMAX is a general method for modeling of nonlinear systems. In the paper, an application of this method for modeling of nonlinearities in dynamic loudspeakers is presented. In most cases, a polynomial representation of the NARMAX model causes an ill-conditioned equation system which indicates that the use of orthogonalization is necessary to solve the system. The high number of coefficients is the main disadvantage of the NARMAX method, and it results in an erroneous model, and an algorithm for identification of coefficients that is noneffective. A modification of the orthogonal algorithm (classical Gram–Schmidt) is presented. It is based on the premise that the coefficient providing the highest error reduction ratio is chosen in every step of the algorithm. The creation of the model stops when the given accuracy is achieved. This way leads to the choice of only the most significant coefficients. The work and effectiveness of this modified algorithm for systems with given nonlinearities at different levels of accuracy of the model are presented in the paper.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
