Automated design of digital systems with parallel architecture

Abstract

The article discusses the modification of a digital signal processing systems design method, based on the parallel decomposition of dynamical systems, which can be described by a transfer function. This method is suitable for the development of digital control and signal processing systems with higher precision and lower delay characteristics by parallelizing the computation process. The program algorithms that allow the automatic conversion of the dynamical system models in the form of a transfer function or zero-pole-gain model to the sum of first and second order transfer functions are represented. A validation of the described method is made by creating and simulating dynamical system model in NI LabVIEW development system. Analysis of the efficiency and accuracy of the derived solution in the time domain is performed. It is shown that the proposed implementation of a dynamical system model can replace the classical approaches to implementation, and is suitable for solving the current problems of digital signal processing.