Functional verification by simulation is often based on behavioral models and represents an important step during the development of microelectronic solutions for automotive applications. The present article describes a data-based approach for semi-automated generation of behavioral models for analog mixed-signal (A/MS) systems. The approach is based on support vector machines and a transformation dictionary for extraction of dynamic properties. The application of this method results in highly accurate pin-compatible behavioral models for A/MS systems with a significant reduction in simulation times. Additionally, the generated models can be easily integrated in hardware or system-level description languages. Another benefit of the proposed method consists in its flexibility to model systems of different physical domains. The emphasized properties will be illustrated by the modeling of an analog-digital system belonging to the automotive domain.
A method for semi-automated modeling of analog-mixed signal systems in automotive applications based on transient simulation data
2007
4 Seiten, 12 Quellen
Conference paper
English
Semi-active damping in automotive systems: Design-by-simulation
Online Contents | 2002
|