Search Results

Future vehicle electrical systems will differ substantially from current ones due to rising requirements. For example driver-assistance and drive-by-wire systems will lead to novel and demanding electrical load profiles which in turn will pose new requirements on the electrical system. Furthermore safety concepts, reliability, availability and diagnosis are getting increasingly important in such systems and thus also in the vehicle's electrical system. In order to meet the upcoming requirements new concepts for future vehicle electrical systems have to be developed such that the new powernet is able to adapt flexibly to different situations or failures by routing the energy through different channels. For efficiency the corresponding development process should be based on modeling and simulation techniques. Depending on the design or analysis task, the powernet is represented through different modeling descriptions.

In this paper an approach to clustering of complex electronic systems using Self-Ordering Maps (SOMs) is presented. SOMs are neural networks which learn through a competitive learning algorithm. In order to use SOMs for the clustering of electronic networks, a representation of the communication behavior in n-dimensional space is developed. The SOM is then used as a nonlinear projection of this space onto a two-dimensional plane. Two examples of clustering are given. The more complex of the two is verified by comparing the behavior of the clustered system and the unclustered system on a simple model of the CAN bus. It is shown that SOMs can be used to effectively cluster complex electronic systems.