System Response Analysis and Model Order Reduction, Using Conventional Method, Bond Graph Technique and Genetic Programming

This research paper basically explores and compares the different modelling and analysis techniques and than it also explores the model order reduction approach and significance. The traditional modelling and simulation techniques for dynamic systems are generally adequate for single-domain systems only, but the Bond Graph technique provides new strategies for reliable solutions of multidomain system. They are also used for analysing linear and non linear dynamic production system, artificial intelligence, image processing, robotics and industrial automation. In the first phase, the system is modelled using Bond Graph technique. It's system response and transfer function with conventional and bond graph method is analysed and then a approach towards model order reduction is observed. The suggested algorithm and other known modem model order reduction techniques are applied to a 11(th) order high pass filter. The order of the model was reduced using four methods, and maximum absolute errors were determined as a function of model order. The methods included the bond graph approach developed, balanced model reduction, the Hankel norm approximation and Schmidt norm model approximation with prescribed eigen values. The model order reduction technique developed in this paper has two principal advantages. Firstly the model order reduction process indicates which system components have the most bearing on the frequency response, secondly the final model retains structural information. The approach towards the genetic tree formation from the bond graph is analysed. The model order reduction using Genetic tree is in progress.[1]