Exploring Benefits of Neuro Fuzzy Controller with Vehicle Health Monitoring

Abstract

This paper presents the architecture and learning procedure-underlying Adaptive- Neural Fuzzy Inference System, a Fuzzy Inference System implemented in the framework of adaptive neural networks. It elaborates the work to employ the ANFIS architecture to model linear function for creating a closed loop system. It tests the comparative performance with simple and hybrid controllers with respect to ‘Pre-trip plan assistance system with vehicle health monitoring’. The system calculates safest traveling distance based on six inputs. The approach is an extension to design of pre trip plan assistance with open loop fuzzy and hybrid fuzzy using genetics [1-3]. This paper mainly proposes performance of ANFIS for calculating safest distance that can be traveled by a vehicle under pre trip plan assistance system with vehicle health monitoring. ANFIS is used in the current work to create a closed loop system and to test comparative performance with simple and hybrid controllers. Nearly 5-8% improvement in the results is obtained if we incorporate hybrid (Mamdani Sugeno) model and neural fuzzy closed loop controller gives further 4% improvement. This system will be helpful for the travelers where long journey is to be commenced and where cost of traveling matters, and frequent variation in weather dominates success of the journey.