Evolutionary fuzzy modeling of pre-trip plan assistance system with vehicle health monitoring

This paper mainly proposes a benefit of methodology for pre trip plan assistance system with vehicle health monitoring. It proposes a comparison of calculating safest distance traveled by a vehicle by evaluating vehicle health monitoring using open loop Mamdani, open loop Sugeno, hybrid fuzzy, closed loop genetic fuzzy and adaptive neuro fuzzy controller, making use of knowledge based system and fuzzy control. The proposed system alerts driver about possibility of completing journey successfully, considering number of the factors like journey condition, journey classification, vehicle condition, optimum distance to be traveled and status of the driver. We propose three-phase development framework. In first phase, fuzzy logic controllers with Mamdani and Sugeno model are employed. Since both have some restrictions, an attempt has been made in this paper to make best of both the world by merging special membership function shapes of the both the models. This helps in both regulatory control as well as tracking control. Nearly 5-8% improvement in the results is obtained if we incorporate hybrid fuzzy (Mamdani Sugeno) model in the system. In second phase, a genetic fuzzy system is proposed to promote the learning performance of logic rules. The resultant hybrid system seems to be highly adaptive and trained through a proper performance, hence is much more sophisticated and has a higher degree of adaptive parameters. In third phase, adaptive fuzzy neural network is proposed to tune membership functions through proper training.