Hierarchical Adaptive Genetic Algorithm Based T-S Fuzzy Controller For Non-linear Automotive Applications

In this paper, a robust and enhanced evolutionary computing assisted Takagi Sugeno (T-S) fuzzy controller was developed for automotive fuel injection control. To augment the rule generation and fuzzy parameter estimation, we propose an enhanced evolutionary computing algorithm named Hierarchical Adaptive Genetic Algorithm (HAGA). The proposed HAGA model was applied to augment T-S fuzzy controller that in conjunction with Fuzzy Clustering Mean (FCM) has enabled optimal rule generation and control parameter estimation. The proposed HAGA model exploits Hierarchical concept-based AGA implementation that itself embodies novelties like adaptive crossover and mutation probability, to enable accurate, swift, and efficient control function by T-S Fuzzy controller. These novelties strengthen the proposed HAGA-TS fuzzy controller to exhibit time efficient and accurate control function that could be of utmost significance for non-linear process control. The proposed controller design is examined for its efficacy over automotive or vehicle data containing fuel injection rate, throttle angle, emission products etc., where considering current emission and/or torque requirements, the throttle angle is varied to achieve environmentally friendly and cost-efficient vehicle design. The simulation results revealed that the proposed HAGA TS-fuzzy controller outperforms other state of art evolutionary computing-based approaches such as GA, PSO based T-S fuzzy controller.