Implementation of Radial Basis Function Artificial Neural Network into an Adaptive Equivalent Consumption Minimization Strategy for Optimized Control of a Hybrid Electric Vehicle

Continued increases in the emission of greenhouse gases by passenger vehicles have accelerated production hybrid electric vehicles. With this increase production, there has been a parallel demand for continuously improving strategies vehicle control. The goal an ideal control strategy is to maximize fuel economy while minimizing emissions. Methods exist which globally optimal may be found. However, these methods are not applicable real-world driving applications since require priori knowledge upcoming drive cycle. Real-time use global as benchmark against performance can evaluated. work previously defined that shown closely approximate and implement radial basis function (RBF) artificial neural network (ANN) dynamically adapts based on past conditions. used Equivalent Consumption Minimization Strategy (ECMS), uses equivalence factor define power train component torque split. An single cycle found offline with RBF-ANN update examining time window characteristics. A total 30 sets training data (drive cycles) RBF-ANN. For majority cycles examined, implementation produce values within ±2.5% obtained factor. advantage it does able implemented real-time meeting or exceeding ECMS. Recommendations made how could improved better results across greater array