This paper presents an innovative four-step method to analyze and design an optimal energy management strategy for a power split power train hybrid vehicle. A hybrid dynamical system theory is introduced to formulate the problem of hybrid vehicle control system that incorporates both continuous and discrete dynamics. The sequential quadratic programming (SQP) method is proposed to optimize power distribution. The dynamic programming method is employed to solve the problem of the vehicle operating mode transitions. A rule-based system and a fuzzy rule system are developed based on the statistical numerical solutions. A genetic algorithm is applied to the simultaneous optimization of parameters of membership functions, weights of the rules and rule sets for the fuzzy rule system and parameters of the rule-based system. The simulation results illustrate the effectiveness and applicability of the proposed design method.