Nowadays, hybrid electric vehicles are becoming a major trend of future vehicle industry due to emission reduction and energy conversation requirements. As a key technology, the related energy management strategy is one of the research focus for the purpose of prolonging battery life and increasing the vehicle endurance. This paper proposed a fuzzy control based energy management strategy for precise control of the energy flow between the Lithium iron phosphate(LFP) battery and Ultra-Capacitor(UC) parallel hybrid electric vehicle. The proposed fuzzy controller takes the power requirement of electric vehicle and State Of Charge(SOC) of LFP battery and UC as three input parameters, a power allocation factor between LFP battery and UC is then determined as an output variable. The simulation result proves that the fuzzy control based energy management strategy helps eliminating the surge current and significantly improve the energy utilization rate.

The energy management is one of the most important issues for the efficiency and performance of the hybrid vehicular power system, including the Lithium-ion battery and Ultra-Capacitor. This paper deals with a dynamic programming based optimal control strategy proposed for the hybrid vehicular power system. The proposed method utilizes the capability of dynamic programming to treat the global optimization problem. Within the optimization process, the total energy consumption is the optimization target and the state of charge of ultra-capacitor is the state variable. When compared to the single energy system, the energy consumption of the hybrid energy system with dynamic programming can reduce 2.5% and the high instantaneous power is allocated to ultra-capacitor, which can reduce the damage to Lithium-ion battery. This paper proves that the dynamic programming algorithm can be applied to the hybrid energy system and presents a rather well performance.

The hypothesis is presented that "cognitive synergy" -- proactive and mutually-assistive feedback between different cognitive processes associated with different types of memory -- may serve as a foundation for advanced artificial general intelligence. A specific AI architecture founded on this idea, OpenCogPrime, is described, in the context of its application to control virtual agents and robots. The manifestations of cognitive synergy in OpenCogPrime's procedural and declarative learning algorithms are discussed in some detail.