The parallel hybrid electric vehicles (PHEV’s) superior performance relies on the associated energy management strategy. This work intends to improve the performance of real-time implementable equivalent consumption minimization strategy (ECMS) so that, optimal battery and fuel energy utilization can be guaranteed in the PHEV. In the ECMS algorithm, the incorporation of intelligent technique is the proposed approach for a novel robust equivalence factor correction concerning the battery state of charge (SOC) for various uncertain driving conditions. With this motive, the significance and necessity of dynamic adjustment in equivalence factor value are first elaborated to achieve the global optimal fuel economy. The two intelligent approaches of fuzzy logic and genetic algorithmically optimized adaptive neuro-fuzzy inference system (ANFIS) have been compared in the adaptive ECMS. Their performance is validated using the prepared three hybrid standard driving cycles and also for training the fuzzy inference system (FIS). The obtained result infers the fuzzy-PI-based AECMS provided the least terminal SOC variance of 3.25 whereas 30.03 for the conventional fixed PI. The proposed ANFIS-ECMS delivers terminal SOC of 29.41%, 28.22% and 28.37% for the three driving cycles which is having variance of 0.42. Even in the real-time validation of the ANFIS-AECMS, achieves a terminal SOC of 27.53% and a fuel economy of 33.37 km/l for the self-developed real-world driving cycle. The entire result of this work proves the proposed strategy achieves significant improvement in battery and fuel energy utilization and also the reduction in emissions compared with rule-based, conventional fixed PI ECMS and fuzzy-PI-based ECMS.