Predictive energy management (PEM) strategy has shown great advantages in improving fuel economy for plug-in hybrid electric vehicles (PHEV). A Markov velocity predictor optimization method and its applications in PHEV energy management is studied in this paper. The initial Markov velocity predictor is constructed using complete driving cycle information and the state space of the Markov velocity predictor is then optimized for specified driving conditions using simulated annealing algorithm (SAA). The practical driving conditions are identified using a multi-feature driving condition recognition unit by using the support vector machine (SVM) method. Based on the driving conditions identified, velocities are predicted using the proposed method and optimized using dynamic programming (DP) algorithm in conjunction with the state of charge (SOC) reference and vehicle state. The energy management strategy derived is then implemented in the vehicle controllers. Comparing with the traditional rule-based energy management strategy, simulation results indicate that the PEM strategy proposed herein can reduce fuel consumption.
Markov velocity predictor based on state space optimization and its applications in PHEV energy management
2024-06-01
Article (Journal)
Electronic Resource
English
PHEV Energy Management Optimization Based on Multi-Island Genetic Algorithm
British Library Conference Proceedings | 2022
|PHEV Energy Management Optimization Based on Multi-Island Genetic Algorithm
SAE Technical Papers | 2022
|Energy management and design optimization for a series-parallel PHEV city bus
Online Contents | 2017
|Energy management and design optimization for a series-parallel PHEV city bus
British Library Online Contents | 2017
|