Abstract-A novel adaptive energy management strategy is proposed for real time power split between fuel cells and supercapacitors in a hybrid electric vehicle in view of the fact that driving patterns greatly affect fuel economy. The driving pattern recognition (DPR) is achieved based on the features extracted from the historical velocity window with a multi-layer perceptron neural network. After the DPR has been obtained, an adaptive fuzzy energy management controller is utilized for power split according to the required power for vehicle running. In order to prolong the fuel cell lifetime whilst decreasing the hydrogen consumption, a genetic algorithm is applied to optimize critical factors such as adaptive gains and fuzzy membership function parameters for several standard driving cycles. In the proposed method, the future driving cycles are not required and the current driving pattern can be successfully recognized, demonstrating that less current fluctuations and fuel consumption can be achieved under various driving conditions. Compared with conventional energy management systems, the proposed framework can ensure the state of charge of supercapacitors within the desired limit.Index Terms-Driving pattern recognition; Neural network classifier; Fuzzy energy management; Genetic Algorithm; FC/SC hybrid electric vehicle I. INTRODUCTION NERGY crisis, environmental pollution and global warming cause fuel cells (FCs) powered vehicles to draw a lot of attention due to their high reliability and low pollutant emission [1]. However, due to slow dynamic response and limited load following capability, hydrogen starvation may occur at power fluctuations, which is impermissible for vehicles [2]. Energy storage devices, such as batteries or capacitors, are usually hybridized by a fuel cell bank as a power buffer during climbing, acceleration and braking [3][4]. Supercapacitors (SCs) have several advantages, such as long life cycle, high power density and fast charge/discharge performance [5], which is an efficient solution to satisfy large instantaneous Manuscript received August 31, 2017; revised March 29, 2018 and May 29, 2018; accepted June 26, 2018. This work was supported in part by the National Natural Science Foundation of China under Grant (61603337). H. Zhou was supported by UK EPSRC under Grant EP/N011074/1 and Royal Society-Newton Advanced Fellowship under Grant NA160342.R. Zhang is with the Belt and Road Information Research Institute, Automation College, Hangzhou Dianzi University, Hangzhou, 310018, P.R. China (e-mail: zrd-el@163.com).J. Tao is with Ningbo Institute of Technology, Zhejiang University, Ningbo, 315100, China (e-mail: tjl810@126.com).H. Zhou is with Department of Informatics, University of Leicester, LE1 7RH, United Kingdom. (e-mail: hz143@leicester.ac.uk).power requirements, absorb the feedback energy and downsize the fuel cells.To achieve efficient power management for a hybrid electric vehicle (HEV), a variety of control strategies have been proposed, such as Haar-wavelet energy management ...