Rule-based Control and Equivalent Consumption Minimization Strategies for Hybrid Electric Vehicle Powertrains: a Hardware-in-the-loop Assessment

Energy Management in Hybrid Electric Vehicles: A Q-Learning Solution for Enhanced Drivability and Energy Efficiency

“…A Jeep Renegade 4xe represented as a parallel P4 architecture, whose scheme is reported in Figure 1, was considered for the purpose of this study [19]. Specifically, the internal combustion engine (ICE) is responsible for powering the front axle, while the electric motor (EM or MGP4) drives the rear axle and is directly connected to the high-voltage battery pack.…”

“…Specifically, the internal combustion engine (ICE) is responsible for powering the front axle, while the electric motor (EM or MGP4) drives the rear axle and is directly connected to the high-voltage battery pack. The main vehicle specifications, obtained by secondary data available online [19], are listed in Table 1. The model and algorithm were developed and implemented within the MATLAB ® simulation environment [51].…”

“…where the subscripts g, f and r refer to the gearbox, the front and rear axle differential efficiencies (η) or transmission ratios (τ), depending on the case. The gear shifting schedule was determined using a rule-based strategy tied to the road speed, aiming to enhance the vehicle's performance, approach real-time vehicle usage, and meet passenger comfort requirements [19]. The battery power (P batt ) was in turn computed considering the electric motor power (P EM ) and the overall losses of the electric motor (P EM,loss ) along with the power related to the auxiliaries (P aux ).…”

“…In the problem under analysis, we employed two distinct algorithms: a global optimization algorithm and a reinforcement-learning-based one. The control strategies selected were optimized to ensure the maintenance of the battery SOC within the 18% to 22% range during charge-sustaining mode, owing to the capacity of the PHEV's battery pack considered for the purpose of this study [19]. In Figure 2, the controller design and its operational scheme are summarized.…”

“…Four operating modes are allowed where in turn the engine (pure thermal) or electric motor (pure electric) provides traction alone, or simultaneously (power-split) or the engine provides traction while recharging the battery (battery charging). Depending on the final application considered (off-line or on-line), several control logics [4][5][6] can be adopted including rule-based [7][8][9][10][11][12], optimization-based [13][14][15][16][17][18][19], data-driven [20][21][22][23][24][25][26][27][28][29][30][31][32] and reinforcement learning (RL) [33][34][35][36][37][38][39][40][41][42][43][44] among the main ones. Rule-based controllers require a substantial calibration effort and they fail to achieve good performance when applied to a driving scenario other than the calibration one.…”