Machine Learning-Based Real-Time Dynamic Programming for Battery Thermal Management System (ML-RTDP-BTMS) for Electric Vehicles

Pack-level modeling of a liquid cooling system for power batteries in electric vehicles

The paradigm shift towards electric mobility has catalysed a substantial surge in research endeavours aimed at augmenting both the performance, life, and durability of lithium-ion batteries deployed within the confines of small electric vehicles. At the crux of this pursuit lies the imperative development of robust battery thermal management systems, indispensable for the meticulous regulation of battery temperature, thereby ensuring seamless operation and bolstering safety protocols. This review paper undertakes a comprehensive synthesis of recent strides achieved in battery thermal management systems for small electric vehicles propelled by lithium-ion batteries. Encompassing a spectrum of methodologies, ranging from passive to active cooling techniques, alongside the incorporation of phase change materials and innovative thermal interface materials, it critically evaluates these strategies. Furthermore, the discourse navigates through the prevailing challenges and charts out prospective trajectories in this domain, poised to foster the evolution of efficient and dependable battery thermal management systems tailored specifically for small electric vehicles. Numerous investigations have focused on the thermal regulation of lithium-ion batteries. Despite the prevalent excitement surrounding small electric vehicles today, the crucial matter of implementing effective battery thermal management systems in small electric vehicles has not received adequate attention, potentially diminishing customer satisfaction with small electric vehicle performance. Thus, the current study aims to delve into the thermal optimization of lithium-ion batteries for small electric vehicles. Initially, the study investigates into discussing design parameters for battery thermal management systems, referencing research conducted on thermal stability, particularly concerning thermal runaway, and the performance of electric vehicles in subzero temperatures regarding battery thermal management systems. Furthermore, the study places emphasis on reviewing and analysing various theoretical and practical heat transfer techniques applied by researchers to lithium-ion batteries to enhance battery thermal management systems. Consequently, the paper’s novel contribution lies in bridging the gap between researchers and manufacturers regarding battery thermal management systems in small electric vehicles, thus propelling innovative battery designs for improved battery thermal management systems in small electric vehicles.

Performance analysis of liquid-based battery thermal management system for Electric Vehicles during discharge under drive cycles

Energy-efficient operation of the thermal management system in electric vehicles via integrated model predictive control

Experimental study on the performance of vehicle integrated thermal management system for pure electric vehicles

Lithium-ion batteries are highly sensitive to temperature, with excessive heat leading to accelerated aging, reduced cycle life, and safety risks such as thermal runaway. Traditional thermal management systems often struggle to maintain optimal battery temperature, especially under high ambient temperatures or dynamic operating conditions. This paper proposes a novel reinforcement learning (RL)-based control method for the coupled thermal management system of a power battery and air conditioning system in a Plug-in Hybrid Electric Vehicle (PHEV). The system integrates the battery cooling circuit with the air conditioning system via a heat exchanger, eliminating the need for a separate radiator. The Deep Deterministic Policy Gradient (DDPG) algorithm is employed to control the water pump speed, optimizing battery temperature in real-time. Experimental results under New European Driving Cycle (NEDC) conditions at 40°C ambient temperature demonstrate that the RL-controlled pump responds faster than the Model Predictive Control (MPC) algorithm, allowing the battery temperature to reach the target temperature of 28°C 1 min earlier with a maximum fluctuation of only 0.8°C. The RL-controlled pump consumes 4 W h more energy than the MPC-controlled pump, while the compressor energy consumption is only 1.68% higher. Additionally, the temperature fluctuations in the passenger cabin under RL control are only 0.1°C higher than under MPC, ensuring passenger comfort. This study highlights the potential of RL-based control for improving the efficiency and stability of integrated thermal management systems in electric vehicles.

Research progress on efficient battery thermal management system (BTMs) for electric vehicles using composite phase change materials with liquid cooling and nanoadditives

Novel battery thermal management system for electric vehicles with a loop heat pipe and graphite sheet inserts

The typical structure of energy management system for new electric vehicle was analyzed to summarize the function. The research trend was pointed out based on the analysis of performance characteristics of energy management system for electric vehicle.

An active energy management system for light two-wheeled electric vehicles

The powertrain in combustion engine and electric vehicles requires a thermal management system to regulate the operating temperature of the under-hood components. The introduction of computer-controlled cooling system actuators (e.g., variable speed fans, pump, and valves) enables power savings over drive cycles. The radiator is typically sized for maximum heat rejection per environmental and vehicle thermal loading conditions. This paper explores the use of multiple radiators to adapt the cooling system operations to driving demands. A nonlinear multiple-input (i.e., fan array speed, pump, and outlet valve positions) thermal model is presented to predict system behavior. A stateflow controller has been designed and implemented to maintain the component temperature within a desired range (~80 °C). A series of experimental tests have been conducted to compare the proposed architecture’s performance against a single radiator design. A standard driving cycle featuring low (20 kW) and high (40 kW) heat loads was implemented in the laboratory for a vehicle starting from rest. The coolant temperature tracking, fan speeds, and fan power draw were studied over the representative operating cycle. The test results show a much faster warmup time (~10 min) and temperature tracking for the twin radiator experimental test as compared to the single radiator (~13 min). The net fan energy consumption was reduced by 4.6% with the twin radiator as opposed to the single-radiator configuration. Considering that engines usually operate at idle to medium loads, these findings can improve the powertrain’s overall performance.

In this paper, a power-split strategy based on a real-time average power method is developed for improving power output of battery and mode switching frequency of a multi-mode hybrid energy storage system (HESS) in electric vehicles. To achieve mode switching and power distribution for the multi-mode HESS, a rule-based strategy is designed based on the high-frequency power demand. Furthermore, a simple real-time average power method is adopted to process the high-frequency power demand. Then, the real-time average power is used as a variable logic threshold value for the power-split strategy. Since the power-split controller responds to the smooth average power rather than the high-frequency power demand, the high-frequency mode switching of the multi-mode HESS can be avoided. The ultra-capacitor works as an enhanced low-pass power filter and the battery can supply smooth and steady output power to the motor inverter. Comparative simulations between the developed power-split strategy and the rule-based strategy are performed. The advantages of the developed power-split strategy for improving the power output of the battery and the mode switching frequency of the multi-mode HESS in electric vehicles are indicated under three typical driving cycles. Moreover, the longer time duration of the real-time average power is designed, the smoother power output of the battery and the lower mode switching frequency of the multi-mode HESS can be achieved.

Multi-objective design optimization of battery thermal management system for electric vehicles

This paper proposes a novel control scheme for hybrid energy storage system(HESS) in electric vehicles. The HESS above is composed of two parts: fuel cell (FC) and super capacitor(SC). FC, as the main power supply, provides a large proportion of required power. Whereas, SC, as the auxiliary energy storage source, plays a great role when starting and braking an electric vehicle(EV). Both energy sources are connected to the DC bus with DC-DC converters. Two converters share the very DC bus which is connected to the traction motor with a power inverter. To make sure the performances of the control system, a control method named generic model control is applied. Simulation results indicate the robustness and static performance of the proposed control scheme.

Energy management strategy (EMS) is a key issue for hybrid energy storage system (HESS) in electric vehicles. By innovatively introducing the current speed information, the vehicle speed optimized fuzzy energy management strategy (VSO-FEMS) for HESS is proposed in this paper. Firstly, the pruned fuzzy rules are formulated by the SOC change of battery and super-capacitor to preallocate the required power of vehicle. Then, the real-time vehicle speed is used to optimize the pre-allocated results based on the principle of vehicle dynamics, so as to realize the optimal allocation of required power. To validate the proposed VSO-FEMS strategy for HESS, simulations were done and compared with other EMSs under the typical urban cycle in China (CYC-CHINA). Results show that the final SOC of battery and super-capacitor are optimized in varying degrees, and the total energy consumption under the VSO-FEMS strategy is 2.43% less than rule-based strategy and 1.28% less than fuzzy control strategy, which verifies the effectiveness of the VSO-FEMS strategy.