Neural ODE-based Optimal Thermal System Control for Electric Vehicles with multi-functional Heat Pump System *

Thermal management optimization of Battery Electric Vehicles via hierarchical NMPC with CMO-trained Neural Models

This paper addresses the problem of energy-efficient thermal management in Battery Electric Vehicles (BEVs), with the goal of extending driving range while ensuring passenger comfort and battery thermal safety. A hierarchical Nonlinear Model Predictive Control (NMPC) framework is proposed, in which the supervisory layer explicitly balances energy consumption and cabin temperature reference tracking over a long horizon and translates this trade-off into optimal actuator command sequences for the integrated heating, ventilation, and air conditioning (HVAC) system and the battery thermal management (BTM) system. These command sequences are then enforced by a lower-layer NMPC, which introduces local corrections to compensate disturbances and modeling uncertainty while tracking an externally specified cabin temperature reference trajectory. To enable predictive control of the highly nonlinear and strongly coupled thermal dynamics, data-driven neural network models are employed as prediction models within both control layers. The proposed approach is developed and validated using a high-fidelity BEV thermal simulator developed at Politecnico di Torino in collaboration with Stellantis N.V., and benchmarked against an industrial rule-based (RB) control strategy over the WLTC driving cycle. Simulation results demonstrate a significant reduction in energy consumption compared to the baseline strategy, while satisfying comfort and battery temperature constraints.

Nonlinear Model Predictive Control of Electric Minibus Integrated Cabin and Powertrain Heat Pump Coolant Loop

Thermal management systems for battery electric vehicles: A comprehensive review and control-based classification

An efficient vehicle thermal management system (VTMS) is essential for ensuring the performance, safety, and driving range of battery electric vehicles (BEVs), and for supporting vehicle-level range performance under representative operating conditions. Maintaining all major thermal subsystems within their optimal temperature ranges is therefore critical to overall vehicle performance and market competitiveness. Over the past decade, VTMS technologies for BEV applications have been extensively investigated. However, existing reviews primarily focus on system configurations, heat-transfer mechanisms, and material properties, with limited systematic analysis from a control-oriented perspective to provide unified theoretical guidance. Therefore, this paper presents a comprehensive review of VTMS control methods for BEVs from a control-theoretical viewpoint. Different from the conventional active/passive/hybrid hardware classification, the proposed control-oriented taxonomy classifies VTMS methods as preventive and corrective strategies according to intervention timing, information source, and dominant control mechanism. Preventive control methods, based on feedforward control principles, mitigate thermal issues through geometric optimization, parametric optimization, and hybrid optimization approaches. Corrective control methods, grounded in feedback concepts, achieve real-time thermal deviation correction through classical, modern, and intelligent control techniques. Comparative studies reveal that preventive control methods offer advantages including high design flexibility, superior temperature uniformity, and mature commercialization, but are constrained by high manufacturing costs, lengthy validation cycles, and increased system weight. Corrective control methods demonstrate excellent performance in battery-pack compatibility, adaptability to complex operating conditions, and multi-subsystem coordination, though their development is limited by computational burden and algorithmic complexity. Intelligent control methods exhibit significant advantages in multi-objective optimization and thermal safety assurance, and show strong potential for improving vehicle-level energy efficiency and driving-range performance under application-specific operating conditions, representing an important future direction of VTMS development. The proposed control-oriented classification framework provides unified theoretical guidance for the design, optimization, and control of BEV VTMS, thereby supporting the coordinated improvement of thermal safety, energy efficiency, and vehicle-level range performance under clearly defined operating conditions.

A Study on Modeling and Control of Thermal Management Systems for Pure Electric Vehicles with Battery Temperature Control

: To address the cooling and preheating requirements of traction batteries in pure electric vehicles, this study proposes an integrated thermal management system coupling the refrigerant, battery, cabin heating, and motor/power-electronics cooling circuits. The system enables indirect natural cooling, chiller-assisted active cooling, and PTC-based low-temperature preheating of the battery. An AMESim/Simulink co-simulation model was developed, and a finite-state machine was used for operating-mode switching. A cooling-demand-based fuzzy controller was further designed, using cabin and battery cooling demands as inputs and a normalized compressor command as the output. By doing simulations with the WLTC (Worldwide Harmonized Light Vehicles Test Cycle), it was shown that under hot conditions the cabin temperature stayed around 22 °C and the battery temperature stayed near 32 °C; under cold conditions, the cabin hit the target temperature within 500–600 seconds, while the battery temperature kept rising; compared with a common PID controller, the fuzzy control strategy made the start of cooling better and reduced the changes in cabin temperature and compressor speed, and these results suggest that the proposed system and strategy can help with battery temperature control and thermal management in pure electric cars.

Model predictive control with BPNN-based prediction for electric drive thermal management system of electric vehicle

Under varying driving conditions, the electric drive thermal management system (EDTMS) of electric vehicle is prone to poor thermal stability, temperature fluctuation, and unnecessary auxiliary energy consumption. To improve the thermal control performance of the EDTMS, an improved EDTMS architecture and a backpropagation neural network (BPNN)-assisted model predictive control (MPC) strategy are investigated. In the improved EDTMS, the motor is cooled by insulating oil, while the motor controller is cooled by a water-cooling circuit. A liquid–liquid heat exchanger and a three-way valve are introduced to realize thermal coupling between the motor oil-cooling circuit and the motor controller water-cooling circuit, as well as switching between the water-cooling short loop and the radiator main loop. For the control strategy, t-distributed stochastic neighbor embedding (t-SNE)-assisted sensitivity analysis is used to select key input variables that characterize the thermal dynamic behavior of the EDTMS. The BPNN prediction model then provides one-step-ahead predictions of the motor oil outlet temperature and the motor controller coolant outlet temperature for MPC. Based on these predictions, MPC coordinates the oil pump speed, water pump speed, and three-way valve opening under actuator and thermal-safety constraints. The EDTMS model (EDTMSM) and BPNN prediction model are validated using experimental data, and the control performance of BPNN-MPC is compared with proportional-integral-derivative (PID) control under three driving cycles. Results indicate that the average error rates of the EDTMSM are below 3.5%, and the BPNN prediction model achieves a MAPE below 0.35% and an absolute error below 0.18°C. Compared with PID control, BPNN-MPC reduces the peak motor oil outlet temperature by 3.79°C, 1.78°C, and 3.71°C, and the peak motor controller coolant outlet temperature by 3.87°C, 1.66°C, and 4.64°C under WLTC, CLTC, and NEDC conditions, respectively. The total actuator energy consumption is reduced by 2.17%, 5.07%, and 4.35%, respectively. These results indicate that BPNN-MPC improves the thermal control performance and energy-saving operation of the EDTMS under multiple driving cycles.

Optimizing Energy Management in Fuel Cell Hybrid Electric Vehicles for Efficient Power Distribution and Enhanced Performance Across Different Driving Conditions

Rising concerns over global warming, emissions, and fossil fuel depletion are driving the adoption of fuel cell hybrid electric vehicles (FHEVs). By integrating a fuel cell with an ultracapacitor, they enhance efficiency and performance, but nonlinear behavior under demanding conditions challenges voltage and speed control. This paper presents a novel control approach that synergistically combines the single‐candidate optimizer (SCO) and the Chien‐physics‐informed neural network (CPINN), referred to as the SCO‐CPINN method. The proposed framework aims to effectively regulate the DC bus voltage and improve the speed tracking accuracy by minimizing the steady‐state error and reducing the response time. A proportional derivative–proportional integral derivative second derivative (PDPID2) controller is designed to stabilize the DC bus voltage and ensure smooth vehicle speed tracking under the European extra‐urban driving cycle (EUDC). The SCO algorithm optimizes power consumption, while the CPINN model predicts vehicle range under varying driving conditions. Implemented in MATLAB, the proposed technique is benchmarked against existing techniques such as the contrastive self‐supervised graph neural network (CSGNN), multi‐objective particle swarm optimization (MOPSO), and soft actor‐critic algorithm (SACA). The SCO‐CPINN controller achieves the lowest steady‐state error of 0.3 V, outperforming CSGNN (3.2 V), MOPSO (4.5 V), and SACA (6.7 V). These results demonstrate the superior accuracy, faster response, and enhanced energy management capability of the proposed method, promoting more efficient and reliable control strategies for FHEVs.