Lithium-ion batteries (LIBs) are critical for various applications, and effective thermal management is important for their safety, performance, and lifespan. Traditional physics-based modeling of battery thermal behavior is computationally complex and requires detailed parameters. Using data-driven modeling to predict thermal characteristics of batteries offers a promising alternative. This review comprehensively examines the utilization of data-driven methods in predicting LIB thermal behavior and designing battery thermal management systems. It explores commonly used data-driven techniques and focuses on their applications in predicting heat generation, temperature distribution, and cooling performance. Specific data-driven models for battery thermal prediction are presented, with a comparative analysis of their strengths and weaknesses. The review concludes that data-driven models can effectively predict battery thermal behavior, offering computational efficiency compared to physics-based simulations. Future research directions include hybrid data-driven/physical modeling, ensemble modeling, and incorporating explainable artificial intelligence techniques to enhance model interpretability. These advancements will lead to more accurate and interpretable models, contributing to the safe and efficient applications of LIB systems.

This study presents an improved comprehensive atomization model for a pressure swirl atomizer. The model integrates internal flow predictions, linear instability analysis of a swirling annular liquid sheet, primary atomization sub-model, and droplet velocity sub-model. Measurement data combined with the inviscid theory model predict the internal flow, providing liquid sheet velocity and thickness at the atomizer outlet. The dispersion relation of surface disturbances is obtained through linear instability analysis. A primary breakup predictive model for particle size distribution is constructed based on the wavelength and growth rate within the full unstable wavenumber range of the dispersion relation. Assuming uniform circumferential distribution and a normal distribution of spray angles, the droplet velocity is assigned according to the liquid sheet velocity. The model is implemented into Eulerian–Lagrangian simulations as initial conditions for discrete phase droplets to simulate the spray field. Results show the model can accurately predict the Sauter mean diameter with an error of less than 6% and effectively predicts the spray structure and spray cone angle. The dependency of the model on its parameters is also studied, determining that the values of the ligament constant and dispersion angle have an obvious impact on the prediction of Sauter mean diameter and spray structure.

This study investigates the turbulent flow characteristics and heat transfer performance within a rectangular cooling channel with an aspect ratio of 5:3 and featuring perforated ribs, then explores the effects of the rib perforation directions on its thermal hydraulic performance. Through experimental tests (transient thermographic liquid crystal technique) and numerical simulations, it is demonstrated that horizontal perforated ribs can effectively reduce pressure loss at a high Reynolds number while maintaining notable heat transfer enhancement. Additionally, changing the rib perforation directions results in diverse effects on flow field and heat transfer. Our results show that horizontal perforated ribs can compress the recirculation vortex behind ribs, enhancing heat transfer by flow scouring, whereas upward-tilted perforated ribs increase flow friction and weaken heat transfer due to coupling of the airflow with the separation vortices behind the ribs. Downward-tilted ribs enhance local heat transfer by directing airflow behind the rib, and can also cause detachment of vortices and reduced friction. Our results indicate that introducing horizontal perforated ribs into a rectangular internal cooling channel can decrease pressure loss without significantly compromising heat transfer performance.

In aero-engine combustion research, the pursuit of cost-effective and rapid methods for acquiring precise flow fields across various operating conditions remains a significant challenge. This study offers novel insights into the rapid modeling of complex multi-swirling flows, introducing flow-field-based analytical methods to evaluate flow topologies, spray dispersion, ignition dynamics, and flame propagation patterns. A data-driven model is proposed to predict the swirling velocity field inside a multi-swirl combustor, using spatial coordinates and air pressure drops as input features. Particle Image Velocimetry (PIV) experiments under different air pressure drops are performed to generate the necessary flow field dataset. A fully connected deep neural network is designed and optimized with a focus on prediction accuracy, training efficiency, and mitigation of over-fitting. The predicted flow characteristics, including swirling jets, shear layers, recirculation zones, and velocity profiles, align closely with the PIV experimental results. This demonstrates the model’s capability to effectively capture the intricate multi-swirling flow structures and the complex relationships between input parameters and the resulting flow field. Furthermore, the trained model shows excellent generalization capability, accurately predicting flow fields under previously unseen operating conditions. Finally, combustion-relevant characteristics, such as ignition and flame propagation, are successfully extracted and analyzed from the predicted flow fields using the proposed deep learning framework.

Dual-orifice atomizers have been developed to overcome the limitations of simplex atomizers—where “simplex” refers to having only a single flow channel—which cannot adjust flow rates over a wide range. This study explores the internal flow and mixing characteristics of dual-orifice atomizers using the Volume of Fluid method. The effects of four key parameters—primary post thickness, primary recess length, secondary swirl number, and mass flow rate ratio—on flow dynamics and atomizer performance, particularly exit film thickness and spray cone angle, are investigated. The results reveal that, before mixing, the low-pressure region created by the swirling flow inside the secondary nozzle increases the primary flow angle and reduces the thickness of the primary liquid film. After mixing, the velocity difference between the primary and secondary flows enhances atomization by promoting greater instability. The impingement position of the primary liquid film is influenced by recess and the low-pressure region inside the secondary nozzle, with longer recess lengths shifting the impingement point upstream. Increases in secondary swirl number, mass flow rate ratio, and primary post thickness further enlarge the low-pressure region, causing the impingement point to move upstream. The mixing regime is defined by the impingement position, with tip mixing creating velocity stratification that increases the instability. The performance of dual-orifice atomizers depends on the impingement position, resulting mixing regime, and secondary flow's swirl intensity. These findings provide valuable insights for optimizing atomizer design to improve performance.

Self-excited sweeping (SES) nozzles have attracted growing interest due to their ability to generate high-frequency oscillating jets. While prior studies have clarified their flow dynamics and atomization under atmospheric conditions, their behavior in crossflow—relevant to aero-engine and afterburner combustors—remains insufficiently understood. This study experimentally investigates the spray characteristics of a SES nozzle operating in a high-speed crossflow, with an emphasis on the influence of injection pressure. A two-dimensional phase Doppler particle analyzer (PDPA) was employed to measure droplet size and velocity distributions at multiple downstream locations. The results show that the spray morphology evolves markedly downstream. Droplet sizes decrease significantly up to the midstream region, while axial velocities increase due to momentum exchange with the crossflow. The sweeping motion of the SES nozzle induces a dominant oscillation frequency of spray characteristics. The amplitude of these oscillations varies spatially, reflecting the combined effects of sweeping dynamics and aerodynamic damping. Compared to the circular nozzle, the SES nozzle exhibits distinct spray characteristics. The circular nozzle demonstrates greater penetration, but the SES nozzle provides wider lateral coverage, a larger overall spray area, and smaller droplets. Injection pressure is found to be a critical parameter governing spray penetration, coverage, droplet size, and oscillatory behavior. Increasing pressure enhances penetration but results in a trade-off with spanwise coverage. At higher pressures, stronger atomization reduces both Sauter mean diameter and oscillation amplitudes. Overall, this work provides insights into the temporal–spatial spray characteristics of SES nozzles in crossflow environments, offering guidance for their application in aerospace propulsion systems.