The heat generation rate (HGR) of lithium-ion batteries is crucial for the design of a battery thermal management system. Machine learning algorithms can effectively solve nonlinear problems and have been implemented in the state estimation and life prediction of batteries; however, limited research has been conducted on determining the battery HGR through machine learning. In this study, we employ three common machine learning algorithms, i.e., artificial neural network (ANN), support vector machine (SVM), and Gaussian process regression (GPR), to predict the battery HGR based on our experimental data, along with cases of interpolation and extrapolation. The results indicated the following: (1) the prediction accuracies for the interpolation cases were better than those of extrapolation, and the R2 values of interpolation were greater than 0.96; (2) after the discharge voltage was added as an input parameter, the prediction of the ANN was barely affected, whereas the performance of the SVM and GPR were improved; and (3) the ANN exhibited the best performance among the three algorithms. Accurate results can be obtained by using a single hidden layer and no more than 15 neurons without the additional input, where the R2 values were in the range of 0.89–1.00. Therefore, the ANN is preferable for predicting the HGR of lithium-ion batteries.
The environmental control system (ECS) is one of the most important systems in the aircraft used to regulate the pressure, temperature and humidity of the air in the cabin. This study investigates the influences of different architectures on the thermal performance and network structure of ECS. The refrigeration and pressurization performances of ECS with four different architectures are analyzed and compared by the endoreversible thermodynamic analysis method, and their external and internal responses have also been discussed. The results show that the connection modes of the heat exchanger have minor effects on the performance of ECSs, but the influence of the air cycle machine is obvious. This study attempts to abstract the ECS as a network structure based on the graph theory, and use entropy in information theory for quantitative evaluation. The results provide a theoretical basis for the design of ECS and facilitate engineers to make reliable decisions.
Based on the equivalent heat transfer capacity, a closed simulation ground-test method of the ram air is proposed, it can provide the ram air's test condition for deriving the performance of commercial airliners’ aircraft environmental control system (ECS). Analyzed results show that the proposed method can simulate different temperatures and pressures at the range of 0∼10 km flight altitudes under the compressor pressure ratio of 1.2 and turbine expansion ratio of 5. Temperatures and pressures can vary from -17.6 ∼ 40°C and 40∼101 kPa, respectively. In the meantime, compared to the traditional fan's simulation method, the energy consumption is decreased about 35%. By analyzing the key factors in method, it shows that altitudes and ACM characteristics can influence the power consumption and other conformance. Therefore, it needs to select ACM machine according to test requirements in engineering applications.
To recover the power from the cabin's exhaust, two schemes are proposed and the thermodynamic parameters and the components’ performance of the two schemes are analysed in this study. Based on the take-off gross weight method, the differences among the two proposed schemes and the state-of-the-art scheme are compared. Results show that compared to the value of state-of-the-art scheme, the fuel penalty loss of scheme I adds 24.4 kg and that of scheme II increases 29.1 kg. In consideration of the compression ratio of the electrical driven compressor, that for scheme I is 1.13 and for scheme II is 2.24. With respect to the value of the state-of-the-art scheme of 2.8, there are about 60% and 21% reduction respectively in the two newly-proposed schemes. Obviously, the two proposed schemes can significantly improve the fresh air pressure and reduce the demand for the performance of the electrical driven compressor, which will be more suitable for the development of the electrical environmental control system.
The aircraft air-cycle system (ACS) provides cabin cooling, dehumidification, and pressurization. As a key component, the water separator removes free moisture from the air, preventing turbine icing/blockage under high humidity and avoiding humidity-induced electronics failures, thus ensuring reliable ACS operation. Existing studies focus mainly on oil and chemical applications, with limited work for aircraft ACS. To address this research gap, this study investigates a straight-through cyclone water separator for aircraft ACS applications. We built a test platform to measure separation efficiency and conducted experiments at swirl angles of 20°, 30°, and 40°. A simulation model based on the Reynolds Stress turbulence model and a discrete phase model was established, and its simulation efficiency agreed with experiments within 4.1%. Simulation on water separator under high-pressure and low-pressure conditions were conducted, revealing internal flow fields and droplet dynamics. Results show each swirl angle has a distinct high-efficiency operating range, enabling selection according to system parameters across air mass flow rates; under varying humidification rate, the 40° swirl generator performed best. Simulations further indicate that higher operating pressure markedly improves performance: pressure loss decreased from 4.5 kPa to 0.7 kPa, while separation efficiency increased by 30.7%.
This article proposes a heating method based on heat pump technology to address the large amount of low-grade waste heat generated by a certain type of ultra-high voltage direct current (UHVDC) converter valve. Thermal performance calculations for two systems, a basic vapor compression heat pump system (BVCHPS) based on thermal expansion valve throttling and an ejector-enhanced heat pump system (EEHPS) are analyzed. The research results show that the EEHPS exhibits superior COP and exergy efficiency when generating hot water above 80 °C using a heat source below 50 °C. Additionally, mathematical modeling analysis identifies optimal structural parameters such as nozzle throat diameter, throat area ratio, and nozzle outlet diameter for the ejector in its design state. The low-temperature waste heat recovered from the UHVDC converter valves can be further used in engineering applications such as heating, refrigeration, seawater desalination, and sewage treatment.