Heat dissipation in high-heat flux micro-devices has become a pressing issue. One of the most effective methods for removing the high heat load of micro-devices is boiling heat transfer in microchannels. A novel approach to flow pattern and heat transfer recognition in microchannels is provided by the combination of image and machine learning techniques. The support vector machine method in texture characteristics successfully recognizes flow patterns. To determine the bubble dynamics behavior and flow pattern in the micro-device, image features are combined with machine learning algorithms and applied in the recognition of boiling flow patterns. As a result, the relationship between flow pattern evolution and boiling heat transfer is established, and the mechanism of boiling heat transfer is revealed.
Under low outdoor temperature and high humidity, frost easily forms on the Heat Exchanger (Exchanger) surface on the outdoor side. The formation and growth of this frost layer will seriously impact the Exchanger’s heat extraction process and the system’s energy efficiency, triggering malfunction in the compressor. To this end, this work first analyzes the formation and growth mechanism of Exchanger surface frosting and condensation. It then summarizes the current research status of Machine Vision (MV) technology in defrosting and decondensation. Further, it previews the follow-up research direction. The experimental findings show that MV technology can automatically observe frost and dew, guaranteeing a real-time understanding of the frost layer. Directly obtaining the frost and dew information from the image can significantly save human resources and improve efficiency.
As urban subway systems have become the backbone of public transportation, fire safety in subway tunnels has attracted increasing attention. The piston wind generated by moving trains complicates smoke propagation and poses significant challenges to conventional smoke control strategies. This study combines scaled experiments and theoretical analysis to investigate the effects of mechanical ventilation systems on smoke propagation and smoke exhaust performance during the emergency stopping of a burning train in subway tunnels. The influences of fire source location and train speed on the performance of vertical shaft ventilation (VSV) and local semi-transverse ventilation (LSTV) are systematically evaluated. The results show that the optimal smoke exhaust performance is achieved when the train stops upstream of the ventilation shaft, with VSV reducing the peak downstream smoke temperature by approximately 70%. To address the limitations of VSV in ultra-long subway tunnels caused by shaft spacing and engineering constraints, a combined ventilation (CV) system integrating LSTV with longitudinal ventilation is proposed. The results demonstrate that the CV system establishes a stable airflow pattern within the tunnel and achieves nearly complete smoke removal within 98 s under different train operating speeds. Moreover, it reduces the dependence of smoke exhaust performance on the fire source location. The findings provide theoretical support and engineering guidance for the design and optimization of mechanical smoke exhaust systems in subway tunnels.