分类: 动力与电气工程 >> 工程热物理学 提交时间: 2017-03-31 合作期刊: 《热科学学报》
摘要: This paper presents effects of heating directions on heat transfer performance of R134a flow boiling in mi- cro-channel heat sink. The heat sink has 30 parallel rectangular channels with cross-sectional dimensions of 500m width 500m depth and 30mm length. The experimental operation condition ranges of the heat flux and the mass flux were 13.48 to 82.25 W/cm2 and 373.3 to 1244.4 kg/m2s respectively. The vapor quality ranged from 0.07 to 0.93. The heat transfer coefficients of top heating and bottom heating both were up to 25 kW/m2 K. Two dominate transfer mechanisms of nucleate boiling and convection boiling were observed according to boiling curves. The experimental results indicated that the heat transfer coefficient of bottom heating was 13.9% higher than top heating in low heat flux, while in high heat flux, the heat transfer coefficient of bottom heating was 9.9%.higher than the top heating, because bubbles were harder to divorce the heating wall. And a modified corre- lation was provided to predict heat transfer of top heating.
分类: 机械工程 >> 机械设计 提交时间: 2024-04-01
摘要: Overstaffing production in underground coal mining is not convenient for daily management, and incomplete information of coal miners hinders the rescue process of firefighters during mine accidents. To address this safety sustainability issue, a novel face recognition method based on an improved multiscale neural network is proposed in this paper. A new depthwise seperable (DS)-inception block is designed and a joint supervised loss function based on center loss theory is developed to constructe a new multiscale model. The miniers can be recognized in the harsh underground environment during the life rescue. Experimental results show that the accuracy, recall and F1-score indexes of the proposed method for the miner face recognition in the underground mining environment are 97.26%, 94.17% and 95.42%, respectively. Transfer model with joint supervised loss can effectively improve the recognition accuracy by about 0.5~1.5%. In addition, the average recognition accuracy of the proposed face recognition method achieves to 91.34% and the miss detection rate is less than 5% in the dugout tunnel of coal mine.