分类： 能源科学 >> 储能技术 提交时间： 2024-03-31
摘要： This work experimentally explores the influence of thesodiumchloride pollution on thePEMFC performancein the marine saltsprayenvironment by analyzing the concentration diffusion characteristics of the sodium chloride in thePEMFC membraneelectrodes. Firstly, a set of experiments were carried out to determine the distribution of the sodium chloride components in the membrane electrodes, where five different salt spray environments (i.e., 100mg/L, 200mg/L, 300mg/L, 400mg/L, and 500mg/L of the salt component, respectively) were used/employed to analyze the concentration diffusion characteristics of the sodium chloride. Then, the obtained samples were microscopically characterized and elementally analyzed by thefield emission scanning electron microscopy(FESEM) and the energy spectrometry. Subsequently, a least squares-based model was proposed to predict the diffusion rate of the contaminatingions inthe membrane electrodes. Lastly, the pollution of the sodium chloride was evaluated/assessed to reveal theperformance degradationof the PEMFCs. The experimental results demonstrated that (1) the sodium chloride fraction existed as crystals orions inthe membrane electrodes in the marine salt spray environment; (2) the sodium chloride poisoning was founded in theproton exchange membranein the form ofsodium ions; (3) and the sodium-to-chloride ratio was proportional to the contamination time and the salt spray in the proton exchange membrane.
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.
点击量
通过
点击量
下载量
评论
