http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Pan Zhang,Yuetong Zhao,Xiangfeng Tian,Yanxi Ji,Yuxuan Shu,Kun Fu,Dong Fu,Lemeng Wang 한국화학공학회 2022 Korean Journal of Chemical Engineering Vol.39 No.11
Tetramethylammonium glycine ([N1111][Gly]) can be completely ionized into cation [N1111]+ and anion [Gly] in aqueous solution. The anion contains an amino -NH2 and a carboxyl -COO, both of which can react with hydrogen sulfide (H2S). Therefore, [N1111][Gly] was used to promote the selective absorption of H2S in coke oven gas (COG) by N-methyldiethanolamine (MDEA). The absorption performance and selectivity of H2S in the aqueous solution of MDEA-[N1111][Gly] were investigated. The effects of MDEA mass fraction, [N1111][Gly] mass fraction, temperature, H2S partial pressure and CO2 partial pressure on the absorption capacity and selectivity were clarified. The results showed that an aqueous solution of MDEA-[N1111][Gly] has good selectivity for H2S in COG. The absorption capacity was large and the mass fraction of the solute in the absorbent reached more than 0.55, thereby having outstanding advantages in the aspects of saving energy consumption and operating cost and having a good application potential.
Improved Convolutional Neural Network for Laser Welding Defect Prediction
Weiwei Huang,Xiangdong Gao,Yuhui Huang,Yanxi Zhang 한국정밀공학회 2023 International Journal of Precision Engineering and Vol.24 No.1
In order to predict the laser welding defects, a convolutional neural network prediction model is established. The keyhole image and plume image collected by a high-speed camera are processed to obtain visual information such as keyhole area and plume area. The rolling mean and standard deviation methods are used to calculate the fluctuation degree indicators of the visual information and the optical radiation information obtained by the photoelectric sensor. Finally, three improved one-dimensional convolutional neural network prediction models with a learning rate dynamic adjustment mechanism are established to predict welding defects. Experimental results indicate that the improved one-dimensional convolutional neural network prediction model can avoid premature convergence four times to achieve the best performance. The fluctuation degree indicators of sensor features can distinguish the welding state more easily than the sensor features. The reliability test of the new weld is carried out. The prediction accuracy of fusion detection model of sensor features and fluctuation degree indicators is 99.21%. The improved model can accurately predict laser welding defects.