http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Thermal management analysis of serial-connection three-chamber piezoelectric pump
Lipeng He,Xiaoqiang Wu,Zheng Zhang,Jingran Wang,Dianbin Hu,Yamei Liu,Guangming Cheng 대한기계학회 2021 JOURNAL OF MECHANICAL SCIENCE AND TECHNOLOGY Vol.35 No.10
The design of a micropump with high performance and excellent reliability on thermal management still remains a challenge for electronic cooling. The performance of a piezoelectric pump with 3 chambers connected in series on thermal management was investigated for electronic cooling in this study. Two S-shaped channel heat sinks and the piezoelectric pump with 3 chambers connected in series were combined to form a loop cooling system. With water as the pumping medium, the tested pump has a flow rate most up to 690.6 ml/min at an input voltage of 220 V and an input frequency of 110 Hz. Suitability of the system has been demonstrated through simulation analysis and experimental verification for temperature control. A temperature reduction of 3 °C of CPU could be achieved at 250 mL/min flow rate generated by the piezoelectric pump with 3 chambers connected in series.
Yongchao Liu,Qidan Zhu,Lipeng Wang 제어·로봇·시스템학회 2022 International Journal of Control, Automation, and Vol.20 No.2
This article focuses on designing a robust adaptive fuzzy asymptotic control method for uncertain switched nonlinear systems in presence of arbitrary switching signals. The unknown dynamics of switched systems are addressed by making use of fuzzy logic systems. Different from the existing approximation-based schemes, the asymptotic tracking performance is achieved by employing a bound estimation method, some smooth functions and the backstepping technique. Through constructing Lyapunov function, the devised scheme can guarantee the stability and asymptotic convergence character of the controlled systems. Finally, the availability of the presented approach is verified via simulation examples.
Prediction and Feature Importance of Earth Pressure in Shields Using Machine Learning Algorithms
Hongyu Huang,Lipeng Liu,Ruilang Cao,Yuxin Cao 대한토목학회 2023 KSCE Journal of Civil Engineering Vol.27 No.2
To reduce subjectivity and uncertainty when maintaining suitable earth pressure in earth pressure shields that can prevent heave or collapse, many prediction models using machine learning algorithms were proposed, but little research into the effects of other parameters on earth pressure has been undertaken, and soil conditioning parameters are always ignored. To establish a model with thorough parameters and probe into influences of other parameters, multiple machine learning algorithms were attempted. Given the accuracy, diversity and functions, random forest (RF), LightGBM and Attention-back-propagation neural network (Attention-BPNN) were further analyzed. Then, two RF models were compared in this research, one with soil conditioning parameters and the other without. Meanwhile, a case study was utilized to verify the reliability of the model. Finally, the feature importance of three models was compared and the variation rules of the most four important features were discussed by controlling variates. The results showed that soil conditioning parameters delivered a significant reduction in the prediction error. The case study demonstrated that the proposed model can satisfy engineering requirements. More earth pressure should give priority to increasing propulsion pressure, advance rate, and reducing foam air flow, rotational speed of screw conveyor, and vice versa.
Deformation and failure mechanism exploration of surrounding rock in huge underground cavern
Zhenhua Tian,Jian Liu,Xiaogang Wang,Lipeng Liu,Xiaobo Lv,Xiaotong Zhang 국제구조공학회 2019 Structural Engineering and Mechanics, An Int'l Jou Vol.72 No.2
In a super-large underground with “large span and high side wall”, it is buried in mountains with uneven lithology, complicated geostress field and developed geological structure. These surrounding rocks are more susceptible to stability issues during the construction period. This paper takes the left bank of Baihetan hydropower station (span is 34m) as a case study example, wherein the deformation mechanism of surrounding rock appears prominent. Through analysis of geological, geophysical, construction and monitoring data, the deformation characteristics and factors are concluded. The failure mechanism, spatial distribution characteristics, and evolution mechanism are also discussed, where rock mechanics theory, FLAC3D numerical simulation, rock creep theory, and the theory of center point are combined. In general, huge underground cavern stability issues has arisen with respect to huge-scale and adverse geological conditions since settling these issues will have milestone significance based on the evolutionary pattern of the surrounding rock and the correlation analyses, the rational structure of the factors, and the method of nonlinear regression modeling with regard to the construction and development of hydropower engineering projects among the worldwide.
SVM Classification for High-dimensional Imbalanced Data based on SNR and Under-sampling
Li Peng,Bi Ting-ting,Liu Yang 보안공학연구지원센터 2015 International Journal of Multimedia and Ubiquitous Vol.10 No.4
Support vector machine (SVM) is biased towards the majority class, in some case dataset is class-imbalanced and the bias is even larger for high-dimensional. In order to improve the classification accuracy of SVM on high-dimensional imbalanced data, we combine signal-noise ratio (SNR) and under-sampling technique based on K-means. In this article firstly we apply SNR into feature selection to reducing the feature amount then solve the problem of data imbalance using under-sampling technique based on K-means. To verify the feasibility of the proposed strategy, we utilize some metrics such as receiver operating characteristic curve (ROC curve) and area under the receiver operating characteristic curve (AUC value).As a result, the AUC value increased by 4%~16% before and after the process. The experimental results show that our strategy is feasible and effective exactly.