检索结果-内蒙古大学图书馆

The International Conference on Forthcoming Networks and Sustainability (FoNeS 2022)

作者： Q. Zeng J. Xu J. Lin Guangzhou Huali College Guangzhou 511300 Guangdong People's Republic of China

As an effective process of passive energy saving, natural ventilation can not only use renewable energy to reduce non-renewable energy, but also improve indoor air quality, providing people with a healthier and more comfortable environment. With the gradual creation of sustainable development space, people pay more and more attention to energy saving, and natural ventilation is also regarded as a system and environmentally friendly ventilation technology. Natural ventilation is an important technical dimension in the construction of greenhouse today. The dual driving force of air pressure and thermal pressure can promote the generation of natural air, thus achieving global cooling, improve thermal comfort, and improve indoor air quality by blowing fresh air. The air pressure and the hot air pressure are always constant and unbalanced. Based on the scientific basis of near air pressure, the effect of the simulated ventilation model is analyzed using CFD phoenics software. Based on CFD numerical simulation technology, the typical structure is simulated on phoenics software platform, and some rules are obtained through analysis. The numerical model uses k-turbulence model, adopts the finite volume method for discrete, second order windward dispersion format, and the algorithm adopts SIMPLE algorithm coupled with speed and pressure. Finally, the outdoor building layout and the exterior window parameters of the typical rooms are obtained, so that the community building can meet the requirements of green ventilation. The experiment has proved that under the simulated terrain of this paper, the average number of indoor air ventilation can reach about 5 times, the air air age is small, and the air quality is improved.

关键词： computational fluid dynamics finite volume methods flow simulation mechanical engineering computing numerical analysis sustainable development turbulence ventilation

来源：评论

学校读者我要写书评

暂无评论

Research on a new type of buffering valve for vehicle shifting

引用

JOURNAL OF engineering-JOE 2020年第9期2020卷 783-788页

作者： Zhang, Qihui Xiong, Wei Ruan, Jian Lv, Qingjun Wang, Zuwen JiangXi Univ Sci & Technol Sch Mech & Elect Engn Ganzhou 341000 Peoples R China DaLian Maritime Univ Ship Electromech Equipment Inst Dalian 116026 Peoples R China Zhejiang Univ Technol Key Lab Special Purpose Equipment & Adv Proc Tech Minist Educ Hangzhou 310014 Peoples R China China North Ind Grp Corp China North Vehicle Res Inst Beijing 100072 Peoples R China

The traditional buffering valve for vehicle shifting mainly relies on the throttle hole and spring to control the pressure in the clutch. However, its accommodative facility and adaption are inferior. Therefore, two-dimensional (2D) digital technology is proposed to be applied to the vehicle shift buffering area, and the 2D digital buffering valve is designed. This study introduces the structure and working principle of the 2D digital buffering valve and establishes the mathematical model of the 2D digital buffering valve. The classical proportional-integral-differential control algorithm is adopted and Matlab/Simulink is used to simulate its control model. Finally, an experimental study is carried out. The study results show that when the frequency is 50 Hz, the amplitude of the valve output pressure decays to -3 dB, and when the frequency is 60 Hz, the phase of the valve output pressure lags by 90 degrees. The output of the 2D digital buffering valve meets the requirement of the change of the oil pressure in the clutch during the vehicle shifting process. The control precision of its buffering pressure characteristic reaches 15%. The simulation and test results of the buffering valve are consistent, which verifies the correctness of the simulation model.

关键词： three-term control mathematics computing clutches valves hydraulic control equipment mechanical engineering computing two-dimensional digital technology vehicle shift buffering area 2D digital buffering valve 2D digital pilot valve buffering valve outlet valve output pressure lags buffering pressure characteristic vehicle shifting traditional buffering valve frequency 60 0 Hz frequency 50 0 Hz noise figure -3 0 dB

来源：评论

学校读者我要写书评

暂无评论

Research on satellite performance degradation assessment based on support vector data description (SVDD)

Research on satellite performance degradation assessment bas...

引用

9th International Symposium on Test Automation & Instrumentation (ISTAI 2022)

作者： S. Wang H. Tian W. Tang S. Zhao P. Wang X. Wang China Academy of Space Technology Beijing People's Republic of China Beijing Institute of Spacecraft System Engineering Beijing People's Republic of China DFH Satellite Co. Ltd. Beijing People's Republic of China

In order to solve the problem that the potential performance degradation of satellites is difficult to be discovered, a performance degradation assessment method for satellites is proposed. First, the entropy of the training samples and the test samples is calculated, then the entropy of the training samples are subjected to SVDD model training to obtain the performance degradation assessment model, and the performance degradation assessment of the test samples is further performed, and the degradation degree is quantitatively classified. Finally, the feasibility of the research method is verified by a case verification of two-floated gyro on an in-orbit satellite.

关键词： artificial satellites data description entropy mechanical engineering computing product life cycle management sampling methods support vector machines

来源：评论

学校读者我要写书评

暂无评论

Study on planetary transmission coupling fault diagnosis based on machine learning

Study on planetary transmission coupling fault diagnosis bas...

引用

9th International Symposium on Test Automation & Instrumentation (ISTAI 2022)

作者： B. Wang S. Dong C. Ma F. Zhou Beijing Information Science and Technology University Beijing People's Republic of China Institute of Data Communication Science and Technology Beijing People's Republic of China

In this paper, the fault diagnosis of a planetary gearbox is studied theoretically and experimentally. A fault diagnosis method combining variational mode decomposition (VMD) and relevance vector machine (RVM) was proposed. Through VMD decomposition of gearbox vibration signals, Through VMD decomposition of gearbox vibration signals, multi-parameter feature vectors were constructed and input into RVM fault identification model to realize effective identification of single fault The simulation model of planetary transmission system and the data acquisition and analysis of scale experiment were used to verify the results. The results show that the diagnostic accuracy of the proposed method is 98.3%, which is true and effective.

关键词： data acquisition fault diagnosis gears learning (artificial intelligence) mechanical engineering computing vibrations

来源：评论

学校读者我要写书评

暂无评论

A study of semi-supervised planetary gearbox condition diagnosis with small samples

A study of semi-supervised planetary gearbox condition diagn...

引用

9th International Symposium on Test Automation & Instrumentation (ISTAI 2022)

作者： Z. Ma Z. Yang C. Ma S. Wang F. Zhou Beijing Information Science and Technology University Beijing People's Republic of China Beijing Jingwei Hirain Technologies Co. lnc. Beijing People's Republic of China

Planetary gearboxes can provide a large transmission ratio in a small space and are widely used in large and complex mechanical equipment such as fans, helicopters and cranes. With the development of technology, the probability of failure is relatively reduced, and the samples of failure data obtained from long time operation are small, so it is important to study the method of planetary gearbox condition detection and fault diagnosis based on small samples. In this paper, the research of planetary gearbox condition diagnosis method based on deep belief network (DBN) is carried out for small sample fault data. The study proposes a fault diagnosis method combining CEEMD-wavelet noise reduction and DBN semi-supervised network from the aspects of small fault sample problem and intelligent diagnosis technology of planetary gearbox. The results show that under the same analysis conditions, the accuracy of the condition diagnosis results of CEEMD-wavelet noise reduction combined with DBN semi-supervised network reaches 97.5%, with higher accuracy and better diagnostic stability.

关键词： belief networks condition monitoring fault diagnosis gears mechanical engineering computing probability wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

Material strain image segmentation algorithm based on improved UNET network

Material strain image segmentation algorithm based on improv...

引用

9th International Symposium on Test Automation & Instrumentation (ISTAI 2022)

作者： Y. Guan Z. Pang H. Sun X. Chen College of Mechanical and Materials Engineering North China University of Technology Beijing People's Republic of China

In the field of sheet metal material forming, mastering the mechanical properties of metal materials is the basis for realizing forming. In order to explore the forming mechanism of anisotropic materials, it is important to use biaxial tensile testing machines to obtain biaxial tensile mechanical properties under different loading paths. Based on the encoder-decoder network structure and the deep learning image segmentation algorithm, the marked deformation region of the specimen is obtained and segmented. The convolution neural network obtain and encode the features of input images in the downsampling area. And bilinear interpolation and deconvolution extend and decode those features in the upsampling area. Finally, the result of image segmentation is obtained. Experimental training results show that the model has a good recognition accuracy.

关键词： convolutional neural nets deep learning (artificial intelligence) deformation image segmentation interpolation mechanical engineering computing sheet materials sheet metal processing tensile strength tensile testing

来源：评论

学校读者我要写书评

暂无评论

Investigation on linearisation of data-driven transport research: two representative case studies

Investigation on linearisation of data-driven transport rese...

引用

15th World Conference on Transport Research (WCTR)

作者： Zou, Yun Kuang, Yan Zhi, Yue Qu, Xiaobo Sch Civil & Environm Engn Univ Technol Sydney Sydney NSW 4007 Australia Griffith Univ Griffith Sch Engn Gold Coast Qld 4222 Australia Binzhou Med Univ Sch Rehabil Med Yantai 264003 Peoples R China Chalmers Univ Technol Dept Architecture & Civil Engn S-41296 Gothenburg Sweden

Transportation engineering, as a practical engineering discipline, relies heavily on the accurate calibration of importation parameters from field data. In the real world, most transport relations possess inherent non-linearity. Two prevailing methods for handling non-linear regression are the non-linear least-squares method (LSM) with an iterative solution, and linearisation for the non-linear regression function. The second method applies a linear regression method to solve the non-linear regression problem but requires a data transformation of the observations from variant coordinates, and the objective function is suspected to be changed accordingly. This work describes the authors' investigation into the problem of non-linear regression through two illustrative examples, the calibration of three non-linear (either exponential or logarithmic) single-regime models for fundamental diagram and the regression of non-linear (power) bunker-consumption model, by applying the weighted LSM (WLSM) and the ordinary LSM to calibrate. It is found that linearising the regression model leads to deviations, and the data transformation can create even more concern with the WLSM because the weights can be redistributed after the data transformation. A further investigation into the linear regression and the non-linear regression gives more suggestions on the choice of regression method.

关键词： transportation least squares approximations mechanical engineering computing regression analysis data-driven transport research transportation engineering nonlinearity nonlinear regression function linear regression method nonlinear regression problem data transformation nonlinear bunker-consumption model regression model

来源：评论

学校读者我要写书评

暂无评论

Assessment of different artificial neural networks for predicting bridge deck condition

Assessment of different artificial neural networks for predi...

引用

4th Smart Cities Symposium (SCS 2021)

作者： N. Elshaboury Construction and Project Management Research Institute Housing and Building National Research Centre Egypt

The bridge deck is the most vulnerable element of the bridge structure to deterioration because it is susceptible to harsh traffic and weather conditions. Therefore, continuous consideration must be dedicated to monitoring the bridge deck condition. In this regard, this research provides an artificial neural network (ANN) model that predicts the bridge deck condition using the Levenberg-Marquardt training algorithm. The proposed model is trained, tested, and validated using the national bridge inventory data in the District of Columbia, United States. Four ANN models with one hidden layer and a different number of neurons in the hidden layer are developed. The hidden layers of the ANN1, ANN2, ANN3, and ANN4 models comprise 5, 15, 25, and 35 neurons, respectively. The models are compared using four assessment metrics (i.e., Nash-Sutcliffe efficiency: NSE, fraction of prediction within a Factor of Two: FACT2, root mean square error: RMSE, and mean bias error: MBE). The ANN2 model (NSE=0.25, FACT2=0.53, RMSE=0.77, and MBE=0.60) outperform the other models during the testing phase. The proposed model has proved its accuracy and robustness in forecasting the bridge deck condition. The research findings can assist bridge stakeholders in setting budget allocation plans and prioritizing maintenance, rehabilitation, and replacement policies.

关键词： bridges (structures) maintenance engineering mean square error methods mechanical engineering computing neural nets

来源：评论

学校读者我要写书评

暂无评论

Influence of lighting rod flange connection parameters on bolt fatigue performance and improvement measures

Influence of lighting rod flange connection parameters on bo...

引用

22nd International Symposium on High Voltage engineering (ISH 2021)

作者： M. Zhao X. Dong J. Wang Y. Yang M. Li W. Zhuang X. Zhang State Grid Xin jiang Company Limited Electric Power Research Institute Urumqi People's Republic of China

Aiming at the problem of multiple accidents of steel pipe lightning rods in high-voltage substations, the bolt stress is calculated by finite element software, the pre-tightening force and the influence of adjacent bolt damage on the flange connecting bolts are analyzed, the rain flow counting method is used to calculate the stress time history, and the known SN is used The curve judges the damage of the bolts on the right side, calculates the damage value within the corresponding time, and obtains the fatigue mechanism of the flange bolts of the steel tube lightning rod of the high-voltage substation, and then proposes methods to reduce the fatigue of the bolts and improve the connection of the steel tube.

关键词： fasteners fatigue finite element analysis flanges mechanical engineering computing pipes steel

来源：评论

学校读者我要写书评

暂无评论

Analysis and design of a pulse-closing vacuum switch for catenary fault detection

引用

IET GENERATION TRANSMISSION & DISTRIBUTION 2019年第13期13卷 2646-2651页

作者： Zhang, Mingzhi Wang, Yi Wen, Huabin Li, Peng Wang, Shuti Beijing Jiaotong Univ Sch Elect Engn Beijing 100044 Peoples R China Beijing Jiaotong Univ Sch Elect & Informat Engn Beijing 100044 Peoples R China

This study presents a novel pulse-closing vacuum switch (PCVS) that is used for catenary fault detection and location. First, as the application background of PCVS, the principle theory of the fault detection and locating system is briefly introduced. Then, the PCVS is analysed and designed based on the detailed analysis of its working process and principle. To validate the performance of the designed PCVS, the multi-physical domain co-simulation numerical model is implemented using the ANSYS Maxwell and ANSYS Simplorer. Finally, a PCVS prototype is developed with permanent magnet closing and repulsive force opening to verify the simulation results. The simulations and experiments both approve that the contact time between the moveable contact and static contact can be controlled to be <6 ms. This meets the pulse-closing technology requirement for the fault detection and locating system.

关键词： finite element analysis vacuum switches fault diagnosis mechanical engineering computing design catenary fault detection novel pulse-closing vacuum switch application background principle theory locating system designed PCVS multiphysical domain co-simulation numerical model PCVS prototype permanent magnet closing pulse-closing technology requirement time 6 0 ms

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：