检索结果-内蒙古大学图书馆

Design and Performance Analysis of HMDV Dynamic Inertial Suspension Based on Active Disturbance Rejection Control

Computer Modeling in Engineering & Sciences 2024年第8期140卷 1485-1506页

作者： Xiaofeng Yang Wei Wang Yujie Shen Changning Liu Tianyi Zhang School of Automotive and Traffic Engineering Jiangsu UniversityZhenjiang212013China Automotive Engineering Research Institute Jiangsu UniversityZhenjiang212013China Chongqing Key Laboratory of Urban Rail Transit System Integration and Control Chongqing400074China State Key Laboratory of Advanced Design and Manufacturing Technology for Vehicle Hunan universityChangsha410082China

This paper addresses the impact of vertical vibration negative effects,unbalanced radial forces generated by the static eccentricity of the hub motor,and road excitation on the suspension performance of Hub Motor Driven Vehicle(HMDV).A dynamic inertial suspension based on Active Disturbance Rejection Control(ADRC)is proposed,combining the vertical dynamic characteristics of dynamic inertial suspension with the features of ADRC,which distinguishes between internal and external disturbances and arranges the transition ***,a simulation model of the static eccentricity of the hub motor is established to simulate the unbalanced radial electromagnetic force generated under static eccentricity.A quarter-vehicle model of an HMDV with a controllable dynamic inertial suspension is then ***,the passive suspension model is studied under different grades of road excitation,and the impact mechanism of suspension performance at speeds of 0–20 m/s is ***,the three main components within the ADRC controller are designed for the second-order controlled system,and optimization algorithms are used to optimize its internal ***,the performance of the traditional passive suspension,the PID-based controllable dynamic inertial suspension,and the ADRC-based controllable dynamic inertial suspension are analyzed under different road *** results show that,under sinusoidal road input,the ADRC-based controllable dynamic inertial suspension exhibits a 52.3%reduction in the low-frequency resonance peak in the vehicle body acceleration gain diagram compared to the traditional passive suspension,with significant performance optimization in the high-frequency *** random road input,the ADRC-based controllable dynamic inertial suspension achieves a 29.53%reduction in the root mean square value of vehicle body acceleration and a 14.87%reduction in dynamic tire *** indicates that the designed controllable dynamic inertia

关键词： HMDV static eccentricity ADRC dynamic inertial suspension road excitation

来源：评论

学校读者我要写书评

暂无评论

A Cost-Sensitive Multi-scale Feature Multi-order Fusion Network for Bearing Fault Diagnosis Under Data Imbalance Conditions

A Cost-Sensitive Multi-scale Feature Multi-order Fusion Netw...

引用

International Conference on Artificial Intelligence and Autonomous Transportation, AIAT 2024

作者： Deng, Shuaiqing Lei, Zihao Wen, Guangrui Su, Yu Liu, Zimin Meng, Zhangxuan Zhang, Zhifen National Key Laboratory of Aviation Power System and Plasma Technology Xi’an Jiaotong University Xi’an710049 China State Key Laboratory for Manufacturing Systems Engineering Xi’an Jiaotong University Xi’an710049 China Key Laboratory of Education Ministry for Modern Design and Rotor-Bearing System Xi’an Jiaotong University Xi’an710049 China

ISBN: (纸本)9789819639724

Railroad transportation plays a vital role in the national economy, and fault diagnosis of its key components is of great significance in ensuring its safe operation. However, due to its long-term operation in a healthy state, it is tough to obtain fault signals, and this class imbalance data seriously degrades the diagnostic capability of intelligent diagnostic algorithms, leading to increased misclassification of minority classes. To address this problem, we propose a cost-sensitive multi-scale feature multi-order fusion network for bearing fault diagnosis under data imbalance conditions. Firstly, a lightweight multi-scale convolutional layer is employed to effectively extract the multi-scale features of the signal. Then the multi-order feature fusion is performed by a hornet to fully utilize the multi-scale information and enhance the ability to mine the limited diagnostic information of the minority class. And the excellent high-dimensional discriminative features are extracted through residual blocks. In addition, an improved cost-sensitive strategy is designed through the posterior probability distribution to rebalance the contribution of each class to the training process for improving the overall diagnostic performance of the model. Finally, the effectiveness and superiority of the proposed method are comprehensively verified by several sets of experiments with different imbalance rates. © Beijing Paike Culture Commu. Co., Ltd. 2025.

关键词： Railroad transportation

来源：评论

学校读者我要写书评

暂无评论

Cavitation recognition of axial piston pumps in noisy environment based on Grad-CAM visualization technique

引用

CAAI Transactions on Intelligence technology 2023年第1期8卷 206-218页

作者： Qun Chao Xiaoliang Wei Jianfeng Tao Chengliang Liu Yuanhang Wang State Key Laboratory of Mechanical System and Vibration Shanghai Jiao Tong UniversityShanghaiChina State Key Laboratory of Fluid Power and Mechatronic Systems Zhejiang UniversityHangzhouChina MoE Key Laboratory of Artificial Intelligence AI InstituteShanghai Jiao Tong UniversityShanghaiChina China Electronic Product Reliability and Environmental Testing Research Institute GuangzhouChina Guangdong Provincial Key Laboratory of Electronic Information Products Reliability Technology GuangzhouChina

The cavitation in axial piston pumps threatens the reliability and safety of the overall hydraulic *** signal can reflect the cavitation conditions in axial piston pumps and it has been combined with machine learning to detect the pump ***,the vibration signal usually contains noise in real working conditions,which raises concerns about accurate recognition of cavitation in noisy *** paper presents an intelligent method to recognise the cavitation in axial piston pumps in noisy ***,we train a convolutional neural network(CNN)using the spectrogram images transformed from raw vibration data under different cavitation ***,we employ the technique of gradient-weighted class activation mapping(Grad-CAM)to visualise class-discriminative regions in the spectrogram ***,we propose a novel image processing method based on Grad-CAM heatmap to automatically remove entrained noise and enhance class features in the spectrogram *** experimental results show that the proposed method greatly improves the diagnostic performance of the CNN model in noisy *** classification accuracy of cavitation conditions increases from 0.50 to 0.89 and from 0.80 to 0.92 at signal-to-noise ratios of 4 and 6 dB,respectively.

关键词： axial piston pump cavitation recognition CNN Grad-CAM spectrogram image

来源：评论

学校读者我要写书评

暂无评论

Late sowing enhances lodging resistance of wheat plants by improving the biosynthesis and accumulation of lignin and cellulose

引用

Journal of Integrative Agriculture 2023年第5期22卷 1351-1365页

作者： DONG Xiu-chun QIAN Tai-feng CHU Jin-peng ZHANG Xiu LIU Yun-jing DAI Xing-long HE Ming-rong State Key Laboratory of Crop Biology Ministry of Science and Technology/Key Laboratory of Crop Ecophysiology and Farming SystemMinistry of Agriculture and Rural Affairs/Agronomy CollegeShandong Agricultural UniversityTai’an 271018P.R.China Jining Agricultural Technology Extension Center Jining 272113P.R.China

Delayed sowing mitigates lodging in wheat. However, the mechanism underlying the enhanced lodging resistance in wheat has yet to be fully elucidated. Field experiments were conducted to investigate the effects of sowing date on lignin and cellulose metabolism, stem morphological characteristics, lodging resistance, and grain yield. Seeds of Tainong 18,a winter wheat variety, were sown on October 8(normal sowing) and October 22(late sowing) during both of the 2015–2016 and 2016–2017 growing seasons. The results showed that late sowing enhanced the lodging resistance of wheat by improving the biosynthesis and accumulation of lignin and cellulose. Under late sowing, the expression levels of key genes(Ta PAL, Ta CCR, Ta COMT, TaCAD, and TaCesA1, 3, 4, 7, and 8) and enzyme activities(TaPAL and TaCAD) related to lignin and cellulose biosynthesis peaked 4–12 days earlier, and except for the TaPAL, TaCCR, and TaCesA1 genes and TaPAL, in most cases they were significantly higher than under normal sowing. As a result, lignin and cellulose accumulated quickly during the stem elongation stage. The mean and maximum accumulation rates of lignin and cellulose increased, the maximum accumulation contents of lignin and cellulose were higher, and the cellulose accumulation duration was prolonged. Consequently, the lignin/cellulose ratio and lignin content were increased from 0 day and the cellulose content was increased from 11 days after jointing onward. Our main finding is that the improved biosynthesis and accumulation of lignin and cellulose were responsible for increasing the stem-filling degree, breaking strength, and lodging resistance. The major functional genes enhancing lodging resistance in wheat that are induced by delayed sowing need to be determined.

关键词： cellulose late sowing lignin lodging resistance wheat

来源：评论

学校读者我要写书评

暂无评论

Loaded tooth contact analysis and meshing stiffness calculation for cracked spiral bevel gears

引用

Chinese Journal of Aeronautics 2025年第3期38卷 593-623页

作者： Zhen LIU Fucai LI Wenjie BAO Xiaolei XU Freeda A.AMIR State Key Laboratory of Mechanical System and Vibration Shanghai Jiao Tong UniversityShanghai 200240China School of Mechatronic Engineering China University of Mining and TechnologyXuzhou 221116China Jiangsu JITRI Composite Equipment Research Institute Co. Ltd.Wuxi 214000China

Tooth cracks may occur in spiral bevel gear transmission system of the aerospace *** this study,an accurate and efficient loaded tooth contact analysis(LTCA)model is developed to predict the contact behavior and time-varying meshing stiffness(TVMS)of spiral bevel gear pair with cracked *** tooth is sliced,and the contact points on slices are computed using roll angle *** the geometric complexity of crack surface,a set of procedures is formulated to generate spatial crack and determine crack parameters for contact *** to the positional relationship between contact point and crack path,each sliced tooth is modeled as a non-uniform cantilever beam with varying reduced effective load-bearing tooth *** the compliance model of the cracked tooth is established to perform contact analysis,along with TVMS calculations utilizing three different *** employing spiral bevel gear pairs with distinct types of cracks as examples,the accuracy and efficiency of the developed approach are validated via comparative analyses with finite element analysis(FEA)***,the investigation on effects of cracks shows that tooth cracks can induce alterations in meshing performance of both entire gear pair and individual tooth pairs,including not only cracked tooth pair but also adjacent non-cracked tooth ***,the proposed model can serve as a useful tool for analyzing the variations in contact behavior and meshing stiffness of spiral bevel gears due to different cracks.

关键词： Bevel gears Gear teeth Cracks Loaded tooth contact analysis Time-varying meshing stiffness Tooth compliance

来源：评论

学校读者我要写书评

暂无评论

Decomposing Visual and Semantic Correlations for Both Fully Supervised and Few-Shot Image Classification

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第4期5卷 1658-1668页

作者： Zhang, Chunjie Zheng, Xiaolong Beijing Jiaotong University Institute of Information Science Beijing100044 China Beijing Jiaotong University Beijing Key Laboratory of Advanced Information Science and Network Technology Beijing100044 China University of Chinese Academy of Sciences State Key Laboratory of Multimodal Artificial Intelligence Systems The State of Key Laboratory of Management and Control for Complex System Institute of Automation Chinese Academy of Sciences School of Artificial Intelligence Beijing100190 China

Most image classification methods are designed to either boost the classification accuracies with abundant supervision, or cope with the shortage of supervision information. This is often achieved by using the visual and semantic information of other sources. However, these methods use the visual and semantic information within the same class independently, leaving their intrinsic correlations unconsidered. Objects and disturbing components as well as noise exist on the same image. Besides, semantic representations also contain noisy information. To solve the problems mentioned above, we propose a novel method for both fully supervised image classification and few-shot image classification by decomposing visual and semantic correlations. We jointly explore the intrinsic correlations of visual and semantic information of images within the same class. For each class, we decompose its visual and semantic correlations using low-rank and sparse constraint respectively. The decomposed low-rank parts character the intrinsic correlations of images can be used in a linear transformation way. Using the decomposed parts of each class, Classification can be achieved by reconstruction error minimization. We conduct experiments on several datasets for both fully supervised image classification and few-shot image classification. Experimental results well show the effectiveness of the proposed method. © 2020 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

A multi-channel image-based method for flight delay prediction in terminal area 4

A multi-channel image-based method for flight delay predicti...

引用

2024 4th International Conference on Intelligent Traffic systems and Smart City, ITSSC 2024

作者： Yang, Yihan Chen, Haiyan Yang, Longwu State Key Laboratory of Air Traffic Management System Nanjing China College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing China

ISBN: (纸本)9781510686304

With the rapid development of civil aviation, flight delays have become increasingly critical. Effectively predicting flight delays has become a research hotspot in recent years. In this paper, we propose a novel flight delay prediction method based on image recognition by applying deep learning techniques. We first rasterize the target terminal area into a grid image of size 25×25. Then, we convert the arrival and departure traffic flow data collected over some time into colors and fill them into the corresponding grids to obtain the arrival and departure traffic flow images. On this basis, we design the prediction model Attention-Complementary Hybrid Network (ACHNet), which can be used for multi-channel image feature fusion. It takes arrival and departure traffic flow images as inputs and fuses the spatial information of these two types of images through the fusion branch. We use the Convolutional Neural Network (CNN)-based prediction model to predict flight delays on arrival and departure traffic flow image sets respectively, and compare the prediction results with those of ACHNet. The experimental results show that the fusion of multi-channel image features can effectively improve the performance of flight delay prediction. © 2025 SPIE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Transient Stability Analysis of Converter-based Islanded Microgrids Based on Iterative Equal Area Criterion Considering Reactive Power Loop Dynamics and Varying Damping

引用

Journal of Modern Power systems and Clean Energy 2024年第4期12卷 1170-1182页

作者： Xilin Li Jingyi Zhang Zhen Tian Xiaoming Zha Wei Wang Meng Huang Chong Shao Hubei Key Laboratory of Power Equipment&System Security for Integrated Energy School of Electrical Engineering and AutomationWuhan UniversityWuhanChina NARI Technology Co. Ltd.NanjingChina State Grid Gansu Electric Power Company LanzhouChina

With the rapid increase in the installed capacity of renewable energy in modern power systems,the stable operation of power systems with considerable power electronic equipment requires further *** converter-based islanded microgrid(CIM)systems equipped with grid-following(GFL)and grid-forming(GFM)voltage-source converters(VSCs),it is challenging to maintain stability due to the mutual coupling effects between different VSCs and the loss of voltage and frequency support from the power *** previous studies,quantitative transient stability analysis was primarily used to assess the active power loop of ***,frequency and voltage dynamics are found to be strongly coupled,which strongly affects the estimation result of stability *** addition,the vary-ing damping terms have not been fully *** bridge these gaps,this paper investigates the transient stability of CIM consid-ering reactive power loop dynamics and varying ***,an accuracy-enhanced nonlinear model of the CIM is derived based on the effects of reactive power loop and post-disturbance frequency jump *** these effects will eliminates the risk of *** reactive power loop dynamics make the model coefficients be no longer constant and thus vary with the power *** evaluate quantitatively the effects of re-active power loop and varying damping on the transient stability of CIM,an iterative criterion based on the equal area criterion theory is *** addition,the effects of parameters on the stable boundary of power system are analyzed,and the dynamic interaction mechanisms are *** and experiment results verify the merits of the proposed method.

关键词： Transient stability converter iterative criterion reactive power loop post-disturbance frequency jump

来源：评论

学校读者我要写书评

暂无评论

A novel piezoelectric actuated micro-tweezer with force sensing for optical fiber manipulation

A novel piezoelectric actuated micro-tweezer with force sens...

引用

2023 IEEE International Conference on Real-Time Computing and robotics, RCAR 2023

作者： Zhao, Haoxiang Rong, Haoran Harbin Institute of Technology State Key Laboratory of Robotics and System Harbin China Heilongjiang University of Science and Technology Harbin China

ISBN: (纸本)9798350327182

With the development of micro-electromechanical systems, micro-manipulation robots are extensively used in micro-nano manufacturing due to their high precision. As the core component of the MEMS, the micro-tweezers which are driven by PZT, ultrasonic motors to grasp millimeter and micron objects have developed rapidly. However, it is pretty tough for these tweezers to attain bendy gripping of objects due to the lack of sensors at the cease of the tweezer. Therefore, a force-sensing micro-tweezer with micro-operating device is designed in this paper, which is appropriate for the clamping of optical fibers of different diameters and controlled with the aid of a single-chip microcomputer. The working principle is that the certain opening at the end of the micro-tweezer is closed when the PZT outputs a tiny displacement which is amplified through the two-stage displacement amplifying mechanism, at some stage in which the PWM sign generated by using the controller and amplified by means of the signal amplifier is transmitted in this device and used to control the PZT. To enforce the function of the pressure feedback grasping of optical fibers of distinctive diameters, the sign generated by the pressure sensor at the end of the micro-tweezer is despatched to the controller after the fiber is being clamped. In this paper, the design, simulation and evaluation of the micro-tweezer, the setup and calibration of the system, and the experiments and performance assessments of the micro-tweezer are carried out. The results exhibit that the micro-tweezer can clamp the fiber with diameter of 100-300μm precisely with its output displacement at 360μm, force-sensing resolution accuracy at 9.8mN, and the clamping force at 0.392N. The force-sensing device now not only has a small volume, but also realizes the speedy replacement of a number of components, which advantage it to be widely-used in future micro-tweezers application scenario. © 2023 IEEE.

关键词： MEMS

来源：评论

学校读者我要写书评

暂无评论

Influence of Repetitive Impulse Waveforms on Surface Discharge Characteristics and Insulation Life for Polyimide Film

引用

CSEE Journal of Power and Energy systems 2024年第2期10卷 746-755页

作者： Zhiyun Han Qingmin Li Yujin Guo Tao Liu Guojing Dong Hanwen Ren State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources North China Electric Power UniversityBeijing 102206China Electric Power Research Institute Beijing 100085China Inner Mongolia Electric Economy and Technology Academy Hohhot 010020China

Accelerated insulation aging problems under high frequency repetitive impulses in power electronic transformers are drawing more and more attention in modern power systems. Partial discharge (PD) characteristics including discharge inception voltage, phase distribution and statistical characteristics on polyimide (PI) surface under different impulse waveforms and the insulation life of PI films are studied in this paper. We carry out experiments based on PD and insulation lifetime test systems, using five different types of repetitive impulses, including three bipolar waves and two unipolar waves. The experimental results show that there is little variation in discharge inception voltage under different waveforms, but great variation in phase distribution and statistical characteristics of PD. In addition, insulation life is approximately the same under different waveforms with the same polarity, and the aging rate under bipolar waveforms is larger than that under unipolar waveforms. We explain the differences between the bipolar and unipolar waveforms on insulation life, which can be concluded that the surface charge under unipolar waveform accumulates more significnatly compared with bipolar waveform and decreases the electric filed strength in discharging the air gap and inhibits surface discharge from occurring.

关键词： Insulation life polyimide film power electronic transformer repetitive impulse surface discharge characteristics

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：