检索结果-内蒙古大学图书馆

2024 China Automation Congress, CAC 2024

作者： Gao, Ming Chen, Hongcai Zhang, Kanjian Wei, Haikun Key Laboratory of Measurement and Control of Complex System Ministry of Education School of Automation Southeast University Nanjing China

ISBN: (纸本)9798350368604

In the field of electronic engineering, the retrieval of circuit diagrams has become an area of considerable research interest. This is attributed to the critical role it plays in consulting legacy electronic designs and in the identification of design plagiarism. Existing image retrieval techniques, which are proficient in managing natural images, typically involve the conversion of images into feature vectors and retrieve similar images according to the closeness of these vectors. However, these methods encounter limitations when adapted to the more specialized and complex domain of circuit diagrams. This paper introduces an innovative approach to the retrieval of circuit diagrams through the use of a graph representation of these diagrams. This novel approach effectively transforms the retrieval task into a graph retrieval problem. The methodology proposed in this paper is comprised of two main components: A recognition algorithm for circuit diagrams designed to accurately extract the components and the topological structure of the circuit and a retrieval strategy based on graph similarity. This methodology is pioneering in its use of graph representation for circuit diagram retrieval, incorporating topological features that are often not considered by conventional image retrieval methods. The experimental results presented in this paper validate the effectiveness of the proposed approach. © 2024 IEEE.

关键词： Circuit Diagram Recognition Circuit Diagram Retrieval Circuit Graph Representation Graph Retrieval

来源：评论

学校读者我要写书评

暂无评论

Refined modeling and experimental verification of a torque motor for an electro-hydraulic servo valve

引用

Chinese Journal of Aeronautics 2023年第6期36卷 302-317页

作者： Zhichuang CHEN Shenghong GE Yulei JIANG Wenhao CHENG Yuchuan ZHU National Key Laboratory of Science and Technology on Helicopter Transmission Nanjing University of Aeronautics and AstronauticsNanjing 210016China Aviation Key Laboratory of Science and Technology on Aero Electromechanical System Integration Nanjing Engineering Institute of Aircraft SystemsNanjing 210061China AVIC Nanjing Servo Control System Co. LtdNanjing 210032China

The Permanent Magnet Torque Motor(PMTM)is the key electro-mechanical conversion device in an Electro-Hydraulic Servo Valve(EHSV).In this work,a refined model of a PMTM is developed,considering the non-working air-gaps between the upper or lower yoke and the armature,the fringing effect at the limiting holes,and the nonlinear permeability of soft magnetic *** on the refined model,the influences of various factors on the calculation accuracy of the magnetic flux at the pole surfaces of the armature and the output torque are *** verifying the validity of the refined model,a Finite Element Analysis(FEA)of the PMTM is conducted,and a test platform is *** with existing models,the refined model can better reveal the intrinsic mechanism of the PMTM,and its calculations are more consistent with the FEA *** experimental results of the armature deflection displacement show that the refined model can accurately describe the output characteristics of the PMTM.

关键词： Calculation accuracy Electro-hydraulic servo valve Experimental verification Finite element analysis Refined model Torque motor

来源：评论

学校读者我要写书评

暂无评论

Thickness measurement of Single-Mode Fiber Coating Layer Based on Forward Brillouin Scattering

引用

IEEE Sensors Journal 2025年第11期25卷 19332-19340页

作者： Zhang, Yongqi Wang, Tao Liu, Yijia Liu, Li Zhang, Mingjiang Taiyuan University of Technology Key Laboratory of Advanced Transducers and Intelligent Control System Ministry of Education College of Physics and Optoelectronic Engineering Taiyuan030024 China Taiyuan University of Technology Shanxi Key Laboratory of Precision Measurement Physics College of Physics and Optoelectronic Engineering Taiyuan030024 China

The coating layer is essential for protecting and applying optical fibers. Nowadays, the thickness measurement of the coating layer relies on point measurement schemes such as the side-looking light distribution method and mechanical method. However, there are some problems with the above methods, such as the trade-off between resolution and field of view, the cutting of the measurement position and the long measurement time. To overcome these problems, we propose a new method based on forward Brillouin scattering, which measures the coating layer thickness of single-mode fibers. The physical properties of the transverse acoustic field involved in forward Brillouin scattering make it possible to measure the thickness of the fiber coating. The corresponding relationship between the transverse acoustic mode frequency and the diameter of the coating layer can be calculated. The coating layer thickness can be measured with high precision by measuring the frequency spectrum of forward Brillouin scattering corresponding to multiple transverse acoustic modes at a given temperature. In the verification experiment, three types of single-mode fibers coated with polyimide are used as the sensing fiber to measure the thickness of the coating layer at multiple temperatures. The experimental results show that the error in the coating layer thickness obtained is less than 0.05 μm. To the best of our knowledge, this is the first demonstration of non-destructive, high-precision monitoring of fiber coating thickness. © 2001-2012 IEEE.

关键词： Acoustic field measurement

来源：评论

学校读者我要写书评

暂无评论

RESEARCH ON GAIT RECOGNITION BY USING 1DCNN BASED ON LOWER LIMB KINEMATIC POSTURE DATA 10

RESEARCH ON GAIT RECOGNITION BY USING 1DCNN BASED ON LOWER L...

引用

10th International Symposium on Test Automation and Instrumentation, ISTAI 2024

作者： Li, Mu Ma, Chao Wang, Shaohong Key Laboratory of Modern Measurement and Control Technology Ministry of Edu. Beijing Information Science and Technology University Beijing China Beijing Key Laboratory of Measurement and Control of Mechanical and Electrical System Beijing Information Science and Technology University Beijing China

ISBN: (纸本)9781837242672

Gait recognition refers to the process of realizing the detection of human identity or health status and other information according to the characteristics of human plantar pressure, video images or human dynamics indicators. With the advantages of non-contact, non-aggression, no need for cooperation and easy to collect, gait recognition technology has been widely used in recent years in the field of public security criminal investigation, medical care, intelligent transportation and other fields. In this study, to meet the needs of gait recognition, IMU sensors are used to acquire human lower limb motion posture data and wavelet transform is used to decompose several components. Then the components were determined and the optimized 1DCNN model is used to carry out gait recognition research. The results showed that the optimized 1DCNN model for gait recognition task exhibits excellent performance with up to 95% accuracy, 96% recall and Fl value, as well as good computational efficiency, which is valuable for clinical automatic gait recognition analysis, rehabilitation engineering and criminal investigation work. Although there are some errors in some gait classifications, our study provides directions for further optimization of the algorithm to improve the accuracy and robustness of gait recognition. © The Institution of Engineering & Technology 2024.

关键词： Crime

来源：评论

学校读者我要写书评

暂无评论

STUDY ON COUPLING FAULT DIAGNOSIS OF THE PLANETARY TRANSMISSION GEARBOX BY USING WAVELET TRANSFORM AND 1DCNN 10

STUDY ON COUPLING FAULT DIAGNOSIS OF THE PLANETARY TRANSMISS...

引用

10th International Symposium on Test Automation and Instrumentation, ISTAI 2024

作者： Qiu, Baolin Ma, Chao Wang, Shaohong Key Laboratory of Modern Measurement and Control Technology Ministry of Education Beijing Information Science and Technology Beijing China Beijing Key Lab of Measurement and Control of Mechanical and Electrical System Beijing Information Science and Technology Beijing China

ISBN: (纸本)9781837242672

Considering the susceptibility of planetary transmission to strong noise interference, a fault diagnosis method is proposed based on Morlet wavelet transform and 1D Convolutional Neural Network (1DCNN). Firstly, the acceleration captured from the transmission is dealt with angle resampling to reduce the dependence of speed on signal characteristics, and band-pass filtering is performed, which parameter is determined by using the fast spectral kurtosis algorithm. Subsequently, the filtered data is decomposed into several multiple intrinsic mode function (IMF) components with the EEMD algorithm and reconstructed according to the correlation coefficient parameter. Then reconstructed data is subjected to further noise reduction processing using wavelet transform and the amplitude in the scale parameter with the highest kurtosis as the input to 1DCNN for training and fault diagnosis classification. The experimental results show that the proposed method can effectively reduce noise interference, the fault diagnosis accuracy of the processed data is relatively high. The fault diagnosis accuracy of the processed data is significantly higher than that of the raw data. © The Institution of Engineering & Technology 2024.

关键词： Noise abatement

来源：评论

学校读者我要写书评

暂无评论

Complex network theory-based optimization for enhancing resilience of large-scale multi-energy system

Complex network theory-based optimization for enhancing resi...

引用

作者： Zhang, Chenwei Wang, Ying Zheng, Tao Zhang, Kaifeng Key Laboratory of Measurement and Control of CSE Southeast University Nanjing210096 China NARI-TECH Nanjing Control System Ltd. Nanjing211000 China

To sustain energy supply capability and mitigate vulnerability to operational failures, enhancing resilience in multi-energy systems (MES) becomes imperative in the face of deliberate attacks and natural disruptions. In this paper, a resilience enhancement optimization model (REOM) is proposed, incorporating various enhancement measures such as adding backup, strengthening physical protection, and constructing new lines. The objective is to minimize the betweenness centrality loss of the MES after being attacked or disrupted, where the betweenness centrality is improved by integrating the power output of energy supply equipment as weighted factors. To accelerate the calculation of shortest paths in large-scale MES, an approximate algorithm for shortest paths is proposed to extract necessary information of shortest paths, through selecting landmarks and converting the target path into the summation of different segments with the landmarks. Then, the REOM is transformed into a bi-level problem while the lower-level one is linearized into a mixed-integer linear programming (MILP) problem, and a genetic algorithm-MILP (GA-MILP) is employed to solve it. Assessing the optimal resilience enhancement plan, a comparison is made with the results obtained under two different attack strategies in the remaining two scenarios through three validation indicators: network fragmentation, decline in energy transfer efficiency, and load loss rate. Through simulations on both a 67-bus power-gas system and a virtual European power-gas system, it was observed that the weighted betweenness centrality loss decreased by 45.37% and 14.95%, respectively, compared to scenarios without the incorporation of the optimal resilience enhancement plan, effectively reinforcing system robustness. © 2024

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

LOWER LIMB GAIT RECOGNITION METHOD BASED ON KNOWLEDGE DISTILLATION 10

LOWER LIMB GAIT RECOGNITION METHOD BASED ON KNOWLEDGE DISTIL...

引用

10th International Symposium on Test Automation and Instrumentation, ISTAI 2024

作者： Wang, Mengdi Wang, Shaohong Ma, Chao Key Laboratory of Modern Measurement and Control Technology Ministry of Edu. Beijing Information Science and Technology Beijing China Beijing Key Lab of Measurement and Control of Mechanical and Electrical System Beijing Information Science and Technology Beijing China

ISBN: (纸本)9781837242672

The need for assistive devices such as lower limb exoskeletons is steadily growing, making quick and precise gait recognition essential for optimal operation of these apparatuses. The knowledge distillation method was applied to gait recognition in this work. First, we took participant lower limb gait data, which we then resampled with step frequency taken into account. Next, multi-layer perceptron (MLP) with distinct layers were modeled by educators and students. The process of knowledge distillation was used to improve the accuracy of participant activity recognition by transferring knowledge from the sophisticated teacher model to the lightweight student model. On the training set, the teacher model's accuracy average was 96.4%. Following the process of knowledge distillation, the accuracy of the student model was 95.48%, representing a 1.12% improvement compared to the non-distilled model, with only 0.53M parameters and shorter training duration. The results demonstrate that knowledge distillation can improve the recognition speed and stability of gait recognition models, enabling more accurate and reliable results within the same patient population, thus providing more effective support for medical diagnosis and rehabilitation treatment. © The Institution of Engineering & Technology 2024.

关键词： Exoskeleton (Robotics)

来源：评论

学校读者我要写书评

暂无评论

PERIODIC STATISTICAL ANALYSIS OF GAIT PHASE SEGMENTATION 10

PERIODIC STATISTICAL ANALYSIS OF GAIT PHASE SEGMENTATION

引用

10th International Symposium on Test Automation and Instrumentation, ISTAI 2024

作者： Fu, Mingkai Wang, Shaohong Ma, Chao Key Laboratory of Modern Measurement and Control Technology Ministry of Edu. Beijing Information Science and Technology Beijing China Beijing Key Lab of Measurement and Control of Mechanical and Electrical System Beijing Information Science and Technology Beijing China

ISBN: (纸本)9781837242672

In order to achieve accurate segmentation of gait phases for precise real-time control of lower limb exoskeleton robots, the periodic statistical analysis of human motion posture by using the inertial measurement unit is conducted. In current research, the data of forward and turning gait types were acquired and every gait type data were devised into eight for different gait phase segmentation. During the process, the phase division values for different types of subjects were calculated and the phase division of different subjects with the same gait type was calculated. The standard deviations for different gaits and phases for the same experimenter are all below 10, primarily oscillated around 4. For gait data from different subjects, the percentages at the same phase are all below 3. The results showed that the results from the feasible method could better accord with the characteristics of each stage of actual *** those results could provide reference for real-time judgment of gait phase and technical support for intelligent control of lower limb exoskeletons. © The Institution of Engineering & Technology 2024.

关键词： Exoskeleton (Robotics)

来源：评论

学校读者我要写书评

暂无评论

Research on Rolling Bearing Fault Diagnosis Based on Classification Generative Adversarial Network

Research on Rolling Bearing Fault Diagnosis Based on Classif...

引用

UNIfied Conference of International Workshop on Defence Applications of Multi-Agent systems, DAMAS 2023, International Conference on Maintenance Engineering, IncoME-V 2023, International conference on the Efficiency and Performance Engineering Network, TEPEN 2023

作者： Kang, Ma Hongjun, Wang School of Mechanical and Electrical Engineering Beijing Information Science and Technology University Beijing100192 China Beijing International Science and Technology Cooperation Base for Intelligent Sensing and Control of High-End Equipment Beijing100192 China Beijing Key Laboratory of Measurement and Control of Electromechanical System Beijing100192 China

ISBN: (纸本)9783031494123

In practical engineering, it is usually difficult to label monitoring data, and the fault diagnosis accuracy is not high in strong noise environment. To solve the above problems, this paper uses Cwt-CatGAN method to process signals and diagnose faults. In this method, CWT is first used to convert one-dimensional original vibration signals into two-dimensional time–frequency graphs as the input of classification generation admixture network. Then, the CatGAN model is obtained through the adversarial training process, and fake samples similar to the extraction distribution of CWT are generated. Finally, the input samples are clustered into certain categories. In addition, the performance of the Cwt-CatGAN method is verified by using the classical rotating machine data set, the experiment is compared with the unsupervised fault diagnosis model CatAAE. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Failure analysis

来源：评论

学校读者我要写书评

暂无评论

Self-supervised Depth Completion with Adaptive Online Adaptation 23

Self-supervised Depth Completion with Adaptive Online Adapta...

引用

7th International Conference on Machine Learning and Soft Computing, ICMLSC 2023

作者： Chen, Yang Tan, Yang Key Laboratory of Measurement and Control of Complex System of Engineering Ministry of Education School of Automation Southeast University Nanjing210096 China

ISBN: (纸本)9781450398633

Although depth completion has achieved remarkable performance relying on deep learning in recent years, these models tend to suffer a performance degradation when exposed to new environments. Online adaptation, where the model is trained in a self-supervised manner during testing, seems a promising technique to alleviate the drop. However, continuous online adaptation may cause the model to over-adapt and miss the optimal parameters, resulting in oscillation or even degradation of the model performance, in addition to wasting computational resources. Therefore, this paper proposes an adaptive online adaptation framework to make model adaptively trigger online adaptation when encountering novel environments and stop adaptation when model has adapted to the current environment. In detail, we design a trigger to detect the familiarity of model to the current scenario based on image similarity and then launch online adaptation when the scenario is novel. Besides, we elaborate a stopper to monitor the error between prediction and depth input and convert online adaptation to inference when online adaptation does not bring improvement for model. Experimental results demonstrate that our method improves the accuracy of model prediction and increases average running speed of the model on each frame in online adaptation. © 2023 ACM.

关键词： Deep learning

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：