检索结果-内蒙古大学图书馆

Importance-Weighted Transfer Learning for Fault Classification under Covariate Shift

Intelligent Automation & Soft Computing 2024年第4期39卷 683-696页

作者： Yi Pan Lei Xie Hongye Su Institute of Cyber-Systems and Control Zhejiang UniversityHangzhou310027China State Key Laboratory of Industrial Control Technology Institute of Cyber-Systems and ControlZhejiang UniversityHangzhou310027China

In the process of fault detection and classification,the operation mode usually drifts over time,which brings great challenges to the *** traditional machine learning based fault classification cannot dynamically update the trained model according to the probability distribution of the testing dataset,the accuracy of these traditional methods usually drops significantly in the case of covariate *** this paper,an importance-weighted transfer learning method is proposed for fault classification in the nonlinear multi-mode industrial *** effectively alters the drift between the training and testing ***,the mutual information method is utilized to perform feature selection on the original data,and a number of characteristic parameters associated with fault classification are selected according to their mutual ***,the importance-weighted least-squares probabilistic classifier(IWLSPC)is utilized for binary fault detection and multi-fault classification in covariate ***,the Tennessee Eastman(TE)benchmark is carried out to confirm the effectiveness of the proposed *** experimental result shows that the covariate shift adaptation based on importance-weight sampling is superior to the traditional machine learning fault classification ***,IWLSPC can not only be used for binary fault classification,but also can be applied to the multi-classification target in the process of fault diagnosis.

关键词： Covariate shift adaption nonlinear multi-mode process importance weight sampling multi-fault classification

来源：评论

学校读者我要写书评

暂无评论

Knowledge Distillation on Driving Intention Generator: Learn Human-like Semantic Reasoning

Knowledge Distillation on Driving Intention Generator: Learn...

引用

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

作者： Wang, Hejun Dong, Jiajun Wang, Yunkai Jiao, Yanmei Xiong, Rong Zhejiang University The State Key Laboratory of Industrial Control Technology Institute of Cyber-Systems and Control Hangzhou China Hangzhou Normal University The School of Information Science and Engineering Hangzhou China

ISBN: (纸本)9798350327182

Semantic information plays a significant role in autonomous vehicles. However, it has remained open how to economically compute and efficiently incorporate semantic information into other frequently applied processes, such as construction of local navigation map, driving decision making and trajectories planning. To address this issue, we introduce Knowledge Distillation to convey semantic reasoning capability. Following the existing intention-guided framework, a semantically incorporated module associates given navigation instruction with acquired visual perception to synthesize driving intention. Our major contribution is to teach the driving intention generator how to propagate considering semantics implicitly. Specifically, we construct a semantic supervisor identical to the driving intention generator. The supervisor transfers semantic reasoning ability to the generator during training process, with which the generator is expected to perform stably and reliably even in extremely sophisticated surroundings or under frequently inaccurate navigation instruction. Through exhaustive experimental validation, our model demonstrates a superior robustness and adaptability compared to the state-of-the-art. Finally, we explain the intrinsic mechanism of our model with visualization. © 2023 IEEE.

关键词： Navigation

来源：评论

学校读者我要写书评

暂无评论

Nonlinear MPC-Based control Framework for Quadruped Robots: Touch-Down in Complex Terrain 42

Nonlinear MPC-Based Control Framework for Quadruped Robots: ...

引用

42nd Chinese control Conference, CCC 2023

作者： Yu, Jiyu Li, Zhang Chen, Yong Wang, Dongqi Zhang, Rui Zhang, Zhuqing Xiong, Rong Wang, Yue Zhejiang University State Key Laboratory of Industrial Control Technology Institute of Cyber-Systems and Control Hangzhou310027 China Research Institute of Nuclear Power Operation WuHan430030 China

ISBN: (纸本)9789887581543

Quadruped robots show potential beyond that of wheeled robots for walking over complex terrain thanks to the bionic leg design, and to take advantage of this, we propose a control framework for a quadruped robot to achieve touch-down in a designated area, aiming to help the robot overcome the challenge in complex terrains. We incorporate a foot placement constraint into a nonlinear model predictive control (MPC) framework guided by global localization, enabling the robot to touch-down in the specified area while maintaining balance. Furthermore, a whole full-body controller is utilized to track the optimized trajectory generated by the MPC. Both simulation and hardware experiments demonstrate the effectiveness of our proposed control framework. © 2023 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Model predictive control

来源：评论

学校读者我要写书评

暂无评论

ERASOR++: Height Coding Plus Egocentric Ratio Based Dynamic Object Removal for Static Point Cloud Mapping

ERASOR++: Height Coding Plus Egocentric Ratio Based Dynamic ...

引用

2024 IEEE International Conference on Robotics and Automation, ICRA 2024

作者： Zhang, Jiabao Zhang, Yu Zhejiang University State Key Laboratory of Industrial Control Technology College of Control Science and Engineering Hangzhou China Key Laboratory of Collaborative Sensing and Autonomous Unmanned Systems of Zhejiang Province Hangzhou China

ISBN: (纸本)9798350384574

Mapping plays a crucial role in location and navigation within automatic systems. However, the presence of dynamic objects in 3D point cloud maps generated from scan sensors can introduce map distortion and long traces, thereby posing challenges for accurate mapping and navigation. To address this issue, we propose ERASOR++, an enhanced approach based on the Egocentric Ratio of Pseudo Occupancy for effective dynamic object removal. To begin, we introduce the Height Coding Descriptor, which combines height difference and height layer information to encode the point cloud. Subsequently, we propose the Height Stack Test, Ground Layer Test, and Surrounding Point Test methods to precisely and efficiently identify the dynamic bins within point cloud bins, thus overcoming the limitations of prior approaches. Through extensive evaluation on open-source datasets, our approach demonstrates superior performance in terms of precision and efficiency compared to existing methods. Furthermore, the techniques described in our work hold promise for addressing various challenging tasks or aspects through subsequent migration. © 2024 IEEE.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

On Klein tunneling of low-frequency elastic waves in hexagonal topological plates

引用

Applied Mathematics and Mechanics(English Edition) 2024年第7期45卷 1139-1154页

作者： Yuxin YAO Yuansheng MA Fang HONG Kai ZHANG Tingting WANG Haijun PENG Zichen DENG School of Mechanics Civil Engineering and ArchitectureNorthwestern Polytechnical UniversityXi’an710072China MIIT Key Laboratory of Dynamics and Control of Complex Systems Northwestern Polytechnical UniversityXi’an710072China State Key Laboratory of Structural Analysis for Industrial Equipment Dalian University of TechnologyDalian116024Liaoning ProvinceChina

Incident particles in the Klein tunnel phenomenon in quantum mechanics can pass a very high potential *** the concept of tunneling into the analysis of phononic crystals can broaden the application *** this study,the structure of the unit cell is designed,and the low frequency(<1 k Hz)valley locked waveguide is realized through the creation of a phononic crystal plate with a topological phase transition *** defect immunity of the topological waveguide is verified,that is,the wave can propagate along the original path in the cases of impurities and ***,the tunneling phenomenon is introduced into the topological valley-locked waveguide to analyze the wave propagation,and its potential applications(such as signal separators and logic gates)are further explored by designing phononic crystal *** research has broad application prospects in information processing and vibration control,and potential applications in other directions are also worth exploring.

关键词： topological metamaterial elastic wave Klein tunneling valley-locked waveguide

来源：评论

学校读者我要写书评

暂无评论

Global optimization of ORC process parameters based on SSL artificial neural network

Global optimization of ORC process parameters based on SSL a...

引用

2023 China Automation Congress, CAC 2023

作者： Qin, Jiabin Zhou, Junjie Wu, Xialai Lin, Ling Yi, Jian Lin, Runze Huzhou University Huzhou Key Laboratory of Intelligent Sensing and Optimal Control for Industrial Systems Huzhou China Zhejiang University State Key Laboratory of Industrial Control Technology Hangzhou China

ISBN: (纸本)9798350303759

The Organic Rankine Cycle (ORC) is a commendable technology for waste heat recovery. However, the optimization problem of ORC operating parameters based on its mechanism model is not easy to be solved for obtaining the global optimal solution, and it is time-consuming. To deal with this problem, a global optimization method of ORC process parameters is proposed to maximize the net output power of the system. Utilizing the SSL Artificial Neural Network (ANN) is utilized as a surrogate model in the optimization, based on this, the parametric optimization problem can be converted into a Mixed-Integer Linear Optimization Problem (MILP). The optimization results show that, compared with the process parameter optimization method based on the ORC mechanism model, the solution time of the optimization is greatly reduced, and the obtained solution is globally optimal. © 2023 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

CDQKL: Consensus-Based Distributed Quantum Kernel Learning 1

CDQKL: Consensus-Based Distributed Quantum Kernel Learning

引用

1st International Conference on Quantum Communications, Networking, and Computing, QCNC 2024

作者： Ma, Wenxuan Liu, Mengxiang Deng, Ruilong State Key Laboratory of Industrial Control Technology The College of Control Science and Engineering Zhejiang University Hangzhou310027 China University of Sheffield Department of Automatic Control and Systems Engineering Sheffield United Kingdom

ISBN: (纸本)9798350366778

The field of quantum computing has developed rapidly in recent years due to its promising trend of surpassing traditional machine learning in terms of speed and effectiveness. Quantum kernel learning is one of the paradigms of quantum machine learning, but the training of quantum kernel is time consuming. Therefore, this work makes the first attempt to introduce a consensus-based distributed approach to quantum kernel learning - named CDQKL - that only requires to exchange model parameter information between adjacent nodes while avoiding the need of sharing local training data. Through comparative experimental studies, the advantages of CDQKL in classification accuracy and convergence speed are verified. Considering the popularization of quantum computing cloud service and miniaturization of quantum terminals, the CDQKL adapting to this trend is able to play a vital role in data security, which implies the far-reaching significance of this work. Our code is available at https://***/Leisurivan/CDOKL. © 2024 IEEE.

关键词： Quantum computers

来源：评论

学校读者我要写书评

暂无评论

Command filter-based I&I adaptive control for MIMO uncertain systems with input saturation and disturbances

引用

Science China(Information Sciences) 2023年第12期66卷 64-79页

作者： Qi HAN Zhitao LIU Hongye SU Xiangbin LIU State Key Laboratory of Industrial Control Technology Institute of Cyber-Systems and ControlZhejiang University School of Electronic Information Engineering Beijing Jiaotong University

This paper develops a control strategy based on immersion and invariance(I&I) adaptive methodology for a class of multi-input multi-output(MIMO) systems in the presence of parametric uncertainty, input saturation, and external disturbance. To avoid the analytic calculation in the backstepping process, a highgain auxiliary system is constructed to compensate for the effect of command filter error. The first-order command filters are also employed in the construction procedure of the I&I adaptive law to simplify its design and remove the structural conditions on the regressors. A filter-based disturbance observer is developed to counteract the effect of the external disturbance produced by a partially known exogenous *** overcome the input saturation nonlinearity, a smooth function is introduced to approximate the input saturation with an extended state and a bounding estimation law. Stringent analysis guarantees the stability of closed-loop system. Finally, simulated examples confirm the effectiveness of the suggested method.

关键词： adaptive control command filtered backstepping disturbance observer immersion and invariance MIMO systems

来源：评论

学校读者我要写书评

暂无评论

Drift-free localisation using prior cross-source map for indoor low-light environments

引用

IET cyber-systems and Robotics 2023年第1期5卷 122-131页

作者： Junyi Tao Weichen Dai Da Kong Jiayan Wan Bin He Yu Zhang State Key Laboratory of Industrial Control Technology College of Control Science and EngineeringZhejiang UniversityHangzhouChina School of Computer Science Hangzhou Dianzi UniversityHangzhouChina Key Laboratory of Collaborative Sensing and Autonomous Unmanned Systems of Zhejiang Province HangzhouChina

In this study,a localisation system without cumulative errors is ***,depth odometry is achieved only by using the depth information from the depth *** the point cloud cross-source map registration is realised by 3D particle filtering to obtain the pose of the point cloud relative to the ***,we fuse the odometry results with the point cloud to map registration results,so the system can operate effectively even if the map is *** effectiveness of the system for long-term localisation,localisation in the incomplete map,and localisation in low light through multiple experiments on the self-recorded dataset is *** with other methods,the results are better than theirs and achieve high indoor localisation accuracy.

关键词： indoor positioning robots

来源：评论

学校读者我要写书评

暂无评论

A BERT-Based Named Entity Recognition Method of Warm Disease in Traditional Chinese Medicine 18

A BERT-Based Named Entity Recognition Method of Warm Disease...

引用

18th IEEE Conference on industrial Electronics and Applications, ICIEA 2023

作者： Song, Zijun Xu, Wen Liu, Zhitao Chen, Liang Su, Hongye Polytechnic Institute Zhejiang University Hangzhou China Binzhou Medical University Yantai China Institute of Cyber-Systems and Control Zhejiang University State Key Laboratory of Industrial Control Technology Hangzhou China

ISBN: (纸本)9798350312201

Traditional Chinese medicine (TCM) documents have been handed down through the ages, containing rich theoretical knowledge and clinical experience. These unstructured data are the foundation for building the digital knowledge system of TCM. However, written in ancient Chinese, the TCM books have complex grammatical rules and terms which are different from modern medicine, inducing difficulty in entity annotation and recognition. In order to solve the problem of lacking labeled data, we construct a dataset with Wenbing Tiaobian, a classic work of TCM on the warm disease, identify six entities and annotate the book with the BIOES method. The BERT-BILSTM-CRF model is used to conduct experiments on the dataset with an F1 value of 91.4%. The results verify the effectiveness of the model in NER tasks and advance the construction of knowledge graphs in TCM. © 2023 IEEE.

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：