检索结果-内蒙古大学图书馆

SGL-PCA: Health Index Construction With Sensor Sparsity and Temporal Monotonicity for Mixed High-Dimensional Signals

引用

IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING 2023年第1期20卷 372-384页

作者： Wang, Feng Wang, Andi Tang, Tao Shi, Jianjun Beijing Jiaotong Univ State Key Lab Rail Traff Control & Safety Beijing 100044 Peoples R China Beijing Jiaotong Univ Sch Mech Elect & Control Engn Beijing 100044 Peoples R China Arizona State Univ Polytech Sch Mesa AZ 85212 USA Georgia Inst Technol H Milton Stewart Sch Ind & Syst Engn Atlanta GA 30332 USA

With advancements in sensor technology, high dimensional signals such as functional curves and images are typically collected from multiple sensors to characterize the degradation of a system. data fusion methods are employed to integrate multisensor signals generated from the system into a scalar health index (HI) to understand the degradation status of the system. This paper develops sparse group LASSO-principal component analysis (SGL-PCA), a method that constructs HIs for image and profile data. First, we remove the smooth background from each sensor signal. Then, we solve the degradation patterns and the degradation paths through a rank-one matrix approximation problem, with the consideration of the sparsity of the measurements related to the degradation process and the monotonicity of the degradation paths. Results from a simulation study and a case study illustrate that the HI constructed by the proposed method outperforms the benchmark methods in identifying the measurements subject to the degradation process and predicting the remaining useful life of the system.

关键词： Degradation Indexes Relays Rail transportation Predictive models Market research Switches Sparse group LASSO PCA health index degradation modeling high dimensional data

来源：评论

学校读者我要写书评

暂无评论

Review of modeling and control Methods of Soft Robots Based on Machine Learning 42

Review of Modeling and Control Methods of Soft Robots Based ...

引用

42nd Chinese control conference, CCC 2023

作者： Wu, Mengyu Zhang, Ying Wu, Xuanye Li, Zhiheng Chen, Wenlin Hao, Lina Academy of Mechanical Engineering & Automation Northeastern University Shenyang110819 China

ISBN: (纸本)9789887581543

The soft robot is a kind of robot with high degree of freedom and continuous deformation. It is mostly made of soft materials, which has the characteristics of high flexibility and high task adaptability. Due to the superelasticity of the material and the continuity of the structure of the soft robots, the traditional modeling and control methods suitable for rigid robot are no longer applicable. Methods of machine learning are being gradually applied. Deep learning can avoid the complex physical modeling process of soft robots, thus realizing data-driven learning. Reinforcement learning can be used to solve the problem of lack of accurate model in robot control. This paper reviewed the application of machine learning in modeling and control of soft robots including kinematics modeling and dynamics modeling of soft robot based on deep learning, and motion control of soft robot based on reinforcement learning. By analyzing and sorting out the bottleneck problems and feasible solutions of data-driven modeling and control schemes of soft robot, the development trend of soft robot technology is discussed. © 2023 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Exploring Architectural Choices and Emerging Challenges in data Management for IoT: A Focus on Digital Innovation and Smart Cities 32

Exploring Architectural Choices and Emerging Challenges in D...

引用

32nd ACM conference on User modeling, Adaptation and Personalization (ACM UMAP)

作者： Barra, Silvio D'Alessandro, Ferdinando Sosovskyy, Oleksandr Univ Naples Federico II Dept Elect Engn & Informat Technol Naples Italy

ISBN: (纸本)9798400704666

Digital innovation is an important and evolving process that refers to the transformation and integration of digital technologies into various aspects of everyday life and work. In this context, innovative digital solutions are often adopted and developed, including the Internet of Things (IoT). In order to fully understand the potential, trends, and challenges related to the implementation of these technologies in data management, we seek to identify the most promising architectural choices for an IoT infrastructure from the perspective of key aspects in the context of data Management. In this way, we aim to provide a comprehensive overview of IoT systems to guide organizations towards more informed decisions, offering cutting-edge solutions and contributing to digital transformation. This work aims to examine aspects such as data Collection, data Aggregation, data Integration, data Security, data Retention, and data analysis, with particular attention to emerging challenges in these contexts. Within the context of digital innovation, our study focuses on several areas of interest. For example, in the field of smart cities, we explore how the use of Cloud, Fog, and Edge Computing technologies can improve video surveillance and promote the use of Artificial Intelligence (AI) for better management of smart cities. Cloud computing, characterized by centralized data processing and storage, represents a well established paradigm of IoT infrastructure. Fog computing extends these capabilities to the network edge, bringing computation and data storage closer to the data source, thereby reducing latency and enhancing real-time processing. Edge computing takes this concept further by processing data directly at or near the data source, minimizing the need for data to traverse long distances to centralized hubs, thus enabling even faster response times and improved efficiency. Additionally, we examine how human-centric methods and user modeling tools can facilitate the trans

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Concept Induction: Analyzing Unstructured Text with High-Level Concepts Using LLooM 24

Concept Induction: Analyzing Unstructured Text with High-Lev...

引用

CHI conference on Human Factors in Computing Sytems (CHI)

作者： Lam, Michelle S. Teoh, Janice Landay, James A. Heer, Jefrey Bernstein, Michael S. Stanford Univ Stanford CA 94305 USA Univ Washington Seattle WA 98195 USA

ISBN: (纸本)9798400703300

data analysts have long sought to turn unstructured text data into meaningful concepts. Though common, topic modeling and clustering focus on lower-level keywords and require significant interpretative work. We introduce concept induction, a computational process that instead produces high-level concepts, defined by explicit inclusion criteria, from unstructured text. For a dataset of toxic online comments, where a state-of-the-art BERTopic model outputs "women, power, female," concept induction produces high-level concepts such as "Criticism of traditional gender roles" and "Dismissal of women's concerns." We present LLooM, a concept induction algorithm that leverages large language models to iteratively synthesize sampled text and propose human-interpretable concepts of increasing generality. We then instantiate LLooM in a mixed-initiative text analysis tool, enabling analysts to shift their attention from interpreting topics to engaging in theory-driven analysis. Through technical evaluations and four analysis scenarios ranging from literature review to content moderation, we find that LLooM's concepts improve upon the prior art of topic models in terms of quality and data coverage. In expert case studies, LLooM helped researchers to uncover new insights even from familiar datasets, for example by suggesting a previously unnoticed concept of attacks on out-party stances in a political social media dataset.

关键词： unstructured text analysis topic modeling human-AI interaction large language models data visualization

来源：评论

学校读者我要写书评

暂无评论

DCLCSE: Dynamic Curriculum Learning Based Contrastive Learning of Sentence Embeddings

引用

IEEE TRANSACTIONS ON BIG data 2025年第2期11卷 635-647页

作者： Liu, Chang Zhang, Dacao Wang, Meng Hefei Univ Technol Sch Comp & Informat Hefei 230029 Anhui Peoples R China

Recently, Contrastive Learning (CL) has made impressive progress in natural language processing, especially in sentence representation learning. Plenty of data augmentation methods have been proposed for the generation of positive samples. However, due to the highly abstract nature of natural language, these augmentations cannot maintain the quality of generated positive samples, e.g., too easy or hard samples. To this end, we propose to improve the quality of positive examples from a data arrangement perspective and develop a novel model-agnostic approach: Dynamic Curriculum Learning based Contrastive Sentence Embedding framework (DCLCSE) for sentence embeddings. Specifically, we propose to incorporate a curriculum learning strategy to control the positive example usage. At the early learning stage, easy samples are selected to optimize the CL-based model. As the model's capability increases, we gradually select harder samples for model training, ensuring the learning efficiency of the model. Furthermore, we design a novel difficulty measurement module to calculate the difficulty of generated positives, in which the model's capability is considered for the accurate sample difficulty measurement. Based on this, we develop multiple arrangement strategies to facilitate the model learning process based on learned difficulties. Finally, extensive experiments over multiple representative models demonstrate the superiority of DCLCSE. As a byproduct, we have released the codes to facilitate other researchers.

关键词： Task analysis Contrastive learning Training Representation learning data augmentation Computational modeling Semantics curriculum learning sample difficulty sentence representation

来源：评论

学校读者我要写书评

暂无评论

A Cascaded Broad Learning System for Manipulator Motion control

A Cascaded Broad Learning System for Manipulator Motion Cont...

引用

2024 International conference on Intelligent Robots and Systems

作者： Zuo, Guoyu Dong, Shuaifeng Zhou, Jiyong Yu, Shuangyue Beijing Univ Technol Fac Informat Technol Beijing 100124 Peoples R China Beijing Key Lab Comp Intelligence & Intelligent S Beijing 100124 Peoples R China

ISBN: (纸本)9798350377712;9798350377705

Intelligent control methods have led to a significant simplification of the robotic arm modeling and control tuning process, and thus they have been widely used. To further improve the precision of robotic arm motion control, this paper proposes a robotic arm motion control strategy based on a cascaded feature-enhanced elastic-net broad learning system (CFE-EN-BLS). This will fully extract data features to improve motion control accuracy. Moreover, ElasticNet regression is introduced to reduce feature redundancy. Finally, Lyapunov stability theory is introduced to constrain the learning parameters of the proposed learning method to enhance the convergence of the control strategy. The simulation and experiment show that the proposed control strategy can realize high-precision trajectory tracking control of the robotic arm.

关键词： Robotic arms

来源：评论

学校读者我要写书评

暂无评论

A Comparative analysis of Network Modelling Approaches for Predicting Performance in Large Scale Networks

A Comparative analysis of Network Modelling Approaches for P...

引用

2025 International conference on Pervasive Computational Technologies, ICPCT 2025

作者： Singh, Khushmeet Agarwal, Pratik Rana, Vikrant Kolli, Jayanth Cheruku, Saketh Reddy Musunuri, Aravindsundeep Dr. A.P.J. Abdul Kalam Technical University U.P. Lucknow India Symbiosis Institute of Technology Pune India Coer University Department of Artificial Intelligence and Machine Learning Roorkee India International Technological University Santa ClaraCA United States Wichita State University KS United States Manipal University India

ISBN: (纸本)9798331508685

choosing the right node to measure is the key to success in large-scale networks;network modeling is a critical tool for detecting performance. The growing size and complexity of modern networks make accurately predicting their performance a crucial requirement for efficient and reliable operation. Numerous network modeling approaches, however, each with unique strengths and limitations, have emerged in response to this. This paper provides a comparative critique of these network modeling approaches and their performance prediction capabilities in large-scale networks. The first category is the analytical modeling approach, where mathematical equations represent network performance. An approach similar to the described process gives very accurate and detailed predictions but must rely on a theoretical understanding of how networks behave and the assumption of ideal networks. The second approach, simulation modeling, designs a virtual model of the network and lets you test it to predict its performance. This allows for greater flexibility, and real-world factors can be included in the heuristics;however, it is potentially very computationally intensive. The third method is machine learning, which involves algorithms that learn patterns in historical network data and create predictions. While this method is able to process intricate data sets and adjust to evolving network states, its precision relies heavily on the quality of the training data. © 2025 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

modeling of melt pool width and melt pool temperature in laser metal deposition based on closed-loop control 19

Modeling of melt pool width and melt pool temperature in las...

引用

19th National conference on Laser Technology and Optoelectronics

作者： Wang, Hedong Wang, Kaixin Lu, Kaiju Chen, Yongxiong National Innovation Institute of Defense Technology Academy of Military Sciences Fengtai East Street fengtai district Beijing China

ISBN: (纸本)9781510683228

Laser metal deposition technology has found broad applications in the aerospace and marine industries due to its various advantages in terms of high material utilization and unlimited forming dimension. However, due to its complex deposition variations, it is difficult to model the relationship between the process parameters. This limitation hinders research on its mechanism of action and control, leading to challenges in ensuring the quality of deposition and stability of the process. In this study, the melt pool width controller and the melt pool temperature controller were developed to investigate the relationship modeling, respectively. Laser power was selected as the only process control output. The positive correlation and strong coupling between melt pool width and temperature were experimentally verified. The Gaussian distribution of the temperature field of the deposition process was investigated as the cause of the nonlinear relationship between melt pool width and temperature. The melt pool width and melt pool temperature model obtained from this Gaussian temperature field fits the experimental data well, with an R2 coefficient of 0.97. This study is of great significance for the mechanism of melt pool temperature on melt pool width during the deposition process. It also contributes to the integration of micro-property control and geometric accuracy control. © 2024 SPIE.

关键词： Marine industry

来源：评论

学校读者我要写书评

暂无评论

Quality-Relevant modeling and Monitoring of Industrial Cyber-Physical Systems: The Semi-Supervised Dynamic Latent Variable Models

IEEE Transactions on Industrial Cyber-Physical Systems

引用

IEEE Transactions on Industrial Cyber-Physical Systems 2025年 3卷 39-47页

作者： Zhou, Le Wang, Yaoxin Wu, Yuanqing He, Shenghuang Song, Zhihuan Zhejiang University of Science and Technology Department of Automation and Electrical Engineering Hangzhou310023 China Guangdong University of Technology Department of Automation Guangzhou510006 China Dongguan University of Technology Department of Computer Science and Technology Dongguan523808 China Ningbo Industrial Internet Institute Ningbo315012 China Zhejiang University Department of Control Science and Engineering Hangzhou310027 China

In modern industrial cyber-physical systems, a mass of process variables has been obtained by the high-sampling online sensors. Meanwhile, the key quality indexes are usually obtained infrequently from the laboratory. Hence, these quality variables are with low sampling rate. To avail of the complete process and quality variables with various sampling rates in the dynamic processes, a set of semi-supervised dynamic latent variable models are proposed for dynamic modeling and quality-relevant monitoring. The proposed models have built a unified structure to consider both the auto-correlations and cross-correlations between the process and quality variables with unbalanced sampling sizes. Hence, the feature extraction of the time series data is dynamically adjusted under the guidance of the quality variables. Then, the quality-relevant monitoring schemes are proposed, which is validated by a numerical case and an actual wastewater treatment process. © 2024 IEEE. All rights reserved.

关键词： Indexes Probabilistic logic Kalman filters Noise Cyber-physical systems Analytical models Parameter estimation Time series analysis process monitoring Numerical models

来源：评论

学校读者我要写书评

暂无评论

Offset-Free Optimal control of Cascaded H-Bridge Converters Based on a Kalman Filter Harmonic Compensator

引用

IEEE TRANSACTIONS ON POWER ELECTRONICS 2025年第1期40卷 625-637页

作者： Poblete, Pablo Aguilera, Ricardo P. Pereda, Javier Cuzmar, Rodrigo H. Alcaide, Abraham M. Lu, Dylan Dah-Chuan Siwakoti, Yam Prasad Acuna, Pablo Pontificia Univ Catolica Chile Dept Elect Engn Santiago 7820436 Chile Univ Technol Sydney Sch Elect & Data Engn Broadway NSW 2007 Australia Pontificia Univ Catolica Chile Dept Elect Engn Santiago 7820436 Chile Pontificia Univ Catolica Chile UC Energy Res Ctr Santiago 7820436 Chile Univ Seville Elect Dept Seville 41092 Spain Univ Talca Dept Elect Engn Curico 3340000 Chile

Cascaded H-bridge (CHB) converters are suitable candidates for numerous applications, including electrical drives, static synchronous compensators, and battery energy storage inverters. Optimal control strategies for CHB converters have attracted significant interest in recent decades due to their flexibility in including multiple control objectives and their simple design process. However, the steady-state performance of these control strategies deteriorates if the CHB converter model has parameter mismatches and/or the submodule (SM) capacitor voltage ripples are not measured. This work proposes a Kalman filter (KF) based strategy to eliminate the steady-state error and undesired low-frequency harmonic components in the CHB converter output currents. The proposed KF strategy estimates the instantaneous arm voltage harmonics representing the converter modeling errors and unaccounted disturbances. Then, these estimated voltage harmonics are used to improve the arm current predictions and obtain a compensation term for the steady-state arm voltage references to be used by the optimal control strategy. Experimental results for three different optimal control schemes are provided for a three-phase CHB converter with nine SMs to confirm the effectiveness of the proposed KF strategy.

关键词： Voltage control Optimal control Power harmonic filters Harmonic analysis Steady-state Predictive models Capacitors Voltage measurement Pulse width modulation State-space methods Cascaded H-Bridge (CHB) Kalman filtering predictive control

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：