检索结果-内蒙古大学图书馆

data-driven Iterative learning control of Nonlinear systems by Adaptive Model Matching

ieee-ASME TRANSACTIONS ON MECHATRONICS 2022年第6期27卷 5626-5636页

作者： Lee, Yu-Hsiu Rai, Sandeep Tsao, Tsu-Chin Natl Taiwan Univ Dept Mech Engn Taipei 106319 Taiwan Cymer San Diego CA 92127 USA Univ Calif Los Angeles Dept Mech & Aerosp Engn Los Angeles CA 90095 USA

Iterative learning control (ILC) has proven successful in the industry for enhancing tracking performance of repetitive tasks. The high accuracy and fast convergence of ILC algorithms hinge on: 1) the knowledge of the system model and 2) an effective learning algorithm. For general industrial systems with nonlinear dynamics, this raises technical challenges because acquiring a nonlinear dynamical model or several linearized models at different operating points may be difficult and costly. It is also non-trivial to determine the learning algorithm for the complex model obtained. To address these challenges, this article proposes a novel data-driven ILC algorithm for single-input-single-output nonlinear systems. Without explicit nonlinear models, our algorithm treats the nonlinear system as an unknown linear time-varying system linearized on a specified input-output (I/O) trajectory in each ILC iteration. A linearly parameterized time-varying adaptive filter is constructed in each ILC iteration so that, when cascading with the nonlinear plant, the I/O dynamics around the specified trajectory follow a linear time-invariant reference model. The ILC error trajectory is then filtered by the adaptive time-varying filter, which represents the inverse dynamics with a bandwidth specified by the reference model, to render fast convergence. The benefits of the proposed data-driven algorithm is demonstrated by comparing to a gradient and Hessian-based data-driven ILC algorithm on a prototypical two-degree-of-freedom nonlinear pendulum.

关键词： Adaptive filtering data-driven control iterative learning control (ILC) nonlinear systems

来源：评论

学校读者我要写书评

暂无评论

Informer-LSTM-EWMA for Panax Notoginseng with Prediction of Early Intervention Time 13

Informer-LSTM-EWMA for Panax Notoginseng with Prediction of ...

引用

13th ieee data driven control and learning systems conference, DDCLS 2024

作者： Ye, Jiahui Yang, Chunxi Zhang, Xiufeng Zhang, Jin Kunming University of Science and Technology Faculty of Mechanical and Electrical Engineering Kunming650504 China Yunnan International Joint Laboratory of Intelligent Control and Application of Advanced Equipment China Kunming University of Science and Technology Faculty of Information Engineering and Automation Kunming650504 China

ISBN: (纸本)9798350361674

Panax notoginseng is one of economic crop with significant medicinal value in southwest China. However, traditional extensive fertilization and irrigation method usually damages the soil, making it difficult to achieve sustainable cultivation of Panax notoginseng. In order to assess the growth status of Panax notoginseng and take timely action, this paper proposed an Informer-LSTM-EWMA model to predict the growth trend of Panax notoginseng in cultivation fields. In the experimental greenhouse, we set up two experimental fields A and B to verify the feasibility of the proposed method. Firstly, wavelet denoising is utilized on the date collected by the sensor. Then, Informer and Long short-term Memory (LSTM) are used to train the denoised data to obtain data prediction. Further process the predicted data through Exponential Weighted Moving Average (EWMA) for trend prediction. Finally, the early intervention time is obtained by searching for the maximum value. The results indicate that the model can predict early intervention time and its predictive performance is far better than that of a single model. © 2024 ieee.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Study on Multi-Timescale Scheduling Strategy Based on Large-Capacity Liquid Flow Battery for Renewable Energy Consumption 13

Study on Multi-Timescale Scheduling Strategy Based on Large-...

引用

13th ieee data driven control and learning systems conference, DDCLS 2024

作者： Li, Dianyang Xiao, Nan Zhan, Keming Jiang, Yuchen Gao, Junpeng Yang, Feiran Power Dispatching Control Center State Grid Liaoning Electric Power Co. Ltd Shenyang110006 China College of Information Science and Engineering Northeastern University Shenyang110004 China

ISBN: (纸本)9798350361674

In order to achieve the full consumption of renewable energy and the reduction of peak and valley loads in the active power system, a multi-objective optimal scheduling strategy for the active power system, i.e., the 'source-storage-load' strategy, which takes into account the participation of controllable loads and energy storage, is proposed. After comprehensively considering the characteristics of the liquid-fluid battery energy storage system and the multi-timescale characteristics of various types of demand response resources on the load side, a multi-timescale scheduling model is established by taking the system operating cost, the penalty cost for wind abandonment, and the penalty cost for loss of load as the objective function, formulating a day-ahead scheduling plan, and guaranteeing a higher accuracy of the forecasting data through intra-day rolling. The simulation results show that the model reduces the wind abandonment rate while ensuring the economic operation of the system. It effectively improves the degree of new energy consumption by the 'source-storage-load' system, which is of great significance for the development and practical application of large-capacity liquid current battery energy storage system. © 2024 ieee.

关键词： Battery storage

来源：评论

学校读者我要写书评

暂无评论

Distributed data-driven Iterative learning control for Consensus Tracking of MASs against Deception Attacks 6

Distributed Data-Driven Iterative Learning Control for Conse...

引用

6th International conference on Electronic Engineering and Informatics, EEI 2024

作者： Zou, Runchang Li, Xuefang Huang, Deqing School of Intelligent Systems Engineering Sun Yat-Sen University shenzhen campus Shenzhen518000 China School of Electrical Engineering Southwest Jiaotong University Chengdu610031 China

ISBN: (纸本)9798350353594

In the paper, we study the problem of distributed model-free adaptive iterative learning control (DMFAILC) for multiagent systems (MAS) under deception attacks. Firstly, we introduce an improved dynamic linearization technology in iteration domain to establish an equivalent data model of MASs. Then, an attacks compensation strategy is developed to mitigate the impact of deception attacks. Subsequently, a DMFAILC scheme is developed based on input and output of the system model. Moreover, the convergence of the consensus tracking error is proved using the contraction mapping method. Finally, a simulation result is provided to verify the effectiveness of the developed DMFAILC scheme. © 2024 ieee.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Autoencoder-Multidimensional Taylor Network for Intelligent Fault Diagnosis Under Privacy Preservation

引用

ieee TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2024年 73卷 1页

作者： Yang, Li Wen, Chenglin Zhou, Zhe Huzhou Univ Sch Engn Huzhou Key Lab Intelligent Sensing & Optimal Cont Huzhou 313000 Peoples R China Guangdong Univ Petrochem Technol Sch Automat Maoming 525000 Peoples R China

data-driven-based intelligent fault diagnosis has achieved significant success. However, the limited number of features and samples often hinders the accuracy of such diagnoses. On the one hand, addressing the issue of low accuracy in intelligent fault diagnosis due to limited features, and the additional complexity of intelligent fault diagnosis algorithms makes people worry about the rationality and interpretability of the decisions made by the model, benefiting from the Taylor series expansion theorem, we propose an intelligent fault diagnosis method based on an autoencoder-multidimensional Taylor network (MTN). On the other hand, to address the problem of low accuracy of intelligent fault diagnosis due to small samples, we introduce federated learning. In federated learning, multiclient data is pooled to improve the accuracy of intelligent fault diagnosis. However, the interaction information between the client and the federation center is easily stolen by eavesdroppers. For this reason, to protect the security of the information interaction between the federated centers and the clients, we propose a hybrid additive and multiplicative coding strategy based on punishing eavesdroppers. Finally, we validate the new method based on the actual flexible rotor and the open-bearing dataset of Western Reserve University. The experimental results show that the intelligent fault detection model proposed in this article can improve the accuracy of fault detection, while the proposed information protection strategy can realize the effect of punishing eavesdroppers. The proposed method in this article is further compared with the latest research methods to verify the advancement of the proposed method.

关键词： Fault diagnosis Federated learning Accuracy Mathematical models Feature extraction Encoding Servers Real-time systems Decoding data models Autoencoder-multidimensional Taylor network (MTN) federation learning hybrid additive and multiplicative coding strategy intelligent fault diagnosis punishing eavesdroppers

来源：评论

学校读者我要写书评

暂无评论

ML driven Thermal Analysis for a Real-Time control System in Satellites

ML Driven Thermal Analysis for a Real-Time Control System in...

引用

ieee Space, Aerospace and Defence conference (SPACE)

作者： Bora, Himangshu Andrade, Prem Mohan, L. Srinivasa Fujii, Akira Patil, Hemesh Jeurkar, Tejas Ansys Inc Pune Maharashtra India Ansys Inc Tokyo Japan Ansys Inc Bengaluru India

ISBN: (纸本)9798350367393;9798350367386

This paper presents a new method of a faster and precise thermal control in space with an emphasis on the need of real-time prediction in dynamic environments. The total irradiation on sun sensors is computed by considering different environmental factors as well as satellite dynamics within the proposed approach. A neural network-based model is trained on this data, which is then coupled with the control system of the satellite for quick thermal adjustment. Successful validation lays the foundation for utilizing simulation-based physics-informed thermal analysis in conjunction with machine learning to influence the control system in near real-time for satellite subsystems.

关键词： Satellite Thermal Analysis Machine learning Thermal control Space mission Realtime control System

来源：评论

学校读者我要写书评

暂无评论

AI driven Process Diagnostic & control: Device Manufacturing 8

AI driven Process Diagnostic & Control: Device Manufacturing

引用

8th Electron Devices Technology & Manufacturing conference (EDTM)

作者： Park, Jaeyong Samsung Hwasung South Korea

ISBN: (纸本)9798350383089;9798350371529

This paper explores the integration of Artificial Intelligence (AI) in process control and diagnostics in semiconductor manufacturing. It highlights current trends, including machine learning (ML) for data alignment and predictive maintenance, and anticipates future advancements in data sharing and standardization. This overview showcases AI's transformative impact on equipment optimization and industry collaboration, underlining its role in shaping efficient, proactive manufacturing processes.

关键词： AI ML Generative AI Manufacturing

来源：评论

学校读者我要写书评

暂无评论

Analysis of factors affecting the future of the Game industry through Machine learning 3

Analysis of factors affecting the future of the Game industr...

引用

3rd International conference on Communication, control, and Intelligent systems, CCIS 2024

作者： Junaid, Mohammed Taneja, Mehak Sehgal, Swastik Bhagwan Parshuram Institute of Technology Ggsipu Dept. of Cse Delhi India Indira Gandhi Delhi Technical University for Women Dept. of Cse & Ai Delhi India Dps R K Puram Delhi India

ISBN: (纸本)9798331528201

The video game industry is a significant economic force, generating billions of dollars in revenue annually. This paper analyses the factors influencing consumer preferences for different types of video games, focusing on platform availability, pricing, game genres, and evolving market trends. data was collected through a survey of over 250 respondents, capturing demographic attributes and gaming preferences. Machine learning techniques, including Decision Tree, Random Forest, and LightGBM, were applied to predict platform preferences and recommend game genres based on age. The Decision Tree model outperformed others with an accuracy of 99.98%, demonstrating its suitability for both tasks. This study provides actionable insights into consumer behaviour, emphasizing the role of brand reputation, marketing efforts, and franchise value in shaping game success. These findings aim to inform game developers and publishers in crafting personalized, data-driven strategies to enhance player engagement and satisfaction. © 2024 ieee.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

data-driven learning Extended State Observers for Nonlinear systems:Design,Analysis and Hardware-in-Loop Simulations

引用

ieee/CAA Journal of Automatica Sinica 2023年第1期10卷 290-293页

作者： Zhouhua Peng Mingao Lv Lu Liu Dan Wang IEEE the School of Marine Electrical Engineering Dalian Maritime UniversityDalian 116026China

Dear Editor, This paper considers the disturbance/uncertainty estimation of first-order nonlinear system subject to fully unknown internal dynamic, external disturbance, and unknown control input *** with existing extended state observer(ESO) where priori knowledge of model parameter such as nominal input gain should be known as a priori.

关键词： priori disturbance nominal

来源：评论

学校读者我要写书评

暂无评论

data-driven Crop Recommendation System for Indian Agriculture: Leveraging Machine learning for Sustainable Development

Data-Driven Crop Recommendation System for Indian Agricultur...

引用

2024 ieee International conference on Computing, Semiconductor, Mechatronics, Intelligent systems and Communications, COSMIC 2024

作者： Raju, Ratheesh Thasleema, T.M. Central University of Kerala Department of Computer Science Kasaragod Periye India

ISBN: (数字)9798331517892

ISBN: (纸本)9798331517892

Agriculture is a critical sector for many of India's population, contributing significantly to the national economy. However, many farmers rely on traditional practices rather than data-driven insights for crop selection, which can lead to adverse financial and psychological outcomes. The study develops an ensemble of Machine learning (ML) models that analyze multiple environmental variables to provide evidence-based crop recommendations to farmers. By integrating features such as rainfall, climate, humidity, soil nutrients, and sowing seasons, the proposed ML model ensemble is designed to recommend crops suited to specific farm conditions. The methodology leverages advanced algorithms to process a comprehensive dataset, including critical parameters like soil properties and climate. Results indicate that this data-driven approach provides accurate and tailored crop recommendations, supporting Precision Agriculture (PA). Adopting such technology promises to transform traditional farming practices, reduce risks, and promote sustainable agricultural development for Indian farmers. © 2024 ieee.

关键词： Adversarial machine 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：