检索结果-内蒙古大学图书馆

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

作者： Jia, Ruining Jin, Xinyi Ni, Xinru Ruan, Mengjiao Yang, Zeyu Wang, Peiliang School of Engineering Huzhou University Huzhou Key Laboratory of Intelligent Sensing and Optimal Control for Industrial Systems Huzhou313000 China

ISBN: (纸本)9798350361674

Deep learning methods can extract reliable feature representations from massive process data to build accurate soft sensor models. However, the data in actual industrial production is often nonlinear, dynamic, and even limited in label samples due to untimely sampling and analysis. Aiming at the above problems, this paper proposes a semi-supervised soft sensor modeling method (SSACF-LSTM) for industrial dynamic information mining based on two-path weight comparison. An unsupervised long short-term memory network (LSTM) encoder-decoder is utilized to extract the hidden dynamic nonlinear information in unlabeled samples. This information is then spliced and masked with the initial input, which is subsequently fed into a deep neural network encoder-decoder for pretraining to learn a self-supervised task that mines correlation information between sequences as well as between samples that is useful for the model. In addition, the LSTM with attentional convolutional fusion serves as an auxiliary path that mines correlation information between variables directly from the initial input to complement the information extracted by self-supervision. Finally, the results of both are linearly weighted to obtain the final prediction. The method is validated in a debutanizer process. The results show that SSACF-LSTM can utilize both labeled and unlabeled data to extract quality-related features for soft sensor modeling, which is better than the semi-supervised LSTM network with historical feature fusion (HFF-ssLSTM), semi-supervised stacked auto-encoder (SSAE), and variational auto-encoder regression (SVAER). © 2024 ieee.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

A multi-agent system empowered by federated learning and genetic programming 31

A multi-agent system empowered by federated learning and gen...

引用

31st ieee conference on Signal Processing and Communications Applications (SIU)

作者： Gomes, Luis Ribeiro, Bruno Lezama, Fernando Vale, Zita Polytech Porto LASI Intelligent Syst Associate Lab GECAD Res Grp Intelligent Engn & Comp Adv Innovat & Dev Porto Portugal

ISBN: (纸本)9798350343557

The use of multi-agent systems enables the modelling of complex and decentralized solutions, giving the ability to have agents representing different entities and assets in a social environment where they can interact and pursue their individual goals. However, multi-agent systems are usually data-driven solutions in which interactions are performed based on data sharing and environmental feedback. Therefore, the integration of multi-agent systems with federated learning, a knowledge-driven approach, allows agents to share knowledge among them in a collaborative and cooperative approach. This integration can be well seen in decentralized solutions where similar entities can benefit from collaborative and cooperative environments. This is the case in industrial environments and in smart grid environments, namely for the improvement of learning models. This paper proposes a methodology composed of a multi-agent system where the agents are empowered by federated learning. The proposed methodology was tested and validated using a genetic programming model with MNIST dataset in terms of feasibility and performance.

关键词： data-driven federated learning genetic programming knowledge-driven multi-agent system

来源：评论

学校读者我要写书评

暂无评论

Design of a Full-Space Tracking and Measurement System Based on the Light Pen with Deep learning Methods 13

Design of a Full-Space Tracking and Measurement System Based...

引用

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

作者： Cui, Yu Li, Xu Na, Jing Gao, Guanbin Xing, Yashan Faculty of Mechanical and Electrical Engineering Kunming University of Science and Technology Kunming650500 China Yunnan Key Laboratory of Intelligent Control and Application Kunming650500 China Luzhou Laojiao Co.Ltd Luzhou646000 China

ISBN: (纸本)9798350361674

Visual measurement, a critical component in industrial production, often faces accuracy challenges due to image distortion at the edges of the field of view, particularly in large spaces. This paper capitalizes on the robust feature-learning capabilities of deep-learning algorithms tailored for industrial robots in factory settings, and introduces a comprehensive tracking and measurement system, grounded in deep learning, specifically designed for light pen industrial robots. The approach begins with an analysis of the industrial robot's workspace, leading to the installation of a binocular vision sensor on a rotating platform. This setup forms the basis for a novel full-space tracking and measurement device for industrial robots, utilizing a light pen. The system integrates a target detection algorithm with a rotation platform control algorithm, ensuring the light pen remains centered in the camera's field of view in real-time. This innovation addresses the limitations of traditional light pens, particularly their restricted measurement range and reduced accuracy. Furthermore, the transformation matrix between the pixel and world coordinate systems is established by analyzing the relationship between the binocular vision sensor and the precision rotating platform. In the process of pinpointing the sphere center coordinates of the light pen probe, the system establishes a mapping relationship between the marker point and the probe's sphere center. It then employs the cross-ratio invariance principle and the least squares method for precise calculations. Finally, the system's accuracy is validated using the actual dimensions of standard gauge blocks and balls as references. Experimental results demonstrate that the geometric measurement error in the proposed tracking and measurement system on these standard objects is less than 0.1mm. These results offer an alternative for full-space tracking and measurement in complex industrial environments. © 2024 ieee.

关键词： Binocular vision

来源：评论

学校读者我要写书评

暂无评论

Power system transient stability preventive control optimization method driven by Stacking Ensemble learning

引用

ENERGY REPORTS 2023年 9卷 757-765页

作者： Xie, Zhijun Zhang, Dongxia Han, Xiaoqing Hu, Wei Taiyuan Univ Technol Shanxi Key Lab Power Syst Operat & Control Taiyuan 030024 Shanxi Peoples R China Tsinghua Univ Dept Elect Engn State Key Lab Control & Simulat Power Syst & Gene Beijing 100084 Peoples R China China Elect Power Res Inst Beijing 100192 Peoples R China

The dynamic characteristics of the power system are becoming more and more complex, and the difficulty of operation control is increasing. Preventive control is the main means of power system transient stability control. This paper proposes a stacking ensemble learning-driven power system transient stability preventive control optimization method. Firstly, a transient stability assessment model based on Stacking Ensemble Deep Belief Nets (SEDBN) network is established in this research. The performance of weak classifiers is improved by SEDBN's multi-layer ensemble structure, and the created transient stability estimator can extract diverse features and has better robustness and generalization abilities. Secondly, the trained transient stability estimator is integrated into the Aptenodytes Forsteri Optimization (AFO) algorithm as a "transient stability constraint discriminator". Finally, with the goal of minimizing the cost of preventive control, an optimization algorithm for the preventive control of power system transient stability driven by SEDBN is established. Simulation results on ieee 39-bus systems show that the proposed method can achieve highly efficient control solutions. (c) 2023 The Authors. Published by Elsevier Ltd. This is an open access article under theCCBYlicense (http://***/licenses/by/4.0/).

关键词： Stacking Ensemble learning Aptenodytes Forsteri Optimization algorithm Transient stability Transient stability preventive control

来源：评论

学校读者我要写书评

暂无评论

Traffic data Augmentation Using GANs for ITS 20

Traffic Data Augmentation Using GANs for ITS

引用

20th Annual International conference on Distributed Computing in Smart Sensor systems and the Internet of Things (DCOSS-IoT)

作者： Dabboussi, Abdul Hamid Jammal, Manar York Univ Elect Engn & Comp Sci Toronto ON Canada York Univ Sch Informat Technol Toronto ON Canada

ISBN: (纸本)9798350369458;9798350369441

Intelligent Transportation systems (ITS) play a pivotal role in shaping the foundation of smart cities, providing data-driven solutions for traffic management, prediction, and safety. However, these applications often face a significant challenge data scarcity. Insufficient data limits the effectiveness of machine learning models in the context of ITS. To address this issue, this paper presents a novel data augmentation solution using Generative Adversarial Networks (GANs). By collecting sensor-based traffic speed data with contextual labels and training a GAN-based model to generate realistic traffic data for specific days and times, this research successfully proposes a solution to the problem of data scarcity. The generated data undergoes comprehensive qualitative and quantitative evaluations, demonstrating its potential to enhance ITS applications. Furthermore, the generated data is utilized to augment the training data for multiple traffic prediction models, effectively enhancing their performance. This approach opens new avenues for the development of intelligent and sustainable transportation systems, ultimately contributing to the advancement of smarter and more resilient cities.

关键词： Intelligent Transportation systems IoT Smart Cities GAN Wasserstein GAN Traffic Prediction Machine learning

来源：评论

学校读者我要写书评

暂无评论

data-driven control of Networked systems with Quantized Measurements Under Try-Once-Discard Protocols 39

Data-Driven Control of Networked Systems with Quantized Meas...

引用

39th Youth Academic Annual conference of Chinese-Association-of-Automation (YAC)

作者： Wang, Chenxi Zou, Lei Li, Na Donghua Univ Coll Informat Sci & Technol Shanghai 201620 Peoples R China Minist Educ Engn Res Ctr Digitalized Textile & Fash Technol Shanghai 201620 Peoples R China

ISBN: (纸本)9798350390780;9798350379228

This paper is concerned with the data-driven control problem for a networked systems with try-once-discard (TOD) protocol and quantization effect. To begin with, we establish a data-based input-output model based on the data collected in a prior experiment. A so-called TOD protocol is adopted to schedule the measurement data of sensors for the purpose of avoiding data collisions, under which only one sensor is permitted to access to the network at each transmission instant. In addition, the measurement data would be quantized before transimission. The objective of this paper is to present a design for an output-feedback controller such that the system output is exponentially ultimately bounded. By utilizing linear matrix inequalities (LMIs), a sufficient condition is guaranteed for the design of the controller. Finally, a numerical simulation is provided to illustrate the effectiveness and validity of the proposed control strategy.

关键词： data-driven control Try-Once-Discard protocol quantization effect ultimate boundedness

来源：评论

学校读者我要写书评

暂无评论

A data-driven ILC Framework for a Class of Nonlinear Discrete-Time systems

引用

ieee TRANSACTIONS ON CYBERNETICS 2022年第7期52卷 6143-6157页

作者： Yu, Xian Hou, Zhongsheng Polycarpou, Marios M. Beijing Jiaotong Univ Sch Elect & Informat Engn Adv Control Syst Lab Beijing 100044 Peoples R China Univ Cyprus KIOS Res & Innovat Ctr Excellence CY-1678 Nicosia Cyprus Qingdao Univ Sch Automat Qingdao 266071 Peoples R China Univ Cyprus Dept Elect & Comp Engn CY-1678 Nicosia Cyprus

In this article, we propose a data-driven iterative learning control (ILC) framework for unknown nonlinear nonaffine repetitive discrete-time single-input-single-output systems by applying the dynamic linearization (DL) technique. The ILC law is constructed based on the equivalent DL expression of an unknown ideal learning controller in the iteration and time domains. The learning control gain vector is adaptively updated by using a Newton-type optimization method. The monotonic convergence on the tracking errors of the controlled plant is theoretically guaranteed with respect to the 2-norm under some conditions. In the proposed ILC framework, existing proportional, integral, and derivative type ILC, and high-order ILC can be considered as special cases. The proposed ILC framework is a pure data-driven ILC, that is, the ILC law is independent of the physical dynamics of the controlled plant, and the learning control gain updating algorithm is formulated using only the measured input-output data of the nonlinear system. The proposed ILC framework is effectively verified by two illustrative examples on a complicated unknown nonlinear system and on a linear time-varying system.

关键词： Time-domain analysis data models control systems Convergence Nonlinear dynamical systems Technological innovation Optimization methods data-driven iterative learning control (ILC) dynamic linearization (DL) Newton-type optimization method nonlinear discrete-time system

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence for control in Laser-Based Additive Manufacturing: A Systematic Review

引用

ieee ACCESS 2025年 13卷 30845-30860页

作者： Sousa, Joao Brandau, Benedikt Darabi, Roya Sousa, Armando Brueckner, Frank Reis, Ana Reis, Luis Paulo Univ Porto FEUP Fac Engn P-4200465 Porto Portugal Univ Porto FEUP Fac Engn Artificial Intelligence & Comp Sci Lab LIACC P-4200465 Porto Portugal Fraunhofer IWS Addit Mfg & Surface Technol Ctr D-01277 Dresden Germany Inst Sci & Innovat Mech & Ind Engn INEGI Unity Adv Mfg P-4200465 Porto Portugal Univ Porto FEUP Fac Engn Associate Lab Energy Transports & Aerosp LAETA P-4200465 Porto Portugal Lulea Univ Technol Dept Engn Sci & Math S-97187 Lulea Sweden JENOPT Automatisierungstech GmbH Res & Dev Laser Proc Ctr D-07745 Jena Germany INESC Technol & Sci INESC TEC Ctr Robot Ind & Intelligent Syst CRIIS P-4200465 Porto Portugal

Laser-based additive manufacturing (LAM) offers the ability to produce near-net-shape metal parts with unparalleled energy efficiency and flexibility in both geometry and material selection. Despite advantages, these processes are inherently, as they are characterized by multiphysics interactions, multiscale phenomena, and highly dynamic behaviors, making their modeling and optimization particularly challenging. Artificial intelligence (AI) has emerged as a promising tool for enhancing the monitoring and control of additive manufacturing. This paper presents a systematic review of AI applications for real-time control of laser-based manufacturing processes, analyzing 16 relevant articles sourced from Scopus, ieee Xplore, and Web of Science databases. The primary objective of this work is to contribute to the advancement of autonomous manufacturing systems capable of self-monitoring and self-correction, ensuring optimal part quality, enhanced efficiency, and reduced human intervention. Our findings indicate that 62.5 % of the 16 analyzed studies have deployed AI-driven controllers in real-world scenarios, with over 56 % using AI for control strategies, such as Reinforcement learning. Furthermore, 62.5 % of the studies employed AI for process modeling or monitoring, which was integral to the development or data pipelines of the controllers. By defining a groundwork for future developments, this review not only highlights current advancements but also hints future innovations that will likely include AI-based controllers.

关键词： Artificial intelligence Process control Monitoring Three-dimensional printing Manufacturing data models Powders Manufacturing processes Uncertainty Production Additive manufacturing artificial intelligence close-loop control machine learning reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Attention-driven Memory Network for Online Visual Tracking

引用

ieee TRANSACTIONS ON NEURAL NETWORKS AND learning systems 2024年第12期35卷 17085-17098页

作者： Zhang, Huanlong Liang, Jiamei Zhang, Jiapeng Zhang, Tianzhu Lin, Yingzi Wang, Yanfeng Zhengzhou Univ Light Ind Coll Elect & Informat Engn Zhengzhou 450002 Henan Peoples R China Shanxi Univ Sch Math Sci Taiyuan 030006 Shanxi Peoples R China Univ Sci & Technol China Inst Adv Technol Hefei 230000 Anhui Peoples R China Northeastern Univ Coll Engn Boston MA 02115 USA

A memory mechanism has attracted growing popularity in tracking tasks due to the ability of learning long-term-dependent information. However, it is very challenging for existing memory modules to provide the intrinsic attribute information of the target to the tracker in complex scenes. In this article, by considering the biological visual memory mechanisms, we propose the novel online tracking method via an attention-driven memory network, which can mine discriminative memory information and enhance the robustness and reliability of the tracker. First, to reinforce effectiveness of memory content, we design a novel attention-driven memory network. In the network, the long memory module gains property-level memory information by focusing on the state of the target at both the channel and spatial levels. Meanwhile, in reciprocity, we add a short-term memory module to maintain good adaptability when confronting drastic deformation of the target. The attention-driven memory network can adaptively adjust the contribution of short-term and long-term memories to tracking results under the weighted gradient harmonized loss. On this basis, to avoid model performance degradation, an online memory updater (MU) is further proposed. It is designed to mining for target information in tracking results through the Mixer layer and the online head network together. By evaluating the confidence of the tracking results, the memory updater can accurately judge the time of updating the model, which guarantees the effectiveness of online memory updates. Finally, the proposed method performs favorably and has been extensively validated on several benchmark datasets, including object tracking benchmark-50/100 (OTB-50/100), temple color-128 (TC-128), unmanned aerial vehicles-123 (UAV-123), generic object tracking -10k (GOT-10k), visual object tracking-2016 (VOT-2016), and VOT-2018 against several advanced methods.

关键词： Attention mechanism long short-term memory (LSTM) network online learning visual tracking

来源：评论

学校读者我要写书评

暂无评论

Classification of Philippine Soybean Variety Using Image Processing Technique and Machine learning Method

Classification of Philippine Soybean Variety Using Image Pro...

引用

ieee International conference on Automatic control and Intelligent systems (I2CACIS)

作者： Diamante, John Christian Dioses, Isaac Angelo M. Dioses, Jesusimo L., Jr. Tomas, John Paul Q. Mapua Univ Sch Informat Technol Makati Metro Manila Philippines Isabela State Univ Coll Comp Studies Informat & Commun Technol San Fabian Echague Isabela Philippines

ISBN: (纸本)9798350372113;9798350372106

Together with dairy and wheat, soybeans are a major agricultural import into the Philippines. Historically, imports accounted for 99% of the country's supply of soybeans from 1995 to 2014, with local manufacturers making up the remaining 1%. The emergence of novel technologies has enabled the classification of diverse agricultural commodities, such as soybean cultivars, by merging computer vision and machine learning methodologies that utilize edge detection algorithms. Precise categorization of seed variants is essential for farmers and seed manufacturers to maintain variety purity, which in turn affects crop productivity and the quality of soybeans provided to nearby retailers. Morphological features were retrieved from pre-processed soybean pictures using the regionprops function, which made use of edge detection methods. After the extraction of features, the data was subjected to pre-processing and machine learning analysis. The KNearest Neighbors (KNN) model classified the data using Euclidean distance. A 75:25 split of the dataset was made into training and testing subsets, with five neighbors being used for categorization. The CL1 and PSB SY2 soybean varieties were classified by the KNN model with an accuracy rate of 85%, indicating a first step in variety classification research.

关键词： machine learning KNN MATLAB image processing edge detection canny

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：