检索结果-内蒙古大学图书馆

IEEE Journal of Selected Areas in Sensors 2024年 1卷 105-113页

作者： Chen, Yongxuan Wang, Dianhui School of Low-Carbon Energy and Power Engineering Xuzhou221116 China China University of Mining and Technology Artificial Intelligence Research Institute Xuzhou221116 China Northeastern University State Key Laboratory of Synthetical Automation for Process Industries Shenyang110819 China

Despite the extensive applications of deep neural networks in data modeling filed, there are still some obvious deficiencies for the implementation in modern industrial cases. There are mainly reflected in the following aspects: first, the architectures are difficult to configure;second, the modeling process is time-consuming;third, the training procedure easily falls into the local optimum situation. To overcome these problems, exploring the nonconnectionist learning model has become a popular topic recently. This article proposes a deep nonconnectionist learning model based on kernel principal component regression (KPCR), which is referred to as stacked KPCR (SKPCR). By stacking multiple KPCR modules, a multilayer learning model is constructed by adopting hierarchical feature extraction. In SKPCR, the model structure is determined incrementally and there is only one parameter needed to be configured for each layer. Furthermore, an enhanced learning strategy is designed for alleviating the information loss problem in the training process. An actual industrial case is used to validate the effectiveness, including the prediction performance and modeling efficiency, of our proposed method. © 2024 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Feature Selection for Multivariate Time Series based on Improved FINCH 6

Unsupervised Feature Selection for Multivariate Time Series ...

引用

6th International Conference on Machine Learning and Natural Language processing, MLNLP 2023

作者： Wang, Ling Liu, Wei Chu, Zhongkun Shunde Innovation School University of Science and Technology of Beijing China School of Automation and Electrical Engineering University of Science and Technology of Beijing Key Laboratory of Knowledge Automation for Industrial Process Ministry of Education Beijing China

ISBN: (纸本)9798400709241

Feature selection is a crucial step in the preprocessing of data mining for multivariate time series. In order to remove irrelevant and redundant features in the multivariate time series, an unsupervised feature selection method based on improved First Integer Neighbor Clustering Hierarchy (FINCH) is proposed to select a compact subset of features containing the most important features. Firstly, the time-lagged cross-correlation (TLCC) is used to measure the redundancy between features, and Inverse Fast Fourier Transform (IFFT) is performed to reduce the computational complexity. Secondly, a new correlation-based clustering centroid and stopping criterion are defined to speed up hierarchical clustering. Finally, feature filtering is performed using the proposed improved FINCH to remove redundant features. Experiments on six benchmark datasets show that the proposed method achieve higher efficiency in dimensional reduction under the same experimental conditions. © 2023 ACM.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Performance Realization for Gas Turbine System: Adaptive Constraint Regulation Framework 6

Performance Realization for Gas Turbine System: Adaptive Con...

引用

6th International Conference on Electronic engineering and Informatics, EEI 2024

作者： Du, Peihao Zhong, Weimin Li, Hongyi Li, Linlin Peng, Xin He, Kaixun School of Electronic and Information Engineering Chongqing Key Laboratory of Generic Technology and System of Service Robots Southwest University Chongqing400715 China School of Automation and Electrical Engineering University of Science and Technology Beijing Key Laboratory of Knowledge Automation for Industrial Processes of Ministry of Education Beijing100083 China East China University of Science and Technology Key Laboratory of Smart Manufacturing in Energy Chemical Process Ministry of Education Shanghai200237 China Engineering Research Center of Process System Engineering Ministry of Education East China University of Science and Technology Shanghai200237 China College of Electrical Engineering and Automation Shandong University of Science and Technology Qingdao266590 China

ISBN: (纸本)9798350353594

With the excessive consumption of fossil energy and the growing environmental pollution caused by its combustion, the gas turbine system (GTS) plays a key role in distributed renewable energy fields due to its versatility, efficiency and controllability. This paper focuses on the adaptive constraint regulation problem for the GTS with time-varying load disturbance, thereby facilitating exact speed tracking to regulate the fuel flow for the turbine under variable load conditions. Therein, a residual transformation dynamics based on the performance function are established for triggering the preset-time residual convergence and output performance constraints. Then, an adaptive constraint controller is developed to ensure the desired regulation level of the GTS. Simulation results illustrate that the proposed strategy can mitigate the load disturbance effect and guarantee the GTS performance constraints. © 2024 IEEE.

关键词： Gas turbines

来源：评论

学校读者我要写书评

暂无评论

Attention-Based Multiagent Graph Reinforcement Learning for Service Restoration

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第5期5卷 2163-2178页

作者： Fan, Bangji Liu, Xinghua Xiao, Gaoxi Kang, Yu Wang, Dianhui Wang, Peng Xi'an University of Technology School of Electrical Engineering Xi'an710048 China Nanyang Technological University School of Electrical and Electronic Engineering 639798 Singapore University of Science and Technology of China Department of Automation School of Information Science and Technology Hefei230027 China China University of Mining and Technology Artificial Intelligence Research Institute Xuzhou221116 China Northeastern University State Key Laboratory of Integrated Automation for Process Industry Shenyang110819 China

With the ongoing integration of distributed energy resources, modern distribution systems are getting sufficient generation capacity to perform active restoration after outages without transmission system support. The model-based approaches are widely used in resolving service restoration problems, relying on accurate system models. Deep reinforcement learning is believed as an alternative solution for problem solving, although it has not been sufficiently explored. In this article, the service restoration process is described as a partially observable Markov decision process and a multiagent graph reinforcement learning approach based on attention is proposed to train multiple agents to coachieve the restoration goal to reinforce the system resilience in coping with extreme events. To consider the connections and correlations between nodes during the service restoration, the state of the active distribution network is defined by graph data that contains features of both topology and nodes. The perceived ability of the agents is empowered by graph convolutional networks during the feature extraction, supplying agents with more comprehensive data to learn more reasonable restoration strategies. In addition, the centralized training with attention is developed for multiagent systems, focusing on the relations between the agents to strengthen the teamwork capability. The performance of the proposed method is verified by a set of comparative studies on the IEEE-118 system with dispatchable generators, rooftop photovoltaics, and energy storage systems simultaneously. © 2023 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Optimized GA-Based PID Control Design for Stick-Slip Suppression in Drill String of Rotary Drilling System

Optimized GA-Based PID Control Design for Stick-Slip Suppres...

引用

International Conference on Artificial Intelligence in Renewable Energetic Systems, IC-AIRES 2024

作者： Mawloud, Tellaa Abderrezak, Aibeche Zinelabidine, Doghmane Mohamed Madjid, Kidouche Automation and Electrification of Process Applied Automation Laboratory Faculty of Hydrocarbons Chemistry University M’Hamed Bougara Boumerdes35000 Algeria Institute of Electrical and Electronics Engineering University M’hamed Bougara Boumerdes Algeria Bob L. Herd Department of Petroleum Engineering Texas Tech University LubbockTX79401 United States

ISBN: (纸本)9783031803000

Stick-slip phenomena in the oil and gas drilling sector cause drillstring vibrations that provide major issues. These vibrations result in reduced drilling efficiency, equipment malfunctions, and possible dangers. This work introduces a thorough method for modeling and regulating stick-slip behavior. It utilizes a mechanical model with three degrees of freedom (3-DOF) that incorporates the influence of dry friction. The model combines both axial and torsional degrees of freedom to precisely reflect the intricate dynamics of the drillstring. Additionally, a control technique is suggested to alleviate stick-slip vibrations. This strategy involves using a hybrid Proportional-Integral-Derivative (PID) controller that has been tuned using Genetic Algorithms (GA). The PID-GA controller is specifically engineered to manage the rotating speed, mitigate stick-slip oscillations, and improve drilling stability. The efficacy of the suggested 3-DOF model and PID-GA control method in reducing stick-slip vibrations during drilling is proven by numerical simulations conducted under different drilling situations. The findings demonstrate notable advancements in drilling performance, such as decreased vibrations caused by friction, improved efficiency in drilling, and extended lifespan of the drillstring. This research significantly helps to the progress of drilling operations by offering a strong framework for modeling and managing stick-slip behavior. As a result, it improves drilling performance and guarantees operational safety in the oil and gas industry. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Gas industry

来源：评论

学校读者我要写书评

暂无评论

Effect of oxygen enrichment on sintering behavior of high proportion vanadium-titanium magnesite concentrates

引用

Journal of Iron and Steel Research International 2023年第11期30卷 2122-2132页

作者： Shi-hong Peng Hao Liu Ze-zheng Sun Chang-wei Li Yue-lin Qin Wei-qiang Liu Guang Wang School of Metallurgy and Materials Engineering Chongqing University of Science and TechnologyChongqing401331China Value-Added Process and Clean Extraction of Complex Metal Mineral Resources Chongqing Municipal Key Laboratory of Institutions of Higher EducationChongqing401331China Chongqing Chuanyi Automation Co. Ltd.Chongqing401120China Process and Systems Engineering Åbo Akademi UniversityÅbo20500Finland Department of Materials Science and Engineering McMaster UniversityOntarioL8S 4L7Canada

To achieve high-efficiency utilization of complex and unmanageable iron-containing minerals,the effects of oxygen enrichment on productivity,yield,flame front speed,exhaust gas peak temperature,and desulphurization reaction of the vanadium-titanium magnetite sintering process as well as sinter tumble index and mineralogy were clarified,with oxygen enrichment concentrations ranging from 21 to 29 vol.%.Results indicated that with increasing the oxygen enrichment concentration from 21 to 27 vol.%,the flame front speed increased from 30.3 to 40.0 mm min^(-1),the yield enhanced from 72%to 77%,and the productivity augmented from 1.83 to 2.67t m^(-2)h^(-1);in the meantime,the tumble index was improved from 73.7%to 77.9%,and the exhaust gas peak temperature rose from 376.4 to 484.8℃.The main reason for the improvement in sintering properties was the increased combustibility of fuels and the generation of proper liquid phase that improved the permeability of the packed *** improved sinter strength is mainly due to the increase in the phase fraction of silico-ferrites of calcium and *** addition,oxygen enrichment sintering could significantly increase the desulphurization level of vanadium-titanium magnetite sinter and the rate of desulphurization reaction during sintering process.

关键词： Sinter Oxygen enrichment Vanadium-titanium magnetite Sintering behavior

来源：评论

学校读者我要写书评

暂无评论

Optimal Control Design for Stick-Slip Vibrations Mitigation in Rotary Drilling Systems

Optimal Control Design for Stick-Slip Vibrations Mitigation ...

引用

International Conference on Artificial Intelligence in Renewable Energetic Systems, IC-AIRES 2024

作者： Tellaa, Mawloud Aibeche, Abderrezak Doghmane, Mohamed Zinelabidine Kidouche, Madjid Automation and Electrification of Process Applied Automation Laboratory Faculty of Hydrocarbons and Chemistry University M’Hamed Bougara Boumerdes35000 Algeria Institute of Electrical and Electronics Engineering University M’hamed Bougara Boumerdes Algeria Bob L. Herd Department of Petroleum Engineering Texas Tech University LubbockTX79401 United States

ISBN: (纸本)9783031803000

Various forms of vibrations can have a negative impact on the drilling process in rotary drilling equipment. The presence of vibrations can result in equipment damage, reduced borehole quality, decreased drilling efficiency, and increased non-productive time. Currently, the sole existing method to control these vibrations is by manually modifying drilling parameters, which is not a reliable technique and might lead to unfavourable economic consequences. Scientists have devised automated control systems to address these irregularities;however the effectiveness of the controllers is still being refined. Lately, the utilization of a PID controller based on particle swarm optimization has demonstrated noteworthy achievements. Nevertheless, the stick-slip vibration mitigation in rotary drilling equipment has not been subjected to testing. This research seeks to investigate and suggest the utilization of a PID controller, fine-tuned using the particle swarm optimization technique, to enhance the effectiveness of controllers developed for the purpose of reducing vibrations in rotary drilling systems. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Stick-slip

来源：评论

学校读者我要写书评

暂无评论

Adaptive Dynamic Programming and Decentralized Optimal Output Regulation of Two-Time-Scale Interconnected Systems 12

Adaptive Dynamic Programming and Decentralized Optimal Outpu...

引用

12th IEEE International Conference on Control, automation and Information Sciences, ICCAIS 2023

作者： Zhao, Jianguo Yang, Chunyu Zhou, Linna Gao, Weinan China University of Mining and Technology School of Information and Control Engineering Xuzhou China Northeastern University State Key Laboratory of Synthetical Automation for Process Industries Shenyang China

ISBN: (纸本)9798350328783

In this paper, we address the decentralized optimal output regulation problem for two-time-scale (TTS) interconnected systems with unknown slow dynamics through adaptive dynamic programming (ADP). Firstly, singular perturbation theory is leveraged to decompose the TTS interconnected system into a slow subsystem and several interconnected fast time-scale subsystems. Secondly, we develop a decentralized optimal control scheme for the fast time-scale subsystems with interconnections. Also, we devise an off-policy ADP algorithm to learn the optimal control strategy for the slow time-scale subsystem with unknown dynamics. Moreover, we combine the slow and fast control strategies to design the composite decentralized optimal output regulator. Both optimality and stability of the closed-loop system are rigorously analyzed. Finally, simulation results are provided to validate the effectiveness of the proposed methodology. © 2023 IEEE.

关键词： Dynamic programming

来源：评论

学校读者我要写书评

暂无评论

Stability Analysis and Impulsive Controller Design for Positive Interval Type-2 Polynomial Fuzzy Systems with Input Saturation 13

Stability Analysis and Impulsive Controller Design for Posit...

引用

13th IEEE International Conference on CYBER Technology in automation, Control, and Intelligent Systems, CYBER 2023

作者： Han, Meng Huang, Yongjie Guo, Ge Wang, Zhengsong School of Control Engineering Northeastern University at Qinhuangdao Qinhuangdao066004 China Northeastern University State Key Laboratory of Synthetical Automation for Process Industries Shenyang110819 China

ISBN: (纸本)9798350315196

This paper designs an impulsive controller for nonlinear positive systems with uncertain parameters and input saturation constraints. To address the issue of modeling errors caused by parameter uncertainties, system modeling is done using an interval type-2 (IT2) polynomial fuzzy model. Also, a premise mismatched controller design strategy is employed to improve controller design flexibility. In addition, to attenuate the conservatism of the analytical results, a novel impulse-time-dependent discretized polynomial copositive Lyapunov function (IDDPCLF) is employed, and the obtained non-convex resultant conditions are handled by the proposed convexification method. Finally, the usefulness of the impulsive controller design approach and the convexification method are verified through an example. © 2023 IEEE.

关键词： Polynomials

来源：评论

学校读者我要写书评

暂无评论

A Semisupervised Soft-Sensor of Just-in-Time Learning With Structure Entropy Clustering and Applications for Industrial processes Monitoring

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2023年第4期4卷 722-733页

作者： Li, Dong Liu, Yiqi Huang, Daoping Xu, Chong South China University of Technology Key Laboratory of Autonomous Systems and Networked Control Ministry of Education School of Automation Science and Engineering Guangzhou510640 China Technical University of Denmark Process and Systems Engineering Center Department of Chemical and Biochemical Engineering Lyngby2800 Denmark South China University of Technology School of Automation Science and Engineering Guangzhou510640 China Gannan Normal University School of Physics and Electronic Information Ganzhou341000 China

To monitor industrial processes properly, soft-sensors are widely used to predict significant but difficult-to-measure quality variables. However, the prediction performances of traditional data-driven soft-sensors are usually unacceptable once suffering from high-nonlinear, high-dimension, and imblance data issues. Therefore, a semisupervised soft-sensor, which is learned by a just-in-time method with structure entropy clustering (SS-JITL-SEC), is proposed aiming to improve prediction performance with a simpler way. Inspired by a divide and conquer strategy, a novel SEC method is proposed to achieve several clusters and then to translate the highly complex and nonlinear modeling problems into simple and linear ones. Moreover, the training dataset is extended through a mixed SS labeling approach. Finally, dissimilarity-based JITL works together with the resulting clustering subdatasets to formulate a local adaptive prediction model. Two datasets from different types of wastewater treatment plants are used to verify the effectiveness of the proposed soft-sensor. The results show that the SS-JITL-SEC soft-sensor can achieve better prediction performance than other standard counterparts, and even for effective process monitoring with the resulted residuals. © 2020 IEEE.

关键词： Entropy

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：