检索结果-内蒙古大学图书馆

Smart World Congress (SWC), IEEE

作者： Qi Shi Xuewu Dai Dongliang Cui Lijuan Cheng The State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang China Faculty of Engineering and Environment Northumbria University Newcastle Upon Tyne UK Purification Equipment Research Institute of CSIC Handan China

With the advancement of computational intelligence, reinforcement learning has been proposed as a solution for train timetable rescheduling (TTR). However, traditional Q-learning approaches face challenges of large memory overhead and slow convergence rate due to the large state and action spaces in TTR. Moreover, Q-learning suffers from limited generalization ability, requiring retraining of the Q-table for handling new delay scenarios. To accelerate convergence speed and improve generalization ability, this paper proposes a deep reinforcement learning (DQN) approach for TTR. An adaptive action generation method is employed to address the slow convergence issue caused by a large action search space. In the proposed DQN, a target network and an experience replay mechanism are used to enhance the generalization ability of reinforcement learning. The performance of the proposed DQN is evaluated through simulation on a high-speed railway in China. Compared to the First-Come, First-Served (FCFS) baseline method, the validated algorithm yields an 80 % improvement in the generated schedules over FCFS. Moreover, the online decision-making process of the tested algorithm takes only 1-2 seconds, outperforming FCFS in terms of efficiency and effectiveness.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on Data Encryption in Lightweight Embedded Web Server 10

Research on Data Encryption in Lightweight Embedded Web Serv...

引用

10th International Conference on Control, automation and Information Sciences, ICCAIS 2021

作者： Li, Pengfei Qu, Junsuo Shi, Haonan Xi'an University of Posts Telecommunications School of Automation Xi'an China Xi'an University of Posts Telecommunications Xi'an Key Laboratory of Advanced Control and Intelligent Process School of Automation Xi'an China Xi'an University of Posts Telecommunications School of Communication and Information Engineering Xi'an China

ISBN: (纸本)9781665440295

From the perspective of reducing the configuration complexity of IoT device parameters and improving data security, a lightweight embedded Web server is designed based on the TencentOS tiny operating system to reduce the hardware requirements of the embedded Web server design. In order to improve the security and transmission reliability of IoT monitoring data, a mechanism for data encryption is proposed. Embedded Elliptic Curve Cryptography (ECC) in Flash inside the chip to ensure the security of key data during transmission. The data monitoring platform receives and decrypts the received data, and stores the data into a database server after processing. The experimental results show that the security of data transmission and reached the expected goals. © 2021 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Energy-efficient Hot-rolling Scheduling of High-quality Steel Products

Energy-efficient Hot-rolling Scheduling of High-quality Stee...

引用

IEEE Symposium Series on Computational Intelligence (SSCI)

作者： Ziyan Zhao Zikuo Bian Chenglong Wang Kun Zou Shixin Liu College of Information Science and Engineering Northeastern University Shenyang China Shandong Iron & Steel Group Rizhao Co. Ltd Rizhao China The State Key Laboratory of Synthetical Automation for Process Industries Shenyang China

Steel production involves many energy-intensive processes. Under the goal of carbon peak and carbon neutrality, it is essential to study the steel production scheduling problems aiming at energy saving to realize the green manufacturing of steel production processes. Aiming at the hot rolling process of high-quality steel products, a novel energy-saving production scheduling problem is studied in this paper. Unlike existing research, this paper additionally considers temperature constraints and the optimization of temperature-keeping equipment assignment in producing high-quality steel products. To solve it efficiently, this paper presents an improved simulated annealing algorithm where destruction and construction strategies from iterated greedy algorithms are embedded into it. Experimental results show that the presented algorithm has obvious advantages compared with other competitive peers. Its excellent solution performance means its great application potential.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Classification on point-cloud of shoe-last curvature using weight-updated boosting based ensemble learning 9

Classification on point-cloud of shoe-last curvature using w...

引用

9th IEEE Joint International Information Technology and Artificial Intelligence Conference, ITAIC 2020

作者： Li, Zairan Wang, Dan Tianjin University Tianjin Key Laboratory of Process Measurement and Control School of Electrical Engineering and Automation China

Optimizing the curvature shape of shoe last is an important research content and a promising direction in current shoe-last design. The emergence of plantar pressure imaging method provided a new technical mean for shoe-last design. The point-cloud dataset was acquired from the plantar pressure experiments which may be used for generating comfort shoe-last curvature, and the key zones on last curvature may be classified and has potential benefit to the designers to produce comfort shoe. In this paper ensemble learning technologies are applied for classifying those points through the proposed weights-updated algorithms. The proposed weights-updated algorithm with boosting operation performed high effectiveness by comparing to k-NN, random forest (RF) and Bayers (NB) in classification accuracy. The proposed boosting based ensemble learning method will be potential applied in interactive design of industry and be beneficial to produce comfort shoes. © 2020 IEEE.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Effect of Intermediate Annealing Temperature and Cold Rolling Deformation on the Texture of Yttrium-Oriented Silicon Steel

SSRN

引用

SSRN 2024年

作者： Guo, Zhihong Liu, Pengjun Ma, Yize Zheng, Yaxu Liu, Yu Zhu, Liguang Zhang, Yuanxiang Zhang, Di Wang, Bo Feng, Jie Lu, Suling School of Material Science and Engineering Hebei Short Process Steel Making Technology Innovation Center Hebei University of Science and Technology Shijiazhuang050018 China School of Material Science and Engineering State Key Laboratory of Rolling Technology and Automation Northeastern University Shenyang110003 China College of Materials Science and Engineering Chongqing University Chongqing400045 China

This study investigates the impact of intermediate annealing temperature on the microstructure and texture of oriented silicon steel. The steel samples were annealed at temperatures of 850℃, 900℃, and 940℃ under different cold rolling deformation conditions. Furthermore, the study examines the influence of adding rare earth Y on the microstructure and texture of the steel after intermediate annealing. Additionally, the research reveals the mechanism by which precipitation affects the microstructure and texture of the intermediate annealed plate of oriented silicon steel. The results indicate that the average grain size of the intermediate annealing plate decreases gradually as the cold-rolled deformation increases. The annealing plate subjected to 60% cold rolling exhibited a Goss texture with an area fraction of 2.78%, while the 72% cold-rolled annealing plate predominantly exhibited a strong Goss texture along with some {114} and {110} textures. The 86% cold-rolled annealing plate displayed a diffuse recrystallization texture, with some textures near {100} and {411}, and formed a Goss texture with an area fraction of 2.21%. Moreover, as the annealing temperature increased, the grain size gradually increased, but the microstructure uniformity decreased. Additionally, different textures were observed within the intermediate annealed plate at different temperatures. Precipitate analysis reveals that samples without Y mainly contain Al2O3 and MnS, while samples with Y contain AlN, YS, and YOxSy. Furthermore, the addition of rare earth Y reduces the density and size of the precipitates. The size of second phase particles decreases and the amount of precipitation increases with higher intermediate annealing temperatures. © 2024, The Authors. All rights reserved.

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

Integrated Stabilizing Control for NCSs with Intermittent Observation and Multiple Random Transmission Delays

Integrated Stabilizing Control for NCSs with Intermittent Ob...

引用

Chinese Control Conference (CCC)

作者： Haoting Sui Cheng Tan Qinglong Zhang Yuzhe Li Wing Shing Wong College of Engineering Qufu Normal University Rizhao China The State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang China The Department of Information Engineering The Chinese University of Hong Kong Shatin N. T. Hong Kong

In this paper, we mainly investigate sampled-data networked control systems (NCSs) operating over wireless communication networks featuring multi-path channels. Affected by limited bandwidth power, the transmission of the observed state signals from the sensor to the controller may suffer packet loss leading to intermittent observation. And due to an unreliable multi-path routing network, the conveyance of control signals from the controller to the actuator is subject to random transmission delays. By proposing an idle-time-based scheduling policy with a pre-defined deadline constraint for signal reception on the actuator side, we transform the integrated system into a stochastic one with constant input delay. Based on this, we derive a set of Riccati-type stabilization conditions, which are necessary and sufficient, and design the stabilizing control policy in terms of the feedback of the optimal estimate with minimum mean square error. Additionally, for the scalar case, we study the existence and uniqueness properties of the maximum sampling period, and develop an algorithm based on system parameters, service quality and packet loss rate.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Q-Learing-Based Multi-Rate Optimal Control and Its Application

Q-Learing-Based Multi-Rate Optimal Control and Its Applicati...

引用

Chinese Control and Decision Conference, CCDC

作者： Zhenxing Xia Wei Dai School of Information and Control Engineering China University of Mining and Technology Xuzhou State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang China

ISBN: (纸本)9781665478977

In this paper, adaptive dynamic programming (ADP) algorithm, with lifting technology, is develop to solve the multi-rate optimal control problem for discrete-time linear systems. We make use of the lifting technology to convert the multi-rate sample control problem to the single-rate one in the uniform cycle. The propose a Q-Leaming based approach to learn the optimal regulator by a value iteration (VI) algorithm. First, a class of continuous-time (CT) linear system with multi-timescale is considered. Then, the convergence of a Q-Learning based algorithm is given. It is proven that the iterative cost function precisely converges to the optimal value, and the control input also converges to the optimal values. Finally, HIL system for grinding process is given to illustrate the effective performance of the proposed method.

关键词： Linear systems Regulators Q-learning System dynamics Heuristic algorithms Optimal control process control

来源：评论

学校读者我要写书评

暂无评论

Self-Healing Control Based on Generalized Observer and Its Application in Sewage Treatment process

Self-Healing Control Based on Generalized Observer and Its A...

引用

第34届中国过程控制会议

作者： Peihao Du Ruyi Jiang Weimin Zhong Xin Peng Linlin Li Xiaolong Wu Key Laboratory of Smart Manufacturing in Energy Chemical Process Ministry of EducationEast China University of Science and Technology School of Automation and Electrical Engineering University of Science and Technology Beijing Faculty of Information Technology Beijing University of Technology

This paper proposes a self-healing control strategy based on a generalized observer,aiming at the widespread sensor additive faults in the activated sludge method-based sewage treatment process(STP).Firstly,the T-S fuzzy system identification scheme of the STP is ***,a generalized discrete system subject to sensor additive fault is constructed,and a stable fuzzy generalized observer is built by configuring some poles of the estimated error dynamic ***,the estimated fault is used to compensate the measurement output,and the self-healing control law is designed according to the pole configuration method to achieve the performance self-recovery of the STP control system under the sensor additive *** experiments are carried out on a standard platform of the STP to show that the proposed output-feedback self-healing control technique not only enables the quick switching of operating points,but also restores the original working condition after a fault,significantly decreasing the performance deterioration caused by sensor faults.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Product Information Units Modeling Oriented to Digital Twin 2

Product Information Units Modeling Oriented to Digital Twin

引用

2020 2nd International Conference on Resources and Environmental Research, ICRER 2020

作者： Bao, Qiangwei Zhao, Gang Yu, Yong Dai, Sheng School of Mechanical Engineering and Automation Beihang University Beijing China Key Laboratory of Aeronautics Smart Manufacturing Beihang University Beijing China Beijing Engineering Technological Research Center of High-Efficient and Green CNC Machining Process Beijing China

To solve the problem of expression of multi-source heterogeneous data of product development and manufacture, a new concept of product information units (IUs) and a new method of product data modeling based on IUs are proposed. Firstly, the definition and composition of IUs are analysed according to the formation time and description object. Secondly, the geometric elements and their topological relationships of products are regarded as bases, depending on which the association methods of various IUs are expounded. Meanwhile, the role of IUs in the construction of digital twin models is pointed out. Finally, the ontology representation of the IUs is realized to prove the feasibility of the method proposed. © Published under licence by IOP Publishing Ltd.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Two-Dimensional Broad Learning System for Data Analytic

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2021年第6期2卷 594-607页

作者： Dai, Wei Zhang, Rui Wang, Qianjin Cheng, Yuhu Wang, Xuesong The Engineering Research Center of Intelligent Control for Underground Space Ministry of Education China University of Mining and Technology Xuzhou221116 China The School of Information and Control Engineering China University of Mining and Technology Xuzhou221116 China The State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang110819 China The School of Electrical Engineering Yancheng Institute of Technology Yancheng221051 China

Recently, a novel learning algorithm called the broad learning system (BLS) has been established by using the theory of pseudoinverse and compressed sensing technology. As an alternative to deep learning, BLS has gained extensive attention in data analytics. Unlike the existing deep structures based learning tools (such as deep neural networks), it is able to rapidly achieve incremental learning, and does not require tedious retraining to remodel the system. However, given image data modeling tasks, 1-D BLS requires a conventional vectorization operation, the dimension of input will be quite large for high resolution image. This operation may result in huge computational complexity, thereby increasing the time of model construction. To resolve this issue, a 2-D version of BLS, namely 2-D-BLS, is first proposed to fast construct randomized learner models by using matrix inputs. Specifically, the proposed method employs left and right projecting vectors to replace the usual high dimensional input weight. Moreover, the theoretical analyses on the superiority of 2-D-BLS against BLS are presented in terms of the algorithm complexity and the difference of random parameter space. Empirical results on MNIST dataset, NORB 3-D object image recognition dataset, ORL dataset, YaleB dataset, and handwritten digit dataset demonstrate that the proposed 2-D-BLS outperforms the existing extensions of BLS and state-of-the-art 2-D machine learning methods in terms of the learning efficiency, showing good potential of 2-D-BLS for image data analytics. Impact Statement-as a novel learning tool, BLS has achieved great success in many fields. Image recognition is one of the most widely used fields of artificial intelligence. But, BLS is a 1-D model, the vectorization operation is necessary to convert matrix input data into a row or a column vector. This operation will lead to "explosion of dimensionality" and increase the time of model construction when it is coming to image data analytic

关键词： Learning systems

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：