检索结果-内蒙古大学图书馆

International Conference on Industrial Artificial Intelligence (IAI)

作者： Qiuman Zeng Tao Lu Gaochang Wu School of Mechanical Engineering and Automation Northeastern University Shenyang China State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang China

ISBN: (数字)9798350356618

ISBN: (纸本)9798350356625

This article introduces a novel fusion framework based on Swin Transformer and deformable attention, primarily designed for infrared and visible image fusion. Our approach comprises four components: feature extraction, an intra-domain fusion module, a cross-domain fusion module, and feature reconstruction. The core innovation lies in the Deformable Cross-Attention module, which integrates cross attention and deformable attention within the Swin Transformer architecture. This design enables our model to effectively fuse relevant feature information from different domains. Moreover, the integration of deformable attention also enhances the flexibility of our attention mechanism, enabling it to focus on data more effectively. The incorporated Swin Transformer's window mechanism significantly reduces the computational cost of attention calculations. The shift window mechanism further enables our model to accommodate images of arbitrary sizes. Additionally, we employ a weighted sum of SSIM loss, texture loss, and intensity loss during training to ensure our network preserves both rich texture information and intensity information. Experimental results demonstrate that our model not only outperforms other state-of-the-art models in terms of quantitative metrics such as SSIM and Qabf’ but also exhibits superior fusion performance in terms of the visual quality.

关键词： Training Measurement Visualization Technological innovation Computational modeling Transformer cores Transformers Feature extraction Computational efficiency Image fusion

来源：评论

学校读者我要写书评

暂无评论

Intelligent Operational Adjustment of Copper Flotation process Based on CBR-GRNN

Intelligent Operational Adjustment of Copper Flotation Proce...

引用

Chinese Control and Decision Conference, CCDC

作者： Hao Yan Xinchun Jia Zhenji Feng Tao Song Fuli Wang School of Automation and Software Engineering Shanxi University Taiyuan China State Key Laboratory of Intelligent Optimized Manufacturing in Mining & Metallurgy Process Beijing Key Laboratory of Process Automation in Mining & Metallurgy Beijing China College of Information Science and Engineering Northeastern University Shenyang China

ISBN: (数字)9798350387780

ISBN: (纸本)9798350387797

The mechanism of the copper flotation process is complex and highly uncertain, making it difficult to establish a precise mechanism model. For a long time, the operational adjustment of the flotation process has mainly relied on manual labor, which makes it difficult to ensure mineral quality and economic benefits for the enterprise. In order to achieve automation of the flotation process operation, this article proposes an intelligent operational adjustment method based on case-based reasoning and the generalized regression neural network (CBR-GRNN). In the offline stage, the working conditions are divided based on PCA and K-means method, and the case bases are established for each type of different working conditions. In the online stage, we first determine the category of the target case and search in the corresponding case base to obtain the most similar operational adjustment solution. Due to the fact that the most similar case may not fully match the target case, further compensation is necessary. Therefore, this paper proposes a new difference-driven case revision scheme using GRNN. The final solution for reuse is the operational adjustment value compensated by GRNN. Finally, the experimental results in an actual copper flotation process have demonstrated that the proposed method can effectively perform operational adjustment. Furthermore, the superiority of the proposed method is further demonstrated by comparing it with the other two techniques.

关键词： Employee welfare Economics automation Uncertainty Neural networks process control Minerals

来源：评论

学校读者我要写书评

暂无评论

Bumpless Transfer Control of Switched Time-Delay Linear Systems with State-dependent Switching 41

Bumpless Transfer Control of Switched Time-Delay Linear Syst...

引用

第41届中国控制会议

作者： Jinghan Li Jun Zhao State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Key Laboratory of Data Analytics and Optimization for Smart Industry (Northeastern University) Ministry of Education College of Information Science and Engineering Northeastern University

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

This paper deals with the bumpless transfer control for switched time-delay *** time-delay bumpless transfer performance for switched linear system is provided,which can suppress control bumps caused by the current state and the time-delay state at the switching ***,by utilizing the multiple Lyapunov functions,under the co-design of the state-dependent switching law and the time-delay controller,a sufficient condition guaranteeing bumpless transfer control of switched time-delay systems is *** effectiveness of the result is validated by an *** result shows that our method reduces the bumpy amplitude while ensuring the stability of the switched time-delay system.

关键词： Switched Systems Time-delay State-dependent Bumpless Transfer

来源：评论

学校读者我要写书评

暂无评论

Bridging the Gap Between Reinforcement Learning and Nonlinear Output-Feedback Control

Bridging the Gap Between Reinforcement Learning and Nonlinea...

引用

第43届中国控制会议

作者： Weinan Gao Zhong-Ping Jiang Tianyou Chai State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Tandon School of Engineering New York University

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

The primary objective of this paper is to bridge the gap between reinforcement learning(RL) and nonlinear output-feedback control by developing a novel solution to direct adaptive optimal control with guaranteed closed-loop *** specifically, for a broad class of nonlinear affine discretetime systems with limited output measurements, we integrate RL and advanced nonlinear control methods to devise highfidelity direct adaptive optimal controllers from data. Under the condition of uniform observability, our original learning-based control solution begins with the reconstruction of the system state from the retrospective input and output data, akin to a deadbeat observer. Subsequently, we propose value iteration algorithms to facilitate the learning of optimal output-feedback control policies and value functions leveraging measured input and output *** ensure feasibility and reliability in practice, we provide rigorous convergence proofs for the proposed learning algorithms along with the stability analysis for the closed-loop *** results are presented to showcase the effectiveness of the developed methodologies, demonstrating their capability to handle the output-feedback adaptive optimal control problems of general nonlinear affine systems.

关键词： Adaptive optimal control output-feedback nonlinear systems reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Quantized Prescribed Performance Control for Second-Order Nonlinear Systems 4

Quantized Prescribed Performance Control for Second-Order No...

引用

4th International Conference on Industrial Artificial Intelligence, IAI 2022

作者： Song, Junguo Zhang, Jinxi College of Information Science and Engineering Northeastern University Shenyang China Northeastern University State Key Laboratory of Synthetical Automation for Process Industries Shenyang China

ISBN: (数字)9781665451208

ISBN: (纸本)9781665451208

This paper designs an output tracking controller for a class of uncertain second-order nonlinear systems with input quantization to solve the prescribed performance control problem. The performance function restrains the convergence rate and precision of the output tracking error. The barrier function is used to confine this error. A simple input quantizer is specially designed for the controller. The resulting control strategy ensures that the prescribed output tracking performance is achieved and all the closed-loop signals are bounded. The control strategy is verified through the simulation result. © 2022 IEEE.

关键词： Controllers

来源：评论

学校读者我要写书评

暂无评论

A Surrogate-Assisted Coevolutionary Algorithm for Expensive Constrained Multiobjective Optimization

A Surrogate-Assisted Coevolutionary Algorithm for Expensive ...

引用

Congress on Evolutionary Computation

作者： Haofeng Wu Qingda Chen Cuie Yang Jinliang Ding Yaochu Jin The State Key Laboratory of Synthetical Automation for Process Industries Shenyang China The School of Engineering Westlake University Hangzhou China

ISBN: (数字)9798350308365

ISBN: (纸本)9798350308372

Surrogate-assisted evolutionary algorithms (SAEAs) are often used for expensive constrained multi-objective optimization problems (CMOPs). However, they exhibit poor convergence and diversity on complex CMOPs because they may consume more evaluations for approximating the constrained Pareto Front (CPF), i.e., the infeasible regions far from the CPF. To address this issue, we propose a surrogate-assisted coevolution-ary algorithm, which improves the convergence and diversity performance by searching on auxiliary problems together with the original CMOP. Firstly, we construct a surrogate model for each objective and constraint function. The primary population searches on both objective and constrained surrogate models, which approximate for the original constrained problem. The secondary population searches on an auxiliary problem, which is a multi-objective optimization problem (MOP) approximated by objective surrogate models. The two populations exchange information to enhance the convergence performance of the primary population. To improve the feasibility, the auxiliary problem is adopted with a certain probability. A novel infill criterion is proposed to guide the selection of high-quality solutions for updating the surrogate model, which relies on the feasible ratio of evaluated solutions. The performance of the proposed algorithm is evaluated on multi-objective and many-objective benchmarks to demonstrate its competitiveness.

关键词： Computational modeling Sociology Evolutionary computation Benchmark testing Search problems Approximation algorithms Statistics

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning for Online Dispatching Policy in Real-Time Train Timetable Rescheduling

引用

IEEE Transactions on Intelligent Transportation Systems 2024年第1期25卷 478-490页

作者： Yue, Peng Jin, Yaochu Dai, Xuewu Feng, Zhenhua Cui, Dongliang Northeastern University State Key Laboratory of Synthetical Automation for Process Industries Shenyang110819 China University of Bielefeld Nature Inspired Computing and Engineering Group Bielefeld33619 Germany University of Surrey Department of Computer Science GuildfordGU2 7XH United Kingdom University of Surrey School of Computer Science and Electronic Engineering GuildfordGU2 7XH United Kingdom

Train Timetable Rescheduling (TTR) is a crucial task in the daily operation of high-speed railways to maintain punctuality and efficiency in the presence of unexpected disturbances. However, it is challenging to promptly create a rescheduled timetable in real time. In this study, we propose a reinforcement-learning-based method for real-time rescheduling of high-speed trains. The key innovation of the proposed method is to learn a well-generalized dispatching policy from a large amount of samples, which can be applied to the TTR task directly. At first, the problem is transformed into a multi-stage decision process, and the decision agent is designed to predict dispatching rules. To enhance the training efficiency, we generate a small yet good-quality action set to reduce invalid explorations. Besides, we propose an action sampling strategy for action selection, which implements forward planning with consideration of evaluation uncertainty, thus improving search efficiency. Extensive experimental results demonstrate the effectiveness and competitiveness of the proposed method. It has been proven that the local policies trained by the proposed method can be applied to numerous problem instances directly, rendering it unnecessary to use human-designed rules. © 2000-2011 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Dissipative Tracking Control of T-S Fuzzy Switched Systems under Bumpless Transfer Performance 41

Dissipative Tracking Control of T-S Fuzzy Switched Systems u...

引用

第41届中国控制会议

作者： Guangxu He Jun Zhao State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Key Laboratory of Data Analytics and Optimization for Smart Industry (Northeastern University) Ministry of Education Collee of Information Science and Engineering Northeastern University

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

This paper studies the tracking control problem of the T-S fuzzy switched systems with the α-dissipativity and the bumpless transfer *** on the reference system,the fuzzy tracking controller will be designed by using the parallel distributed compensation *** sufficient conditions in terms of linear matrix inequalities are obtained to guarantee the adissipative tracking bumpless transfer performance via the co-design of the bumpless transfer controller and the state-dependent switching law,even if the tracking problem of each fuzzy subsystems is not ***,an example is given to validate the effectiveness of the results.

关键词： T-S fuzzy switched systems α-dissipative tracking bumpless transfer control

来源：评论

学校读者我要写书评

暂无评论

A Token-Sparsity-Based Image Panoptic Segmentation Method for Natural Scenes

A Token-Sparsity-Based Image Panoptic Segmentation Method fo...

引用

第43届中国控制会议

作者： Han Liu Peng Zhang Dali Chen Jun Fu State Key Laboratory of Synthetical Automation for Process Industries Northeastern University School of Information Science and Engineering Northeastern University

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

Panoptic segmentation is the task of assigning unique semantic labels and instance IDs to each pixel in the image,which can realize image understanding more ***,most of the recent work is based on transformer mechanism to achieve powerful partitioning performance,but they always have huge computing *** propose a token-sparsity-based image panoptic segmentation method,named the Token Sparse Transformer(TS-Former),for panoptic segmentation to achieve a balance between segmentation performance and computing *** work is based on Mask2Former,and the key improvement involves the design of a sparse pixel decoder for implementing sparse attention *** ensure that the most effective tokens are selected,a foreground selector-based scoring mechanism is used with ground truth labels for *** the COCO dataset,our method can balance model performance and computational consumption better than most existing panoptic segmentation *** to the baseline model,when 28.6% of tokens are used for sparse attention calculation,the panoptic segmentation performance(PQ) of the model is only reduced by less than 1%,while the FLOPs value is reduced by 12%.

关键词： Panoptic segmentation Token sparsity Attention mechanism Deep learning

来源：评论

学校读者我要写书评

暂无评论

Bipartite coordination for the Structurally Balanced Networks 4

Bipartite coordination for the Structurally Balanced Network...

引用

4th International Conference on Data-Driven Optimization of Complex Systems, DOCS 2022

作者： Yu, Shuhang Zhang, Huaguang Northeastern University College of Information Science and Engineering Shenyang China Northeastern University State Key Laboratory of Synthetical Automation for Process Industries Shenyang China

ISBN: (数字)9781665459822

ISBN: (纸本)9781665459822

Under the signed graph, the bipartite containment control problem is studied for the linear multi-agent systems. Since structurally balanced is one of the characteristics of signed graph, M-matrix given in many articles on containment control does not apply to this paper. Thus, a concise and novel method is presented to solved such problem. A novel definition about bipartite containment is given to show that agents in different groups will reach different coordination, respectively. A distributed bipartite observer is proposed to estimate the state of the convex hull. Then, a distributed state feedback control protocol is designed to solve the main problem of this paper. Finally, a numerical example is given to illustrate the validity of the theoretical results. © 2022 IEEE.

关键词： Multi agent 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：