检索结果-内蒙古大学图书馆

A data-driven open decision framework based on adaptive evidential reasoning rule

Computers and Industrial Engineering 2025年 206卷

作者： Fu, Chao Chang, Wenjun Xue, Min Lu, Guangyan School of Management Hefei University of Technology Hefei Box 270 Anhui Hefei230009 China Key Laboratory of Process Optimization and Intelligent Decision-making Ministry of Education Anhui Hefei230009 China Ministry of Education Engineering Research Center for Intelligent Decision-Making & Information System Technologies Anhui Hefei230009 China Department of Operation Management CRRC Qishuyan Instiute Co. Ltd Jiangsu Changzhou213011 China

Data accumulation is beneficial to efficiently make decisions on new cases. However, it is rare to use the historical data of experienced decision makers to help inexperienced decision makers generate solutions to new cases in an open and adaptive way. To address this issue, a data-driven open decision framework is developed based on an adaptive evidential reasoning (ER) rule. Giving two assumptions, criterion weights are learned from historical individual and overall assessments while criterion reliabilities are learned from historical individual assessments and gold standards. The adaptive ER rule is developed based on two abstract functions with the variables of criterion weight and criterion reliability, respectively, whose properties are analyzed. With these foundations, the general situation of the open decision framework is demonstrated from the learning, aggregation, and prediction hierarchies. Three special situations of the framework are presented to make it flexible. The historical data of more experienced decision makers are allowed in the framework to ensure its openness. The applicability of the general situation of the open decision framework is examined by its use in helping diagnose breast lesions. Its performance is highlighted by the comparison with the three special situations of the framework, five representative machine learning algorithms, and the framework with four forms of two abstract functions. © 2025 Elsevier Ltd

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

End-to-end Automatic Targetless Calibration between Low-resolution LiDARs and Cameras based on Cross-modal Attention

End-to-end Automatic Targetless Calibration between Low-reso...

引用

Chinese control and decision Conference, CCDC

作者： Tianyang Huang Jun-Guo Lu Ming Wei Qing-Hao Zhang Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai China

ISBN: (数字)9798350387780

ISBN: (纸本)9798350387797

LiDARs and cameras, commonly used sensors on autonomous vehicles and robots, require precise calibration for accurate joint environmental perception. Current calibration methods, capable of adjusting both intrinsic and extrinsic parameters, often depend on physical targets or human intervention, making them unsuitable for automatic online calibration. Moreover, these methods are primarily optimized for dense point clouds, as they are often tuned on open datasets featuring high-quality point cloud data. However, low-resolution LiDARs, preferred for their cost-effectiveness, are prevalent in practical applications. To automate the calibration process while maintaining high precision on sparse point clouds, multi-modal image registration techniques are leveraged to develop an end-to-end, cross-attention-based neural network for automatic calibration of low-resolution LiDARs and Cameras. Specifically, given an initial perturbation on point clouds, our network is capable of recovering the true extrinsic parameters without manual intervention. Additionally, specialized input preprocessing and training strategies are incorporated to enhance performance with sparse point clouds. Promising results are achieved on both open datasets and custom sensor acquisitions, highlighting the effectiveness and adaptability of our network to diverse scenarios.

关键词： Point cloud compression Training Image registration Visualization Laser radar Perturbation methods Neural networks

来源：评论

学校读者我要写书评

暂无评论

Topology Identification for Distribution systems Based on Bayesian Nonparametric Model and Gaussian Mixture Ensemble Kalman Filter

Topology Identification for Distribution Systems Based on Ba...

引用

Power and Electrical Engineering (ACPEE), 5th Asia Conference on

作者： Tingting Zhang Wen Zhang School of Control Science and Engineering Shandong University Jinan China Key Laboratory of Power System Intelligent Dispatch and Control of Ministry of Education School of Electrical Engineering Shandong University Jinan China

ISBN: (数字)9798350309638

ISBN: (纸本)9798350309645

To ensure the secure and reliable operation of active distribution systems (ADSs), it is essential to efficiently and accurately identify their time-varying topology. This paper proposes an estimation-based topology identification (TI) method for ADSs considering topology changes. The TI problem is formulated by a forecasting-aided estimation model, which is depicted by a discrete-time switching state-space model. The topology change process is described by a Bayesian nonparametric model that allows TI with limited knowledge of topology libraries. Then the Gaussian mixture ensemble Kalman filter (GM-EnKF) is employed to carry out the TI, where the underlying probability density is approximated by using Gaussian mixture model. In this case, the proposed method become capable of handling the unavoidable non-Gaussian noises in realistic distribution systems. Test results on various ADSs validates the effectiveness of the proposed GM-EnKF-based TI method on accurate and efficient topology identification.

关键词： Noise Estimation Termination of employment Switches Predictive models Topology Bayes methods

来源：评论

学校读者我要写书评

暂无评论

Evolutionary Dynamics of Cooperation on Coupled Networks

Evolutionary Dynamics of Cooperation on Coupled Networks

引用

control Theory and Applications (ICoCTA), International Conference on

作者： Zhenyu Shi Qi Su Department of Automation Ministry of Education of China Key Laboratory of System Control and Information Processing Shanghai Engineering Research Center of Intelligent Control and Management Shanghai Jiao Tong University Shanghai China

ISBN: (数字)9798331506155

ISBN: (纸本)9798331506162

Network reciprocity has been recognized as a crucial mechanism for promoting the evolution of cooperation. However, prior studies on network reciprocity have predominantly focused on isolated networks, neglecting the interconnected nature of real-world systems. In reality, many large-scale systems are closely coupled, where the interaction patterns between systems differ significantly from those within individual networks. Motivated by this observation, we construct a strategy evolution model on coupled networks to explore the effects of such interconnections. Our findings reveal that coupled networks foster cooperation more effectively than isolated networks. This advantage persists across various network structures, suggesting the universality of this phenomenon. Interestingly, we discover that the strength of the coupling plays a pivotal role: weaker coupling between networks is more conducive to the emergence and stability of cooperation compared to stronger coupling. These results high-light the importance of considering cross-system interactions in understanding and designing mechanisms to enhance cooperative behavior.

关键词： Couplings Stability analysis Large-scale systems control theory Game theory

来源：评论

学校读者我要写书评

暂无评论

Cluster Consensus Problem on Time-varying Higher-Order Interaction Networks

Cluster Consensus Problem on Time-varying Higher-Order Inter...

引用

IEEE Conference on decision and control

作者： Haoyu Wei Lulu Pan Haibin Shao Dewei Li Wenbin Yu Department of Automation Shanghai Jiao Tong University and Key Laboratory of System Control and Information Processing Ministry of Education of China and Shanghai Engineering Research Center of Intelligent Control and Management Shanghai China

ISBN: (数字)9798350316339

ISBN: (纸本)9798350316346

This paper examines the cluster consensus problem of higher-order interaction networks on switching networks. The matrix-valued inter-agent coupling mechanism is employed to capture the higher-order interactions amongst neighboring agents. Specifically, for a higher-order interaction network with both positive definite and positive semi-definite coupling matrices, we examine the scenario in which the nullspace of positive semi-definite coupling matrices is constructed by a set of orthogonal basis vectors. From the perspective of the lower-order component graph -the projection of network structure onto the direction of each orthogonal basis–results on the explicit characterization of cluster consensus of higher-order interaction networks are provided. Moreover, for time-varying higher-order interaction networks, necessary and sufficient conditions are provided to ensure that a time-varying network shares the same steady-state values as the integral time-invariant network. Simulation results are provided to demonstrate the theory.

关键词： Couplings Sufficient conditions Network topology Simulation Switches Vectors Topology Steady-state Matrix decomposition Convergence

来源：评论

学校读者我要写书评

暂无评论

Probabilistic Electricity Price Forecasting and Uncertainty Estimation Using Deep Bayesian Model with Multi-Distribution Fusion

SSRN

引用

SSRN 2024年

作者： Shao, Zhen Han, Yating Fu, Chao Zha, Jianrui Yang, Shanlin School of Management Hefei University of Technology Hefei230009 China Key Laboratory of Process Optimization and Intelligent Decision-making Ministry of Education Anhui Hefei230009 China Philosophy and Social Sciences Laboratory of Data Science and Smart Society Governance Hefei University of Technology Ministry of Education Hefei230009 China Ministry of Education Engineering Research Center for Intelligent Decision-Making & Information System Technologies Hefei230009 China

Probabilistic electricity price forecasting (EPF) is paramount for stakeholder scheduling and trading in deregulated energy markets. However, during the process of establishing a probability prediction model, the consequential aleatoric and epistemic uncertainties are indistinguishable. Moreover, identifying epistemic uncertainty rather than aleatoric uncertainty is significant for conducting credible probabilistic EPF in cases with expected and unexpected fluctuations. This article proposes a hybrid approach under a Bayesian probability framework for performing reliable and accurate probabilistic forecasting. Specifically, it applies Bayesian deep learning model to convey the latent probability distribution of electricity prices, which represents the desirable epistemic uncertainty and inevitable aleatoric uncertainty. The embedded architecture employs a multi-head attention mechanism (MHAM) to allocate previous hidden states of long short-term memory (LSTM) cells, detecting both the local and global price patterns simultaneously. Considering the forecasting bias arising from aleatoric uncertainty in the process of establishing Bayesian networks, a new Wasserstein distance-based multi-distribution fusion mechanism driven by evidence theory is proposed and employed to identify and mitigate the aleatoric uncertainty of credible probabilistic EPF problems. The effectiveness of the proposed approach is evaluated on two real-world electricity price datasets and compared with twelve state-of-the-art models. © 2024, The Authors. All rights reserved.

关键词： Bayesian networks

来源：评论

学校读者我要写书评

暂无评论

intelligent Pre-warning Method of Transmission Line Icing Based on Stack Denoising Autoencoder 5th

Intelligent Pre-warning Method of Transmission Line Icing Ba...

引用

Proceedings of the 5th International Conference on Clean Energy and Electrical systems - Proceedings of CEES 2023

作者： Wang, Chunyi Liu, Wei Zhou, Heng Liu, Yutian Shandong Electric Power Company State Grid Shandong Jinan250001 China Weihai Power Supply Company State Grid Shandong Weihai264200 China Key Laboratory of Power System Intelligent Dispatch and Control of Ministry of Education Shandong University Shandong Jinan250061 China

ISBN: (纸本)9789819938872

In order to reduce the impact of transmission line icing on the secure operation of power grid in extreme weather, an online pre-warning method based on stack denoising autoencoder (SDAE) is proposed in this paper. First, considering deicing phenomenon, geographical factors and current thermal effect under different operating conditions, sample selection, data revision and sample cluster are carried out. Then, the prediction model of ice thickness growth based on SDAE is established and trained off-line. Finally, the icing trend is evaluated according to the real-time weather information, and combining with the current data as well as the cumulative effect of time, the line ice thickness is predicted online so as to conduct ice severity pre-warning. The simulation results demonstrate that the proposed method can improve the noise adaptability and prediction accuracy. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Electric lines

来源：评论

学校读者我要写书评

暂无评论

A Reinforcement Learning Approach for Robust Restoration of Generators in Power system

A Reinforcement Learning Approach for Robust Restoration of ...

引用

2022 Chinese Automation Congress, CAC 2022

作者： Li, Huimiao Yang, Xiaozhou Zhai, Chao Hubei Key Laboratory of Advanced Control and Intelligent Automation Fo Complex Systems China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan China Future Resilient Systems Singapore-ETH Centre Create Campus Singapore

ISBN: (纸本)9781665465335

In the past decades, cascading blackouts have caused serious damages to power systems and affected the normal operation of society, so it is crucial to quickly restore the damaged power system to normal state. In this paper, a reinforcement learning (RL) approach is developed to achieve the robust restoration of generators in power systems. Firstly, the performance recovery of damaged power system is modeled as markov decision process, and constraints such as line voltage and active power output of generators are considered. Secondly, a RL algorithm is proposed to search the optimal control strategy for generator units recovery. Based on the proposed restoration approach, Q-learning algorithm is employed to obtain the optimal strategy for power supply of generaors in power grids. Finally, numerical simulations are carried out on IEEE 9-bus system under different scenarios of external disturbances and certainties. The simulation results demonstrate the effectiveness and feasibility of the proposed approach. © 2022 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Multi-Criteria Approach for Evaluating Voltage Regulation Characteristics Facilitating Flexible Operations of Fossil-Fueled Power Generators

A Multi-Criteria Approach for Evaluating Voltage Regulation ...

引用

IEEE General Meeting Power& Energy Society

作者： Nuo Xu Xiaodong Chu Key Laboratory of Power System Intelligent Dispatch and Control of the Ministry of Education Shandong University Jinan P. R. China

Conventional fossil-fueled power generators are one of flexibility options to accommodate the ever increasing penetration of fluctuating renewable energy whereas their capability constraints are not negligible. A multi-criteria approach is proposed in this paper for evaluating voltage regulation characteristics of fossil-fueled power generators to facilitate their flexible operations. First, an evaluation index system is established accounting for three vital criteria including steady-state performance, dynamic performance, and transient performance of the excitation system. Second, Bayesian BWM and CRITIC methods are used to determine respectively each index’s subjective and objective weights in which the game theory is leveraged to obtain the combined weights. Finally, PROMETHEE II is exploited to rank candidate generators based on the preference functions. The proposed multi-criteria approach is tested on an example system to verify its feasibility and effectiveness. The generator with balanced performance in all aspects prevails in the evaluation of the voltage regulation characteristics.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Time-attenuating Twin Delayed DDPG Reinforcement Learning for Trajectory Tracking control of Quadrotors

arXiv

引用

arXiv 2023年

作者： Deng, Boyuan Sun, Jian Li, Zhuo Wang, Gang School of Automation Beijing Institute of Technology Beijing100081 China Key Laboratory of Intelligent Control and Decision of Complex System Beijing Institute of Technology Beijing100081 China

Continuous trajectory tracking control of quadrotors is complicated when considering noise from the environment. Due to the difficulty in modeling the environmental dynamics, tracking methodologies based on conventional control theory, such as model predictive control, have limitations on tracking accuracy and response time. We propose a Time-attenuating Twin Delayed DDPG, a model-free algorithm that is robust to noise, to better handle the trajectory tracking task. A deep reinforcement learning framework is constructed, where a time decay strategy is designed to avoid trapping into local optima. The experimental results show that the tracking error is significantly small, and the operation time is one-tenth of that of a traditional algorithm. The OpenAI Mujoco tool is used to verify the proposed algorithm, and the simulation results show that, the proposed method can significantly improve the training efficiency and effectively improve the accuracy and convergence stability. Copyright © 2023, The Authors. All rights reserved.

关键词： Reinforcement 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：