检索结果-内蒙古大学图书馆

Parallel system Based Quantitative Assessment and Self-evolution for Artificial Intelligence of Active Power Corrective control

引用

CSEE Journal of Power and Energy systems 2024年第1期10卷 13-28页

作者： Tianyun Zhang Jun Zhang Feiyue Wang Peidong Xu Tianlu Gao Haoran Zhang Ruiqi Si School of Electrical Engineering and Automation Wuhan UniversityWuhan 430072HubeiChina State Key Laboratory for Management and Control of Complex System Institute of AutomationChinese Academy of SciencesBeijing 100190China

In artificial intelligence(AI)based-complex power system management and control technology,one of the urgent tasks is to evaluate AI intelligence and invent a way of autonomous intelligence ***,there is,currently,nearly no standard technical framework for objective and quantitative intelligence *** this article,based on a parallel system framework,a method is established to objectively and quantitatively assess the intelligence level of an AI agent for active power corrective control of modern power systems,by resorting to human intelligence evaluation *** this basis,this article puts forward an AI self-evolution method based on intelligence assessment through embedding a quantitative intelligence assessment method into automated reinforcement learning(AutoRL)systems.A parallel system based quantitative assessment and self-evolution(PLASE)system for power grid corrective control AI is thereby constructed,taking Bayesian Optimization as the measure of AI evolution to fulfill autonomous evolution of AI under guidance of their intelligence assessment *** results exemplified in the power grid corrective control AI agent show the PLASE system can reliably and quantitatively assess the intelligence level of the power grid corrective control agent,and it could promote evolution of the power grid corrective control agent under guidance of intelligence assessment results,effectively,as well as intuitively improving its intelligence level through selfevolution.

关键词： AI quantitative intelligence assessment and self-evolution automated reinforcement learning Bayesian optimization corrective control parallel system

来源：评论

学校读者我要写书评

暂无评论

Self-supervised Depth Completion with Adaptive Online Adaptation 23

Self-supervised Depth Completion with Adaptive Online Adapta...

引用

7th International Conference on Machine Learning and Soft Computing, ICMLSC 2023

作者： Chen, Yang Tan, Yang Key Laboratory of Measurement and Control of Complex System of Engineering Ministry of Education School of Automation Southeast University Nanjing210096 China

ISBN: (纸本)9781450398633

Although depth completion has achieved remarkable performance relying on deep learning in recent years, these models tend to suffer a performance degradation when exposed to new environments. Online adaptation, where the model is trained in a self-supervised manner during testing, seems a promising technique to alleviate the drop. However, continuous online adaptation may cause the model to over-adapt and miss the optimal parameters, resulting in oscillation or even degradation of the model performance, in addition to wasting computational resources. Therefore, this paper proposes an adaptive online adaptation framework to make model adaptively trigger online adaptation when encountering novel environments and stop adaptation when model has adapted to the current environment. In detail, we design a trigger to detect the familiarity of model to the current scenario based on image similarity and then launch online adaptation when the scenario is novel. Besides, we elaborate a stopper to monitor the error between prediction and depth input and convert online adaptation to inference when online adaptation does not bring improvement for model. Experimental results demonstrate that our method improves the accuracy of model prediction and increases average running speed of the model on each frame in online adaptation. © 2023 ACM.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Active Distribution Grid Risk Prevention and control Method Based on Biological Immune Mechanism 3rd

Active Distribution Grid Risk Prevention and Control Method ...

引用

3rd International Joint Conference on Energy, Electrical and Power Engineering, CoEEPE 2023

作者： Zhao, Hui Ma, Jun Yue, Youjun Wang, Hongjun Tianjin Key Laboratory of Complex System Control Theory and Tianjin University of Technology Tianjin China

ISBN: (纸本)9789819739394

Aiming at the insufficient optimization ability of traditional active distribution network (ADN) fault recovery, a combination of immune mechanism and immune genetic algorithm is proposed for risk prevention and control. First, a risk assessment model is constructed from the perspective of reliability of equipment operation and consequences of faults;second, for the first N scenarios with higher risk, a fault pre-recovery scheme is established with the objectives of restoring the most power supply, minimizing the number of switching times, and minimizing the network loss, and the immune genetic algorithm is used to solve the problem. The N scenarios are recorded in the set of expected incidents to expand the immune memory cell library;finally, the simulation is carried out using the IEEE 33-node distribution network model as an example, and the simulation results show the feasibility of the proposed risk prevention and control strategies and the algorithms used, which lays a foundation for the subsequent fast and accurate recovery of power supply. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Electric power distribution

来源：评论

学校读者我要写书评

暂无评论

A Noise-Excitation Generative Adversarial Network for Actuator Fault Diagnosis of Multi-legged Robot

引用

无人系统（英文） 2023年第2期11卷 159-173页

作者： Liling Ma Jian Guo Jiehao Li Junzheng Wang State Key Laboratory of Complex System Intelligent Control and Decision School of Automation Beijing Institute of TechnologyBeijing 100081P.R.China

This research provides a novel approach for detecting multi-legged robot actuator *** most significant concept is to design the Fault Diagnosis Generative Adversarial Network(FD-GAN)to fully adapt to the fault diagnosis problem with insufficient *** found that it is difficult for methods based on classification and prediction to learn failure patterns without enough data.A straightforward solution is to use massive amounts of normal data to drive the diagnostic *** introduce frequency-domain information and fuse multi-sensor data to increase the features and expand the difference between normal data and fault data.A GAN-based framework is designed to calculate the probability that the enhanced data belongs to the normal *** uses a generator network as a feature extractor,and uses a discriminator network as a fault probability evaluator,which creates a new use of GAN in the field of fault *** the many learning strategies of GAN,we find that a key point that can distinguish the two types of data is to use the hidden layer noise with appropriate discrimination as the *** also design a fault location method based on binary search,which greatly improves the search efficiency and engineering value of the entire *** have conducted a lot of experiments to prove the diagnostic effectiveness of our architecture in various road conditions and working *** compared FD-GAN with popular diagnostic *** results show that our method has the highest accuracy and recall rate.

关键词： Actuator fault diagnosis multi-legged robot generative adversarial network attention mechanism

来源：评论

学校读者我要写书评

暂无评论

Interval analysis for neural networks with application to fault detection

引用

Science China(Information Sciences) 2024年第11期67卷 222-237页

作者： Zhenhua WANG Youdao MA Song ZHU Thach Ngoc DINH Yi SHEN Department of Control Science and Engineering Harbin Institute of Technology National Key Laboratory of Complex System Control and Intelligent Agent Cooperation School of Mathematics China University of Mining and Technology The CEDRIC-Lab Conservatoire National des Arts et Métiers (CNAM)

This paper investigates an interval analysis method for neural networks and applies it to fault detection for systems with unknown but bounded measurement noise. First, a novel interval analysis method is presented, which can compute the bounds of the output of a feedforward neural network subject to a bounded input. By applying the proposed interval analysis method to a network trained with fault-free system data, adaptive thresholds for fault detection are computed. Finally, one can acquire fault detection results via a fault detection strategy. The proposed method can achieve tight bounds of the network output and employ simple operations, which leads to accurate fault detection results and a low computational burden.A numerical simulation and an experiment on an AC servo motor are given to illustrate the effectiveness and superiority of the proposed method.

关键词： interval analysis feedforward neural network fault detection adaptive thresholds

来源：评论

学校读者我要写书评

暂无评论

RSD-Diff: Boundary-Frequency Feature-Enhanced Rail Surface Defect Inspection with Diffusion-Based Transformer Decoder 10

RSD-Diff: Boundary-Frequency Feature-Enhanced Rail Surface D...

引用

10th International Conference on systems and Informatics, ICSAI 2024

作者： Wang, Dezhou Su, Shixiang Lu, Xiaobo School of Automation Southeast University Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing China

ISBN: (纸本)9798331510138

Rail surface defect inspection is an essential task for the railway system. However, due to the similarity of the background and defect foreground pixels, uneven textures, irregular shapes and multiple scales of the existing defects, the inspection accuracy is still required to be further improved. In this paper, we first expand our dataset by GAN-based method for the scarcity of the defect samples. Then, we propose a diffusion-based model to perform the classification and segmentation task. The diffusion model predicts the mask from the Gaussian noise broken ground truth by successive designed transformer decoder. Meanwhile, to better distinguish the pixels in the boundary or other illegible regions, a boundary-frequency feature enhancement module (BFM) is proposed to make the model pay more attention to the defect-related features. Experiments on the rail surface defect dataset revealed that the proposed diffusion-based transformer decoder and BFM can work well together and efficiently improve the rail surface defect segmentation accuracy. © 2024 IEEE.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Guided Transformative GAN: Joint Face Image Super-Resolution and Frontalization 10

Guided Transformative GAN: Joint Face Image Super-Resolution...

引用

10th International Conference on systems and Informatics, ICSAI 2024

作者： Mu, Minghao Wang, Wei Lu, Xiaobo School of Automation Southeast University Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing China

ISBN: (纸本)9798331510138

Joint face super-resolution and frontalization of non-frontal low-resolution faces is of significant importance for many face analysis applications. However, at the same time, it is a challenging task. In this paper, a novel Guided Transformative Generative Adversarial Network (GT-GAN) is proposed to address the challenge of generating frontal high-resolution face images from non-frontal low-resolution face images. Existing methods usually treat super-resolution and frontalization as two separate tasks, leading to unsatisfactory processing results. GTG AN innovatively achieves both goals within a unified frame-work. Specifically, we propose Profile Attention Guidance (PAG) to generate landmark heatmaps that provide a priori pose information to the generative network and direct its attention to critical facial regions. In addition, an Attention Fusion Transformation Module (AFTM) is proposed to significantly improve the hallucination performance of the network by utilizing the attention mechanism and STNs, combined with sequential feature enhancement strategies. The experimental results show that GT-GAN exhibits superior performance in the joint face super-resolution and frontalization task on the public face dataset Multi-PIE, which provides new ideas and references for this challenging topic. © 2024 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

BeltLineNet: A Shape-Prior-Guided Lightweight Network for Real-Time Deviation Detection in Circular Pipe Conveyors

引用

IEEE Sensors Journal 2025年第11期25卷 20024-20036页

作者： Zhao, Long Su, Jinhui Zhong, Yusheng Xie, Weiwei Su, Jinya Chen, Xisong Chen, Congyan Li, Shihua Southeast University Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education School of Automation Nanjing210096 China Fujian Longking Intelligent Conveying Engineering Co. Ltd Longyan China

Belt deviation in circular pipe conveyor systems could lead to material spillage, environmental contamination, reduced efficiency, and accelerated belt wear. Real-time belt deviation detection is crucial for ensuring safe and efficient operation. However, existing methods, primarily developed for flat-belt systems, heavily rely on distinct belt-background semantics, making them unsuitable for circular conveyors where indistinct target features, motion blur, and occlusions pose significant challenges. To address these issues, we reformulate the deviation detection task as an object detection problem, proposing BeltLineNet, a lightweight, real-time deviation detection network specifically designed for circular pipe conveyors. Our method integrates explicit feature learning with a coarse-to-fine global feature fusion mechanism, enhancing belt line representation under complex conditions. Additionally, a shape-prior loss strategy is introduced to improve supervision during training, ensuring more accurate detection of elongated targets. The model is also optimized for real-time deployment through layer-adaptive pruning, achieving a balance between accuracy and computational efficiency. Extensive comparative experiments involving 8 state-of-the-art (SOTA) feature extraction networks and 6 feature enhancement strategies on a self-collected dataset under industrial conditions demonstrate that BeltLineNet surpasses SOTA feature extraction and fusion networks, improving average precision (AP) by 8.23% before pruning and 6.33% after pruning. © 2001-2012 IEEE.

关键词： Belt conveyors

来源：评论

学校读者我要写书评

暂无评论

Reduction of data amount in data-driven design of linear quadratic regulators

引用

control Theory and Technology 2024年第4期22卷 532-542页

作者： Shinsaku Izumi Xin Xin School of Systems Engineering Kochi University of TechnologyKamiKochi782-8502Japan School of Automation Southeast Universityand Key Laboratory of Measurement and Control of Complex Systems of EngineeringMinistry of EducationNanjing210096JiangsuChina

This paper discusses the data-driven design of linear quadratic regulators,i.e.,to obtain the regulators directly from experimental data without using the models of *** particular,we aim to improve an existing design method by reducing the amount of the required experimental *** the data amount leads to the cost reduction of experiments and computation for the data-driven *** present a simplified version of the existing method,where parameters yielding the gain of the regulator are estimated from only part of the data required in the existing *** then show that the data amount required in the presented method is less than half of that in the existing method under certain *** addition,assuming the presence of measurement noise,we analyze the relations between the expectations and variances of the estimated parameters and the *** a result,it is shown that using a larger amount of the experimental data might mitigate the effects of the noise on the estimated *** results are verified by numerical examples.

关键词： Data-driven design Linear quadratic regulators Linear systems Riccati equation Stochastic properties

来源：评论

学校读者我要写书评

暂无评论

HarmonyNav: Robot Navigation in Human-Robot Coexistence Environment Considering Group and Pedestrian Intentions

HarmonyNav: Robot Navigation in Human-Robot Coexistence Envi...

引用

2024 Jiangsu Annual Conference on Automation, JACA 2024

作者： Wang, Yutao Fang, Fang Liu, Chenyang Fan, Tao Li, Yi The Key Laboratory of Measurement and Control of Complex Systems of Engineering School of Automation Southeast University Ministry of Education Nanjing210096 China

ISBN: (纸本)9781837242689

Service robots must navigate efficiently and harmoniously in human-robot coexistence environments. Previous studies often treated pedestrians as independent entities, ignoring human intentions and leading to group intersections and performance issues. We introduce HarmonyNav, a crowd navigation algorithm that enhances human-robot harmony. Our method uses Human-Robot Interaction sub-networks to account for indirect group impacts on pedestrians and predicts pedestrian trajectories to infer intentions. Employing proximal policy optimization (PPO) in reinforcement learning, we develop a harmonious navigation policy. In simulation experiments, our results show improved navigation performance, reducing group intersections and individual intrusions. © The Institution of Engineering & Technology 2024.

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：