检索结果-内蒙古大学图书馆

Aeroengine thrust estimation and embedded verification based on improved temporal convolutional network

Chinese Journal of Aeronautics 2024年第1期37卷 106-117页

作者： Wanzhi MENG Zhuorui PAN Sixin WEN Pan QIN Ximing SUN Key Laboratory of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education Dalian University of TechnologyDalian 116024China School of Control Science and Engineering Dalian University of TechnologyDalian 116024China

Thrust estimation is a significant part of aeroengine thrust control *** traditional estimation methods are either low in accuracy or large in *** further improve the estimation effect,a thrust estimator based on Multi-layer Residual Temporal Convolutional Network(M-RTCN)is *** solve the problem of dead Rectified Linear Unit(ReLU),the proposed method uses the Gaussian Error Linear Unit(GELU)activation function instead of ReLU in residual *** the overall architecture of the multi-layer convolutional network is adjusted by using residual connections,so that the network thrust estimation effect and memory consumption are further ***,the comparison with seven other methods shows that the proposed method has the advantages of higher estimation accuracy and faster convergence ***,six neural network models are deployed in the embedded controller of the micro-turbojet *** Hardware-in-the-Loop(HIL)testing results demonstrate the superiority of M-RTCN in terms of estimation accuracy,memory occupation and running ***,an ignition verification is conducted to confirm the expected thrust estimation and real-time performance.

关键词： Thrust estimation Temporal convolutional network Embedded deployment Hardware-in-the-loop testing Ignition verification

来源：评论

学校读者我要写书评

暂无评论

Cooperative decision-making algorithm with efficient convergence for UCAV formation in beyond-visual-range air combat based on multi-agent reinforcement learning

引用

Chinese Journal of Aeronautics 2024年第8期37卷 311-328页

作者： Yaoming ZHOU Fan YANG Chaoyue ZHANG Shida LI Yongchao WANG School of Aeronautic Science and Engineering Beihang UniversityBeijing 100191China Key Laboratory of Industrial Control Technology Institute of Cyber-Systems and ControlZhejiang UniversityHangzhou 310027China

Highly intelligent Unmanned Combat Aerial Vehicle(UCAV)formation is expected to bring out strengths in Beyond-Visual-Range(BVR)air *** Multi-Agent Reinforcement Learning(MARL)shows outstanding performance in cooperative decision-making,it is challenging for existing MARL algorithms to quickly converge to an optimal strategy for UCAV formation in BVR air combat where confrontation is complicated and reward is extremely sparse and *** to solve this problem,this paper proposes an Advantage Highlight Multi-Agent Proximal Policy Optimization(AHMAPPO)***,at every step,the AHMAPPO records the degree to which the best formation exceeds the average of formations in parallel environments and carries out additional advantage sampling according to ***,the sampling result is introduced into the updating process of the actor network to improve its optimization ***,the simulation results reveal that compared with some state-of-the-art MARL algorithms,the AHMAPPO can obtain a more excellent strategy utilizing fewer sample episodes in the UCAV formation BVR air combat simulation environment built in this paper,which can reflect the critical features of BVR air *** AHMAPPO can significantly increase the convergence efficiency of the strategy for UCAV formation in BVR air combat,with a maximum increase of 81.5%relative to other algorithms.

关键词： Unmanned combat aerial vehicle(UCAV)formation Decision-making Beyond-visual-range(BVR)air combat Advantage highlight Multi-agent reinforcement learning(MARL)

来源：评论

学校读者我要写书评

暂无评论

Directed Acyclic Graphs With Tears

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2023年第4期4卷 972-983页

作者： Chen, Zhichao Ge, Zhiqiang State Key Laboratory of Industrial Control Technology College of Control Science and Engineering Zhejiang University Hangzhou310027 China Peng Cheng Laboratory Shenzhen518000 China

Bayesian network is a frequently used method for fault detection and diagnosis in industrial processes. The basis of Bayesian network is structure learning which learns a directed acyclic graph (DAG) from data. However, the search space will scale super-exponentially with the increase of process variables, which makes the data-driven structure learning a challenging problem. To this end, the DAGs with NOTEAR methods are being well studied not only for their conversion of the discrete optimization into continuous optimization problem but also their compatibility with deep learning framework. Nevertheless, there still remain challenges for NOTEAR-based methods: 1) the infeasible solution results from the gradient descent based optimization paradigm;2) the truncation operation to promise the learned graph acyclic. In this work, the reason for challenge 1) is analyzed theoretically, and a novel method named DAGs with tears method is proposed based on mix-integer programming to alleviate challenge 2). In addition, prior knowledge is able to incorporate into the new proposed method, making structure learning more practical and useful in industrial processes. Finally, a numerical example and an industrial example are adopted as case studies to demonstrate the superiority of the developed method. © 2020 IEEE.

关键词： Numerical methods

来源：评论

学校读者我要写书评

暂无评论

RAGAN: Regression Attention Generative Adversarial Networks

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2023年第6期4卷 1549-1563页

作者： Jiang, Xiaoyu Ge, Zhiqiang Zhejiang University State Key Laboratory of Industrial Control Technology College of Control Science and Engineering Hangzhou310027 China Peng Cheng Laboratory Shenzhen518000 China

Despite surrounding by Big Data, we still need to learn from insufficient data in many scenarios. Building an accurate regression model for a small amount of data is a pretty tricky and exciting problem. At present, it is a promising solution to augment limited real data by generating data through generative adversarial networks (GANs). However, when GAN is used to generate labeled data in regression modeling, it lacks attention to the relationship between independent and dependent variables, resulting in poor performance of regression modeling. This article proposes a novel regression attention GAN (RA-GAN) for augmented regression modeling. Regression attention mechanisms are introduced into network parameters learning of both generator and discriminator in RA-GAN to establish a known relationship between variables. This makes RA-GAN restore the regression information during data generation. In addition, an indicator called cross regression score is designed to describe the quality of the generated data before augmented regression modeling, effectively evaluating data augmentation performance in advance. The effectiveness and superiority of the proposed methods are verified in an actual industrial soft-sensing case and a diabetes prediction case through data augmentation regression applications. © 2020 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Effects of triclosan adsorption on intestinal toxicity and resistance gene expression in Xenopus tropicalis with different particle sizes of polystyrene

引用

Journal of Environmental sciences 2024年第12期146卷 176-185页

作者： Zhuo Dai Zikai Wang Xinying Pan Li Zheng Yanbin Xu Qingxia Qiao Guangdong Key Laboratory of Environmental Catalysis and Health Risk Control Guangzhou Key Laboratory Environmental Catalysis and Pollution ControlInstitute of Environmental Health and Pollution ControlCollege of Environmental Science and EngineeringGuangdong University of TechnologyGuangzhou 510006China

Microplastics(MPs)are commonly found with hydrophobic contaminants in the water column and pose a serious threat to aquatic *** effects of polystyrene microplastics of different particle sizes on the accumulation of triclosan in the gut of Xenopus tropicalis,its toxic effects,and the transmission of resistance genes were *** results showed that co-exposure to polystyrene(PS-MPs)adsorbed with triclosan(TCS)caused the accumulation of triclosan in the intestine with the following accumulation capacity:TCS+5μm PS group>TCS group>TCS+20μm PS group>TCS+0.1μm PS *** experimental groups showed increased intestinal inflammation and antioxidant enzyme activity after 28 days of exposure to PS-MPs and TCS of different particle *** TCS+20μm PS group exhibited the highest upregulated expression of pro-inflammatory factors(IL-10,IL-1β).The TCS+20μm group showed the highest increase in enzyme activity compared to the control ***-MPs and TCS,either alone or together,altered the composition of the intestinal microbial *** addition,the presence of more antibiotic resistance genes than triclosan resistance genes significantly increased the expression of tetracycline resistance and sulfonamide resistance genes,which may be associated with the development of intestinal inflammation and oxidative *** study refines the aquatic ecotoxicity assessment of TCS adsorbed by MPs and provides informative information for the management and control of microplastics and non-antibiotic bacterial inhibitors.

关键词： Polystyrene Triclosan Xenopus-tropicalis Resistance genes Gut community

来源：评论

学校读者我要写书评

暂无评论

Improved Residual Reinforcement Learning for Dynamic Obstacle Avoidance of Robotic Arm 13

Improved Residual Reinforcement Learning for Dynamic Obstacl...

引用

13th IEEE Data Driven control and Learning Systems Conference, DDCLS 2024

作者： Liu, Zhenting Liu, Shan College of Control Science and Engineering Zhejiang University State Key Laboratory of Industrial Control Technology Hangzhou310027 China

ISBN: (纸本)9798350361674

This paper proposes an improved residual deep reinforcement learning method for robot arm dynamic obstacle avoidance and position servo. The proposed method first simplifies the state space by constructing key points and pre-trains a model capable of completing obstacle avoidance tasks using the simplified state. Then, when training with real state information, a guiding network is used to help accumulate good samples, which improves the training efficiency. To overcome the convergence difficulty of residual DQN in robot arm obstacle avoidance, this paper incorporates the action of the feedback controller into the action space and uses incremental reward values to evaluate the actions. Simulation results demonstrate that the proposed method can effectively achieve robot arm dynamic obstacle avoidance and position servo. © 2024 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

An improved adaptive minimum entropy deconvolution method in bearing fault detection 4

An improved adaptive minimum entropy deconvolution method in...

引用

4th International Conference on Mechanical, Electronics, and Electrical and Automation control, METMS 2024

作者： Liao, Zihao Xu, Jinglun Jin, Minglv Cao, Yuqi Cao, Yunqi Hou, Dibo Huang, Pingjie State Key Laboratory of Industrial Control Technology College of Control Science and Engineering Zhejiang University Hangzhou310027 China

ISBN: (数字)9781510679887

ISBN: (纸本)9781510679870

Bearings, a crucial element in rotating machinery, are most susceptible to failure during operation, making up over half of all malfunctions. Detecting bearing faults in a timely manner can be quite challenging due to the frequent influence of strong noise on the fault features. To address the issue, an adaptive parameter optimization based on Minimum Entropy Deconvolution (MED) method in conjunction with Infogram is proposed. First, the Infogram is created through spectral negentropy, followed by the construction of a filter that utilizes the center frequency and the frequency band exhibiting the highest spectral negentropy. This filter is then applied to the original vibration signal in order to isolate the frequency band that contains the most significant bearing fault information. Then, based on MED method, the autocorrelation function and L1 norm are introduced to evaluate the filtered signal to realize the adaptive search of deconvolution filter length. Finally, the characteristic frequency components are extracted by envelope spectrum analysis. The validation of the effectiveness of the proposed method is conducted on a public dataset across various bearing operating conditions. The verification results show that this method can accurately detect the conditions of bearings, and extract more distinctive characteristic frequency components compared with some relevant techniques. © 2024 SPIE.

关键词： Spectrum analysis

来源：评论

学校读者我要写书评

暂无评论

Class-Imbalance and Client-Imbalance Federated Learning for Fault Diagnosis 13

Class-Imbalance and Client-Imbalance Federated Learning for ...

引用

13th IEEE Data Driven control and Learning Systems Conference, DDCLS 2024

作者： Sun, Shu Qian, Jinchuan Zhang, Xinmin Song, Zhihuan College of Control Science and Engineering Zhejiang University State Key Laboratory of Industrial Control Technology Hangzhou310027 China

ISBN: (纸本)9798350361674

With the development of big data, data-driven fault diagnosis models have experienced rapid growth. However, as the complexity of models increases, there is a corresponding rise in the demand for data. To obtain a substantial amount of data, traditional approaches involve centralizing datasets from multiple factories for training. However, due to heightened emphasis on data privacy from enterprises and regulatory bodies, this method becomes more challenging to implement and poses risks of data leakage. In response to this challenge, this paper designs a novel federated learning-based fault diagnosis modeling approach. Each local device trains its model on its local dataset and subsequently uploads updated model parameters to a central server for global model aggregation and updating. However, it is worth noting that in industrial processes, there may be concurrent class imbalance and data client imbalance, which brings challenges to fault diagnosis modeling based on federated learning. To address this challenge, we further propose a dynamic client aggregation fault diagnosis method based on category loss in federated learning. Experimental results indicate that the proposed approach not only protects data privacy in imbalanced class and client scenarios but also achieves outstanding fault recognition accuracy and robustness. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Open-source dataset for traffic light and countdown display detection in urban environment

引用

science China(Information sciences) 2025年第5期68卷 407-408页

作者： Shuchun WAN Haitao DING Jianwei ZHANG Yunfeng HU Hong CHEN State Key Laboratory of Automotive Simulation and Control Jilin University Department of Control Science and Engineering Jilin University College of Electronic and Information Engineering Tongji University

Here we introduce an open-source dataset for traffic light and countdown display detection,which includes three subsets:a subset of traffic light data,a subset of traffic light and countdown display data,and a subset ...

关键词：

来源：评论

学校读者我要写书评

暂无评论

Detecting the One-Shot Dummy Attack on the Power industrial control Processes With an Unsupervised Data-Driven Approach

引用

IEEE/CAA Journal of Automatica Sinica 2023年第2期10卷 550-553页

作者： Zhenyong Zhang Yan Qin Jingpei Wang Hui Li Ruilong Deng the State Key Laboratory of Public Big Data and the College of Computer Science and Technology Guizhou UniversityGuiyang 550025China the School of Chemical and Biomedical Engineering Nanyang Technological UniversitySingapore 639798Singapore the State Key Laboratory of Industrial Control Technology and the College of Control Science and Engineering Zhejiang UniversityHangzhou 310027China IEEE

Dear Editor,Dummy attack(DA), a deep stealthy but impactful data integrity attack on power industrial control processes, is recently recognized as hiding the corrupted measurements in normal measurements. In this letter, targeting a more practical case, we aim to detect the oneshot DA, with the purpose of revealing the DA once it is ***, we first formulate an optimization problem to generate one-shot DAs. Then, an unsupervised data-driven approach based on a modified local outlier factor(MLOF) is proposed to detect them.

关键词： Dummy Power letter

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：