检索结果-内蒙古大学图书馆

2023 5th International Conference on Artificial Intelligence Technologies and Applications, ICAITA 2023

作者： Xiang, Hao Guangxi Colleges and Universities Key Lab. of Complex System Optimization and Big Data Processing Yulin Normal University Yulin537000 China

The characteristics of LS-SVR are analyzed. LS-SVR is fitted for modeling small samples and high dimensional data, but the performance of LS-SVR is related to the specific data distribution, the kind of kernel function, its related kernel parameter, and the penalty coefficient. In this paper, the radial basis function is applied as the kernel function of LS-SVR, and the real double-chain coding target gradient quantum genetic algorithm (DCQGA) is applied to optimize the kernel parameter and penalty item coefficient of LS-SVR, then the regression prediction model DCQGALSSVR is proposed. It is of great significance to build an accurate and reliable fault prediction model for the health monitoring and fault diagnosis of liquid rocket engines. The thrust of a liquid rocket engine is an important factor in its health monitoring. By predicting the thrust change value and comparing the predicted value with the engine thrust threshold, it can be predicted whether the engine will fail at a certain time. In this paper, the proposed DCQGALSSVR model is used to model the thrust of a liquid rocket engine. The simulation results show that the average relative error is 0.37% using LSSVR for modeling on 12 test samples, and is 0.3186% using DCQGALSSVR on the same samples. It can be seen that DCQGALSSVR is effective for the health monitoring of liquid rocket engines, so it has a certain promotion significance. © Published under licence by IOP Publishing Ltd.

关键词： Radial basis function networks

来源：评论

学校读者我要写书评

暂无评论

The improved quantum genetic algorithm with its application in fault diagnosis 3

The improved quantum genetic algorithm with its application ...

引用

2023 3rd International Conference on Computer, Remote Sensing and Aerospace, CRSA 2023

作者： Xiang, Hao Guangxi Colleges and Universities Key Lab. of Complex System Optimization and Big Data Processing Yulin Normal University Yulin537000 China

In this paper, by analyzing the characteristics of the simulated annealing algorithm (SA) and the real double-chain coding target gradient quantum genetic algorithm (DCQGA), the real double-chain coding target gradient quantum genetic simulated annealing algorithm (DCQGSAA) is proposed. Because the performance of LSSVR is extraordinarily sensitive to its key parameters, the proposed algorithm is used to optimize these parameters, then a hybrid non-parametric prediction model is put forward. This model is used in fault prediction of liquid rocket engine thrust. The simulation results show that the proposed model is effective for small samples and multi-dimensional fault prediction. © Published under licence by IOP Publishing Ltd.

关键词： Simulated annealing

来源：评论

学校读者我要写书评

暂无评论

PS-TTL: Prototype-based Soft-lab.ls and Test-Time Learning for Few-shot Object Detection 24

PS-TTL: Prototype-based Soft-labels and Test-Time Learning f...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Gao, Yingjie Zhang, Yanan Huang, Ziyue Liu, Nanqing Huang, Di SKLCCSE Beihang University Beijing China SIST Southwest Jiaotong University Chengdu China Zhejiang Industrial Big Data and Robot Intelligent System Key Lab. Hangzhou China

ISBN: (纸本)9798400706868

In recent years, Few-Shot Object Detection (FSOD) has gained widespread attention and made significant progress due to its ability to build models with a good generalization power using extremely limited annotated data. The fine-tuning based paradigm is currently dominating this field, where detectors are initially pre-trained on base classes with sufficient samples and then fine-tuned on novel ones with few samples, but the scarcity of lab.led samples of novel classes greatly interferes precisely fitting their data distribution, thus hampering the performance. To address this issue, we propose a new framework for FSOD, namely Prototype-based Soft-lab.ls and Test-Time Learning (PS-TTL). Specifically, we design a Test-Time Learning (TTL) module that employs a mean-teacher network for self-training to discover novel instances from test data, allowing detectors to learn better representations and classifiers for novel classes. Furthermore, we notice that even though relatively low-confidence pseudo-lab.ls exhibit classification confusion, they still tend to recall foreground. We thus develop a Prototype-based Soft-lab.ls (PS) strategy through assessing similarities between low-confidence pseudo-lab.ls and category prototypes as soft-lab.ls to unleash their potential, which substantially mitigates the constraints posed by few-shot samples. Extensive experiments on both the VOC and COCO benchmarks show that PS-TTL achieves the state-of-the-art, highlighting its effectiveness. The code and model are availab.e at https://***/gaoyingjay/PS-TTL. © 2024 ACM.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

A Fault Diagnosis Method for Electric Vehicle Lithium Power Batteries Based on Dual-Feature Extraction from the Time and Frequency Domains

引用

Journal of Electrochemical Energy Conversion and storage 2025年第3期22卷 031008页

作者： Chang, Chun Dai, Jiuhe Pan, Yaliang Lv, Lu Gao, Yang Jiang, Jiuchun Hubei Key Lab. for High Efficiency Utiliz. of Solar Ener. and Oper. Control of Energy Storage System Hubei University of Technology Wuhan430068 China Sunwoda Electronic Co. Ltd Shenzhen518108 China School of Electric Power South China University of Technology Guangzhou510640 China

This study focuses on the safety and reliability issues of lithium-ion batteries, proposing a fault diagnosis strategy that leverages dual-feature extraction from both the time and frequency domains. Additionally, by modifying the traditional autoencoder, the study proposes a feature-guided autoencoder as an unsupervised model for extracting features in the time domain. Initially, wavelet packet decomposition and its energy-denoising treatment are employed to refine fault information within battery voltage signals. Subsequently, the reconstruction error outputted by the Feature-Guided Autoencoder is utilized as the time-domain fault feature, while the cosine similarity of the energy of signals in various frequency bands obtained after wavelet packet decomposition serves as the frequency-domain fault feature. Ultimately, this article selects the Isolation Forest algorithm for two-dimensional outlier detection of time and frequency features. Experimental results demonstrate that the feature-guided autoencoder proposed in this study not only enhances the sensitivity of time-domain fault features compared to traditional autoencoders and their variants but also optimizes issues related to training time and computational load. The effectiveness of the proposed dual-feature fault diagnosis method in both the time and frequency domains is validated through data from two actual vehicles, showing superior early fault detection capability relative to single-feature fault diagnosis methods. Copyright © 2024 by ASME.

关键词： Wavelet decomposition

来源：评论

学校读者我要写书评

暂无评论

Anionic formulation of electrolyte additive towards stable electrocatalytic oxygen evolution in seawater splitting

引用

Journal of Energy Chemistry 2022年第9期31卷 361-369,I0010页

作者： Meng Yu Jinhan Li Fangming Liu Jiuding Liu Wence Xu Honglu Hu Xijie Chen Weichao Wang Fangyi Cheng Key Laboratory of Advanced Energy Materials Chemistry(Ministry of Education) Engineering Research Center on High-Efficiency Energy Storage(Ministry of Education)Renewable Energy Conversion and Storage CenterCollege of ChemistryNankai UniversityTianjin 300071China Integrated Circuits and Smart System Lab.(Shenzhen) Renewable Energy Conversion and Storage CenterTianjin Key Laboratory of Photo-Electronic Thin Film Device and TechnologyCollege of Electronic Information and Optical EngineeringNankai UniversityTianjin 300071China

Hydrogen generation through seawater electrolysis provides a promising,attractive pathway towards the utilization of sustainable ***,the catalytic activity and stability of oxygen evolution anode are severely limited by the chloride-induced corrosion and competitive oxidation *** this work,we demonstrate an anion-assisted performance improvement strategy by quick and universal screening of electrolyte additive via correlating Cl-repellency with the anionic ***,the addition of phosphate ions is found to enable highly stable alkaline seawater splitting at industry-level current density(0.5 A cm^(-2))over 500 h using transition metal hydroxides as anodic *** situ experiments and theoretical simulations further reveal that the dynamic anti-corrosion behaviors of surface-adsorbed phosphate ions are attributed to three factors including repelling Cl-ions without significantly blocking OH-diffusion,preventing transition metal dissolution and acting as a local pH buffer to compensate the fast OH-consumption under high current electrolysis.

关键词： Alkaline seawater splitting Oxygen evolution reaction Stability enhancement Chloride corrosion Phosphate

来源：评论

学校读者我要写书评

暂无评论

An Intelligent WSN-Based Digital Twin Design for Photovoltaic Power Generation Forecast 6

An Intelligent WSN-Based Digital Twin Design for Photovoltai...

引用

6th IEEE International Conference on Electronics and Communication Engineering, ICECE 2023

作者： Wan, Hang Qiu, Zhizhuo Quan, Rui David, Michael Derigent, William Hubei University of Technology Hubei Key Lab. for High-Efficiency Utiliz. of Solar Ener. and Oper. Control of Energy Storage System Wuhan China University of Lorraine Cran Cnrs Umr 7039 Vandœuvre-les-Nancy France

ISBN: (纸本)9798350328721

Photovoltaic power generation has been extensively utilized for power supply in remote areas. Due to the effect of weather and environmental conditions, its power generation experiences fluctuations. This paper proposes a dedicated WSN-based digital twin design for photovoltaic power generation. In this design, WSN is used to regularly collect and transmit monitoring data. The cloud platform and neural network are then integrated to displays equipment's status and predict power generation. Experimental results demonstrate that this digital twin design can effectively display the real-time operating status and environmental information. Using the LSTM-CNN algorithm achieve an accurate power prediction, with the RMSE and MAE values of 0.436 and 0.209 respectively. The real-time status monitoring and power prediction of photovoltaic equipment can not only provide a basis for fault diagnosis, but also optimize power grid dispatch in remote areas. © 2023 IEEE.

关键词： Wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

YASA axial flux machine with non-uniform arrangement of stator segmented modules for reducing harmonics of back EMF 5

YASA axial flux machine with non-uniform arrangement of stat...

引用

5th IEEE International Electrical and Energy Conference, CIEEC 2022

作者： Wang, Xiaoguang Li, Xiaofeng Liu, Cheng Zhang, Guoguang Xu, Wei Hubei University of Technology Hubei Key Lab. for High-efficiency Utiliz. of Solar Ener. and Oper. Control of Energy Storage System Wuhan China Huazhong University of Science and Technology Wuhan China

ISBN: (数字)9781665411042

ISBN: (纸本)9781665411042

Stator yokeless and segmented armature (YASA) axial flux permanent magnet (AFPM) machine with soft magnetic composite (SMC) core has the advantages of compact structure and high power density, but the concentrated winding will product abundant harmonics of back EMF. In this paper, the non-uniform arrangement of segmented stator modules is proposed for YASA machine, which are each segmented-stator module is arranged non-uniformly in the circumferential direction. Firstly, the relationship between segmented-stator module uniform arrangement and non-uniform arrangement of no-load back EMF is obtained by phasor diagram. Then, the non-uniform distribution coefficient of no-load back EMF is established, and its no-load characteristics are analyzed. Finally, the proposed method and structure are proved by finite element analysis (FEA). The results show that the non-uniform distribution coefficient is accurate within the allowable error range, and the non-uniform arrangement of segmented-stator module can effectively reduce harmonics and improve the sinusoidal properties of no-load back EMF to improve the performance of YASA machine. © 2022 IEEE.

关键词： Stators

来源：评论

学校读者我要写书评

暂无评论

Intersecting-boundary-sensitive fingerprinting for tampering detection of DNN models 24

Intersecting-boundary-sensitive fingerprinting for tampering...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Xiaofan Bai Chaoxiang He Xiaojing Ma Bin Benjamin Zhu Hai Jin School of Cyber Science and Engineering Huazhong University of Science and Technology National Engineering Research Center for Big Data Technology and System and Services Computing Technology and System Lab and Hubei Engineering Research Center on Big Data Security and Hubei Key Laboratory of Distributed System Security Microsoft School of Computer Science and Technology Huazhong University of Science and Technology and National Engineering Research Center for Big Data Technology and System and Services Computing Technology and System Lab and Cluster and Grid Computing Lab.

Cloud-based AI services offer numerous benefits but also introduce vulnerabilities, allowing for tampering with deployed DNN models, ranging from injecting malicious behaviors to reducing computing resources. Fingerprint samples are generated to query models to detect such tampering. In this paper, we present Intersecting-Boundary-Sensitive Fingerprinting (IBSF), a novel method for black-box integrity verification of DNN models using only top-1 lab.ls. Recognizing that tampering with a model alters its decision boundary, IBSF crafts fingerprint samples from normal samples by maximizing the partial Shannon entropy of a selected subset of categories to position the fingerprint samples near decision boundaries where the categories in the subset intersect. These fingerprint samples are almost indistinguishable from their source samples. We theoretically establish and confirm experimentally that these fingerprint samples' expected sensitivity to tampering increases with the cardinality of the subset. Extensive evaluation demonstrates that IBSF surpasses existing state-of-the-art fingerprinting methods, particularly with larger subset cardinality, establishing its state-of-the-art performance in black-box tampering detection using only top-1 lab.ls. The IBSF code is availab.e at: https://***/CGCL-codes/IBSF.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design of BOOST converter based on CN3306 chip 7

Design of BOOST converter based on CN3306 chip

引用

7th International Conference on Electrical Engineering, Control and Robotics, EECR 2021

作者： Linbo, Gan Anfei, Xu Ziqiang, Xi Xiaogang, Du Hubei Key Lab. of Solar Energy Efficient Utilization and Energy Storage System Operation Control Hubei University of Technology Wuhan430068 China

CN3306 is a current mode fixed frequency PWM boost type multiple battery charging management integrated circuit. This article introduces the basic principles and characteristics of CN3306, and designs a boost circuit based on the characteristics of CN3306 chip with stable voltage, small ripple range and low power consumption. Explained in detail how to select peripheral circuit parameters and the practical application of CN3306 in BOOST circuit, and use the PSIM simulation software to build a photovoltaic power generation system model for simulation verification, the result reached the expected value. © Published under licence by IOP Publishing Ltd.

关键词： Low power electronics

来源：评论

学校读者我要写书评

暂无评论

Research on High Power Ultrasonic Power Supply Based on Cascaded 9 Level Technology 5

Research on High Power Ultrasonic Power Supply Based on Casc...

引用

5th International Conference on New Energy and Future Energy system, NEFES 2020

作者： Zhou, C.H. Zhang, C.Z. Zhang, W.Y. Tian, Y. Wang, C.R. Shu, Y.H. Hubei Key Lab. for High-efficiency Utiliz. of Solar Ener. and Oper. Control of Energy Storage System Hubei University of Technology Wuhan430068 China

In view of the low output power and high power density of ultrasonic power supply, a high power ultrasonic power supply based on 9-level inverter technology is proposed. The inverter of the power supply consists of two H-bridge units cascaded to form a 9-level converter, which outputs the 9-level voltage waveform, which can significantly improve the output power of the ultrasonic power supply, reduce the inductance of the matching network, and reduce the power density of the ultrasonic wave. The phase difference method based on PI control is used to track the resonance frequency. By analyzing the system structure, working principle and control strategy of the ultrasonic power supply, modeling and simulation were conducted on Matlab.Simulink to verify the feasibility and effectiveness of the scheme. © Published under licence by IOP Publishing Ltd.

关键词： Simulink

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：