检索结果-内蒙古大学图书馆

A strategy for high-entropy copper alloys composition design assisted by deep learning based on data reconstruction and network structure optimization

引用

JOURNAL OF MATERIALS RESEARCH AND TECHNOLOGY-JMR&T 2024年 31卷 1326-1336页

作者： Tan, Fei Jiang, Yanbin Lei, Qian Zhang, Hongtao Zhang, Lijun Xiao, Zhu Xu, Guofu Zhao, Yuyuan Li, Zhou Cent South Univ Sch Mat Sci & Engn Changsha 410083 Peoples R China Cent South Univ State Key Lab Powder Met Changsha 410083 Peoples R China Univ Sci & Technol Beijing Beijing Adv Innovat Ctr Mat Genome Engn Beijing 100083 Peoples R China Ningbo Univ Technol Sch Mech & Automot Engn Ningbo 315336 Peoples R China Univ Liverpool Sch Engn Ctr Mat & Struct Liverpool L69 3GH England

Complex mapping relationships between high-entropy alloy compositions and performances struggle to precisely elucidate by traditional machine learning models, hindering the accurate and efficient design of highperformance alloys. In this work, a novel alloy design strategy combined self-decision deep neural network, data reconstruction with network structure optimization was proposed, which effectively enhanced the model's ability to predict the mapping relationships between high-dimensional composition spaces and mechanical properties of alloy. Compared to other machine learning methods, significantly improves model prediction accuracy (hardness model: 97.98%;strength model: 94.40%). Through above model, the mechanical properties of 308 new (CuNiMn)-X high-entropy copper alloys was studied added other elements such as Al, Ti, Cr, and Fe, which designed and produced a novel (CuNiMn)60Al20Cr20 alloy with high hardness of 474 HV, high compressive strength of 2322 MPa, and high fracture strain of 25.20%. The primary factors influencing alloy performance and their respective thresholds were also quantitatively revealed (hardness: electronegativity deviation (0.02, 0.1) and nuclear charge deviation (0, 0.25);compressive strength: mean nuclear charge (25, 30) and mean atomic radius (134 p.m.)). These findings provide a new perspective and approach for the design and mechanism understanding of high-performance alloys with complex compositions.

关键词： Alloy composition design Mechanical property Deep learning Data reconstruction network structure optimization

来源：评论

学校读者我要写书评

暂无评论

Underwater glider motion parameter generation based on structure-optimized deep belief network and BP neural network

引用

APPLIED SOFT COMPUTING 2025年 169卷

作者： Hu, Hao Zhou, Yongjian Zhang, Zhao Peng, Xingguang Northwestern Polytech Univ Sch Marine Sci & Technol Xian Peoples R China

The underwater glider (UG) must promptly adjust its motion parameters to adapt to varying ocean conditions, ensuring mission safety and navigation efficiency. Therefore, this paper proposes a novel UG motion parameter generation method to rapidly determine the optimal pitch angle and diving depth. This method addresses two key challenges: dataset construction and generation model accuracy. First, an effective dataset is constructed by extracting relevant features from path segments, seabed topography, and ocean currents. Second, we present a structure-optimized deep belief network and back propagation neural network (SO-DBN-BPNN) model, which automates the design of network structures. This model maximizes the feature extraction capability of DBN and the generalization ability of BPNN, significantly enhancing overall performance. The SO-DBN-BPNN model achieves determination coefficients of 93.005% for pitch angle and 99.903% for diving depth, outperforming eight state-of-the-art models in accuracy. Furthermore, the proposed method is applied to assist the UG executing multi-point exploration missions. Simulation results show that this method can rapidly generate high-precision motion parameters, offering reliable support for UG navigation.

关键词： Underwater glider Motion parameter generation network structure optimization Deep belief network Back propagation neural network

来源：评论

学校读者我要写书评

暂无评论

Tensor tree learns hidden relational structures in data to construct generative models

引用

MACHINE LEARNING-SCIENCE AND TECHNOLOGY 2025年第2期6卷 025002-025002页

作者： Harada, Kenji Okubo, Tsuyoshi Kawashima, Naoki Kyoto Univ Grad Sch Informat Kyoto 6068501 Japan Univ Tokyo Inst Phys Intelligence Tokyo 1130033 Japan Univ Tokyo Inst Solid State Phys Kashiwa 2778581 Japan Univ Tokyo Transscale Quantum Sci Inst Bunkyo Ku Tokyo 1130033 Japan

Based on the tensor tree network with the Born machine framework, we propose a general method for constructing a generative model by expressing the target distribution function as the amplitude of the quantum wave function represented by a tensor tree. The key idea is dynamically optimizing the tree structure that minimizes the bond mutual information. The proposed method offers enhanced performance and uncovers hidden relational structures in the target data. We illustrate potential practical applications with four examples: (i) random patterns, (ii) QMNIST handwritten digits, (iii) Bayesian networks, and (iv) the pattern of stock price fluctuation pattern in S&P500. In (i) and (ii), the strongly correlated variables were concentrated near the center of the network;in (iii), the causality pattern was identified;and in (iv), a structure corresponding to the eleven sectors emerged.

关键词： generative modeling Born machine tensor network tensor tree network structure optimization mutual information

来源：评论

学校读者我要写书评

暂无评论

A sparse regularized soft sensor based on GRU and self-interpretation double nonnegative garrote: From variable selection to structure optimization

引用

CONTROL ENGINEERING PRACTICE 2024年 153卷

作者： Sui, Lin Sun, Wenxin Liu, Wentao Xiong, Weili Jiangnan Univ Sch Internet Things Engn Key Lab Adv Proc Control Light Ind Minist Educ Wuxi 214122 Peoples R China

Soft sensors, as a significant paradigm for industrial intelligence, are extensively utilized in large-scale industrial integration systems to estimate the pivotal quality variables. For deep neural network-based soft sensors, redundancy in input variables and network structure has emerged as one of the most important challenges. In this article, a sparse regularized soft sensor based on the gated recurrent unit (GRU) and self- interpretation dual nonnegative garrote is proposed. Initially, a proficiently trained GRU network is established as the pre-trained model, followed by the design of a set of self-interpretation factors based on the mean influence value of different input variables. Secondly, the contraction coefficients of the nonnegative garrote are sequentially incorporated into the GRU input and hidden layer weight matrices. Meanwhile, the self- interpretation factors are introduced into the constraints of the nonnegative garrote algorithm to guide it to adaptively adjust the applied penalty strength based on the relative importance of different input variables. The strategy integrates variable selection with the model training process to sparsify the network structure and provide self-interpretable variable selection results. Finally, the performance of the developed approach is verified through a practical application in power plant desulfurization systems. The case studies demonstrate that the developed approach for soft sensor modeling outperforms other existing methods and shows promising application prospects. In addition, the validity of the self-interpretable variable selection results is verified via the known mechanism analysis and expert experience.

关键词： Soft sensors Nonnegative garrote Gated recurrent unit Variable selection network structure optimization Large-scale industrial systems

来源：评论

学校读者我要写书评

暂无评论

A review on convolutional neural network in rolling bearing fault diagnosis

引用

MEASUREMENT SCIENCE AND TECHNOLOGY 2024年第7期35卷 072002-072002页

作者： Li, Xin Ma, Zengqiang Yuan, Zonghao Mu, Tianming Du, Guoxin Liang, Yan Liu, Jingwen Shijiazhuang Tiedao Univ Hebei Prov Collaborat Innovat Ctr Transportat Powe Shijiazhuang 050043 Peoples R China Shijiazhuang Tiedao Univ Sch Elect & Elect Engn Shijiazhuang 050043 Peoples R China Shijiazhuang Tiedao Univ State Key Lab Mech Behav & Syst Safety Traff Engn Shijiazhuang 050043 Peoples R China Shijiazhuang Tiedao Univ Sch Traff & Transportat Shijiazhuang 050043 Peoples R China State Grid Shijiazhuang Elect Power Supply Co Shijiazhuang 050051 Peoples R China

The health condition of rolling bearings has a direct impact on the safe operation of rotating machinery. And their working environment is harsh and the working condition is complex, which brings challenges to fault diagnosis. With the development of computer technology, deep learning has been applied in the field of fault diagnosis and has rapidly developed. Among them, convolutional neural network (CNN) has received great attention from researchers due to its powerful data mining ability and feature adaptive learning ability. Based on recent research hotspots, the development history and trend of CNN is summarized and analyzed. Firstly, the basic structure of CNN is introduced and the important progress of classical CNN models for rolling bearing fault diagnosis in recent years is studied. The problems with the classic CNN algorithm have been pointed out. Secondly, to solve the above problems, combined with recent research achievements, various methods and principles for optimizing CNN are introduced and compared from the perspectives of deep feature extraction, hyperparameter optimization, network structure optimization. Although significant progress has been made in the research of fault diagnosis of rolling bearings based on CNN, there is still room for improvement and development in addressing issues such as low accuracy of imbalanced data, weak model generalization, and poor network interpretability. Therefore, the future development trend of CNN networks is discussed finally. And transfer learning models are introduced to improve the generalization ability of CNN and interpretable CNN is used to increase the interpretability of CNN networks.

关键词： rolling bearing fault diagnosis convolutional neural network hyperparameter optimization network structure optimization transfer learning interpretability

来源：评论

学校读者我要写书评

暂无评论

optimization of Table Tennis Swing Action Supported by the Temporal Convolutional network Algorithm in Deep Learning

引用

IEEE ACCESS 2024年 12卷 178362-178374页

作者： Sun, Shaoxuan Zheng, Hongyu Lin, Zhixin Shandong Univ Weihai Phys Educ Dept Weihai 264200 Shandong Peoples R China Shandong Univ Weihai Sch Mech Elect & Informat Engn Weihai 264200 Shandong Peoples R China

To enhance the navigation accuracy and interpretability of Unmanned Aerial Vehicles (UAVs) in sports analysis, this study proposes an improved model based on the Temporal Convolutional network (TCN) algorithm, integrated with Explainable Artificial Intelligence. The model aims to analyze real-time data collected by Internet of Things sensors mounted on UAVs to capture athletes' swing actions during table tennis matches, thereby providing transparent decision support. The research effectively addresses the vanishing gradient problem by replacing the traditional Rectified Linear Unit (ReLU) activation function with Leaky ReLU, while simplifying the network structure through the use of a Global Average Pooling layer to reduce model complexity. Additionally, the residual structure is fine-tuned to adapt to dynamic environmental features, thereby enhancing the model's capability to recognize swing actions. During the experimental phase, the model is evaluated using a dataset of swing actions collected by UAVs, comprising 55,582 data samples, which are divided into training and testing sets in a 3:2 ratio. The results reveal that the proposed improved TCN achieves remarkable outcomes in table tennis swing action recognition, with an algorithmic recognition accuracy of 99.43%, as well as recall, precision, and F1 scores of 99.00%. This algorithm's recognition accuracy surpasses that of TCN, Long Short-Term Memory, and Convolutional Neural network-Long Short-Term Memory algorithms by 10.57%, 3.65%, and 2.70%, respectively. The enhancement in recognition performance provides robust support for the technical training and competitive performance of table tennis players. This research outcome offers new insights into the application of UAVs in sports analysis and lays the groundwork for optimizing models and feature extraction techniques in broader sports application scenarios.

关键词： Sports Convolution Feature extraction Brain modeling Autonomous aerial vehicles Navigation Kernel Classification algorithms Accuracy Training Temporal convolutional network UAV navigation network structure optimization table tennis explainable artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

3D Vehicle Detection Algorithm Based onMultimodal Decision-Level Fusion

引用

Computer Modeling in Engineering & Sciences 2023年第6期135卷 2007-2023页

作者： Peicheng Shi Heng Qi Zhiqiang Liu Aixi Yang School of Mechanical Engineering Anhui Polytechnic UniversityWuhu241000China Department Polytechnic Institute of Zhejiang University Hangzhou310000China

3D vehicle detection based on LiDAR-camera fusion is becoming an emerging research topic in autonomous *** algorithm based on the Camera-LiDAR object candidate fusion method(CLOCs)is currently considered to be a more effective decision-level fusion algorithm,but it does not fully utilize the extracted features of 3D and ***,we proposed a 3D vehicle detection algorithm based onmultimodal decision-level ***,project the anchor point of the 3D detection bounding box into the 2D image,calculate the distance between 2D and 3D anchor points,and use this distance as a new fusion feature to enhance the feature redundancy of the ***,add an attention module:squeeze-and-excitation networks,weight each feature channel to enhance the important features of the network,and suppress useless *** experimental results show that the mean average precision of the algorithm in the KITTI dataset is 82.96%,which outperforms previous state-ofthe-art multimodal fusion-based methods,and the average accuracy in the Easy,Moderate and Hard evaluation indicators reaches 88.96%,82.60%,and 77.31%,respectively,which are higher compared to the original CLOCs model by 1.02%,2.29%,and 0.41%,*** with the original CLOCs algorithm,our algorithm has higher accuracy and better performance in 3D vehicle detection.

关键词： 3D vehicle detection multimodal fusion CLOCs network structure optimization attention module

来源：评论

学校读者我要写书评

暂无评论

Grey Wolf optimization-Based Deep Echo State network for Time Series Prediction

引用

FRONTIERS IN ENERGY RESEARCH 2022年 10卷

作者： Chen, Xiaojuan Zhang, Haiyang Changchun Univ Sci & Technol Sch Elect Informat Engn Changchun Peoples R China

The Echo State network (ESN) is a unique type of recurrent neural network. It is built atop a reservoir, which is a sparse, random, and enormous hidden infrastructure. ESN has been successful in dealing with a variety of non-linear issues, including prediction and classification. ESN is utilized in a variety of architectures, including the recently proposed Multi-Layer (ML) architecture. Furthermore, Deep Echo State network (DeepESN) models, which are multi-layer ESN models, have recently been proved to be successful at predicting high-dimensional complicated non-linear processes. The proper configuration of DeepESN architectures and training parameters is a time-consuming and difficult undertaking. To achieve the lowest learning error, a variety of parameters (hidden neurons, input scaling, the number of layers, and spectral radius) are carefully adjusted. However, the optimum training results may not be guaranteed by this haphazardly created work. The grey wolf optimization (GWO) algorithm is introduced in this study to address these concerns. The DeepESN based on GWO (GWODESN) is utilized in trials to forecast time series, and therefore the results are compared with the regular ESN, LSTM, and ELM models. The findings indicate that the planned model performs the best in terms of prediction.

关键词： time series prediction deep echo state network grey wolf optimization network structure optimization combined cycle power plant

来源：评论

学校读者我要写书评

暂无评论

Echo state network optimization using binary grey wolf algorithm

引用

NEUROCOMPUTING 2020年 385卷 310-318页

作者： Liu, Junxiu Sun, Tiening Luo, Yuling Yang, Su Cao, Yi Zhai, Jia Guangxi Normal Univ Sch Elect Engn Guilin Peoples R China Ulster Univ Sch Comp Engn & Intelligent Syst Londonderry BT48 7JL North Ireland Univ Edinburgh Business Sch Management Sci & Business Econ Grp 29 Buccleuch Pl Edinburgh EH8 9JS Midlothian Scotland Univ Salford Salford Business Sch Salford M5 4WT Lancs England

The echo state network (ESN) is a powerful recurrent neural network for time series modelling. ESN inherits the simplified structure and relatively straightforward training process of conventional neural networks, and shows strong computational capabilities to solve nonlinear problems. It is able to map low-dimensional input signals to high-dimensional space for information extraction, but it is found that not every dimension of the reservoir output directly contributes to the model generalization. This work aims to improve the generalization capabilities of the ESN model by reducing the redundant reservoir output features. A novel hybrid model, namely binary grey wolf echo state network (BGWO-ESN), is proposed which optimises the ESN output connection by the feature selection scheme. Specially, the feature selection scheme of BGWO is developed to improve the ESN output connection structure. The proposed method is evaluated using synthetic and financial data sets. Experimental results demonstrate that the proposed BGWO-ESN model is more effective than other benchmarks, and obtains the lowest generalization error. (C) 2019 Elsevier B.V. All rights reserved.

关键词： Echo state network Binary grey wolf optimization Time series network structure optimization

来源：评论

学校读者我要写书评

暂无评论

Agricultural Information Retrieval in Geographically Distributed networks

Agricultural Information Retrieval in Geographically Distrib...

引用

5th International Conference on Agro-Geoinformatics (Agro-Geoinformatics)

作者： Chen Wei Li Zhemin Zhang Chao Wang Dongjie Wu Chen Chinese Acad Agr Sci Agr Informat Inst Beijing Peoples R China Minist Agr Key Lab Agriinformat Serv Technol Beijing Peoples R China

As the rapid development of information technology and agricultural applications, agricultural information has been widely distributed geographically in a region. It is observed that agricultural production and trading activities tend to be localized in many cases. Effective retrieval of geographically distributed information can facilitate agricultural production as well as trading. In this paper, an agricultural information retrieval approach is proposed for geographically distributed networks. The network structure of the unstructured peer-to-peer network is introduced. A topic-aware agent reputation model that combines individual-and social-level reputations is adopted to distinguish different information retrieval performance on various topics. A location-based network structure optimization method is proposed to gather geographically small distance agents together. A hybrid query routing approach is presented that combines topic-aware agent reputation scores and location-based ratings. Simulation experiments are conducted for the evaluation of the proposed approach. The results of the experiments show good performance of it.

关键词： agricultural information retrieval peer-to-peer network geographically distributed network network structure optimization query routing

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：