检索结果-内蒙古大学图书馆

Method for rail surface defect detection based on neural network architecture search

MEASUREMENT SCIENCE AND TECHNOLOGY 2025年第1期36卷 016027-016027页

作者： Min, Yongzhi Jing, Qinglong Li, Yaxing Lanzhou Jiaotong Univ Sch Automat & Elect Engn Lanzhou 730070 Gansu Peoples R China Lanzhou Jiaotong Univ Gansu Prov Ctr Artificial Intelligence & Graph Ima Lanzhou 730070 Gansu Peoples R China

This study addresses the inherent limitations of implementing neural network architecture search algorithms for rail surface defect detection, including low search efficiency and the oversight of edge features on the rail surface. A sophisticated multi-level neural network architecture search framework is proposed that integrates and emphasizes rail surface edge features. The framework utilizes the Z-Score normalization method to quantify the edge concern of rail surface defect samples, combined with an Edge-Loss function to enhance edge feature recognition capabilities. Furthermore, acknowledging the sensitivity of defect features to spatial resolution changes, a multi-level neural network architecture search space is meticulously designed. In the cell-level search space, a method combining partial channel sampling with operation pruning is employed to enhance model search efficiency and regularization. In the network-level search space, optimal paths for resolution change are established, allowing for the screening and aggregation of defect features at various levels to facilitate the adaptive extraction of multi-scale edge defect features. Experimental outcomes indicate that this method significantly reduces computational resource usage by approximately 75% and increases mIOU by 2.6% relative to traditional architecture search methods. Moreover, it demonstrates robust capability in accurately recognizing defective edges on rail surfaces, thereby substantiating the method's effectiveness.

关键词： rail surface defects detection neural network architecture search edge defects features learning partical channels sampling

来源：评论

学校读者我要写书评

暂无评论

Efficient Fault Diagnosis of Rolling Bearings Using neural network architecture search and Sharing Weights

引用

IEEE ACCESS 2021年 9卷 98800-98811页

作者： Pham, Minh Tuan Kim, Jong-Myon Kim, Cheol Hong Chonnam Natl Univ Dept ICT Convergence Syst Engn Gwangju 61186 South Korea Univ Ulsan Sch IT Convergence Ulsan 44610 South Korea Soongsil Univ Sch Comp Sci & Engn Seoul 06978 South Korea

Bearing is one of the most vital components of industrial machinery. The failure of bearing causes severe problems in the machinery. Therefore, continuous monitoring for the bearings is essential rather than regular manual checking, with the requirement for accuracy of prediction and efficiency. This paper proposes a novel intelligent bearing fault condition monitoring and diagnosis method focusing on computation efficiency, which is an important aspect of a continuous monitoring and embedded-based diagnosis device. In the proposed method, acoustic emission signals containing bearing health information are converted into 2-D spectrograms by Constant Q-Transform (CQT) before using a convolutional neural network to infer the bearing state. To reduce the latency while maintaining high accuracy, we propose an efficient search space for neural network architecture search, i.e., a channel distribution search, that automatically obtain the best performing network. Moreover, we present a separation between two processes of condition monitoring and fault diagnosis to save overall computing resources, with a policy of sharing weights in the training process and sharing features in the testing process. The experimental results show that the proposed method reduces about 50% inference time compared to previous methods while achieving an accuracy of 99.82% for eight types of single and compound fault diagnosis for variable rotational speeds.

关键词： Time-frequency analysis Fault diagnosis Monitoring Feature extraction Task analysis neural networks Computer architecture Acoustic emission bearing fault condition monitoring bearing fault diagnosis convolutional neural network neural network architecture search

来源：评论

学校读者我要写书评

暂无评论

Research on an ultrasonic detection method for weld defects based on neural network architecture search

引用

MEASUREMENT 2023年第1期221卷

作者： Zhang, Rui Gao, Mei-Rong Zhang, Peng-Yun Zhang, Yong-Mei Fu, Liu-Hu Chai, Yan-Feng Taiyuan Univ Sci & Technol Coll Comp Sci & Technol Taiyuan 030024 Peoples R China North China Univ Technol Sch Informat Beijing 100144 Peoples R China Shanxi Design & Res Inst Mech & Elect Engn Co Ltd Taiyuan 030009 Peoples R China

In order to further reduce the subjectivity of network design and improve the ability of model feature extraction, an ultrasonic detection method for weld defects based on neural network architecture search is proposed. Through the designed multi-level and multi-branch search space and an untrained architecture search and evaluation method, an efficient defect classification network was automatically constructed to complete the task of weld defect classification. Experiments were carried out on a self-constructed data set, and compared with the manually designed model, the classification accuracy of defect types reached 95.26% when the number of parameters was only 7.3 M. Compared with the model constructed using neural network architecture search, the proposed method can reduce the searching time to 8.29% of the baseline model while weighing multiple conflicting objectives, which proved the efficiency and effectiveness of the proposed method.

关键词： Weld defects Ultrasonic testing neural network architecture search Multi-objective optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Convolutional neural network Graph-based Embedding for neural architecture search

引用

Procedia Computer Science 2023年 229卷 47-54页

作者： Evgeny Bessonnitsyn Vsevolod Shaldin Valeria Efimova Viacheslav Shalamov ITMO University Kronverksky Pr. 49 bldg. A St. Petersburg 197101 Russia

Recently, network architecture search is gaining popularity. The neural network representation as a directed acyclic graph is considered for subsequent architecture optimization. Currently, most of the existing encoders rely only on the model layer properties and do not take into account the attributes of layers. This work proposes an algorithm for mapping a CNN network to a vector space considering the layer attributes, such as different dimensions of a particular layer. The proposed algorithm was compared with D-VAE and DVAE-EMB and showed less information loss caused by the mapping of a network to a vector space. As the results show, the performance of the model was shown after direct conversion to embedding and reverse conversion to architecture. The method allows more accurate neural network architecture mapping into a vector form, which will improve the search for the best architecture. The method implementation is publicly available at https://***/Turukmokto/GraphEmbedding-dev .

关键词： neural network architecture search vector representation variational autoencoder graphs with attributes

来源：评论

学校读者我要写书评

暂无评论

A lightweight neural network search algorithm based on in-place distillation and performance prediction for hardware-aware optimization

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2025年 151卷

作者： Kang, Siyuan Sun, Yinghao Li, Shuguang Xu, Yaozong Li, Yuke Chen, Guangjie Xue, Fei Univ Elect Sci & Technol China Sch Automat Engn Chengdu 611731 Peoples R China Sichuan Prov Engn Res Ctr Vehicle Intelligent Syst Chengdu 611731 Peoples R China China Automot Technol & Res Ctr Co Ltd Tianjin 300300 Peoples R China

Due to the limited computing resources of edge devices, traditional object detection algorithms struggle to meet the efficiency and accuracy requirements of autonomous driving. Consequently, designing a neural network model that balances hardware resource requirements, operating speed, and accuracy is crucial. To address this, by integrating algorithm with hardware characteristics, we propose a lightweight neural network architecture search algorithm based on in-place distillation and performance predictor (LNIP). Initially, we focus on optimizing the operators of the you only look once version 8 nano (YOLOv8n) and dynamically adjust its network structure. Then, we trained a super-network using a progressive shrinking strategy, the sandwich rule, and in-place distillation. Subsequently, we employed a Gaussian process to model the relationship between network architecture and accuracy, utilizing encoding methods and custom kernel function to develop high-performance predictor. Finally, during the search process, we introduce a reward function based on Pareto optimality to balance the performance of the model with hardware constraints. Building upon this foundation, we design an efficient search algorithm based on the performance predictor to progressively explore the optimal network structure tailored to hardware characteristics. We compared our lightweight network with state-of-the-art methods on the BDD100K, COCO, and PASCAL VOC datasets and deployed it on the Black Sesame A1000 and NVIDIA Xavier for comprehensive evaluation. On the NVIDIA Xavier, the lightweight network achieves a latency of 11.81 ms and an edge precision of 46.1 %. These experimental results demonstrate that our method outperforms existing methods in balancing hardware constraints and model performance.

关键词： neural network architecture search Performance predictor Pareto optimality In-place distillation Object detection

来源：评论

学校读者我要写书评

暂无评论

Auto-CsiNet: Scenario-Customized Automatic neural network architecture Generation for Massive MIMO CSI Feedback

引用

IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS 2024年第10期23卷 14759-14775页

作者： Li, Xiangyi Guo, Jiajia Wen, Chao-Kai Jin, Shi Southeast Univ Natl Mobile Commun Res Lab Nanjing 210096 Peoples R China Natl Sun Yat Sen Univ Inst Commun Engn Kaohsiung 80424 Taiwan

Deep learning has brought about a revolution in the design of the channel state information (CSI) feedback module in wireless communications. However, designing the optimal neural network (NN) architecture for CSI feedback can be a laborious and time-consuming process, and manual design can be prohibitively expensive for customized NNs tailored to different scenarios. To tackle this challenge, this paper proposes the use of neural architecture search (NAS) to automate the generation of scenario-customized CSI feedback NN architectures. By employing automated machine learning and gradient-descent-based NAS, an efficient and cost-effective architecture design process is achieved, requiring less expert experience and design time, thus lowering the design threshold. The proposed approach leverages implicit scene knowledge and integrates it into the scenario customization process in a data-driven manner, fully exploiting the potential of deep learning in a given scenario. To address the issue of excessive search, early stopping and elastic selection mechanisms are employed, further enhancing the proposed scheme. The experimental results demonstrate that the generated architecture, known as Auto-CsiNet, outperforms manually-designed models in terms of reconstruction performance (achieving approximately 14% improvement) and complexity (reducing by approximately 50%), highlighting the effectiveness of the NAS-based automatic scheme. Furthermore, the paper analyzes the impact of the scenario on the NN architecture and capacity.

关键词： Massive MIMO CSI feedback deep learning neural network architecture search Massive MIMO CSI feedback deep learning neural network architecture search

来源：评论

学校读者我要写书评

暂无评论

An effective dual-predictor controller mechanism using neural architecture search for optimization of residential energy hub system

引用

DISCOVER COMPUTING 2025年第1期28卷 1-22页

作者： Lan, Guojun Tang, Jian Chen, Jie Xing, Jingshu Zhao, Lijun State Grid Inner Mongolia Eastern Power Co Ltd Econ & Technol Res Inst Hohhot 010010 Inner Mongolia Peoples R China

The energy hub integrates heating, cooling, and electrical units for residential setups equipped with photovoltaic (PV) systems and energy storage, aiming to minimize energy consumption costs while optimizing the performance of the energy hub system. However, uncertainties such as fluctuations in electricity market prices and variations in solar irradiance can disrupt the stability and robustness of the optimal control of the system. To address this, we propose a dual-predictor controller mechanism, which integrates a recurrent neural network (RNN) sequence predictor based on neural architecture search (NAS). As dataset complexity and scale continue to increase, designing appropriate RNN architectures tailored to different data distributions has become a critical factor in overcoming performance bottlenecks in sequence prediction tasks. More specifically, the neural architecture of RNN is optimized by differentiable architecture search (DARTS), known as an effective NAS method. In this way, RNN has better ability of forecasting disturbances caused by uncertainties within the complex system. Then, we design a robust model predictive controller (RMPC) in the dual-predictor controller framework, and uses linear inequality matrices to ensure the precise planning under uncertain conditions, which further enhances the stability of the optimized control strategy. Simulation results under various scenarios demonstrate that the proposed optimal control strategy is notably effective in reducing energy hub costs.

关键词： Dual-predictor control Energy hub Energy consumption costs neural network architecture search

来源：评论

学校读者我要写书评

暂无评论

Automatic High-Performance neural network Construction for Channel Estimation in IRS-Aided Communications

引用

IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS 2024年第9期23卷 10667-10682页

作者： Shi, Haoqing Huang, Yongming Jin, Shi Wang, Zheng Yang, Luxi Southeast Univ Sch Informat Sci & Engn Nanjing 210096 Peoples R China Southeast Univ Natl Mobile Commun Res Lab Nanjing 210096 Peoples R China Purple Mt Labs Pervas Commun Ctr Nanjing 211111 Peoples R China

Accurate channel estimation is an essential prerequisite for achieving significant performance gains in intelligent reflecting surface (IRS)-aided communication systems. Recent studies have shown that deep neural network-based channel estimation holds promise as a competitive alternative to conventional methods. However, existing neural network-based approaches typically involve manual design of network architectures through a trial-and-error process, demanding extensive domain knowledge and human resources. In this paper, we propose an automatic approach to construct a high-performance neural network architecture for channel estimation. Our method, called the channel estimation neural network architecture search (CENAS), utilizes a truncated back-propagation optimization search strategy to explore a neural network tailored for channel estimation. By carefully designing a search space tailored to channel estimation tasks, the automatically constructed network surpasses both conventional and deep learning-based channel estimation algorithms. The convergence of our framework's network construction process is comprehensively analyzed, providing formal evidence of its convergence properties. Additionally, the proposed framework exhibits good generalization and applicability by allowing flexible adjustment of hyperparameters to generate networks with varying scales. Empirical results show the stability and the improved performance of CENAS framework, validating its effectiveness and desirability.

关键词： Channel estimation neural networks Wireless communication Optimization Estimation Task analysis MISO communication Intelligent reflecting surface channel estimation neural network architecture search deep learning

来源：评论

学校读者我要写书评

暂无评论

U-DARTS: Uniform-space differentiable architecture search

引用

INFORMATION SCIENCES 2023年第1期628卷 339-349页

作者： Huang, Lan Sun, Shiqi Zeng, Jia Wang, Wencong Pang, Wei Wang, Kangping Jilin Univ Coll Comp Sci & Technol Changchun Peoples R China Jilin Univ Key Lab Symbol Computat & Knowledge Engn Minist Educ Changchun Peoples R China Heriot Watt Univ Sch Math & Comp Sci Edinburgh Scotland

Differentiable architecture search (DARTS) is an effective neural architecture search algorithm based on gradient descent. However, there are two limitations in DARTS. First, a small proxy search space is exploited due to memory and computational resource constraints. Second, too many simple operations are preferred, which leads to the network deterioration. In this paper, we propose a uniform-space differentiable architecture search, named U-DARTS, to address the above problems. In one hand, the search space is redesigned to enable the search and evaluation of the architectures in the same space, and the new search space couples with a sampling and parameter sharing strategy to reduce resource overheads. This means that various cell structures are explored directly rather than cells with same structure are stacked to compose the network. In another hand, a regularization method, which takes the depth and the complexity of the operations into account, is proposed to prevent network deterioration. Our experiments show that U-DARTS is able to find excellent architectures. Specifically, we achieve an error rate of 2.59% with 3.3M parameters on CIFAR-10. The code is released in https://github .com /Sun -Shiqi /U -DARTS.

关键词： Automatic machine learning Deep learning neural network architecture search Image recognition

来源：评论

学校读者我要写书评

暂无评论

EAS-CNN: automatic design of convolutional neural network for remote sensing images semantic segmentation

引用

INTERNATIONAL JOURNAL OF REMOTE SENSING 2023年第13期44卷 3911-3938页

作者： Zhou, Han Yang, Jianyu Zhang, Tingting Dai, Anjin Wu, Chunxiao China Agr Univ Coll Land Sci & Technol Beijing Peoples R China China Agr Univ Coll Land Sci & Technol Yuanmingyuan West Rd 2 Beijing 100193 Peoples R China

Accurate and effective semantic segmentation methods for remote sensing are important for applications such as precision agriculture, urban planning, and disaster monitoring. Convolutional neural networks (CNN) have achieved remarkable performance in the field of remote sensing semantic segmentation. However, the design of CNNs is both time-consuming and necessitates a substantial amount of domain expertise and experience. To address the aforementioned issues, we propose a neural architecture search method called EAS-CNN. The method constructs a search space based on a U-shaped structure and utilizes a fixed-length encoding solution based on gene expression suppression to preserve potential useful information during the evolution process. Furthermore, an improved genetic strategy is proposed to enhance search efficiency and save computational resources. In this paper, we evaluate the proposed EAS-CNN method against state-of-the-art semantic segmentation methods and verify its effectiveness. Experimental results show that EAS-CNN achieves high OA values of 91.2% and 91.6% on the Vaihingen and Postman datasets, respectively. Furthermore, we conduct a thorough analysis of the experimental results and summarize effective design patterns for model architecture to enhance remote sensing semantic segmentation tasks.

关键词： Remote sensing semantic segmentation neural network architecture search convolutional neural network >

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：