检索结果-内蒙古大学图书馆

Chinese automation Congress (CAC)

作者： Yuan Huang Chi Xu Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education School of Automation China University of Geosciences Wuhan China

ISBN: (数字)9798350368604

ISBN: (纸本)9798350368611

Recent advancements in Novel View Synthesis using neural radiance fields and 3D Gaussian splatting have demon-strated promising results. However, these methods conventionally rely on accurate initial poses and point clouds from the model of structure from motion, which poses challenges in sparse input views. To addressing these drawbacks, we introduces an novel method for view synthesis based on 3D Gaussian splatting. Our approach operates on sparse input views without the prerequisite of pose priors, achieving reconstruction and real-time rendering of novel perspectives. For the deficiency of camera poses and point cloud, we employ an end- to-end deep learning model to recover the 3D structure from a few of 2D images to initialize the 3D Gaussian point cloud. In addressing the issue with few-shot, we utilize the differentiable rasterization module to render depth map and apply regulation on it. Additionally, we incorporate supervision between input views by interpolating to generate novel perspectives during training. Experimental results demonstrate that our proposed method significantly enhances the capabilities of 3D Gaussian splatting for novel view synthesis in sparse views and without the necessity of camera pose priors.

关键词： Point cloud compression Training Solid modeling Three-dimensional displays Structure from motion Cameras Rendering (computer graphics) Regulation Real-time systems Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Tracking performance limitations of MIMO discrete-time networked control systems with multiple constraints

引用

Science China(Information Sciences) 2023年第8期66卷 267-268页

作者： Xiaowei JIANG Bin ZHANG Xiangyong CHEN Huaicheng YAN School of Automation China University of Geosciences Key Laboratory of Industrial Internet of Things & Networked Control Ministry of Education Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education School of Automation and Electrical Engineering Linyi University Key Laboratory of Smart Manufacturing in Energy Chemical Process of the Ministry of Education

Dear editor,Networked control systems(NCSs) have attracted widespread attention in some fields because they offer the advantages of reduced cabling, greater resource sharing,and ease of installation and maintenance [1]. However, in an unreliable network environment, network constraints can significantly limit the performance of NCSs.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Weighting Factors Autotuning Strategy for Model Predictive Torque control of Permanent Magnet Synchronous Motor Based on Adaptive Multi-objective Black Hole Algorithm

A Weighting Factors Autotuning Strategy for Model Predictive...

引用

第42届中国控制会议

作者： Zixiang Zhou Tao Wu School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems System Integration and Industrial Robotics Laboratory

The rational design of weighting factors in the cost function for finite control set model predictive torque control(FCS-MPTC) has been a matter of great interest in power electronics and electrical drives. In order to solve this problem, a weighting factors autotuning strategy for FCS-MPTC of permanent magnet synchronous motor(PMSM) based on the adaptive multi-objective black hole algorithm(AMOBH) is proposed. In this paper, the design process of the FCS-MPTC algorithm is first analyzed in detail. Then, an AMOBH algorithm that can take into account both population convergence and population diversity is introduced, and based on this algorithm, the design problem of the weighting factors is successfully transformed into a multiobjective optimization problem by means of reconstructing the cost function and designing the motor operation information collected in real time as the objective functions of the multi-objective optimization algorithm. Simulation results show that the proposed method can find a set of weighting factor combinations suitable for different working condition requirements, and these weighting factors can effectively improve the operation performance of the PMSM system.

关键词： Model Predictive Torque control Weighting Factors Multi-objective Optimization Algorithm Permanent Magnet Synchronous Motor

来源：评论

学校读者我要写书评

暂无评论

Frequency Domain-Based Low-Rank Approximation for Magnetic Anomaly Detection

Frequency Domain-Based Low-Rank Approximation for Magnetic A...

引用

Sensing, Measurement & Data Analytics in the era of Artificial Intelligence (ICSMD), International Conference on

作者： Yumeng Lv Congyu Liao Huan Liu Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems School of Automation China University of Geosciences Wuhan China Department of Radiology Stanford University CA USA

ISBN: (数字)9798331529192

ISBN: (纸本)9798331529208

Current magnetic anomaly detection (MAD) methods prioritize signal-to-noise ratio (SNR) over signal features and edge information, leading to signal distortion. To address this issue, a new MAD approach utilizes structured lowrank approximation and block singular value decomposition based on the spatial frequency domain, dubbed FL-BSVD is proposed. First, the low-rankness structure of the magnetic anomaly signal is obtained through 2D Discrete Fourier Transform (2D-DFT) and structured Hankel transformation. Then, block singular value decomposition is applied to the Hankel matrix to reduce noise while preserving more signal edge features and enhancing detection accuracy. Finally, a field experiment comparing FL-BSVD with four commonly used methods is conducted. The experiment confirms that FL-BSVD can effectively recover magnetic anomaly signal features and edge information in a strong noisy environment.

关键词： Image edge detection Frequency-domain analysis Noise reduction Magnetic domains Feature extraction Noise measurement Magnetic anomaly detection Signal to noise ratio Singular value decomposition Periodic structures

来源：评论

学校读者我要写书评

暂无评论

Temperature Rising Model of Tubular Permanent Magnet Linear Synchronous Motor Based on Transfer Learning-Deep Neural Network

Temperature Rising Model of Tubular Permanent Magnet Linear ...

引用

第42届中国控制会议

作者： YiFei Wang Tao Wu School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems System Integration and Industrial Robotics Laboratory

High temperature rise of permanent magnet linear synchronous motor can lead to irreversible demagnetization of the motor permanent magnet, which can negatively affect the motor performance. To address this problem, a thermal modeling analysis method based on Transfer learning-Deep neural network(TL-DNN) was proposed in this paper. Its specific implementation steps include(1) corresponding to different heat source inputs, the equivalent thermal circuit method and the finite element analysis was adopted based on the structure and main parameters of PMLSM including overall average temperature rise, coil temperature rise and permanent magnet temperature rise from the data sets of the motor;(2) TL-DNN was used to fit the functional relationship between the input source features and the output targets based on the characteristics of the sample data sets. In order to verify the accuracy of the prediction model with small sample data sets, this paper divided the proportion of the data set and compared the results with other classic nonparametric models(random forest, support vector machine, and deep neural network). The results show that the TL-DNN model outperforms other machine learning models and has better robustness and generalization ability when the training datasets are insufficient, and achieves an organic combination of physical field path model and data-driven model, which provides a feasible solution for PMLSM modeling in the case of small samples.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Efficient Facial Expression Recognition Network Based on Spot-Adaptive Knowledge Distillation 26

Efficient Facial Expression Recognition Network Based on Spo...

引用

26th International Conference on Industrial Technology, ICIT 2025

作者： Wen, Xin Liu, Zhen-Tao Chen, Dan School of Automation China University of Geosciences Wuhan430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education China

ISBN: (纸本)9798331521950

Facial expression recognition plays a key role in promoting the development of comprehensive intelligence and building friendly human-computer interaction. Due to the interference of feature noise in expression data, the lightweight facial expression recognition model with fewer parameters is difficult to learn more expression features through simple training, which limits the improvement of its recognition performance. An efficient facial expression recognition network based on Spot-adaptive Knowledge Distillation is proposed in this paper. Inspired by VoVNetV2, the network designed in this paper is lightweightly improved using Depthwise Separable Convolution and the parameter-free SimAM attention mechanism, reducing the number of parameters to 0.21 M. To further improve the recognition accuracy of the model, Spot-adaptive Knowledge Distillation is employed to improve the characterization ability of the model. The recognition accuracies of the student network designed in this paper on the KDEF and RAF-DB datasets are 93.05% and 81.17% respectively after spot-adaptive distillation. © 2025 IEEE.

关键词： Facial Expression Recognition Knowledge Distillation Lightweight Neural Network

来源：评论

学校读者我要写书评

暂无评论

Semantic Segmentation of Indoor Point Clouds with the Channel Attention Mechanism

Semantic Segmentation of Indoor Point Clouds with the Channe...

引用

2022 Chinese automation Congress, CAC 2022

作者： Liu, Wei Lu, Yisheng Zhang, Tao Chen, Jun School of Automation China University of Geosciences Wuhan430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China Engineering Research Center of Intelligent Technology for Geoexploration Ministry of Education Wuhan430074 China

ISBN: (纸本)9781665465335

In recent years, the semantic segmentation of 3D point cloud has received increasing attention the field of computer vision, because 3D point cloud can better reflect our 3D space. Because of the unstructured and disordered characteristics of 3D point cloud data, semantic segmentation of point cloud is still a difficult task. Our network automatically learns the importance of feature channels by adding a channel attention module, which enables the network to obtain better training results. After the channel attention module is fused, the important channels in the features are enhanced, and the unimportant channels are suppressed, making the network training more efficient. In this paper, we propose an indoor point cloud semantic segmentation method combined with channel attention mechanism. The experimental results show that our method achieves better results than other methods. © 2022 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Estimation of Bottom-Hole Pressure Based on Bayesian Optimization and Bidirectional Long Short-Term Memory Neural Network 43

Estimation of Bottom-Hole Pressure Based on Bayesian Optimiz...

引用

43rd Chinese control Conference, CCC 2024

作者： Zhang, Zihan Lu, Chengda Wang, Yawu Zhou, Yang Wu, Min She, Jinhua China University of Geosciences School of Future Technology Wuhan430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China Ministry of Education Engineering Research Center of Intelligent Technology for Geo-Exploration Wuhan430074 China China University of Geosciences School of Automation Wuhan430074 China Tokyo University of Technology School of Engineering Hachioji192-0982 Japan

ISBN: (纸本)9789887581581

Bottom-hole pressure (BHP) plays a crucial role in a drilling process. The accurate estimation of BHP ensures safe and efficient drilling operations. Artificial neural networks can predict BHP indirectly by analyzing the non-linear relationship with wellhead variables. This paper introduces a BHP estimation model that leverages Bayesian optimization and a bidirectional long short-term memory neural network (BO-BiLSTM). The model employs Bayesian optimization to determine optimal hyperparameters, including the number of hidden layers, initial learning rate, and L2 regularization parameter. The BO-BiLSTM model achieves a mean absolute percentage error of 2.056% and an R-squared score of 0.94596. The results demonstrate that the presented model enhances estimation precision and outperforms other methods examined in this study. This method facilitates indirect measurement of BHP using wellhead data, and contributes to the exploration of deep-sea resources in complex environments. © 2024 Technical Committee on control Theory, Chinese Association of automation.

关键词： Bottom hole pressure

来源：评论

学校读者我要写书评

暂无评论

Blast Furnace Gas Utilization Rate Prediction Model based on Northern Goshawk Optimization and Long Short-Term Memory in Massive Data Set

Blast Furnace Gas Utilization Rate Prediction Model based on...

引用

Industrial Cyber-Physical Systems (ICPS)

作者： Yue Zhou Weihua Cao Zhuofu Zhang Yan Yuan School of Automation China University of Geosciences Wuhan China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan China

Affected by the global New Crown Pneumonia epidemic, energy prices in the global market continue to rise. The high quality production and energy saving of steel companies have become an important task. The blast furnace is the front-end core of the steel manufacturing process. The blast furnace gas utilization rate can effectively characterize the internal airflow distribution, blast furnace operation and energy consumption level of the blast furnace. The blast furnace Gas Utilization Rate (GUR) can effectively characterize the internal airflow distribution, blast furnace operation and energy consumption level. Most of the existing studies are based on data-driven models. The shallow neural network model is selected. But blast furnace iron making has complex uncertainty. Massive data samples under industrial information technology need to be processed. The robustness and generalization ability of the prediction model are not satisfactory. To address the above problems, this paper proposes a prediction model based on NGO-LSTM regression. The model parameter searchs can be intelligently. It achieves high-precision prediction results for massive data samples. Firstly, the selection of feature parameters is completed by maximal information coefficient. Secondly, the strong coupling of blast furnace ground needs to fully predict the relationship between the characteristic parameters. The Long Short-Term Memory (LSTM) neural network with certain memory capability is selected. And multiple parameters of this neural network model are optimized by the Northern Goshawk Optimization (NGO) algorithm. An NGO-LSTM regression prediction model is established. In this paper, experiments are carried out using actual production data. The experimental results show that the proposed method can accurately predict the blast furnace gas utilization rate. This can provide a reference for improving blast furnace product quality, reducing costs and increasing efficiency.

关键词： Energy consumption Neural networks Production Predictive models Blast furnaces Prediction algorithms Robustness

来源：评论

学校读者我要写书评

暂无评论

A distributed high-density resistivity meter working on a two-wire cable 3

A distributed high-density resistivity meter working on a tw...

引用

2020 3rd International Symposium on Power Electronics and control Engineering, ISPECE 2020

作者： Dong, Xiquan Luo, Wang Wang, Hongpeng Ge, Jian Liu, Huan Dong, Haobin School of Automation China University of Geosciences Wuhan Hubei430074 China Hubei Key Laboratory of Advance Control and Intelligent Automation for Complex Systems Wuhan Hubei430074 China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan Hubei430074 China

High-density resistivity meter is a common instrument used in shallow geophysical exploration. At present, the structure of the centralized high-density resistivity meter is bulky, while the distributed instrument needs more than 7 core cables, and the long measuring line needs to relay power supply to the intelligent electrode to provide enough voltage, so it is not convenient to use in the field. Aiming at the above problems, a new type of distributed high-density meter is developed, which can realize the power supply, communication, and measurement functions of distributed high-density meter and carry out multi-channel measurement through the time-division multiplexing of a two-wire cable and the short-time power supply of supercapacitor. Finally, the performance of the instrument was verified by experiments. © Published under licence by IOP Publishing Ltd.

关键词： Cables

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：