检索结果-内蒙古大学图书馆

2023 IEEE International Conference on Industrial technology, ICIT 2023

作者： Huo, Mingyi Qiao, Xinyu Wang, Hao Jiang, Yuchen Luo, Hao Harbin Institute of Technology Department of Control Science and Engineering Harbin China

ISBN: (纸本)9798350336504

Health status of components of equipments in intelligent control systems affects the operation of systems and the quality of products. In the process of monitoring intelligent control systems, signal frequency analysis is often used to determine whether the equipment is faulty. Therefore, it is crucial to estimate the frequency of the operating signals effectively. Considering the disturbance and noise, a time-domain robust frequency estimation approach is proposed in this paper. Different from the frequency-domain methods, the proposed approach can estimate the frequencies of signal by constructing the subspace of disturbance and using the eigenvalue identification, which avoids the spectral leakage problem caused by the traditional frequency-domain method and has the advantage of simple calculation. Furthermore, the proposed approach can also reconstruct the original signal through the oblique projection. Finally, the effectiveness and feasibility of the approach are verified, which has a certain reference value. © 2023 IEEE.

关键词： Frequency estimation

来源：评论

学校读者我要写书评

暂无评论

Data Synthesizing for Specific Human Action Segmentation

Data Synthesizing for Specific Human Action Segmentation

引用

2023 IEEE International Conference on Industrial technology, ICIT 2023

作者： Lin, Xiaotian Xu, Leiyang Wang, Qiang Harbin Institute of Technology Department of Control Science and Engineering Harbin China

ISBN: (纸本)9798350336504

Temporal action segmentation has been one of the most challenging tasks in human activity analysis because it involves segmenting and recognizing actions in long action sequences, which requires a higher-level understanding of human activities. Many deep learning models have emerged and achieved excellent performance in action segmentation tasks. However, these models often require a large amount of labeled data for training. Generally, public datasets can help train models. But collecting and labeling sufficient training data can be costly for some specific actions that do not exist in public datasets. Therefore, we propose a framework for specific human action segmentation using data augmentation. Specifically, given a few labeled action sequences, we first segment them into short-trimmed action segments by label and then use a motion blending method to randomly combine these action segments representing different categories to form many new labeled action sequences. In this way, we can build a synthetic action dataset for the specific action, which provides enough data for training large-scale models. Our experimental results show that SOTA skeleton-based action segmentation models work well with our synthetic action dataset, and data augmentation can also improve the performance of these models. © 2023 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Backup control of Vehicle Braking System based on Electronic Parking Brake Actuator 7

Backup Control of Vehicle Braking System based on Electronic...

引用

7th CAA International Conference on Vehicular control and Intelligence, CVCI 2023

作者： Houhua, Jing Shihao, Liu Qinggan, Lin Yihang, Guan Department of Control Science and Engineering Harbin Institute of Technology Harbin China

ISBN: (纸本)9798350340488

With the impact of electrification and intelligentization of automotive chassis, the brake by wire system has gradually become mainst.eam, and reliable backup braking control has also become an important component in the development of autonomous driving technology. This paper studies the backup braking control method based on the electronic parking brake actuator. Firstly, the structure and working principle of the electronic parking brake system are analyzed, and a system model is established to reveal the correlation between the braking clamping force and motor current and position. Then, a closed-loop control method based on current and position is proposed for backup braking control. Finally, experimental verification of the backup braking control performance is conducted on a physical test bench, and the robustness under voltage disturbances is tested to verify the feasibility of the backup braking solution. © 2023 IEEE.

关键词： Backup braking Clamping force control Current closed-loop control Position closed-loop control

来源：评论

学校读者我要写书评

暂无评论

An Improved Rail Crack Classification Method Based on Wavelet Multi-Resolution Analysis and Signal Separability

An Improved Rail Crack Classification Method Based on Wavele...

引用

2023 China Automation Congress, CAC 2023

作者： Cui, Jiazhong Shen, Yi Zhang, Xin Chang, Yongqi Song, Shuzhi Song, Qinghua Harbin Institute of Technology Department of Control Science and Engineering Harbin China

ISBN: (纸本)9798350303759

Rail crack is a serious threat to the safety of train operations. Accurately classifying various types of rail crack is a crucial aspect in preventing potential accidents. To address this challenge, this paper proposes an improved rail crack classification method based on wavelet multi-resolution analysis (WMRA) and signal separability. By using electromagnetic acoustic emission (EMAE) technique, crack-related acoustic emission (AE) signals are generated, which are then decomposed into sub-signals using WMRA. Subsequently, the best feature set (BFS) is obtained from each sub-signal based on the constructed feature separability index (ST). The signal separability index (SSI) is constructed to evaluate the information quantity of each sub-signal for subsequent signal analysis. Finally, by leveraging the BFS and the most informative sub-signal, crack classification is performed. Comparative analysis with conventional approaches reveals a remarkable enhancement in the accuracy of rail crack classification, specifically within a reduced feature dimension. Noteworthy, this method demonstrates the frequency band concentration effect of EMAE, thereby providing valuable insights for further research in the field of rail crack classification. © 2023 IEEE.

关键词： Acoustic emissions

来源：评论

学校读者我要写书评

暂无评论

Using Image Pre-Processing to Improve Navigation Line Extraction Based on Pix2Pix Net on Small-size Datasets

Using Image Pre-Processing to Improve Navigation Line Extrac...

引用

2023 IEEE International Conference on Industrial technology, ICIT 2023

作者： Zheng, Hao Wang, Qiang Harbin Institute of Technology Department of Control Science and Engineering Harbin China

ISBN: (纸本)9798350336504

Autonomous navigation of the machine in the farm is an essential part of an automatic farm. GNSS(Global Navigation Satellite System) is an effective navigation technology, but it lacks sufficient precision in agricultural applications and is limited in price and range of use. Traditional image processing is difficult to deal with the changeable outside environment. Deep neural networks are becoming more effective for navigation, but it is time-consuming work to produce datasets and train. In this paper, we proposed a navigation line extraction method for agriculture based on Pix2Pix net with image pre-processing. We first separated the crops from the background to remove useless information. Then the binary image would go through the Pix2Pix net that would draw a red line following the crop row near the middle of the image. After that, we extracted the red line and used the least square to calculate the angle to guide the robot along the crops. The experiments indicated that image pre-processing could decline useless data in the picture, leading to a better neural network performance in navigation line extraction. At the same time, data optimization could reduce the requirements of neural network datasets, and make the model more adaptable to similar environments. © 2023 IEEE.

关键词： Crops

来源：评论

学校读者我要写书评

暂无评论

Int&Int: A Two-Pathway Network for Skeleton-Based Action Recognition 18

Int&Int: A Two-Pathway Network for Skeleton-Based Action Rec...

引用

18th IEEE Conference on Industrial Electronics and Applications, ICIEA 2023

作者： Qi, Xiangyuan He, Zhen Wang, Qiang Harbin Institute of Technology Department of Control Science and Engineering Harbin China

ISBN: (纸本)9798350312201

Human action recognition has recently attracted a lot of researchers, while most of them mainly focus on the local dynamics or global information alone and cannot focus on both the intensity and the integrity of the action. In this work, we propose a two-pathway Int&Int network(Intensity&Integrity) for skeleton-based action recognition to satisfy both aspects, where the great complementarity between the two pathways further enhances the performance. Besides, for Integrity pathway, we apply the uniform sampling strategy. For Intensity pathway, we introduce the intensity-dependent sampling, where a clip composed of consecutive frames around the frame with the largest motion intensity is sampled. Moreover, we explain various definitions of the motion intensity containing different semantic information based on the extracted 2D human poses. For each pathway, the poses are represented by a 3D heatmap volume and 3D-CNNs of both pathways have the same architecture. Late fusion is used to ensemble them. The model is evaluated on two action recognition datasets, FineGYM-99 and HMDB-51, and it achieves superior performance on both of them. The code has been shown at https://***/SarahQi666/Int-and-Int. © 2023 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

A Finite-time Distributed Cooperative control Approach for Microgrids

引用

CSEE Journal of Power and Energy Systems 2022年第4期8卷 1194-1206页

作者： Jiancheng Zhang Xinsheng Wang Lingyu Ma Department of Control Science and Engineering Harbin Institute of TechnologyHarbin 150006China Department of Information Engineering Shandong Management UniversityJinan 250100China

Reactive power sharing cannot be achieved using many existing microgrid(MG)control methods,but the convergence speed of these methods is *** solve these problems,a finite-time distributed control approach is proposed in this paper,which is based on the hierarchical control *** hierarchical control structure consists of a dual loop control,a droop control used as a primary control and a secondary ***,the secondary controller is modeled,and the MG system composed of distributed generators(DGs)is considered as a multi-agent *** secondary controller consists of a frequency regulator,voltage regulator and power ***,the adaptive virtual impedance module is established,using the output of the reactive power regulator as its ***,a dual loop controller is combined with a primary controller and secondary controller to generate a pulse width modulation(PWM)signal to control the power and voltage of the *** order to reduce the fluctuation of the MG,a damping module is introduced when the structure of the system ***,the stability of the proposed control strategy is proved by the related theorems.A simulation system is established in the Matlab environment,and the simulation results show that the proposed method is effective.

关键词： Consensus droop control finite-time microgrid power sharing virtual impedance

来源：评论

学校读者我要写书评

暂无评论

A dual-path inst.nce segmentation network based on nuclei contour in histology image

引用

Discover Artificial Intelligence 2023年第1期3卷 1-14页

作者： Li, Jiangqi Li, Xiang Li, Minglei Yan, Pengfei College of Mathematical Sciences BoHai University JinZhou121000 China Department of Control Science and Engineering Harbin Institute of Technology Harbin150001 China

Accurate segmentation of nuclei in histology images is essential for digital pathology. However, previous work should have considered integrating nuclei contour information into network learning. The main problems are (1) nuclei contour information needs to be fully considered, resulting in inaccurate spatial location of nuclei. (2) Small nuclei in dense regions or irregularly shaped nuclei cannot be segmented. (3) Mainst.eam networks consider more long-distance semantic information and larger receptive fields and do not consider the fusion of feature maps with different semantics. To solve the above problems, we have proposed a contour-based dual-path inst.nce segmentation network. Firstly we reconstructed the nuclei contour information using algorithms and morphological manipulations. Provide input for subsequent contouring networks. Then we designed a dual-path network. It can extract nuclei features and contour features independently in the encoding stage and fuse the feature maps at different scales in the decoding stage. In the decoding stage, we use the attention module with a newly designed fusion mechanism, which allows us to fuse different semantics of feature maps for simple and efficient fusion. Finally, using the watershed algorithm, we use the network segmentation results to get the inst.nce segmentation results of the nuclei. We used four publicly available datasets, including Kumar, CPM-15, CPM-17, and TNBC, which contain the nuclei of many organs and different forms of nuclei in the human body. Compared with the mainst.eam methods, we obtained the best AJI metrics, which are 0.656,0.717, and 0.602. In conclocess can effectively improve the performance of the nuclei inst.nce segmentation network. It can accurately locate the scattered nuclei in space with small segmented nuclei in dense regions. © The Author(s) 2023.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Synchronous control of H-type Linear Motor System via Super-Twisting Sliding Mode

Synchronous Control of H-type Linear Motor System via Super-...

引用

2024 China Automation Congress, CAC 2024

作者： Liu, Jiawei Li, Xiaolei Tang, Feilong Kui, Qixin Spasic, Miodrag D. Department of Control Science and Engineering Harbin Institute of Technology Harbin China Department of Control Systems Faculty of Electronic Engineering University of Nis Nis Serbia

ISBN: (纸本)9798350368604

In this paper, a synchronous control strategy based on super-twisting sliding mode algorithm is proposed to enhance the tracking accuracy and robustness of H-type linear motor systems. Such systems are widely utilized in precision manufacturing owing to their high precision and fast response. Firstly, the dynamic model is established based on the coupling dynamics analysis of the H-type system. Secondly, a super-twisting sliding mode controller (STSMC) with linear terms is designed, which effectively reduces the chattering associated with conventional sliding mode control, while maintaining good robustness. Thirdly, a super-twisting extended state observer (STESO) is introduced to handle large fluctuations in the early estimation process of linear extended state observer (LESO), so as to effectively observe and compensate the uncertainties and external disturbances. Finally, experimental results demonstrate that the STESO-based STSMC greatly improves the anti-disturbance ability and tracking accuracy of the H-type system. © 2024 IEEE.

关键词： Sliding mode control

来源：评论

学校读者我要写书评

暂无评论

Adversarial Training with Maximal Coding Rate Reduction 58

Adversarial Training with Maximal Coding Rate Reduction

引用

58th Asilomar Conference on Signals, Systems and Computers, ACSSC 2024

作者： Chu, Hsiang-Yu Zhao, Hongbo Flierl, Markus Kth Royal Institute of Technology Stockholm Sweden Harbin Institute of Technology Department of Control Science and Engineering Harbin China

ISBN: (纸本)9798350354058

Deep convolutional networks can solve various complex tasks in the field of image processing. However, adversarial attacks have been shown to have the ability of fooling deep learning models. Adversarial training is one commonly used strategy to improve the robustness of deep learning models against.adversarial examples, which is performed by incorporating adversarial examples into the training process. Traditionally, during this process, cross-entropy loss is used as the loss function. In order to improve the robustness of deep learning models against.adversarial examples, we propose in this paper two new methods of adversarial training by applying the principle of Maximal Coding Rate Reduction (MCR2). We evaluate the performance of different adversarial training methods by comparing the clean accuracy and adversarial accuracy. It is shown that adversarial training with the MCR2 loss function yields a more robust network than the traditional adversarial training method. In our experiments, adversarial accuracies are improved by up to 10%. The two loss functions are discussed by using a model. © 2024 IEEE.

关键词： Adversarial machine learning

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：