检索结果-内蒙古大学图书馆

IEEE Instrumentation and Measurement technology Conference

作者： Ningyuan Wang Qiang Wang Qimin Zhang Jiulong Xie Department of Control Science and Engineering Harbin Institute of Technology Harbin China

In adaptive grinding tasks, robotic arms are required to autonomously accomplish uniform grinding of work-pieces with unknown sizes and arbitrary surface characteristics. This brings a great challenge to planning and control of robotic arms. In order to achieve adaptive grinding in terms of grinding path and grinding degree, an offline-online planning framework incorporating shortest grinding path offline generation and contact force online control is proposed in this paper. Under the case that workpiece size is unknown and the distribution of points to be ground is arbitrary, the shortest grinding path is generated adaptively by size estimation and Double-layer Ant Colony System(DACS) based optimal sorting algorithm. Grinding degree planning and contact force control are applied to adaptively adjust grinding degree. In order to more sufficiently utilize computational resources to minimize grinding path length, DACS is designed and applied in optimal sorting algorithm to make the latter gradually improve its optimization capability by self-optimization. Experiment results demonstrate the capability of the proposed planning framework to achieve adaptive grinding in terms of grinding path and grinding degree as well as the self-optimization capability of DACS-based optimal sorting algorithm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Adaptive Planning of Optimal Grinding Path based on Improved MAX-MIN Ant System

Adaptive Planning of Optimal Grinding Path based on Improved...

引用

Chinese control and Decision Conference, CCDC

作者： Ningyuan Wang Qiang Wang Department of Control Science and Engineering Harbin Institute of Technology Harbin China

In grinding tasks of robotic arms, grinding efficiency is a very important factor. In this paper, an efficient grinding path planning is proposed to improve grinding efficiency by adaptively shortening grinding path as much as possible for workpieces with unknown sizes and arbitrary surface characteristics. First, the size of workpiece is calculated based on information of all points to be ground, and the length of the shortest path along the surface of workpiece between arbitrary two points is obtained based on workpiece size. Second, MAX-MIN Ant System (MMAS) is improved through modifications of pheromone concentration update mechanism as well as the adding of pheromone concentration disturbance to enhance its efficiency and optimization capability, and improved-MMAS is applied in optimal sorting algorithm to adaptively generate the shortest grinding path on the workpiece with arbitrary surface characteristics. Experiment results validate that the proposed grinding path planning can adaptively generate the shortest grinding path on workpieces with unknown sizes and arbitrary surface characteristics.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MAD: Meta Adversarial Defense Benchmark

arXiv

引用

arXiv 2023年

作者： Peng, Xiaoxu Zhou, Dong Sun, Guanghui Shi, Jiaqi Wu, Ligang The Department of Control Science and Engineering Harbin Institute of Technology Harbin China

Adversarial training (AT) is a prominent technique employed by deep learning models to defend against adversarial attacks, and to some extent, enhance model robustness. However, there are three main drawbacks of the existing AT-based defense methods: expensive computational cost, low generalization ability, and the dilemma between the original model and the defense model. To this end, we propose a novel benchmark called meta adversarial defense (MAD). The MAD benchmark consists of two MAD datasets, along with a MAD evaluation protocol. The two large-scale MAD datasets were generated through experiments using 30 kinds of attacks on MNIST and CIFAR-10 datasets. In addition, we introduce a meta-learning based adversarial training (Meta-AT) algorithm as the baseline, which features high robustness to unseen adversarial attacks through few-shot learning. Experimental results demonstrate the effectiveness of our Meta-AT algorithm compared to the state-of-the-art methods. Furthermore, the model after Meta-AT maintains a relatively high clean-samples classification accuracy (CCA). It is worth noting that Meta-AT addresses all three aforementioned limitations, leading to substantial improvements. This benchmark ultimately achieved breakthroughs in investigating the transferability of adversarial defense methods to new attacks and the ability to learn from a limited number of adversarial examples. Our codes and attacked datasets address will be available at https://***/PXX1110/Meta_AT. Copyright © 2023, The Authors. All rights reserved.

关键词： Large dataset

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

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

引用

Conference on Vehicle control and Intelligence (CVCI)

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

With the impact of electrification and intelligentization of automotive chassis, the brake by wire system has gradually become mainstream, 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.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MMDR: A Result Feature Fusion Object Detection Approach for Autonomous System

arXiv

引用

arXiv 2023年

作者： Zhang, Wendong Department of Control Science and Engineering Harbin Institute of Technology Harbin China

Object detection has been extensively utilized in autonomous systems in recent years, encompassing both 2D and 3D object detection. Recent research in this field has primarily centered around multimodal approaches for addressing this issue. In this paper, a multimodal fusion approach based on result feature-level fusion is proposed. This method utilizes the outcome features generated from single modality sources, and fuses them for downstream tasks. Based on this method, a new post-fusing network is proposed for multimodal object detection, which leverages the single modality outcomes as features. The proposed approach, called Multi-Modal Detector based on Result features (MMDR), is designed to work for both 2D and 3D object detection tasks. Compared to previous multimodal models, the proposed approach in this paper performs feature fusion at a later stage, enabling better representation of the deep-level features of single modality sources. Additionally, the MMDR model incorporates shallow global features during the feature fusion stage, endowing the model with the ability to perceive background information and the overall input, thereby avoiding issues such as missed detections. Copyright © 2023, The Authors. All rights reserved.

关键词： Object detection

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

Chinese Automation Congress (CAC)

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

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.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Variable Frequency Phase-Shift Modulation Technique for Single Stage Dual-Active-Bridge AC-DC Converter 11

Variable Frequency Phase-Shift Modulation Technique for Sing...

引用

11th International Conference on Power Electronics - ECCE Asia, ICPE 2023-ECCE Asia

作者： Guo, Dongxin Wang, Panbao Ren, Chunguang Guerrero, Josep M. Harbin Institute of Technology School of Electrical Engineering and Automation Harbin China Taiyuan University of Technology Shanxi Key Lab. of Power System Operation and Control Taiyuan China Aalborg University Department of Energy Technology Aalborg Denmark

ISBN: (纸本)9788957083505

This article proposes a variable frequency phase-shift modulation technique for single stage dual-active-bridge (DAB) AC-DC converter. This isolated single-stage single-phase converter consists of a DAB and a full bridge (FB) inverter. The proposed strategy applies a composite control strategy combining frequency modulation and extended phase shift (EPS) method to overcome the drawback of the non-linear power control of traditional phase-shift control scheme, which significantly reduces the complexity of the controller algorithm. Moreover, the synchronous inverter control applied to the back-end FB inverter is designed, which can realize the energy conversions in a single-stage, and a high frequency (HF) filter capacitor can replace the electrolytic capacitor at the output side DC-link. Thus, the safety of system operation improves and the power density of the system increases. Finally, simulation results confirm the validity and practical feasibility of the proposed control strategy. © 2023 The Korean institute of Power Electronics.

关键词： Electrolytic capacitors

来源：评论

学校读者我要写书评

暂无评论

A Subspace-aided Fault Diagnosis Approach for Electrical Drive Systems

A Subspace-aided Fault Diagnosis Approach for Electrical Dri...

引用

On-Line Conference (ONCON), Industrial Electronics Society Annual

作者： Xinyu Qiao Hao Wang Xiaoyi Xu Hao Luo Kuan Li Department of Control Science and Engineering Harbin Institute of Technology Harbin China Shanghai Aerospace Control Technology Institute Shanghai China

For the safe operation of electrical drive systems, a data-driven fault diagnosis approach is proposed by subspace-aided signal reconstruction in this paper. Specifically, based on the subspace identification method (SIM), the frequency estimation of the signal is reformulated into the eigenvalue identification, which can be directly extracted from the time-domain signal. The subspace frequency estimation approach can avoid the problem of spectrum leakage. Under the known frequency estimation, the amplitude and phase estimation are adopted by the least squares (LS) method. The signal is reconstructed for fault detection by estimating frequency, phase, and amplitude. The fault detection scheme is designed to be helpful for the implementation of fault diagnosis in the periodic signal. Eventually, the effectiveness of the proposed approach is verified.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Attack prevention and detection for cyber-physical systems based on coprime factorization technique

Attack prevention and detection for cyber-physical systems b...

引用

IEEE International Symposium on Industrial Electronics (ISIE)

作者： Shimeng Wu Hao Luo Yuchen Jiang Kuan Li Department of Control Science and Engineering Harbin Institute of Technology Harbin China Shanghai Aerospace Control Technology Institute Shanghai China

While cyber-physical systems (CPSs) bring convenience to industrial production and human life, they are, in the mean time, exposed to the threat of cyber-physical attacks, which have the characteristics of concealment and vital destruction. Recent reports on several horrible attack events aroused people’s attention to the security of CPSs. Motivated by this, this paper proposes a defense scheme based on co-prime factorization technology, consisting of attack prevention and detection. This scheme utilizes residual signals that are commonly used in fault diagnosis to realize secure transmission because these residual signals do not contain essential system knowledge. At the same time, a filter module is added, which makes use of noise signals to cover and protect the reference signals and the operation status of the system. By this means, the secure transmission method reduces the leakage of system information and interferes with the design of stealthy attacks, which need sufficient system knowledge. Furthermore, it realizes the detection of non-stealthy attacks under the same framework. Simulation results on a linear system with random parameters demonstrate the effectiveness of the proposed scheme.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Bias-Policy Iteration Based Adaptive Dynamic Programming for Linear Fully Actuated Systems

Bias-Policy Iteration Based Adaptive Dynamic Programming for...

引用

Fully Actuated System theory and Applications (CFASTA), Conference on

作者： Huaiyuan Jiang Xuefei Yang Chuanchuan Xu Kangkang Zhang Center for Control Theory and Guidance Technology Harbin Institute of Technology Harbin China Nanjing Research Institute of Electronic Engineering Nanjing China Department of Mechanical Engineering University of Hong Kong Hong Kong China

ISBN: (数字)9798350373691

ISBN: (纸本)9798350373707

In this paper, the bias-policy iteration based optimal control of fully actuated systems is further reconsidered. With the help of the fully actuated property, a more neat bias-PI method for the fully actuated cases is established with the convergence proof. The data-driven implementation for the proposed algorithm is introduced accordingly. A numerical example verifies the effectiveness of the proposed results.

关键词： Linear systems Adaptive systems Heuristic algorithms Optimal control Dynamic programming Complex systems Convergence

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：