检索结果-内蒙古大学图书馆

Efficient learning of robust quadruped bounding usingpretrained neural networks

IET Cyber-systems and robotics 2022年第4期4卷 331-338页

作者： Zhicheng Wang Anqiao Li Yixiao Zheng Anhuan Xie Zhibin Li Jun Wu Qiuguo Zhu Institute of Cyber-Systems and Control Zhejiang UniversityZhejiangChina Intelligent Robot Research Center Zhejiang LabZhejiangChina Department of Computer Science University College LondonLondonUK State Key Laboratory of Industrial Control Technology Zhejiang UniversityZhejiangChina

Bounding is one of the important gaits in quadrupedal locomotion for negotiating *** authors proposed an effective approach that can learn robust bounding gaits more efficiently despite its large variation in dynamic body *** authors first pretrained the neural network(NN)based on data from a robot operated by conventional model-based controllers,and then further optimised the pretrained NN via deep reinforcement learning(DRL).In particular,the authors designed a reward function considering contact points and phases to enforce the gait symmetry and periodicity,which improved the bounding *** NN-based feedback controller was learned in the simulation and directly deployed on the real quadruped robot Jueying Mini successfully.A variety of environments are presented both indoors and outdoors with the authors’*** authors’approach shows efficient computing and good locomotion results by the Jueying Mini quadrupedal robot bounding over uneven *** cover image is based on the Research Article Efficient learning of robust quadruped bounding using pretrained neural networks by Zhicheng Wang et al.,https://***/10.1049/csy2.12062.

关键词： legged locomotion reinforcement learning robot learning

来源：评论

学校读者我要写书评

暂无评论

Small Photoresist Defect Samples Augmentation Based on Generative Adversarial Network

Small Photoresist Defect Samples Augmentation Based on Gener...

引用

IEEE Information Technology, Networking, Electronic and Automation control Conference

作者： Guang Yang Zhihang Li Zhijia Yang Shuping Cui State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang China University of Chinese Academy of Sciences Beijing China Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China

Photoresist coating technology is an important part of the surface treatment of semiconductor wafers. The presence of bubbles in photoresist can seriously affect the quality of wafers, however, the lack of sufficient bubble samples makes intelligent automatic detection techniques impossible. To solve such a problem, we propose B-GAN based on adversarial generative network, and design a mapping network for potential encoding mapping and a synthetic network for high-quality bubble image generation, so that defective bubble samples can be automatically generated. Experiments prove that our method achieves excellent results.

关键词： Image coding Automation Image synthesis Resists Manuals Generative adversarial networks Coatings

来源：评论

学校读者我要写书评

暂无评论

Dynamic Identification for a Manipulator Model based on Stribeck Friction using the Quasi-Newton Iterative Method

Dynamic Identification for a Manipulator Model based on Stri...

引用

IEEE International Conference on robotics and Biomimetics

作者： Feng Xiao Feilong Zhang Bing Han Hualiang Zhang School of Information Science and Engineering Shenyang University of Technology Shenyang China State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China University of Chinese Academy of Sciences Beijing China Key Laboratory of Networked Control Systems Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Chinese Academy of Sciences Institutes for Robotics and Intelligent Manufacturing Shenyang China State Key Laboratory of Fluid Power and Mechatronic Systems School of Mechanical Engineering Zhejiang University Hangzhou China

The performance of dynamic control is intimately tied to modeling accuracy. However, traditional estimation methods and friction models, such as the least squares method and the Coulomb plus viscous model, fail to reflect the actual characteristics accurately. Particularly, the linear nature of the Coulomb plus viscous model overlooks the nonlinear static features of joint friction at slower velocities. To improve the rationality of the model structure, we integrate the Stribeck friction model into the Coulomb plus viscous model. However, introducing such nonlinearities compromises the applicability of the least squares method. As a countermeasure, we propose a new strategy that combines the least square method and the Quasi-Newton iterative method to identify the parameters of the modified nonlinear model. Additionally, the design of the excitation trajectory is critical to achieve high identification accuracy. We utilized the inverse of the smallest singular value of the observation matrix as the objective function. By minimizing it with the interior point method, we generate the excitation trajectory well-suited to stimulate dynamic characteristics. Then we leverage the discrepancies between the measured and estimated torques to assess the precision of the dynamic parameters of the manipulator. Remarkably, our proposed algorithm reduces the mean absolute error of the estimated torque by over 20.40%. Finally, an experiment of the industrial manipulator by hand guiding grab and drag is performed and shows that the proposed approach can provide the manipulator with comprehensive torque compensation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Event-Triggered Output Voltage Practical Tracking control for Uninterruptible Power Supply systems

Event-Triggered Output Voltage Practical Tracking Control fo...

引用

Chinese control and Decision Conference, CCDC

作者： Ben Wu Wei Liu Weijie Sun Key Laboratory of Autonomous Systems and Networked Control Ministry of Education School of Automation Science and Engineering South China University of Technology Guangzhou China

In this paper, by using the output regulation theory, we research the output voltage practical tracking problem for un-interruptible power supply systems under event-triggered control technique. By configuring the desired poles for a controllable pair and solving the regulator equations, a state feedback gain and a feedforward gain can be obtained for designing the control law. Further, under event-triggered mechanism, a control law that can be applied to a digital platform directly is designed to solve our problem. Moreover, it can be verified that the voltage tracking error can converge to a pre-specified neighborhood of the origin.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on optimization method of routing buffer linkage based on Q-learning

Research on optimization method of routing buffer linkage ba...

引用

2021 International Conference on Advanced Manufacturing Technology and Electronic Information, AMTEI 2021

作者： Han, Zhonghua Qi, Hongfeng Chang, Daliang Gong, Wei Dai, Shilong School of Information and Control Engineering Shenyang Jianzhu University Shenyang110168 China Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang110016 China Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang110169 China

According to the characteristics of the painting process of passenger car manufacturing enterprises, by formulating the routing buffer linkage rules based on the total renewal cost, the linkage process of the bus in the routing buffer is controlled, and an improved Q-learning (Q- The routing buffer of learning) algorithm quickly finds the optimal path method. According to the actual production situation, this method improves the dynamic parameters of the algorithm on the basis of the traditional Q-learning algorithm, and improves the optimization speed and accuracy of the algorithm by establishing the correlation between the work-in-process and its neighboring work-in-process in the current state. Through multiple sets of example simulation tests, the effectiveness of the Q-learning algorithm in solving the optimization problem of routing buffer linkage is verified. © Published under licence by IOP Publishing Ltd.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Research on Industrial control Network Security Measurement Method Based on GRU-SVM

Research on Industrial Control Network Security Measurement ...

引用

2022 Chinese Automation Congress, CAC 2022

作者： Chen, Hengfei Liu, Xianda Sheng, Chuan Pan, Hao College of Information Engineering Shenyang University of Chemical Technology Shenyang China Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang China Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang China

ISBN: (纸本)9781665465335

Since the industrial Internet entered people's field of vision, industrial control network security has gradually received attention. Traditional network security measurement methods rely on the accuracy of situation sequences and historical situation values, and various factors in the network have a great influence on the results. However, compared with industrial control networks, the number and types of affected factors are less than those of the modern Internet. Therefore, based on the research on network security situational awareness, this paper proposes an industrial control network security measurement method model based on GRU-SVM. First, the data sets with threat type labels are classified, and then the similarity scoring mechanism and softmax function are introduced, to process the classification results. For the GRU-SVM classification module, the analysis of the simulation results shows that the convergence is better and the robustness is stronger. For the safety prediction measurement part, by comparing with different models, the mean absolute error and root mean square error are smaller and the reliability is higher. © 2022 IEEE.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

Aerogel defect detection using terahertz waves

Aerogel defect detection using terahertz waves

引用

International Conference on Infrared and Millimeter Waves

作者： Yehao Ma Liran Shen Yuqi Cao Dibo Hou Guangxin Zhang Department of Control Science and Engineering State Key Laboratory of Industrial Control Technology Zhejiang University Hangzhou China Robotics Institute Ningbo University of Technology Ningbo China

ISBN: (数字)9798350370324

ISBN: (纸本)9798350370331

Aerogel is known as super insulation materials and has already been applied to manufacture thermal protection parts of aerospace equipment. Terahertz (THz) wave has good penetration to non-metallic and non-polar materials. To explore its potential in aerogel defect detection, the absorption coefficient and refractive index of aerogel were studied. As a result, the absorption spectrum of aerogel has not obvious absorption peak, and THz wave has great penetration for aerogel. Additionally, two aerogel samples with different sizes of defects were imaged with two time domain parameters (pulse peak and pulse valley) and two frequency domain parameters (absorption coefficient and refractive index). The study is of key importance for THz wave in nondestructive testing for aerogel, offering a rapid and non-destructive detection method for aerogel defects.

关键词： Insulation Absorption Frequency-domain analysis Nondestructive testing Refractive index Aerospace materials Time-domain analysis Protection Defect detection Testing

来源：评论

学校读者我要写书评

暂无评论

key Parameters Prediction for Intelligent control and Energy Optimization Based on MIC-BWO-XGBoost 2

Key Parameters Prediction for Intelligent Control and Energy...

引用

2nd International Conference on Cyber-Energy systems and Intelligent Energy, ICCSIE 2024

作者： Lv, Changyao Wang, Yaqi Chen, Yudong Yu, Zhuo Hu, Guoliang Wu, Hongliang Li, Shuai Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang110016 China Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang110169 China University of Chinese Academy of Sciences Beijing100049 China College of Information Engineering Shenyang University of Chemical Technology Shenyang110142 China Shanghai Aircraft Manufacturing Co. Ltd. Shanghai201324 China

ISBN: (纸本)9798350373318

In the aviation industry, anodic oxidation serves as a core process for surface modification of aluminum alloy components, albeit accompanied by high energy consumption. Accurate prediction of key parameters can offer decision support for the intelligent control and energy optimization of anodic oxidation. However, the limited sample size resulting from the high cost of data collection and the complex nonlinear patterns caused by the synergy of multiple factors pose a challenge in accurately predicting key parameters. Therefore, we propose a key parameters prediction method based on the Maximum Information Coefficient (MIC), Beluga Whale Optimization algorithm (BWO), and XGBoost algorithm. Considering the adverse impact of low correlation parameters on prediction accuracy, we first use MIC to extract features from the original data. Then, XGBoost is used to integrate multiple decision trees to ensure the strong fitting ability for nonlinear relationships. Compared to deep learning models, XGBoost performs well even in a limited sample size. In addition, considering XGBoost is prone to overfitting training data as an ensemble learning algorithm, we employ the BWO to optimize four key parameters of the model that are difficult to choose, thereby enhancing model's generalization. The model's performance is evaluated using Mean Squared Error (MSE), Mean Absolute Error (MAE), and Mean Absolute Percentage Error (MAPE), with values of 0.04388, 0.09410, and 0.20730%, respectively. The experimental results demonstrate that the proposed method outperforms traditional approaches, enabling precise prediction of key parameters and holding significant value for the intelligent control and energy optimization of anode oxidation processes. © 2024 IEEE.

关键词： Anodic oxidation

来源：评论

学校读者我要写书评

暂无评论

Analysis and compensation of kinematic errors in a five-axis machine tool based on an internal data-driven method 10

Analysis and compensation of kinematic errors in a five-axis...

引用

2024 10th International Conference on Applied Materials and Manufacturing Technology, ICAMMT 2024

作者： Wu, Junjie Ji, Yulei Zhong, Lei Wang, Yuhan State Key Laboratory of Mechanical System and Vibration School of Mechanical Engineering Shanghai Jiao Tong University Shanghai200240 China Meta Robotics Institute Shanghai Jiao Tong University Shanghai200240 China Shanghai TOP Numerical Control Technology Co. Ltd Shanghai201100 China

The increasing demand for highly efficient and precise machining in the aerospace industry is leading to increasingly stringent requirements for machine tool accuracy measurement and compensation technologies. However, existing methods can only measure the accuracy of machine tools after they have been shut down, using instruments that do not measure the kinematic errors during the machining process. To address this issue, a method for real-time prediction of kinematic errors in a five-axis machine tool has been proposed to enhance machining accuracy and efficiency. The method employs a neural network-based predictive model, which has been trained and validated through experimental testing and data collection using internal sensors of the machine tool. The study reveals that this predictive model can effectively forecast the kinematic errors, through real-time compensation, and can reduce errors by 60-86%, significantly enhancing machine performance. © Published under licence by IOP Publishing Ltd.

关键词： Aerospace industry

来源：评论

学校读者我要写书评

暂无评论

Design of Functional Safety Pressure Transmitter and Safety Assessment 23

Design of Functional Safety Pressure Transmitter and Safety ...

引用

23rd IEEE International Conference on High Performance Computing and Communications, 7th IEEE International Conference on Data Science and systems, 19th IEEE International Conference on Smart City and 7th IEEE International Conference on Dependability in Sensor, Cloud and Big Data systems and Applications, HPCC-DSS-SmartCity-DependSys 2021

作者： Yan, Bingjun Zhou, Xiufang Zhang, Bo Wang, Zhiping Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang110016 China Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang110169 China University of Chinese Academy of Sciences Beijing100049 China

ISBN: (纸本)9781665494571

Based on functional safety standard IEC61508, this paper studies the functional safety approaches of the pressure transmitter. Following the 1oo1D architecture, self-diagnostics measures are used in this functional safety pressure transmitter. In order to improve diagnostic coverage, dual CPUs are used to compare results at different calculation stages. The FTA analysis and Markov model are used for safety verification. Furthermore, the safety failure fraction (SFF) and probability of failure on demand (PFD) are analysed, and the results indicate that safety integrity level is SIL2. © 2021 IEEE.

关键词： Transmitters Smart cities Phase frequency detectors Markov processes Reliability engineering Hardware Safety

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：