检索结果-内蒙古大学图书馆

Time-delayed feedback stochastic resonance enhanced minimum entropy deconvolution for weak fault detection of rolling element bearings

引用

Chinese Journal of Physics 2022年 76卷 1-13页

作者： Yun, Xialun Mei, Xuesong Jiang, Gedong State Key Laboratory for Manufacturing Systems Engineering Xi'an Jiaotong University Xi'an 710048 China Shaanxi Key Laboratory of Intelligent Robots Xi'an Jiaotong University Xi'an 710049 China School of Mechanical Engineering Xi'an Jiaotong University Xi'an 710049 China

Early fault characteristics of roller element bearings are overwhelmed by strong background noise and vibrational responses excited by other parts in machinery. Stochastic resonance (SR) can use noise to enhance weak useful signal detection, but when noise imbedded in signals is too strong to trigger SR. In this paper, therefore, we would propose a time-delayed feedback SR enhanced minimum entropy deconvolution method to enhance weak fault characteristic of roller element bearings, where minimum entropy deconvolution is used to preprocess vibration signals to partly eliminate strong noise imbedded in signals and then the preprocessed signals are fed into time-delayed feedback SR to further enhance weak fault characteristics. In time-delayed feedback SR, the signal-to-noise ratio (SNR) is seen as an indicator to optimize the adjusting parameters of the time-delayed feedback SR for triggering the optimal resonance. Finally, a simulation and a bearing fault experiment are performed to demonstrate the feasibility of the proposed method, respectively. The detected results indicate that the proposed method can detect weak fault characteristics precisely and is superior to minimum entropy deconvolution and fast kurtogram methods. © 2021

关键词： Early fault diagnosis Rolling element bearings Stochastic resonance Weak characteristic detection

来源：评论

学校读者我要写书评

暂无评论

Design of a High Speed 360-degree Panoramic Video Acquisition System Based on FPGA and USB 3.0

引用

IEEE Sensors Journal 2023年 1-1页

作者： Lyu, Congyi Peng, Jianqing Zhou, Weiguo Yang, Shanshan Liu, Yunhui Intelligent Robotics Institute Key Laboratory of Biomimetic Robots and Systems Ministry of Education State Key Laboratory of Intelligent Control and Decision of Complex Systems School of Mechatronical Engineering Beijing Institute of Technology Beijing China

This paper presents a FPGA-based hardware architecture for capturing real-time panoramic images and the parallel implementation of an image stitching algorithm based on the scale-invariant feature transform (SIFT) features. First, the system transfers the images captured by five CMOS sensors to the designed FPGA board through the FMC adapter plate. Then, the system employs the FPGA-based parallel computing to extract the SIFT features and detect the best matching region and points for image registration. Finally, in order to obtain the panoramic image with smooth changes at the junctions, images of the adjacent images are fused. Using the designed FPGA platform makes it possible to extract the SIFT and stitch the images in real-time, which is not realized in most panoramic imaging systems. The panoramic system, developed using the Xilinx Zynq®-7000 all programmable SOC, can capture video of 5*640*480 images at the speed of 60 fps. To enable high-speed image transfer from the imaging system to the host computer, the USB3.0 interface with the transmission speed of 359MB/s has been developed. The real-time efficiency of the parallel system will be demonstrated by the simulations and experiments. IEEE

关键词： Real time systems

来源：评论

学校读者我要写书评

暂无评论

TS-NeRF: temporal and structural regularization for few-shot neural radiance fields 3

TS-NeRF: temporal and structural regularization for few-shot...

引用

3rd International Conference on Electronic Information Engineering, Big Data, and Computer Technology, EIBDCT 2024

作者： Wei, Yunpei Zhang, Weimin Li, Fangxing Guo, Ziyuan School of Mechatronical Engineering Beijing Institute of Technology Beijing China Zhengzhou Academy of Intelligent Technology Zhengzhou China Key Laboratory of Biomimetic Robots and Systems Beijing Institute of Technology Ministry of Education Beijing China Wuhan Second Ship Design and Research Institute Wuhan China

ISBN: (纸本)9781510680449

For NeRF(Neural Radiance Fields), synthesizing new views from sparse inputs poses a challenge as too few inputs can lead to artifacts in the rendered views. Recent methods have tackled this issue by introducing external supervision or utilizing regularization based on priors like depth to enhance reconstruction quality. Few-shot NeRF requires additional constraint information to ensure reconstruction quality. To address this, we employed two novel regularization methods. Firstly, we introduced a loss related to view structure, reshaping multiple random points into a batch to capture the relationships between points. This structural regularization method is termed SSLIP. Additionally, studies indicate that high-frequency signals during reconstruction hinder neural networks from effectively learning low-frequency information. Based on this research, we improved the encoding of positional codes, enabling their frequency to increase with the number of training iterations, referred to as temporal regularization. This enhancement ensures NeRF effectively learns lowfrequency information during the initial training stages. Our method, building upon the current state-of-the-art ViP-NeRF model, achieved superior results on the LLFF dataset. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Image processing

来源：评论

学校读者我要写书评

暂无评论

Surgical instrument segmentation algorithm based on improved DeepLab-V3+

引用

Procedia Computer Science 2024年 250卷 195-200页

作者： Xue Li Yuxin Ji Qingyao Liu Xingguang Duan Changsheng Li The School of Mechatronical Engineering Beijing Institute of Technology Beijing 100081 China The Key Laboratory of Biomimetic Robots and Systems Beijing Institute of Technology Ministry of Education Beijing 100081 China

Endoscope-based surgical robots have become prevalent in clinical settings, offering precise segmentation information of surgical instruments to robotic systems. However, existing surgical instrument segmentation algorithms often face challenges in real-time processing and accuracy due to complex environmental factors. This paper introduces an improved DeepLab-V3+ segmentation algorithm to address these issues. The proposed method utilizes MobileNetV2 as the backbone network and introduces an improved space pyramid pooling module to enhance channel features. To validate the effectiveness of this method, experiments were conducted using a public endoscopic surgery dataset for both quantitative and qualitative analysis. Results from both types of experiments demonstrate the efficacy of the proposed method. The average mIOU reaches as high as 88.90%, indicating accurate and stable segmentation of surgical instruments.

关键词： surgical instrument segmentation lightweight multi-scale features deep learning

来源：评论

学校读者我要写书评

暂无评论

Improved Dense Nested Attention Network Based on Transformer for Infrared Small Target Detection

arXiv

引用

arXiv 2023年

作者： Bao, Chun Cao, Jie Ning, Yaqian Zhao, Tianhua Li, Zhijun Wang, Zechen Zhang, Li Hao, Qun Key Laboratory of Biomimetic Robots and Systems Ministry of Education Beijing Institute of Technology Beijing100081 China

Infrared small target detection based on deep learning offers unique advantages in separating small targets from complex and dynamic backgrounds. However, the features of infrared small targets gradually weaken as the depth of convolutional neural network (CNN) increases. To address this issue, we propose a novel method for detecting infrared small targets called improved dense nested attention network (IDNANet), which is based on the transformer architecture. We preserve the dense nested structure of dense nested attention network (DNANet) and introduce the Swin-transformer during feature extraction stage to enhance the continuity of features. Furthermore, we integrate the ACmix attention structure into the dense nested structure to enhance the features of intermediate layers. Additionally, we design a weighted dice binary cross-entropy (WD-BCE) loss function to mitigate the negative impact of foreground-background imbalance in the samples. Moreover, we develop a dataset specifically for infrared small targets, called BIT-SIRST. The dataset comprises a significant amount of real-world targets and manually annotated labels, as well as synthetic data and corresponding labels. We have evaluated the effectiveness of our method through experiments conducted on public datasets. In comparison to other state-of-the-art methods, our approach outperforms in terms of probability of detection (Pd), false-alarm rate (Fa), and mean intersection of union (mIoU). The mIoU reaches 90.89% on the NUDT-SIRST dataset and 79.72% on the SIRST dataset. The BIT-SIRST dataset and codes are available openly at https://***/EdwardBao1006/bit_sirst. © 2023, CC BY-NC-ND.

关键词： Entropy

来源：评论

学校读者我要写书评

暂无评论

Bipedal Walking Outdoors with a Point-footed Robot via Reinforcement Learning

Bipedal Walking Outdoors with a Point-footed Robot via Reinf...

引用

Intelligent Robotics and Automatic Control (IRAC), International Conference on

作者： Yuanxi Zhang Zhangguo Yu Xuechao Chen Yidong Du Zishun Zhou Junyao Gao School of Mechatronical Engineering Beijing Institute of Technology Beijing China Key Laboratory of Biomimetic Robots and Systems Ministry of Education Beijing China

ISBN: (数字)9798350389807

ISBN: (纸本)9798350389814

The bipedal robot can perfectly adapt to the scenes of human society without the need for additional structural design and motion planning. Although model-based control algorithms achieve multiple types of motion, the control robustness is still insufficient in the face of complex dynamic environments. Reinforcement learning (RL) methods have recently produced good results in the field of bipedal robots. In order to explore information and exploit it better in the robot state space, we introduced a transformer structure that is more sensitive to temporal information into the RL framework. Benefiting from the self-attention mechanism in the transformer, our observation scheme extracts more state features, allowing the bipedal robot to achieve robust outdoor locomotion, including bipedal walking on asphalt, marble and grass terrains, including the test of performance on the most commonly used asphalt according to quantitative data.

关键词： Legged locomotion Training Asphalt Heuristic algorithms Reinforcement learning Transformers Robot sensing systems Feature extraction State estimation robots

来源：评论

学校读者我要写书评

暂无评论

Manual Alignment of Dual End-Effectors for Piezo-Driven Microhand

Manual Alignment of Dual End-Effectors for Piezo-Driven Micr...

引用

IEEE International Conference on Real-time Computing and Robotics (RCAR)

作者： Jichao Pang Dan Liu Xiaoqing Tang Yan Chen Qiang Huang Tatsuo Arai Xiaoming Liu Beijing Advanced Innovation Center for Intelligent Robots and Systems and School of Mechatronical EngineeringBeijing Institute of Technology Key Laboratory of Biomimetc Robots and Systems Ministry of Education State Key Laboratory of Intelligent Control and Decision of Complex System Beijing China Center for Neuroscience and Biomedical Engineering The University of Electro-Communications Tokyo Japan

ISBN: (数字)9798350372601

ISBN: (纸本)9798350372618

In recent years, micromanipulator with dual end-effectors called microhand has been widely used in industrial and biological fields. Whether the tip positions of the two end-effectors of the microhand can be accurately aligned seriously affects the precise grasping of the microhand. However, few researchers have presented practical ways for precisely aligning the tip positions of a 6-DOF microhand’s two end- effectors. This paper proposes a novel, inexpensive, lightweight, robust, and easy-to-use microhand dual end-effectors clamping device that can precisely and quickly align the two end-effectors of a 6-DOF microhand. First, we describe the microhand dual end-effectors clamping device’s lightweight structural design. After that, we simplify the microhand dual end-effectors clamping device model and create a mathematical model to determine the relationship between the end-effectors’ tip position and the rotation angles of screw No.1, screw No.2, screw No.3 of the microhand dual end-effectors clamping device. Through experimentation, we are able to attain precise alignment of the two end-effectors tip positions of the 6-DOF microhand, so we confirm that our mathematical model is true. Finally, we use the impulse response of PZT in the microhand’s lower module to confirm the stability of the microhand dual end- effectors clamping device. We believe that the proposed the microhand dual end-effectors clamping device has great potential in industrial and biological applications as a universal tool for precise alignment of the tip positions of the two end-effectors of a 6-DOF microhand.

关键词： Costs Accuracy Fasteners End effectors 6-DOF Mathematical models Biology

来源：评论

学校读者我要写书评

暂无评论

Effects of Prior Knowledge for Stair Climbing of Bipedal robots Based on Reinforcement Learning

Effects of Prior Knowledge for Stair Climbing of Bipedal Rob...

引用

International Conference on Advanced Robotics and Mechatronics (ICARM)

作者： Mengya Su Yasen Jia Yan Huang School of Mechantronical Engineering Beijing Institute of Technology Beijing China Key Laboratory of Biomimetic Robots and Systems Ministry of Education Beijing China Beijing Advanced Innovation Center for Intelligent Robots and Systems Beijing Institute of Technology Beijing China

ISBN: (数字)9798350385724

ISBN: (纸本)9798350385731

Bipedal robots with two legs are capable of traversing various terrains like level ground and staircases. Applying Reinforcement Learning (RL) based control can realize stable climbing stairs of bipedal robots. Prior knowledge of robots such as surrounding terrain information may improve the performance of climbing stairs. However, the impacts of prior knowledge on locomotion of bipedal robots across various terrains have not been systematically studied. In this work, we analyzed the effects of the amount of prior knowledge about terrain in front of the robot with RL-based control. Simulation results showed that introducing prior knowledge about terrain to bipedal robots can increase the maximum allowable ground height variation, realize smooth transition from level-ground walking to stair climbing, and improve disturbance rejection and energy efficiency. Prior knowledge is a trade-off between environmental information acquisition and computational complexity reduction. We find that there exists an optimal amount of prior knowledge for disturbance rejection and energy efficiency of stair climbing.

关键词： Legged locomotion Mechatronics Simulation Reinforcement learning Stairs Energy efficiency Computational complexity robots

来源：评论

学校读者我要写书评

暂无评论

Modeling and Design of Dynamic Series-parallel Hybrid Lower-limb Mechanism

Modeling and Design of Dynamic Series-parallel Hybrid Lower-...

引用

IEEE International Conference on Mechatronics and Automation

作者： Zhuo Chen Zhangguo Yu Xuechao Chen Fei Meng Chencheng Dong Xin Zhu School of Mechatronical Engineering Beijing Institute of Technology Beijing China Key Laboratory of Biomimetic Robots and Systems Ministry of Education Beijing China

ISBN: (数字)9798350388077

ISBN: (纸本)9798350388084

Humanoid robots are required to exhibit exceptional dynamic motion capabilities, particularly in the lower extremities, while undertaking repetitive, high-intensity, or high-risk tasks in human environments. However, the intricate lower limb structure and high limb mass ratio give rise to substantial errors when relying on reduced-order models. This research presents a novel evaluation methodology that effectively analyzes the mechanical properties of lower limb structures during the design phase. This methodology facilitates early detection and optimization of structural issues, thereby enhancing the motion performance and stability of humanoid robots. Furthermore, a novel design approach for the lower limb structure is proposed, employing a series-parallel coupling multistage transmission structure. This design enables the attainment of a compact overall structure and robust power output by integrating the drive structure of the knee and ankle into the thigh and pelvis. Finally, the practical implementation of this method is realized, demonstrating its efficacy in reducing joint load through running simulations.

关键词： Analytical models Mechatronics Humanoid robots Thigh Stability analysis Reduced order systems Pelvis

来源：评论

学校读者我要写书评

暂无评论

Placement Optimization for Humanoid Robot Manipulation Using a Task-Driven Planning Method

Placement Optimization for Humanoid Robot Manipulation Using...

引用

IEEE International Conference on Cyborg and Bionic systems (CBS)

作者： Haozhou Liu Yibei Ma Xuechao Chen Zhangguo Yu School of Mechatronical Engineering Beijing Institute of Technology (BIT) Beijing China Key Laboratory of Biomimetic Robots and Systems Ministry of Education Beijing China

ISBN: (数字)9798350388039

ISBN: (纸本)9798350388046

Planning a placement is crucial for humanoid robots to successfully execute specific manipulation tasks. While a feasible solution of placement ensures that the end-effector can reach the desired poses, it does not specify the arm configuration during the task. This paper introduces a task-driven planning method to optimize placement for manipulation tasks, enhancing overall configuration manipulability. Our approach employs heuristic designs to define manipulation tasks with key information besides the desired relative poses between the end-effector and targets. We establish a quadratic programming (QP) controller to track these desired poses, enabling the automatic generation of joint trajectories. Additionally, we use Particle Swarm Optimization (PSO) to optimize placement based on task information, aiming to minimize end-effector pose errors and maximize manipulability. The effectiveness of our method is demonstrated through experiments conducted with the BHR humanoid robot.

关键词： Target tracking Human-machine systems Humanoid robots End effectors Real-time systems Planning Trajectory Quadratic programming Particle swarm optimization Optimization

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：