检索结果-内蒙古大学图书馆

Aeroengine remaining useful life prediction via integrating enhanced inverted transformer and spatiotemporal graph learning

引用

ISA Transactions 2025年

作者： Sun, Shilong Ding, Hao Zhao, Zida Zhou, Yu Wang, Dong Xu, Wenfu School of Robotics and Advanced Manufacturing College of Artificial Intelligence Harbin Institute of Technology Shenzhen China Guangdong Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics Shenzhen China College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China State Key Laboratory of Mechanical System and Vibration Shanghai Jiao Tong University Shanghai200240 China

Accurate prediction of aeroengine Remaining Useful Life (RUL) is critical for ensuring flight safety, minimizing maintenance costs, and improving operational efficiency. This study proposes a novel model, the Fourier-Enhanced Inverted Transformer with Graph-Augmented Spatiotemporal Modeling (FIT-GSTM), to enhance RUL prediction performance. FIT-GSTM combines an inverted Transformer with a Spatiotemporal Graph Convolutional Network (STGCN) to effectively capture global spatiotemporal dependencies across multi-sensor data. To further enrich feature representation, the model incorporates Fast Fourier Transform (FFT) to extract frequency-domain information and fuses it with time-domain features, enhancing robustness to noise. Additionally, the integration of Memory Tokens and Reversible Instance Normalization (RevIN) strengthens the model's ability to retain long-term dependencies and adapt to heterogeneous data distributions. Experimental evaluations on the C-MAPSS dataset demonstrate that FIT-GSTM achieves superior RUL prediction accuracy and generalization compared to existing methods, highlighting its potential for real-world deployment in aeroengine health management. © 2025 ISA

关键词： Fast Fourier transforms

来源：评论

学校读者我要写书评

暂无评论

Exploring Eye-tracking based Biomarkers to Assess Cognitive Abilities in Autistic Children: A Feasibility Study

引用

IEEE Journal of Biomedical and Health Informatics 2025年 PP卷 PP页

作者： Zhang, Hanlin Hu, Chunchun Wang, Zhiyong Zhou, Bingrui Wang, Xinming Nie, Wei Ye, Qinyi Lin, Ruihan Xu, Xiu Liu, Honghai Children's Hospital of Fudan University Department of Child Health Care Shanghai201102 China Harbin Institute of Technology State Key Laboratory of Robotics and System School of Mechanical Engineering and Automation Shenzhen518055 China Peng Cheng Laboratory Shenzhen518000 China

Cognitive assessment can reveal a person's cognitive processing and behavioral patterns, making it an indispensable component of autism intervention and prognosis. Existing machine-assisted cognitive assessment methods primarily focus on children's performance outcomes, overlooking distinctive behavioral models, particularly characteristics of eye movement behavior, which have been demonstrated as the most direct indicators of cognitive abilities. In this study, we explore eye-tracking biomarkers for assisting cognitive assessment through a series of meticulously designed multi-level human-computer interaction protocols, encompassing three cognitive abilities: pairing and categorization, emotion recognition, and social interaction. A platform embedded with an eye-tracking module has been developed to reliably collect and analyze eye movement data, even in the presence of unrestricted large head movements in children. Experimental results indicate that there are significant group differences between autism and typically developing children in the eye-tracking features of total fixation duration, response latency, time to first fixation, mean fixation duration, and visit count in the absence of significant intergroup differences in the Wechsler Preschool and Primary Scale of Intelligence (WPPSI) and Wechsler Intelligence Scale for Children (WISC) assessment results. In addition, certain eye movement features in each group are correlated with WPPSI/WISC scale scores, enabling clinical cognitive assessments within each group based on these eye movement features. This study suggests that using eye-tracking features as biomarkers to assist detailed cognitive assessments holds significant potential for the intervention and prognosis of autism. © 2013 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Research on accurate fire source localization and seconds-level autonomous fire extinguishing technology

引用

Scientific Reports 2025年第1期15卷 1-13页

作者： Ren, Xu Qu, keyu Guo, Junlong Yin, Hesheng Huang, Bo The State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin 150001 China School of Electrical and Electronic Engineering Nanyang Technological University Singapore Singapore

With the continuous development of intelligent technology, robots have entered various industries. Firefighting robots have become a hot topic in the field of firefighting and rescue equipment. For firefighting robots, autonomous firefighting technology is the core capability. It includes three steps: flame recognition, fire source location, autonomous firefighting. At present, flame recognition has been widely studied, but the adaptability is poor for different flames. For fire source location technology only rough positioning has been achieved. For autonomous firefighting, the time-consuming water point feedback adjustment method is often used. Those are not suitable for the actual fire rescue. So we proposed to use the visual information, thermal imaging morphological and thermal data of the flame for deep learning, which greatly improves the adaptability of flame recognition. The centimeter-level high-precision positioning of the fire source is achieved. Finally, the proposed water cannon fire source projection method is used to realize rapid water cannon movement instruction generation, and achieve rapid autonomous firefighting. The test results show that the proposed fire source identification algorithm can identify all fire sources up to 15 m at a speed about 15Fps. It can rapid autonomous firefighting within 0.5 s. © The Author(s) 2025.

关键词： Autonomous firefighting High-precision fire positioning Lidar fusion

来源：评论

学校读者我要写书评

暂无评论

An Iterative Task-Driven Framework for Resilient LiDAR Place Recognition in Adverse Weather

arXiv

引用

arXiv 2025年

作者： Zhao, Xiongwei Wang, Yang Sun, Qihao Bai, Haojie Xie, Xingxiang Shenzhen518071 China State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin150006 China School of Information Communication Technology Shenzhen Institute of Information Technology Shenzhen518071 China

LiDAR place recognition (LPR) plays a vital role in autonomous navigation. However, existing LPR methods struggle to maintain robustness under adverse weather conditions such as rain, snow, and fog, where weather-induced noise and point cloud degradation impair LiDAR reliability and perception accuracy. To tackle these challenges, we propose an Iterative Task-Driven Framework (ITDNet), which integrates a LiDAR Data Restoration (LDR) module and a LiDAR Place Recognition (LPR) module through an iterative learning strategy. These modules are jointly trained end-to-end, with alternating optimization to enhance performance. The core rationale of ITDNet is to leverage the LDR module to recover the corrupted point clouds while preserving structural consistency with clean data, thereby improving LPR accuracy in adverse weather. Simultaneously, the LPR task provides feature pseudo-labels to guide the LDR module’s training, aligning it more effectively with the LPR task. To achieve this, we first design a task-driven LPR loss and a reconstruction loss to jointly supervise the optimization of the LDR module. Furthermore, for the LDR module, we propose a Dual-Domain Mixer (DDM) block for frequency-spatial feature fusion and a Semantic-Aware Generator (SAG) block for semantic-guided restoration. In addition, for the LPR module, we introduce a Multi-Frequency Transformer (MFT) block and a Wavelet Pyramid NetVLAD (WPN) block to aggregate multi-scale, robust global descriptors. Finally, extensive experiments on the Weather-KITTI, Boreas, and our proposed Weather-Apollo datasets demonstrate that, demonstrate that ITDNet outperforms existing LPR methods, achieving state-of-the-art performance in adverse weather. The datasets and code will be made publicly available at https://***/Grandzxw/ITDNet. © 2025, CC BY.

关键词： Image coding

来源：评论

学校读者我要写书评

暂无评论

Comprehensive Performance Optimization of a Novel Anthropomorphic Dexterous Hand

引用

IEEE robotics and Automation Letters 2025年第7期10卷 6816-6823页

作者： Yifan Ma Weiwei Shang Fei Zhang Shunxiang Pang Shuqing Dai Zhengkun Yi Guotao Li Shuang Cong Department of Automation University of Science and Technology of China Hefei China Guangdong Provincial Key Laboratory of Robotics and Intelligent System Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing China

Grasp and in-hand manipulation of dexterous hands are essential for daily operational tasks. In this study, an optimized design method for a novel anthropomorphic dexterous hand is proposed, which improves the comprehensive performance of grasp and manipulability of the dexterous hand. The constraints of multi-fingered contact force and kinematics are established with full consideration of the applicability to the objects of different sizes and the shape characteristics of finger contact surface. The performance index of in-hand manipulation ability is proposed, and the optimization problem is constructed through the technique for order preference by similarity to ideal solution (TOPSIS) to achieve multi-objective optimization of precision grasp and in-hand manipulation. Finally, simulation and experiment verify the feasibility of our prototype and optimization method. The results show that the in-hand translation space and in-hand rotation range are increased by 20% and 8.5%, respectively. Our dexterous hand has excellent abilities of multi-fingered interaction and in-hand manipulation, which can perform 33 grasp gestures and two/three-fingered in-hand manipulation. This study provides a valuable reference for the design of dexterous hands with anthropomorphic functions.

关键词： Thumb Hands Kinematics Grasping Force Performance analysis IP networks Electronics packaging Cables Accuracy

来源：评论

学校读者我要写书评

暂无评论

Evaluation of motor unit tracking across hand movements by combining high-density surface electromyography with ultrafast ultrasound

引用

Computers in Biology and Medicine 2025年 193卷 110325-110325页

作者： Yin, Zongtian Chen, Chen Meng, Jianjun Zhu, Xiangyang State Key Laboratory of Mechanical System and Vibration Shanghai Jiao Tong University Shanghai China Meta Robotics Institute Shanghai Jiao Tong University Shanghai China

Objective: Motor unit (MU) activities provide the primary output from the central nervous system to muscles, and have found wide applications in neurophysiological investigation and human-machine interface. However, the current decoding methods usually struggle with MU tracking across movements. A common compromise is comparing motor unit action potentials extracted from electromyography (EMG) signals, but this only considers electrical responses and requires further validation. This study aims to simultaneously collect EMG and ultrasound (US) signals, extracting both electrical and mechanical responses of MU discharges, to validate their feasibility for MU tracking across movements. Methods: Ten able-bodied subjects participated in experiments involving isometric contraction of six hand movements. High-density surface EMG signals and ultrafast US images were concurrently recorded from the forearm muscles. The EMG signals were decomposed into MU spike trains and the separation vectors were kept for MU decoding across movements. The three-dimensional activation zone of each MU, including the action potentials on the skin surface and the twitch area in the muscle cross-sections, was extracted to validate the tracking performance. Main results: On average, 37 ± 17 MUs were identified from each decomposition, of which 20±16,2±2, and 2 ± 1 MUs were successfully tracked based on action potential, twitch area, and both, respectively. Conclusion and Significance: These results demonstrate strong evidence for the feasibility of tracking MUs using pre-trained separation vectors, supported by both electrical and mechanical responses. In addition, the study provides a benchmark to track MU activities across hand movements, extending the potential applications of neural decoding in neurophysiological investigation and human-machine interfacing. © 2025 Elsevier Ltd

关键词： Blind source separation Motor unit tracking Neural decoding Surface electromyography Ultrafast ultrasound

来源：评论

学校读者我要写书评

暂无评论

Study on wear mechanism of small ball-end grinding wheel and surface integrity of complex component under high-speed machining condition

引用

Wear 2025年

作者： Qin, Biao Liu, Henan Cheng, Jian Tian, Jinchuan Sun, Jiangang Chen, Mingjun School of Mechatronics Engineering Harbin Institute of Technology Heilongjiang Harbin150001 China State Key Laboratory of Robotics and System Harbin Institute of Technology Heilongjiang Harbin150001 China Zhengzhou Research Institute Harbin Institute of Technology Zhengzhou450000 China

The small ball-end fine diamond grinding wheel is well-suited for machining complex components with small curved surface structures, demonstrating high-precision and high-quality machining capabilities. By increasing the speed of the workpiece, the issue of poor grinding performance caused by the small diameter of the ball-end grinding wheel can be effectively overcome. However, this strategy inevitably increases wheel wear and affects surface integrity. To address these challenges, this paper systematically investigates the grinding characteristics of the small ball-end grinding wheel. First, grinding experiments were performed to investigate the influence of workpiece speed, feed rate, and grinding depth on the material removal rate, wheel wear, and surface integrity. Then, the wear mechanism of the grinding wheel was analyzed. The wear modes of the grinding wheel at high workpiece speeds include metal adhesive wear and abrasive grain fracture, which enhance the self-sharpening of the grinding wheel while accelerating its wear. Furthermore, the surface morphology creation mechanism of fused silica under different material removal modes was revealed. Moreover, the correlation between material removal rate and surface roughness caused by wheel wear was revealed. A high-speed grinding strategy was subsequently proposed based on the relationship between the grinding characteristics and grinding parameters of the small ball-end grinding wheel under various grinding conditions. Finally, the feasibility of this grinding strategy was validated through its application to the machining of the complex curved fused silica hemispherical resonator (HSR). Experimental results indicate that under the high workpiece speed condition, the best surface roughness of HSR decreases from 90.5 nm to 62.2 nm, while the maximum grinding wheel wear increases from 9.7 μm to 11.5 μm, with minimal impact on surface integrity. Therefore, the high-speed grinding strategy proposed in this study ho

关键词： Fused silica

来源：评论

学校读者我要写书评

暂无评论

Layered structural engineering of Bi 2 O 3 /PP and WO 3 /PP composites for γ-ray shielding in high energy range: anisotropic attenuation mechanisms via Monte Carlo simulation and experiments

引用

Journal of Materials Research and Technology 2025年 36卷 10324-10336页

作者： Xiangjie Duan Jie Zhao Shuaida Song Na Zhou Jizhuang Fan Bo Tian Yunchen Du State Key Laboratory of Space Power-Sources School of Chemistry and Chemical Engineering Harbin Institute of Technology Harbin 150001 People's Republic of China State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin 150006 People's Republic of China Heilongjiang Institute of Atomic Energy Heilongjiang Academy of Sciences Harbin 150081 People's Republic of China

The development of non-toxic and flexible polymer-based shielding composites has become a research hotspot due to the severe harm of γ ray to living organisms, mechanical equipment, and environment. However, the γ-ray shielding performance of polymer-based composites in high-energy range remains unsatisfactory. Herein, FLUKA Monte Carlo simulations capable of visualizing γ-photon transport behaviors are investigated in Bi 2 O 3 /PP and WO 3 /PP multi-layer composites with various layered configurations. The simulation results reveal significant anisotropic attenuation effects on shielding characteristics caused by layered configurations and incident path of γ-photons relative to the interface position. Subsequently, single-layer, AB, and sandwich-like ABA composites with a fixed thickness of 2.0 mm are experimentally fabricated via melt-mixing and hot press methods. At 1332 keV, sandwich-like WPPBPPWPP composite (WO 3 /PP outer layers + Bi 2 O 3 /PP core) achieves linear attenuation coefficients and radiation protection efficiency of 0.31 cm −1 and 6 %, respectively, which are 29 % higher than those of single-layer composite. These improvements originate from multiple scattering induced by interlayer interface. Additionally, layered configurations with externally placed high-density fillers (WO 3 ) and internally placed high atomic number fillers (Bi 2 O 3 ) further promote γ-photon attenuation in high-energy range. Experimental results validate the anisotropic shielding trends observed in MC simulations. Moreover, multi-layer composites demonstrate significantly improved energy storage capacity, thermal stability, and oxidation resistance while maintaining comparable to those of single-layer composites. This work provides a scalable strategy for developing non-toxic and flexible shielding materials applicable in nuclear protection, medical devices, and aerospace systems, where lightweight and efficient radiation attenuation are critical.

关键词： Polymer-based composites Multi-layer structural engineering γ-Ray shielding Monte Carlo simulation Anisotropy attenuation Heterogeneous interface

来源：评论

学校读者我要写书评

暂无评论

A review of solar concentration technology applications in deep space exploration: Environmental adaptability and performance comparison

Space Solar Power and Wireless Transmission

引用

Space Solar Power and Wireless Transmission 2025年第1期2卷 43-53页

作者： Yanlong Zhang Pengzhen Guo Mengfan Tian Huazhi Chen Rongqiang Liu Zongquan Deng Lifang Li National Key Laboratory of Aerospace Mechanism Harbin Institute of Technology Harbin 150001 PR China National Key Laboratory of Laser Spatial Information Harbin Institute of Technology Harbin 150001 PR China National Key Laboratory of Space Environment and Matter Behaviors Harbin Institute of Technology Harbin 150001 PR China State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin 150001 PR China

Deep space exploration missions and the construction of planetary research stations impose strict demands on energy self-sufficiency systems. Solar energy, due to its abundant availability and sustainability, has become the preferred solution. However, extreme environmental conditions in space – including drastic temperature fluctuations, vacuum environments, high-energy particles, and intense radiation – pose significant challenges to the performance and lifespan of solar energy systems. Concentration technology, which enhances photoelectric and photothermal conversion efficiency by focusing sunlight, is crucial for space missions. This review examines the primary environmental factors affecting the performance of solar concentrators, including solar irradiance, thermal cycling, vacuum-induced outgassing, radiation effects, and impacts from micrometeoroids and orbital debris. The analysis focuses on three types of high-temperature concentrators: Fresnel lenses, Scheffler concentrators, and parabolic dish concentrators. Fresnel lenses are characterized by low cost and simple structure but are susceptible to optical degradation at high temperatures. Scheffler concentrators utilize geometric optimization to improve uniformity of light distribution, while parabolic dish concentrators achieve high optical efficiency, making them suitable for high-energy applications though requiring precise solar tracking. Performance comparisons in the thermal power range of 0 to 25 kW reveal that parabolic dish concentrators excel in high-power scenarios with greater efficiency and smaller aperture sizes. Conversely, Fresnel lenses and Scheffler concentrators are more effective in medium to low-temperature applications. Based on these findings, this review emphasizes the need to select concentrators according to mission requirements and outlines future research directions. These include the development of advanced materials, optimized optical designs, and improvements in system integr

关键词： Deep space exploration Solar concentrators Extreme environmental conditions

来源：评论

学校读者我要写书评

暂无评论

Ultrahigh energy density and rapid response dielectric elastomer for advanced soft robots

引用

Chemical Engineering Journal 2025年 515卷

作者： Du, Chengzhen Yan, Peinan Zou, Jiang Guo, Yutong Pang, Zimo Li, Sijia Chen, Yujie Fan, Qunfu Liu, Hezhou State Key Laboratory of Metal Matrix Composites School of Materials Science and Engineering Shanghai Jiao Tong University Shanghai200240 China Robotics Institute State Key Laboratory of Mechanical System and Vibration School of Mechanical Engineering Shanghai Jiao Tong University Shanghai200240 China National Engineering Research Center of Special Equipment and Power System for Ship and Marine Engineering Shanghai200030 China

Dielectric elastomer actuators (DEAs) require high energy density to simultaneously achieve high mechanical output while enabling compact and lightweight actuator design. However, the realization of high energy density is constrained by the high driving electric field and the significant hysteretic relaxation. Herein, we present a DE featuring a bimodal-network structure and multiple hydrogen bonds interactions, which possesses outstanding properties, including a low Young's modulus, optimal dielectric properties, and low mechanical loss. The DE achieves a maximum actuation strain of 200 % at a low driving electric field of 60 V μm−1 with a rapid response. Remarkably, it exhibits an output force of 0.95 N and an ultrahigh specific energy of 283 J kg−1, approximately 7 times that of natural muscle. A series of soft robots with different structures and functions are fabricated to showcase the immense potential of our DE in various applications. This work provides a novel strategy to fabricate high performance artificial muscles for soft robotics. © 2025 Elsevier B.V.

关键词： Dielectric properties of solids

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：