检索结果-南通市图书馆

Toward Trustworthy Decision-Making for Autonomous Vehicles:A Robust Reinforcement Learning Approach with Safety Guarantees

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

engineering 2024年第2期33卷 77-89页

作者： Xiangkun He Wenhui Huang Chen Lv School of mechanical and aerospace engineering Nanyang Technological UniversitySingapore 639798Singapore

While autonomous vehicles are vital components of intelligent transportation systems,ensuring the trustworthiness of decision-making remains a substantial challenge in realizing autonomous ***,we present a novel robust reinforcement learning approach with safety guarantees to attain trustworthy decision-making for autonomous *** proposed technique ensures decision trustworthiness in terms of policy robustness and collision ***,an adversary model is learned online to simulate the worst-case uncertainty by approximating the optimal adversarial perturbations on the observed states and environmental *** addition,an adversarial robust actor-critic algorithm is developed to enable the agent to learn robust policies against perturbations in observations and ***,we devise a safety mask to guarantee the collision safety of the autonomous driving agent during both the training and testing processes using an interpretable knowledge model known as the Responsibility-Sensitive Safety ***,the proposed approach is evaluated through both simulations and *** results indicate that the autonomous driving agent can make trustworthy decisions and drastically reduce the number of collisions through robust safety policies.

关键词： Autonomous vehicle Decision-making Reinforcement learning Adversarial attack Safety guarantee

A path planning algorithm for a crop monitoring fixed-wing unmanned aerial system

在线全文

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2024年第08期67卷 5-23页

作者： Longhao QIAN Yi Lok LO Hugh Hong-tao LIU Institute of aerospace Studies University of Toronto Department of mechanical engineering The University of Hong Kong

With the growing demand for automation in agriculture, industries increasingly rely on drones to perform crop monitoring and surveillance. In this regard, fixed-wing unmanned aerial systems(UASs)are viable platforms for scanning a large crop field, given their payload capacity and range. To achieve maximum coverage without landing for battery replacement, an algorithm for producing a minimal required energy survey path is essential. Hence, an energy-aware coverage path planning algorithm is proposed *** constraints for a fixed-wing UAS to fly at low altitudes while achieving full coverage of the crop field are first analyzed. Then, the full path is decomposed into straight-line and U-turn primitives. Finally, an algorithm to calculate a combination of straight-line segments and U-turns is proposed to obtain the path with minimum required energy consumption. The genetic algorithm is used to efficiently determine the order of the straight-line paths to traverse. Case studies show that the proposed algorithm can produce planning results for a convex-polygon-shaped crop field.

关键词： aerial survey energy minimization fixed-wing UAS genetic algorithm path planning

同方期刊数据库

Tuning heterogeneous microstructures to enhance mechanical properties of nano-TiN particle reinforced Haynes 230 composites by laser powder bed fusion

在线全文

学校读者我要写书评

暂无评论

Rare Metals 2024年第9期43卷 4548-4565页

作者： Wen-Jie Liu Hui Li Qian-Xing Yin He-Jun Du School of Power and mechanical engineering Wuhan University The Institute of Technological Sciences Wuhan University School of mechanical&aerospace engineering Nanyang Technological University

Laser powder bed fusion(LPBF) is considered to be one of the most promising additive manufacturing technologies for producing components with geometries and high geometrical precision that are unattainable by traditional technologies. The superalloy exhibits exceptional mechanical and high-temperature performances,rendering it a prime candidate for advanced aero-engine applications. Despite the high demand for LPBF-manufactured superalloys, the superalloy is one of the materials manufactured difficultly by LPBF due to their large laser absorptivity fluctuation, poor molten pool stability and sharp temperature gradient. Hence, superalloys are characterized by severe pores, undesirable coarse columnar grains and poor mechanical properties. In this work, the effect of nano-Ti N particles on defects, molten pool characteristics and microstructure and performance of the composites were investigated. The 4.5 wt% Ti N/Haynes230 samples exhibited exceptional nanohardness and elastic modulus with maximum values reaching 5.53 GPa and 240.03 GPa, respectively. These superior mechanical properties were attributed to the combined effects of spatter and gas pore inhibition, grain refinement and duplex nanophases strengthening. Moreover, the stability of molten pool was enhanced, and spatter was effectively suppressed by adding nano-Ti N particles, while grain refinement and columnar to equiaxed transitions were promoted. Furthermore, the matrix exhibited a high dislocation density due to a significant hindrance of dislocation movement caused by massive nano-phases(e.g., Ti N and M23C6), resulting in the formation of extensive dislocation tangles and *** work offers novel insights into the role of nanoparticles reinforced superalloy composites by LPBF.

关键词： Composites Laser powder bed fusion mechanical properties Microstructure Molten pool characteristics

Automatic Miscalibration Detection and Correction of LiDAR and Camera Using Motion Cues

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of mechanical engineering 2024年第2期37卷 318-329页

作者： Pai Peng Dawei Pi Guodong Yin Yan Wang Liwei Xu Jiwei Feng School of mechanical engineering Southeast UniversityNanjing 211102China School of mechanical engineering Nanjing University of Science and TechnologyNanjing 210014China School of mechanical and aerospace engineering Nanyang Technological UniversitySingaporeSingapore

This paper aims to develop an automatic miscalibration detection and correction framework to maintain accurate calibration of LiDAR and camera for autonomous vehicle after the sensor ***,a monitoring algorithm that can continuously detect the miscalibration in each frame is designed,leveraging the rotational motion each individual sensor ***,as sensor drift occurs,the projection constraints between visual feature points and LiDAR 3-D points are used to compute the scaled camera motion,which is further utilized to align the drifted LiDAR scan with the camera ***,the proposed method is sufficiently compared with two representative approaches in the online experiments with varying levels of random drift,then the method is further extended to the offline calibration experiment and is demonstrated by a comparison with two existing benchmark methods.

关键词： Autonomous vehicle LiDAR and camera Miscalibration detection and correction Sensor drift

Spray,droplet evaporation,combustion,and emission characteristics of future transport fuels for compression-ignition engines:A review

在线全文

学校读者我要写书评

暂无评论

Journal of Traffic and Transportation engineering(English Edition) 2024年第4期11卷 575-613页

作者： Leang So Khuong Nozomu Hashimoto Osamu Fujita Division of mechanical and aerospace engineering Faculty of Engineering Hokkaido University Faculty of Automotive engineering National Polytechnic Institute of Cambodia

This review examines the potential of hydrogen, ammonia, and biodiesel as alternative fuels,focusing on spray dynamics, droplet evaporation, combustion, and emissions. Hydrogen offers superior combustion characteristics but faces challenges in NOxemissions. Strategies like nonpremixed direct injection, increased intake boost pressure, and low-pressure EGR are suggested for robust hydrogen combustion in compression-ignition engines. Control of hydrogen start of injection（SOI） and water injection（WI） are identified as effective techniques for reducing NOxemissions. Ammonia shows inferior combustion and higher NOxand unburned NH3emissions in the same conditions as conventional fuels with conventional engines. Understanding ammonia spray and evaporation conditions is significant for optimizing an ammonia-air mixture and minimizing wall impingement and ammonia trap in the crevice,thereby improving combustion and emission reduction. Increasing intake pressure, injection pressure, and EGR rate, employing a turbulent jet, and preheating ammonia improve efficiency and reduce NOxemissions. Utilizing ammonia combustion requires the implementation of after-treatment systems such as NH3adsorber and De NOxcatalysts to mitigate unburned NH3and NOxemissions. Biodiesel affects the fuel supply system, combustion, and emission characteristics according to its viscosity and density. Increasing injection pressure and blending with volatile fuels enhance spray and combustion. Optimum biodiesel preheating temperatures for the injection pump and injector are crucial for achieving the best pump capacity and spray formation. By utilizing biodiesel-PODE blends and investigating low-temperature biodiesel combustions, there is potential to improve thermal efficiency and PMNOxtrade-off. Therefore, carbon-neutral fuel adoption should be accelerated to mitigate CO2emissions, highlighting the importance of combustion techniques and emissions reduction strategies.

关键词： Carbon-neutral fuels Spray formation Droplet evaporation Injection strategies Combustion efficiency Emission reduction

Machining dynamics and chatters in micro-milling:A critical review on the state-of-the-art and future perspectives

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Aeronautics 2024年第7期37卷 59-80页

作者： Qingshun BAI Peng WANG Kai CHENG Liang ZHAO Yabo ZHANG School of mechanical and Electrical engineering Harbin Institute of TechnologyHarbin 150001China Department of mechanical and aerospace engineering Brunel University LondonUxbridge UB83PHUK

Micro-milling technology is widely applied in micro manufacturing,particularly for the fabrication of miniature and micro ***,the chatters and machining dynamics related issues in micro-milling are often the main challenges restricting its machining quality and *** research works have rendered that the machining dynamics and chatters in micro-milling are more complex compared with the conventional macro-milling process,likely because of the size effect and rigidity of the micro-milling system including the tooling,workpiece,process variables,materials involved,and the high-speed milling machines,and further their collective dynamic ***,in this paper,the state of the art focusing on micro-milling chatters and dynamics related issues over the past years are comprehensively and critically reviewed to provide some insights for potential researchers and ***,typical applications and the problems caused by the machining dynamics and chatters in micro-milling have been put forward in this ***,the research on the underlying micro-cutting mechanics and dynamics,stability analysis,chatters detection,and chatter suppression are summarized ***,the underlying scientific and technological challenges are discussed particularly against typical precision engineering ***,the possible future directions and trends in research and development of micro-milling have been discussed.

关键词： Micro-milling Machining dynamics Micro-cutting mechanics Stability lobe diagram(SLD) Chatters suppression Digital twin

Experimental evaluation of mechanical compression of lattice trusses made with Ti6Al4V for aerospace use

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Aeronautics 2024年第5期37卷 520-532页

作者： Carlo Giovanni FERRO Sara VARETTI Paolo MAGGIORE Department of mechanical and aerospace engineering Politecnico di TorinoCorso Duca degli AbruzziTorino 10124Italy

Lattice structures are three-dimensional structures composed of repeated geometrical shapes with multiple interconnected nodes,providing high strength-to-weight ratios,customizable properties,and efficient use of materials.A smart use of materials leads to reduced fuel consumption and lower operating costs,making them highly desirable for aircraft ***,the customizable properties of lattice structures allow for tailoring to specific design requirements,leading to improved performance and safety for *** advantages make lattice structures an important focus for research and development in the aviation *** paper presents an experimental evaluation of the mechanical compression properties of lattice trusses made with Ti6Al4V,designed for use in an anti-ice *** truss structures were manufactured using additive manufacturing techniques and tested under compressive loads to determine mechanical *** showed that lattice trusses exhibited high levels of compressive strength,making them suitable for use in applications where mechanical resistance and durability are critical,such as in anti-ice *** also highlight the potential of additive manufacturing techniques for the fabrication of lattice trusses with tailored mechanical *** study provides valuable insights into the mechanical behavior of Ti6Al4V lattice trusses and their potential applications in anti-ice systems,as well as other areas where high strength-to-weight ratios are *** results of this research contribute to the development of lightweight,efficient,and durable anti-ice systems for use in aviation and other industries.

关键词： Additive Manufacturing(AM) Selective Laser Sintering(SLM) Anti ice systems Lattice structures Aircraft on board systems Design of Experiments(DOE)

Modeling urban scale human mobility through big data analysis and machinelearning

在线全文

学校读者我要写书评

暂无评论

Building Simulation 2024年第1期17卷 3-21页

作者： Yapan Liu Bing Dong Department of mechanical&aerospace engineering Syracuse University263 Link HallSyracuseNY 13244USA

In the United States,the buildings sector consumes about 76%of electricity use and 40% of all primary energy use and associated greenhouse gas *** behavior has drawn increasing research interests due to its impacts on the building energy ***,occupant behavior study at urban scale remains a challenge,and very limited studies have been *** an effort to couple big data analysis with human mobility modeling,this study has explored urban scale human mobility utilizing three months Global Positioning System(GPS)data of 93,o00 users at Phoenix Metropolitan *** research extracted stay points from raw data,and identified users'home,work,and other locations by Density-Based Spatial Clustering ***,daily mobility patterns were constructed using different types of *** propose a novel approach to predict urban scale daily human mobility patterns with 12-hour prediction horizon,using Long Short-Term Memory(LSTM)neural network *** shows the developed models achieved around 85%average accuracy and about 86%mean *** developed models can be further applied to analyze urban scale occupant behavior,building energy demand and flexibility,and contributed to urban planning.

关键词： urban human mobility big data analysis urban scale occupant behavior recurrent neural networks

Numerical study of the near-wall vortical structures in particle-laden turbulent flow by a new vortex identification method-Liutex

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Hydrodynamics 2024年第1期36卷 53-60页

作者： Farid Rousta Goodarz Ahmadi Bamdad Lessani Chaoqun Liu Department of mechanical and aerospace engineering Clarkson UniversityPotsdamNYUSA mechanical engineering and engineering Science The University of North Carolina at CharlotteNCUSA Department of Mathematics University of Texas at ArlingtonArlingtonTXUSA

This study investigates turbulent particle-laden channel flows using direct numerical simulations employing the Eulerian-Lagrangian method.A two-way coupling approach is adopted to explore the mutual interaction between particles and fluid *** considered cases include flow with particle Stokes number varying from St=2 up to St=100 while maintaining a constant Reynolds number of Reτ=180 across all cases.A novel vortex identification method,Liutex(Rortex),is employed to assess its efficacy in capturing near-wall turbulent coherent structures and their interactions with *** Liutex method provides valuable information on vortex strength and vectors at each location,enabling a detailed examination of the complex interaction between fluid and particulate *** widely acknowledged,the interplay between clockwise and counterclockwise vortices in the near-wall region gives rise to low-speed streaks along the *** low-speed streaks serve as preferential zones for particle concentration,depending upon the particle Stokes *** is shown that the Liutex method can capture these vortices and identify the location of low-speed ***,it is observed that the particle Stokes number(size)significantly affects both the strength of these vortices and the streaky structure exhibited by ***,a quantitative analysis of particle behavior in the near-wall region and the formation of elongated particle lines was carried *** involved examining the average fluid streamwise velocity fluctuations at particle locations,average particle concentration,and the normal velocity of particles for each set of particle Stokes *** investigation reveals the intricate interplay between particles and near-wall structures and the significant influence of particles Stokes *** study contributes to a deeper understanding of turbulent particle-laden channel flow dynamics.

关键词： Turbulent channel flow particle-laden flow direct numerical simulation(DNS) Eulerian-Lagrangian vortex identification turbulence coherent structures Liutex