A5100614605- Tribology and Lubrication Engineering
- Gear and Bearing Dynamics Analysis
- Magnetic Bearings and Levitation Dynamics
- High-Temperature Coating Behaviors
- Autonomous Vehicle Technology and Safety
- Hydraulic and Pneumatic Systems
- Nuclear Materials and Properties
- Advanced Algorithms and Applications
- Neural Networks and Applications
- Advanced Measurement and Metrology Techniques
- Fault Detection and Control Systems
- Iterative Learning Control Systems
- Advanced machining processes and optimization
- Lubricants and Their Additives
- Traffic control and management
- Vehicle Dynamics and Control Systems
- Machine Fault Diagnosis Techniques
- Advanced materials and composites
- Advanced Sensor and Control Systems
- Fuzzy Logic and Control Systems
- Metallurgy and Material Forming
- Robotic Path Planning Algorithms
- Reinforcement Learning in Robotics
- Mechanical Engineering and Vibrations Research
- Traffic and Road Safety
First Affiliated Hospital of Henan University of Science and Technology
2025
Jiangsu University
2022-2024
Tongji University
2015-2024
Sun Yat-sen University
2024
Beijing General Research Institute of Mining and Metallurgy
2016-2024
Wuhan Ship Development & Design Institute
2024
North China Electric Power University
2024
Peking University
2024
Nanjing University of Science and Technology
2024
Advanced Technology & Materials (China)
2019-2024
Purpose The purpose of this paper is to investigate the tribological properties liquid paraffin with SiO 2 nanoparticles additive made by a sol‐gel method. Design/methodology/approach as an in are measured using ball‐on‐ring wear tester determine optimal concentration. mechanism that and friction reduced studied scanning electron microscopy (SEM), energy dispersive spectrometry (EDS), atomic force microscope (AFM). Findings Experimental results indicate sizes synthesized distributed...
This paper presents a novel local motion planning framework in hierarchical manner for autonomous vehicles to follow trajectory and agilely avoid obstacles. In the upper layer, new path-planning method based on resistance network is applied plan behaviors (e.g. lane keeping or changing), where human-like factors can be included simulate different driver styles, such as aggressive, moderate, conservative. The planned results (i.e. lane-change command path) will guide lower-layer planner...
Recently, thanks to the introduction of human feedback, Chat Generative Pre-trained Transformer (ChatGPT) has achieved remarkable success in language processing field. Analogically, drivers are expected have great potential improving performance autonomous driving under real-world traffic. Therefore, this study proposes a novel framework for evolutionary decision-making and planning by developing hybrid augmented intelligence (HAI) method introduce feedback into learning process. In...
An efficient intelligent fault diagnosis model was proposed in this paper to timely and accurately offer a dependable basis for identifying the rolling bearing condition actual production application. The is mainly based on an improved butterfly optimizer algorithm‐ (BOA‐) optimized kernel extreme learning machine (KELM) model. Firstly, roller bearing’s vibration signals four states that contain normal state, outer race failure, inner ball failure are decomposed into several intrinsic mode...
IC metrology is a necessary means for measuring the fabrication performance in semiconductor industry. It significant yield enhancement and process control. However, real-time monitoring of wafer production required recent years especially 300mm manufacturing. Therefore, virtual (VM) developed tide demand. novel technology to predict results based on previous measurements, instead practically. Consequently it can assist achieving total quality management enable run-to-run In this paper...
Active pedestrian collision avoidance (APCA) systems can significantly reduce road injuries and thus have attracted considerable attention from both the automobile transportation industries. Numerous studies focused on APCA; however, it remains challenging to model variable complex scenarios in a safe, efficient low-cost way. For this purpose, paper proposes novel multipedestrian risk assessment framework comprising motion prediction module, checking module module. First, of ego vehicle (EV)...
Abstract Artificial intelligence empowers the rapid development of autonomous intelligent systems (AISs), but it still struggles to cope with open, complex, dynamic, and uncertain environments, limiting its large-scale industrial application. Reliable human feedback provides a mechanism for aligning machine behavior values holds promise as new paradigm evolution enhancement intelligence. This paper analyzes engineering insights from ChatGPT elaborates on traditional feedback. Then, unified...
Background Immunotherapy research for esophageal cancer is progressing rapidly, particularly locally advanced unresectable cases. Despite these advances, the prognosis remains poor, and traditional staging systems like AJCC inadequately predict outcomes. This study aims to develop validate a nomogram cancer-specific survival (CSS) in patients. Methods Clinicopathological data patients diagnosed between 2010 2021 were extracted from Surveillance, Epidemiology, End Results (SEER) database....
Abstract Distributed-drive electric vehicles (EVs) replace internal combustion engine with multiple motors, and the novel configuration results in new dynamic-related issues. This paper studies coupling effects between parameters responses of dynamic vibration-absorbing structures (DVAS) for EVs driven by in-wheel motors (IWM). Firstly, a DVAS-based quarter suspension model is developed distributed-drive EVs, from which nine five are selected effect analysis. A two-stage global sensitivity...
Decision-making and motion planning are extremely important in autonomous driving to ensure safe a real-world environment. This study proposes an online evolutionary decision-making framework for based on hybrid data- model-driven method. First, data-driven module deep reinforcement learning (DRL) is developed pursue rational performance as much possible. Then, model predictive control (MPC) employed execute both longitudinal lateral tasks. Multiple constraints defined according the...