A5038307223- Electric and Hybrid Vehicle Technologies
- Vehicle Dynamics and Control Systems
- Mechanical Engineering and Vibrations Research
- Industrial Technology and Control Systems
- Hydraulic and Pneumatic Systems
- Real-time simulation and control systems
- Iterative Learning Control Systems
- Topic Modeling
- Soil Mechanics and Vehicle Dynamics
- Advanced Text Analysis Techniques
- Control Systems in Engineering
- Advanced Battery Technologies Research
- EEG and Brain-Computer Interfaces
- Advanced Memory and Neural Computing
- Neural Networks and Applications
- Vehicle emissions and performance
- Natural Language Processing Techniques
- Robotic Path Planning Algorithms
- Electric Vehicles and Infrastructure
- Simulation and Modeling Applications
- Crystallization and Solubility Studies
- Neural dynamics and brain function
- Extremum Seeking Control Systems
- X-ray Diffraction in Crystallography
- Traffic control and management
Yanshan University
2016-2025
Shenyang University of Technology
2023-2025
Second Affiliated Hospital of Nanchang University
2023-2024
Nanchang University
2023-2024
Beijing University of Chemical Technology
2023
Xi'an University of Architecture and Technology
2019-2023
Carrier (United States)
2023
Shanghai Key Laboratory of Trustworthy Computing
2023
East China Normal University
2023
Tianjin Internal Combustion Engine Research Institute
2020-2022
ABSTRACT The use of large‐scale agricultural machinery for plant protection in nonstandard orchards mountainous areas is very limited, while small‐wheeled robots have great application prospect. To address the false judgment visual information caused by shading branches and leaves difficulty avoiding obstacles complex orchard terrain, an operation trajectory optimization approach based on improved dynamic window algorithm (DWA) with ant colony (ACO) was developed. First, environment acquired...
Sweet potato (Ipomoea batatas (L.) Lam.) with high yield and diverse nutrients, is the third most important food crop in world. Manganese (Mn) an essential cofactor that plays a critical role development maturation of crop. However, molecular mechanism underlying sweet response to Mn remains unclear. In this study, treatment increased depth yellow color potato, augmented sugar carotenoid accumulation storage roots, accompanied decline plant hormones. Especially, Mn-treated roots displayed...
Motor imagery-based brain-computer interface (MI-BCI) inefficiency phenomenon is one of the biggest challenges in MI-BCI research. BCI subject defined as who cannot achieve classification accuracy higher than 70% since considered to be minimum for communication by BCI. About 15-30% people are according investigation. Most existing studies used common spatial patterns (CSP) extract motor imagery feature and identify based on obtained accuracy. We think performance maybe suppressed because CSP...
This study presents the test results of three specimens traditional Chinese timber frames (TCTFs) with two types column heights and vertical loads. The were initially loaded to damage, then strengthened different numbers shape memory alloy (SMA) wires retested. lateral performance, such as failure modes, envelop curves, stiffness degradation, energy consumption, was analyzed evaluate SMA strengthening effects. Results showed that bearing capacity, stiffness, consumption evidently improved,...
An independent-wheel-drive electric vehicle has the advantage of better implementation precise motion and stability control. However, when is moving on a road that complex slopes various adhesion coefficients subjected to structural limitations systems, driving performance will deteriorate. In order make full use drive torque every motor improve vehicle’s climbing accelerating abilities, basis designs dual-motor coaxial-coupling system sliding-mode controller, traction control was developed....
Abstract Achieving accurate speed prediction provides the most critical support parameter for high-level energy management of plug-in hybrid electric vehicles. Nowadays, people often drive a vehicle on fixed routes in their daily travels and predictions these are possible with random machine learning, but accuracy still needs to be improved. The traditional algorithms is difficult further improve after reaching certain accuracy; problems, such as over fitting, occur process improving...
The recently proposed quantum language model (QLM) aimed at a principled approach to modeling term dependency by applying the probability theory. latest development for more effective QLM has adopted word embeddings as kind of global information and integrated quantum-inspired idea in neural network architecture. While these LMs are theoretically general also practically effective, they have two major limitations. First, not taken into account interaction among words with multiple meanings,...
This paper aims to develop an efficient pattern recognition method for engine fault end-to-end detection based on the echo state network (ESN) and multi-verse optimizer (MVO). Bispectrum is employed transform one-dimensional time-dependent vibration signal into a two-dimensional matrix with more impact features. A sparse input weight-generating algorithm designed ESN. Furthermore, deep ESN model built by fusing fixed convolution kernels autoencoder (AE). novel traveling distance rate (TDR)...
Abstract The road adhesion coefficient is a key factor influencing automatic emergency braking (AEB) and anti‐lock system (ABS) safety control of trucks. With the fading introduced, covariance gain adjusted in real time, strong tracking unscented Kalman filter (STUKF) algorithm modified to estimate more accurately. Composed an ABS fuzzy sliding mode controller (SMC) AEB controller, AEB/ABS coordinated strategy with estimation designed for three‐axle heavy vehicle. effects are verified...
Although Deep Neural Networks (DNNs) have achieved excellent performance in many tasks, improving the generalization capacity of DNNs still remains a challenge. In this work, we propose novel regularizer named Ensemble-based Decorrelation Method (EDM), which is motivated by idea ensemble learning to improve DNNs. EDM can be applied hidden layers fully connected neural networks or convolutional networks. We treat each layer as an several base learners through dividing all units into...
When a vehicle hits pothole, the reaction force of pothole on tire causes an <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">imbalance</i> in driving forces both sides and may cause wheels to jump, potentially resulting path deviation roll instability. To address these issues, cooperative control system for tracking stability is proposed. Roll achieved by moment generated reasonably distributing torque among four IWMs. The necessary...
A computational method, based on DFT and electrical double-layer interface models with explicit hydrogen bonding, is developed to accurately predict potential-dependent reaction pathways, catalytic activity, product selectivity of CO 2 reduction.