A5053960408- Advanced Algorithms and Applications
- Advanced Control Systems Optimization
- Iterative Learning Control Systems
- Adaptive Control of Nonlinear Systems
- Fault Detection and Control Systems
- Industrial Technology and Control Systems
- Advanced Sensor and Control Systems
- Process Optimization and Integration
- Tunneling and Rock Mechanics
- Stability and Control of Uncertain Systems
- Neural Networks and Applications
- Distributed Control Multi-Agent Systems
- Advanced machining processes and optimization
- Control Systems and Identification
- Sensorless Control of Electric Motors
- Metaheuristic Optimization Algorithms Research
- Guidance and Control Systems
- Advanced Surface Polishing Techniques
- Advanced Control Systems Design
- Neural Networks Stability and Synchronization
- Underwater Vehicles and Communication Systems
- Fuzzy Logic and Control Systems
- Drilling and Well Engineering
- Geotechnical Engineering and Analysis
- Evolutionary Algorithms and Applications
Dalian University of Technology
2015-2024
Commercial Aircraft Corporation of China (China)
2024
China Railway Construction Corporation (China)
2024
Zhengzhou University
2024
Nantong University
2019-2022
Fudan University
2020
Huazhong University of Science and Technology
2000-2015
Dalian University
2007-2013
Analysis and Testing Centre
2011-2013
Zhaotong University
2012
Background: The efficient and accurate diagnosis of pulmonary adenocarcinoma before surgery is considerable significance to clinicians. Although computed tomography (CT) examinations are widely used in practice, it still challenging time-consuming for radiologists distinguish between different types subcentimeter nodules. there have been many deep learning algorithms proposed, their performance largely depends on vast amounts data, which difficult collect the medical imaging area. Therefore,...
Hydrogenated amorphous silicon (a-Si:H) has garnered considerable attention in the semiconductor industry, particularly for its use solar cells and passivation layers high performance cells, owing to exceptional photoelectric properties scalable manufacturing processes. A comprehensive understanding of thermal transport mechanism a-Si:H is essential optimizing management ensuring reliable operation these devices. In this study, we developed a neuroevolution machine learning potential based...
Semantic segmentation of panoramic images plays a key role in many applications, such as security monitoring and autonomous driving. With the rapid development deep learning, some networks are developed to segment semantically. However, these don't have special modules correct image distortion according principle, which makes feature extraction unreasonable during convolution because distortion. This article proposes novel semantic network for outdoor scenes based on convolution. The...
As a novel simulated evolutionary computation technique, artificial fish swarm algorithm (AFSA) shows many promising characters. This paper presents the use of AFSA as new tool which sets up neural network (NN), adjusts its parameters, and performs feature reduction, all simultaneously. In optimization process, features hidden units are encoded into real-valued (AF), give out method designing fitness function. The experimental results on several public domain data from UCI show that our can...
Reliable feature extraction from 3D point cloud data is an important problem in many application domains, such as reverse engineering, object recognition, industrial inspection, and autonomous navigation. In this paper, a novel method proposed for extracting the geometric features based on discrete curves. We extract curves research behaviors of chord lengths, angle variations, principal curvatures at Then, corresponding similarity indicators are defined. Based indicators, can be extracted...
The paper presents model-free proportional–integral–derivative (PID) type iterative learning control (ILC) approach for the nonlinear batch process. dynamic linearisation method is considered, which uses input-output (I/O) measurements to update model at each iteration. Based on newly updated and error information of previous iteration, optimal PID gains are iteratively. quadratic performance index employed optimise parameters controller, then an data-driven (DDILC) scheme established...
Abstract Stability criteria and hybrid controllers' design problems for a class of uncertain switched systems with interval time‐varying delay are considered in this paper. Based on the average dwell time method, by choosing new appropriate Lyapunov‐Krasovskii functional which fully utilizes information both lower upper bounds delay, delay‐range‐dependent stability stabilization conditions first derived terms linear matrix inequalities. Moreover, order to obtain much less conservative...
A robust adaptive observer for a class of nonlinear systems is proposed based on generalized dynamic recurrent neural networks (DRNN), which does not require off-line training phase. The stability and boundedness the state estimates NN weights are proven. No exact knowledge matching uncertain function, such as output or linear-parameterized condition in observed system, assumed. Simulation results show effectiveness DRNN observer.