A5102794545- Metallurgy and Material Forming
- Industrial Technology and Control Systems
- Sensorless Control of Electric Motors
- Advanced Neural Network Applications
- Robotics and Sensor-Based Localization
- Advanced Algorithms and Applications
- Iterative Learning Control Systems
- Advanced machining processes and optimization
- Gear and Bearing Dynamics Analysis
- Advanced Image and Video Retrieval Techniques
- Industrial Automation and Control Systems
- Adaptive Control of Nonlinear Systems
- Elevator Systems and Control
- Assembly Line Balancing Optimization
- Infrared Target Detection Methodologies
- Scheduling and Optimization Algorithms
- Electric Motor Design and Analysis
- Mineral Processing and Grinding
- Advanced Manufacturing and Logistics Optimization
- Tribology and Lubrication Engineering
- Advanced Sensor and Control Systems
- Control Systems in Engineering
Yanshan University
2006-2025
Institute of Electrical Engineering
2006-2007
<title>Abstract</title> Object detection using Unmanned Aerial Vehicles (UAVs) has emerged as a crit- ical application across diverse domains. However, the wide-angle views of drones often result in images containing high density small objects, posing chal- lenges for object such few learnable features, significant occlusion, and an imbalanced distribution positive negative samples. To address these issues, this paper introduces AGLC-YOLO, enhanced version YOLOv7 architecture specifically...
In the original model reference adaptive induction motor speed sensorless system based on flux linkage, there is a large fluctuation of rotational in transient and steady state. When estimated, integral part voltage affects accuracy estimated with high-frequency signals noise. order to solve above problems further improve system’s anti-interference performance estimation at low speed, an improved method that combines fuzzy proportional control sliding mode proposed, by adopting genetic...
To tackle the multi-objective problem in process of tandem cold rolling, a mathematical model multi-object optimization is presented. Taking equal relatively power and prevent slippage as objective functions. Aiming to Standard Genetic Algorithm (SGA), such premature convergence, oscillation over-randomization iterative process, an Improved Adaptive (IAGA) applied optimize system. The algorithm decides crossover rate mutation chromosome based on individual adaptive value calculation make...
Abstract A novel sliding mode observer for speed estimation in sensorless induction motor drives at zero and low is proposed this paper. First, aiming the poor stability when runs speed, analyze reasons of a new feedback gains design method proposed. Second, problem ignored flux error which cause compensation put forward, can improve accuracy dynamic steady state system. Meanwhile, continuous function given replace sign, to restrain chattering observer. Detailed simulation results are...
The quality and yield of products in the process aluminum hot rolling is affected seriously by load distribution. distribution tandem actually a problem multi-objective optimization(MOO). model schedule was established based on slippage factor, which also set as an optimization objective. In this paper, improved NSGA-II applied to optimize rolling. This paper proposed method select best solution preference after NSGA-II. shows its ability preventing
A novel flux observer is proposed with a view to improving the stability and reliability of sensorless vector control system an induction motor, which robust regard different parameters features no phase lag or attenuation.At same time PI controllers are replaced in double-closed loop active disturbance rejection controller (ADRC), reduces overshoot when speed changes further improves steady-state performance system.Finally, method based on Symmetric Strong Tracking Extended Kalman Filter...
Single and multi-object optimization planning are presented for 1370mm tandem cold rolling schedules separately, in which, BP neural network with self-learning function is adopted to predict the force instead of traditional models. Analysis comparison existing offered, performance optimal satisfying.