A5100649898- Fault Detection and Control Systems
- Advanced Algorithms and Applications
- Machine Fault Diagnosis Techniques
- Power Systems and Renewable Energy
- Energy Load and Power Forecasting
- High-Voltage Power Transmission Systems
- Icing and De-icing Technologies
- HVDC Systems and Fault Protection
- Advanced Sensor and Control Systems
- Smart Materials for Construction
- Wireless Communication Networks Research
- Mineral Processing and Grinding
- Microgrid Control and Optimization
- Spectroscopy and Chemometric Analyses
- Advanced Memory and Neural Computing
- Metaheuristic Optimization Algorithms Research
- Anomaly Detection Techniques and Applications
- Machine Learning and ELM
- Advanced Measurement and Detection Methods
- Network Traffic and Congestion Control
- Advanced Antenna and Metasurface Technologies
- Power Systems Fault Detection
- Mobile Agent-Based Network Management
- Metamaterials and Metasurfaces Applications
- Advanced Battery Technologies Research
Yunnan University
2015-2025
China Electronics Technology Group Corporation
2024-2025
Chongqing University
2009-2025
Affiliated Hospital of Youjiang Medical University for Nationalities
2025
Guangxi University of Science and Technology
2025
National University of Defense Technology
2009-2024
PowerChina (China)
2024
Beijing Information Science & Technology University
2024
Jilin Province Science and Technology Department
2024
Jilin University
2024
For imbalanced bearing fault diagnosis, generative adversarial networks (GANs) are a common data augmentation (DA) approach. Nevertheless, current GAN-based methods cannot update the generator from time–frequency domain simultaneously, downgrading authenticity of signal character. In this article, Fourier-like transform GAN (FTGAN), novel method, is proposed by introducing transformer (FLT) based on autoencoder (AE) to improve synthetic quality. FLT approximates discrete Fourier (DFT) neural...
Freshwater biodiversity is under great threat across the globe as evidenced by more severe declines relative to other types of ecosystems. Some main stressors responsible for these concerning trends habitat fragmentation, degradation, and loss stemming from anthropogenic activities, including energy production, urbanization, agriculture, resource extraction. Habitat protection restoration both play an integral role in efforts save freshwater associated ecosystem services further decline. In...
Nowadays rice has become one of the world's staple foods. Rice in southern China is also a food for everyone, however, with development China's industrialization model, many industrial areas may be contaminated by heavy metals, leading to contamination agricultural areas. With recent years, Nanning heavily area, and favourite food. Therefore, it matter concern detect whether metals contaminate due environmental factors. Five administrative villages were selected from 12 districts, 20%...
We propose a novel approximate adder design to significantly reduce energy consumption with very moderate error rate. The improved rate and critical path delay stem from the employed carry prediction technique that leverages information less significant input bits in parallel manner. An magnitude reduction scheme is proposed further amount of once detected low cost. Implemented commercial 90 nm CMOS process, it shown up 2.4× faster 43% more efficient over traditional adders while having an...
The accurate extraction of roads is a prerequisite for the automatic other road features. This letter describes method detecting boundaries from mobile laser scanning (MLS) point clouds in an urban environment. key idea our directly constructing saliency map on 3-D unorganized to extract boundaries. consists four major steps, i.e., partition with assistance vehicle trajectory, salient construction and points extraction, curb detection lowest fitting. performance proposed evaluated scene...
This brief proposes a novel design scheme for approximate adders and comparators to significantly reduce energy consumption while maintaining very low error rate. The considerably improved rate critical path delay stem from the employed carry prediction technique that leverages information less significant input bits in parallel manner. proposed designs have been adopted VLSI-based neuromorphic character recognition chip with unsupervised learning implemented on chip. approximation errors of...
Industrial oscillation recordings are often corrupted by underlying nonstationary trend and noisy artifacts, which can occlude features of interest complicate subsequent detection diagnosis. However, there considerably fewer techniques available in the literature for systematically removing both noise terms from measurements. To cater general detrending denoising needs oscillatory signals, this article proposes an integrated framework featuring following steps: 1) The ensemble empirical mode...
This article presents a control system structure, as well algorithm, that combines neural networks with fuzzy logic for dynamical compensation of both structured and unstructured uncertainties. <P xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">A new reasoning method is derived in the mechanism implemented cerebellar model articulation controller (CMAC), which outperforms conventional controllers by reducing computational complexity providing...
Knowledge distillation (KD) has been proved effective for compressing large-scale pre-trained language models. However, existing methods conduct KD statically, e.g., the student model aligns its output distribution to that of a selected teacher on pre-defined training dataset. In this paper, we explore whether dynamic knowledge empowers adjust learning procedure according competency, regarding performance and efficiency. We dynamical adjustments three aspects: adoption, data selection,...
Subway vehicle roofs must be inspected when entering and exiting the depot to ensure safe subway operations. This paper presents an improved method for detecting foreign objects on based YOLOv7 algorithm. First, we capture images of using a line-scan camera at entrance exit, creating dataset roof objects. Subsequently, address shortcomings algorithm by introducing Ghost module, weighted bidirectional feature pyramid network (WBiFPN), Wise intersection over union (WIoU) bounding-box...
Oscillation detection has been a hot research topic in industries due to the high incidence of oscillation loops and their negative impact on plant profitability. Although numerous automatic techniques have proposed, most them can only address part practical difficulties. An is heuristically defined as visually apparent periodic variation. However, manual visual inspection labor-intensive prone missed detection. Convolutional neural networks (CNNs), inspired by animal systems, raised with...
Abstract Fault detection in industrial processes is essential for enhancing production safety. Despite the application of neighborhood preserving embedding (NPE) algorithm fault as a manifold learning technique, notable limitation exists-NPE overlooks local geometric structure, leading to suboptimal and occasional false alarms. This paper introduces Gaussian kernel weighted NPE (KW-NPE) address this challenge. Specifically designed precise weight assignment structures, KW-NPE strategically...
Abstract In the field of power systems, variational mode decomposition (VMD) algorithm is widely utilized in data preprocessing stage prediction models for wind power, photovoltaic load, and other related areas. However, if two key parameters VMD—mode number penalty factor—are not properly set, results may suffer from mixing repetition. Moreover, boundary effect issue VMD causes numerical oscillations at boundaries results, thereby leading to distortion. To address these problems, this paper...
虚拟数字人技术近年来发展迅速，被广泛用于各类专业领域。虚拟数字人技术提供广泛的学习对话环境、模拟各领域的语言交流方式，弥补了传统关联词教学中缺乏的大量句子练习的缺陷。研究在数智苏格拉底式教学背景下，使用3S3L 提示语策略打造的虚拟数字人课堂形成了独具特色的新型教学范式。旨在充分发挥虚拟数字人的技术优势，设计虚拟数字人辅助关联词教学内容来探索虚拟数字人在视听化中文教学课堂的发展方向，以期实现数字人融入教学的实践与应用，进而为国际中文教育领域未来利用虚拟数字人辅助汉语教学提供浅显的教学参考。
The design of analog circuits is a cornerstone integrated circuit (IC) development, requiring the optimization complex, interconnected sub-structures such as amplifiers, comparators, and buffers. Traditionally, this process relies heavily on expert human knowledge to refine objectives by carefully tuning sub-components while accounting for their interdependencies. Existing methods, Bayesian Optimization (BO), offer mathematically driven approach efficiently navigating large spaces. However,...