A5100646162- Advanced machining processes and optimization
- Microgrid Control and Optimization
- Smart Grid Energy Management
- Computer Graphics and Visualization Techniques
- Advanced Numerical Analysis Techniques
- Industrial Technology and Control Systems
- Smart Grid Security and Resilience
- Robotic Mechanisms and Dynamics
- Advanced Measurement and Metrology Techniques
- Advanced Surface Polishing Techniques
- Islanding Detection in Power Systems
- 3D Shape Modeling and Analysis
- Machine Learning and ELM
- Image Enhancement Techniques
- Advanced Algorithms and Applications
- Manufacturing Process and Optimization
- Spectroscopy and Chemometric Analyses
- Optimal Power Flow Distribution
- Simulation and Modeling Applications
- Anomaly Detection Techniques and Applications
- Advanced Machining and Optimization Techniques
- Power Systems and Technologies
- IoT Networks and Protocols
- Power Line Communications and Noise
- CCD and CMOS Imaging Sensors
Hefei University of Technology
2015-2025
Chuzhou University
2025
North China Institute of Science and Technology
2025
Nanjing University of Science and Technology
2023-2024
Nanjing University
2013-2024
Tsinghua University
2012-2024
Henan Normal University
2024
Shenzhen University
2024
China University of Mining and Technology
2024
Shandong University of Technology
2024
Real-time smart grid monitoring is critical to enhancing resiliency and operational efficiency of power equipment. Cloud-based edge-based fault detection systems integrating deep learning have been proposed recently monitor the in real time. However, state-of-the-art cloud-based may require uploading a large amount data suffer from long network delay, while schemes do not adequately consider requirement thus cannot provide flexible optimal performance. To solve these problems, we study...
Incipient fault detection in power distribution systems is crucial to improve the reliability of grid. However, nonstationary nature and inadequacy training dataset due self-recovery incipient signal make a great challenge. In this article, we focus on address above challenges. particular, propose an adaptive time–frequency memory (AD-TFM) cell by embedding wavelet transform into long short-term (LSTM), extract features time frequency domains from signals. We scale parameters translation...
Abstract During the processing of deep mining, revealing distribution abutment pressure is significant for controlling stability entry. In this study, roof-cutting coalface was investigated by FLAC3D and self-developed flexible detection unit (FDU). numerical simulation, double-yield model built to analyze goaf under fracturing roofs maintain entry (FRME). Compared with non-fracturing side, peak value advanced on side reduced 19.29% average, influence range (span) increases 30.78% distance...
Resistive-random-access-memory (ReRAM) based processing-in-memory (R2PIM) accelerators show promise in bridging the gap between Internet of Thing devices' constrained resources and Convolutional/Deep Neural Networks' (CNNs/DNNs') prohibitive energy cost. Specifically, R2PIM enhance efficiency by eliminating cost weight movements improving computational density through ReRAM's high density. However, is still limited dominant input partial sum (Psum) digital-to-analog (D/A) analog-to-digital...
Abstract Organic–inorganic halide perovskites have been intensively investigated as potential photovoltaic materials due to their exceptional optoelectronic properties and successful applications in perovskite solar cells (PSCs). However, a large number of defect states still exist the PSCs so far are detrimental power conversion efficiencies (PCEs) stability. Here, an effective strategy incorporating single-crystalline graphene quantum dots (GQDs) into films is proposed passivate states....
Lithium batteries have been widely used in our daily lives for their high energy density and long-term stability. However, safety problems are of paramount concern consumers, which restricts scale applications. Gel polymer electrolytes (GPEs) compensate the defects liquid leakage lower ionic conductivity solid electrolytes, attracted a lot attention. Herein, 3D interconnected highly porous structural gel electrolyte was prepared with alginate dressing as host material, poly(ethylene oxide)...
Accurate and robust recognition of burning state for sintering process rotary kiln plays an important role in the design image-based intelligent control systems. Existing approaches such as consensus-based methods, temperature-based methods image segmentation-based could not achieve satisfactory performance. This paper presents a flame system using set heterogeneous features fusion techniques. These features, i.e., color feature, global local configuration are able to characterize different...
Clinker free lime (f-CaO) content plays a crucial role in determining the quality of cement. However, existing methods are mainly based on laboratory analysis and with significant time delays, which makes closed-loop control f-CaO impossible. In this paper, multisource data ensemble learning-based soft sensor model is developed for online estimation clinker content. To build such model, input flame images, process variables, corresponding output rotary cement kiln were collected from No. 2...
Smart grid plays a crucial role for the smart society and upcoming carbon neutral society. Achieving autonomous fault detection is critical system state awareness, maintenance, operation. This article focuses on monitoring in discusses inherent technical challenges solutions. In particular, we first present basic principles of detection. Then explain new requirements detection, challenges, their possible A case study introduced as preliminary addition, highlight relevant directions future research.
In this paper, we introduce a simulacrum of hospital called Agent Hospital that simulates the entire process treating illness. All patients, nurses, and doctors are autonomous agents powered by large language models (LLMs). Our central goal is to enable doctor agent learn how treat illness within simulacrum. To do so, propose method MedAgent-Zero. As can simulate disease onset progression based on knowledge bases LLMs, keep accumulating experience from both successful unsuccessful cases....
Texture feature has been widely used in object recognition, image content analysis and many others. Among various approaches to texture extraction, Gabor filter emerged as one of the most popular ones. filter-based extractor is fact a bank defined by its parameters including frequencies, orientations smooth Gaussian envelope. In literature, different parameter settings have suggested, banks created these work well general. From perspective pattern classification, however, thus designed may...