A5101986134- Anomaly Detection Techniques and Applications
- Building Energy and Comfort Optimization
- Fault Detection and Control Systems
- Power Systems and Technologies
- Solar Radiation and Photovoltaics
- Remote Sensing and LiDAR Applications
- Software System Performance and Reliability
- Urban Heat Island Mitigation
- Structural Integrity and Reliability Analysis
- Online Learning and Analytics
- Artificial Intelligence in Healthcare
- Geotechnical Engineering and Underground Structures
- Generative Adversarial Networks and Image Synthesis
- Digital Media Forensic Detection
- Machine Fault Diagnosis Techniques
- Material Properties and Failure Mechanisms
- Cavitation Phenomena in Pumps
- Icing and De-icing Technologies
- Hydraulic and Pneumatic Systems
- Energy Load and Power Forecasting
- Collaboration in agile enterprises
- Organizational Management and Leadership
- Coal Properties and Utilization
- Photovoltaic System Optimization Techniques
- Sparse and Compressive Sensing Techniques
China University of Mining and Technology
2025
University of Newcastle Australia
2024
Yanshan University
2024
Eindhoven University of Technology
2022-2023
Tianjin University
2022
Chengdu University
2022
State Key Laboratory of Hydraulic Engineering Simulation and Safety
2022
State Key Laboratory of Hydrology-Water Resources and Hydraulic Engineering
2022
Jilin University
2021
Shenyang Aerospace University
2019
Although trees and urban vegetation have a significant influence on solar irradiation in the built environment, their impact daylight energy consumption is often not considered building performance environment simulation studies. This paper presents novel method for comprehensive irradiance assessment that considers dynamic partial shading impacts from trees. The proposed takes point clouds as input consists of three subsequent steps: (a) DGCNN-based segmentation, (b) fusion model...
To reveal the influence of ultra-close coal seams mining on surrounding rock disturbance, PFC2D is introduced to establish a simplified particle flow model strata in deeply buried mine, damage and stress evolution characteristics were studied based double seam mining. The results show that after excavation, fracture length reached an accuracy 97% compared with theoretical calculation results, showing good match calculations initial level obtained by subsequent monitoring consistent measured...
Student attrition poses significant societal and economic challenges, leading to unemployment, lower earnings, other adverse outcomes for individuals communities. To address this, predictive systems leveraging machine learning Big Data aim identify at-risk students early intervene effectively. This project focuses on extracting key parameters from past dropout data construct a model alert authorities promptly. Two preliminary trials refine models, establish evaluation standards, optimize...
Abstract The Photovoltaic (PV) Performance Modeling Collaborative (PVPMC) organized a blind PV performance modeling intercomparison to allow modelers blindly test their models and ability against real system data. Measured weather irradiance data were provided along with detailed descriptions of systems from two locations (Albuquerque, New Mexico, USA, Roskilde, Denmark). Participants asked simulate the plane‐of‐array irradiance, module temperature, DC power output six submit results Sandia...
Raytracing-based methods are widely used for quantifying irradiation on building surfaces. Urban 3D surface models necessary input raytracing simulations, which can be generated from open-source point cloud data with the help of reconstruction algorithms. In research and engineering practice, various algorithms being this purpose; each leading to different mesh topologies corresponding performance. This paper compares impacts four by investigating their performance using DAYSIM simulations....
Student attrition poses significant societal and economic challenges, leading to unemployment, lower earnings, other adverse outcomes for individuals communities. To address this, predictive systems leveraging machine learning big data aim identify at-risk students early intervene effectively. This study leverages key parameters influencing student dropout, develop a model, enable real-time monitoring timely interventions by educational authorities. Two preliminary trials refined models,...
In machine learning, stochastic gradient descent (SGD) is widely deployed to train models using highly non-convex objectives with equally complex noise models. Unfortunately, SGD theory often makes restrictive assumptions that fail capture the non-convexity of real problems, and almost entirely ignore exist in practice. this work, we make substantial progress on shortcoming. First, establish SGD's iterates will either globally converge a stationary point or diverge under nearly arbitrary...
Generative adversarial networks (GANs) are known for their strong abilities on capturing the underlying distribution of training instances. Since seminal work GAN, many variants GAN have been proposed. However, existing GANs almost established assumption that dataset is clean. But in real-world applications, this may not hold, is, be contaminated by a proportion undesired When such datasets, will learn mixture desired and instances, rather than data only (target distribution). To target from...
Targeting at the problem of pavement cracking under long-term load, this study developed a new-type semi-rigid base layer structure based on CGC (cement stabilized macadam - graded broken stone cement macadam) combinations, and used ANSYS to simulate proposed conditions different modulus deflection thickness, vertical strain values top surface roadbed, transverse tensile stress bottom layer. The simulation results indicate that, various mechanical properties new can well meet specifications,...
For In order to solve the problems of weak signal characteristics and extraction difficulty during early fault stage inter-shaft bearing, this paper introduces quantum theory into calculation information entropy, proposes a new feature method bearings, entropy. Firstly, based on basic principle theory, multi-qubit system acoustic emission is established, entropy constructed. Then, four different working conditions signal, i.e. outer ring fault, rolling element inner trouble-free, are...
Ideas on educational psychology suggest that a learning process occurs when people participate within social communities. A model is constructed based two primary factors in the : knowledge storage and interactive ability of each person. Results simulations are consistent with some actual phenomena including average achieved different effects under conditions. Functions main teachers' influences also studied discussed.
Generative adversarial networks (GANs) are known for their strong abilities on capturing the underlying distribution of training instances. Since seminal work GAN, many variants GAN have been proposed. However, existing GANs almost established assumption that dataset is clean. But in real-world applications, this may not hold, is, be contaminated by a proportion undesired When such datasets, will learn mixture desired and instances, rather than data only (target distribution). To target from...
Freight yard is the basic production unit of railway freight transportation. The slotting optimization in it significant to increase utilization site, reduce operating cost and enhance benefits transportation enterprise. This paper analyzes major factors influencing optimization, puts forward an optimized mathematical model which based on principle minimizing time store fetch goods. Moreover, are transformed with penalty-function; meanwhile, improved genetic algorithm taken as method....
According to ZFW20A-252 GIS equipment, this paper proposes a low-cost (Gas Insulated Switchgear) digital transformation program that carries out design and implementation of the Intelligent Electronic Device (IED) operated by GIS. By making lot experiments about IED GOOSE messages, opening closing state, upload displacement as well response time, it is confirmed not only meets requirements fast message transmission delay must be less than 3ms, but also improves stability under different...
The new energy-saving conductors have been developed, which can significantly reduce transmission loss. Through icing test and wind tunnel test, the aerodynamic characteristics are experimentally studied. Firstly, actual conditions of single quad-bundle conventional conductor under different atmospheric environmental parameters (such as: velocity, time, temperature) Then, considering that rotation load in environment, influence velocity on growth is studied, drag coefficient compared with...
The goal of anomaly detection is to identify anomalous samples from normal ones. In this paper, a small number anomalies are assumed be available at the training stage, but they collected only several types, leaving majority types not represented in dataset all. To effectively leverage kind incomplete knowledge by anomalies, we propose learn probability distribution that can model samples, also guarantee assign low density values for anomalies. end, an anomaly-aware generative adversarial...