A5020797698- Energy Load and Power Forecasting
- Machine Fault Diagnosis Techniques
- Advanced Clustering Algorithms Research
- Time Series Analysis and Forecasting
- Fuzzy Logic and Control Systems
- Face and Expression Recognition
- Financial Risk and Volatility Modeling
- Wind Energy Research and Development
- Wind Turbine Control Systems
- Anomaly Detection Techniques and Applications
- Magnetic Bearings and Levitation Dynamics
- Power System Reliability and Maintenance
- Transportation Systems and Infrastructure
- Complex Systems and Time Series Analysis
- Data Stream Mining Techniques
- Structural Health Monitoring Techniques
University of Manchester
2013-2020
Fuzzy C-means has been utilized successfully in a wide range of applications, extending the clustering capability K-means to datasets that are uncertain, vague and otherwise hard cluster. This paper introduces C-means++ algorithm which, by utilizing seeding mechanism K-means++ algorithm, improves effectiveness speed C-means. By careful disperses initial cluster centers through data space, resulting approach samples starting representatives during initialization phase. The well spread input...
Every company listed on the London Stock Exchange is classified into an industry sector based its primary activity, however, it may be both more interesting and valuable to group similarly performing companies their historical stock price record over a long period of time. Using fuzzy clustering analysis with correlation-based metric, we obtain insightful categorization groups boundaries, giving arguably realistic detailed view relationships. Once cluster performed, analyze behaviour...
Traditionally, predictive maintenance of wind turbines has relied on experts to perform time consuming feature pre-processing using statistical, and frequency domain analysis. Recent advancements in Convolutional Neural Networks have opened the potential for featureless approaches that learn discriminating patterns from big data sets without expert intervention. Given multi-dimensional series representing sensed electric currents, this paper we explore optimal window length can be used...
Data-driven wind generator condition monitoring systems largely rely on multi-stage processing involving feature selection and extraction followed by supervised learning. These stages require expert analysis, are potentially error-prone do not generalize well between applications. In this paper, we introduce a collection of end-to-end Convolutional Neural Networks for advanced turbine generators. End-to-end models have the benefit utilizing raw, unstructured signals to make predictions about...
Abstract At present, over 1500 offshore wind turbines (OWTs) are operating in the UK with a capacity of 5.4GW. Until now, research has mainly focused on how to minimise CAPEX, but Operation and Maintenance (O&M) can represent up 39% lifetime costs an farm, due assets’ high cost harsh environment which they operate. Focusing O&M, HOME Offshore project (www.homeoffshore.org) aims derive advanced interpretation fault mechanisms through holistic multiphysics modelling farm. With present...