Adrian Stetco

Dr. Adrian Stetco

University of Manchester
orcid

Research Focus & Metrics

Academic Career Length

14Years (2013-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 April 2019 in Renewable Energy
Verified
Journal Article
Open access
Adrian StetcoAdrian Stetco
Adrian Stetco
FDFateme Dinmohammadi
Fateme Dinmohammadi
Xingyu ZhaoXingyu Zhao
Xingyu Zhao
Valentin RobuValentin Robu
Valentin Robu
David FlynnDavid Flynn
David Flynn
GNGoran Nenadic
Goran Nenadic

1 November 2015 in Expert Systems with Applications
Verified
Journal Article
Open access
Adrian StetcoAdrian Stetco
Adrian Stetco
Xiao-Jun ZengXiao-Jun Zeng
Xiao-Jun Zeng
JKJohn Keane
John Keane
Paper proposes the Fuzzy C-means++ method for improving the effectiveness and speed of the Fuzzy C-means algorithm.This method works by spreading the initial cluster representatives in the data space at initialization.The proposed algorithm achieves superior results on both artificially generated and real world data sets. Fuzzy C-means has been utilized successfully in a wide range of applications, extending the clustering capability of the K-means to datasets that are uncertain, vague and otherwise hard to cluster. This paper introduces the Fuzzy C-means++ algorithm which, by utilizing the seeding mechanism of the K-means++ algorithm, improves the effectiveness and speed of Fuzzy C-means. By careful seeding that disperses the initial cluster centers through the data space, the resulting Fuzzy C-means++ approach samples starting cluster representatives during the initialization phase. The cluster representatives are well spread in the input space, resulting in both faster convergence times and higher quality solutions. Implementations in R of standard Fuzzy C-means and Fuzzy C-means++ are evaluated on various data sets. We investigate the cluster quality and iteration count as we vary the spreading factor on a series of synthetic data sets. We run the algorithm on real world data sets and to account for the non-determinism inherent in these algorithms we record multiple runs while choosing different k parameter values. The results show that the proposed method gives significant improvement in convergence times (the number of iterations) of up to 40 (2.1 on average) times the standard on synthetic datasets and, in general, an associated lower cost function value and Xie-Beni value. A proof sketch of the logarithmically bounded expected cost function value is given.

1 October 2013
Verified
Conference Paper
Closed access
Adrian StetcoAdrian Stetco
Adrian Stetco
Xiao-Jun ZengXiao-Jun Zeng
Xiao-Jun Zeng
JKJohn Keane
John Keane
Every company listed on the London Stock Exchange is classified into an industry sector based on its primary activity, however, it may be both more interesting and valuable to group similarly performing companies based on their historical stock price record over a long period of time. Using fuzzy clustering analysis with a correlation-based metric, we obtain a more insightful categorization of the companies into groups with fuzzy boundaries, giving arguably a more realistic and detailed view of their relationships. Once cluster analysis is performed, we analyze the behaviour of discovered groups in terms of the volatility of their returns using both standard deviation and exponentially weighted moving average. This approach has the potential to be of practical relevance in the context of diversified portfolio construction as it can detect fuzzy clusters of correlated stocks that have lower inter-cluster correlation, analyze their volatility and sample potentially less risky combination of assets.

1 December 2019
Verified
Conference Paper
Closed access
Adrian StetcoAdrian Stetco
Adrian Stetco
AMAnees Mohammed
Anees Mohammed
SDSinisa Djurovic
Sinisa Djurovic
GNGoran Nenadic
Goran Nenadic
JKJohn Keane
John Keane
Traditionally, predictive maintenance of wind turbines has relied on experts to perform time consuming feature pre-processing using statistical, time and frequency domain analysis. Recent advancements in Convolutional Neural Networks have opened the potential for using featureless approaches that learn the discriminating patterns from big data sets without expert intervention. Given multi-dimensional time series data representing sensed electric currents, in this paper we explore the optimal window length that can be used to accurately determine its speed and load using Convolutional and Residual Networks. Choosing an optimal window length is a trade-off between accuracy and number of predictions per second. Fast predictions for operating parameters are useful in maintenance strategies but they come at a cost of decreased accuracy (as there is less data available in a shorter time interval). We show how fusing multiple signals can achieve high accuracy with nine speed and load cases varying from 375rpm with 0% load to 1500rpm and 100% load. Using Class Activation Maps we investigate features in the time domain picked up by the network to make its classification decisions. Further, we train the networks to predict the drive loads in a regression setting where the models are able to generalize well on unseen cases.

15 September 2020 in Energies
Verified
Journal Article
Open access
PDF file
Adrian StetcoAdrian Stetco
Adrian Stetco
JRJuan Melecio Ramirez
Juan Melecio Ramirez
AMAnees Mohammed
Anees Mohammed
Sinisa DurovicSinisa Durovic
Sinisa Durovic
GNGoran Nenadic
Goran Nenadic
JKJohn Keane
John Keane
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 and do not generalize well between applications. In this paper, we introduce a collection of end-to-end Convolutional Neural Networks for advanced condition monitoring of wind turbine generators. End-to-end models have the benefit of utilizing raw, unstructured signals to make predictions about the parameters of interest. This feature makes it easier to scale an existing collection of models to new predictive tasks (e.g., new failure types) since feature extracting steps are not required. These automated models achieve low Mean Squared Errors in predicting the generator operational state (40.85 for Speed and 0.0018 for Load) and high accuracy in diagnosing rotor demagnetization failures (99.67%) by utilizing only raw current signals. We show how to create, deploy and run the collection of proposed models in a real-time setting using a laptop connected to a test rig via a data acquisition card. Based on a sampling rate of 5 kHz, predictions are stored in an efficient time series database and monitored using a dynamic visualization framework. We further discuss existing options for understanding the decision process behind the predictions made by the models.

9 June 2019
Verified
Conference Paper
Closed access
PDF file
LZLin Zi
Lin Zi
Adrian StetcoAdrian Stetco
Adrian Stetco
JCJ. Carmona-Sanchez
J. Carmona-Sanchez
DCD. Cevasco
D. Cevasco
Maurizio ColluMaurizio Collu
Maurizio Collu
MBM. Barnes
M. Barnes
At present, over 1500 offshore wind turbines (OWTs) are operating in the UK with a capacity of 5.4GW. Until now, the research has mainly focused on how to minimise the CAPEX, but Operation and Maintenance (O&M) can represent up to 39% of the lifetime costs of an offshore wind farm, mainly due to the assets’ high cost and the harsh environment in which they operate. Focusing on O&M, the HOME Offshore research project (www.homeoffshore.org) aims to derive an advanced interpretation of the fault mechanisms through holistic multiphysics modelling of the wind farm. With the present work, an advanced model of dynamics for a single wind turbine is developed, able to identify the couplings between aero-hydro-servo-elastic (AHSE) dynamics and drive train dynamics. The wind turbine mechanical components, modelled using an AHSE dynamic model, are coupled with a detailed representation of a variable-speed direct-drive 5MW permanent magnet synchronous generator (PMSG) and its fully rated voltage source converters (VSCs). Using the developed model for the wind turbine, several case studies are carried out for above and below rated operating conditions. Firstly, the response time histories of wind turbine degrees of freedom (DOFs) are modelled using a full-order coupled analysis. Subsequently, regression analysis is applied in order to correlate DOFs and generated rotor torque (target degree of freedom for the failure mode in analysis), quantifying the level of inherent coupling effects. Finally, the reduced-order multiphysics models for a single offshore wind turbine are derived based on the strength of the correlation coefficients. The accuracy of the proposed reduced-order models is discussed, comparing it against the full-order coupled model in terms of statistical data and spectrum. In terms of statistical results, all the reduced-order models have a good agreement with the full-order results. In terms of spectrum, all the reduced-order models have a good agreement with the full-order results if the frequencies of interest are below 0.75Hz.