scholarly journals Alarms-related wind turbine fault detection based on kernel support vector machines

2019 ◽  
Vol 2019 (18) ◽  
pp. 4980-4985
Author(s):  
Yueqi Wu ◽  
Xiandong Ma
Keyword(s):  
Support Vector Machines ◽  
Fault Detection ◽  
Wind Turbine ◽  
Support Vector ◽  
Vector Machines ◽  
Kernel Support Vector Machines

scholarly journals Wind Turbine Multi-Fault Detection and Classification Based on SCADA Data

Energies ◽  
2018 ◽  
Vol 11 (11) ◽  
pp. 3018 ◽  
Author(s):  
Yolanda Vidal ◽  
Francesc Pozo ◽  
Christian Tutivén
Keyword(s):  
Support Vector Machines ◽  
Fault Detection ◽  
Wind Turbine ◽  
Condition Monitoring ◽  
Wind Turbines ◽  
Principal Component ◽  
Support Vector ◽  
Fault Detection And Classification ◽  
First Choice ◽  
Vector Machines

Due to the increasing installation of wind turbines in remote locations, both onshore and offshore, advanced fault detection and classification strategies have become crucial to accomplish the required levels of reliability and availability. In this work, without using specific tailored devices for condition monitoring but only increasing the sampling frequency in the already available (in all commercial wind turbines) sensors of the Supervisory Control and Data Acquisition (SCADA) system, a data-driven multi-fault detection and classification strategy is developed. An advanced wind turbine benchmark is used. The wind turbine we consider is subject to different types of faults on actuators and sensors. The main challenges of the wind turbine fault detection lie in their non-linearity, unknown disturbances, and significant measurement noise at each sensor. First, the SCADA measurements are pre-processed by group scaling and feature transformation (from the original high-dimensional feature space to a new space with reduced dimensionality) based on multiway principal component analysis through sample-wise unfolding. Then, 10-fold cross-validation support vector machines-based classification is applied. In this work, support vector machines were used as a first choice for fault detection as they have proven their robustness for some particular faults, but at the same time have never accomplished the detection and classification of all the proposed faults considered in this work. To this end, the choice of the features as well as the selection of data are of primary importance. Simulation results showed that all studied faults were detected and classified with an overall accuracy of 98.2%. Finally, it is noteworthy that the prediction speed allows this strategy to be deployed for online (real-time) condition monitoring in wind turbines.

Support Vector Machine for Recognition of White Blood Cells of Leukaemia

2011 ◽  
pp. 93-122 ◽  
Author(s):  
Stanislaw Osowski ◽  
Tomasz Markiewicz
Keyword(s):  
Support Vector Machines ◽  
Blood Cells ◽  
White Blood Cells ◽  
Myelogenous Leukaemia ◽  
Image Feature ◽  
Gaussian Kernel ◽  
Support Vector ◽  
Vector Machines ◽  
Kernel Support Vector Machines ◽  
The Individual

This chapter presents an automatic system for white blood cell recognition in myelogenous leukaemia on the basis of the image of a bone-marrow smear. It addresses the following fundamental problems of this task: the extraction of the individual cell image of the smear, generation of different features of the cell, selection of the best features, and final recognition using an efficient classifier network based on support vector machines. The chapter proposes the complete system solving all these problems, beginning from cell extraction using the watershed algorithm; the generation of different features based on texture, geometry, morphology, and the statistical description of the intensity of the image; feature selection using linear support vector machines; and finally classification by applying Gaussian kernel support vector machines. The results of numerical experiments on the recognition of up to 17 classes of blood cells of myelogenous leukaemia have shown that the proposed system is quite accurate and may find practical application in hospitals in the diagnosis of patients suffering from leukaemia.

Sign in / Sign up

Export Citation Format

Share Document