• Engineering
  • Published 2013

A machine learning approach to Structural Health Monitoring with a view towards wind turbines

@inproceedings{Dervilis2013AML,
  title={A machine learning approach to Structural Health Monitoring with a view towards wind turbines},
  author={Nikolaos Dervilis},
  year={2013}
}
The work of this thesis is centred around Structural Health Monitoring (SHM) and is divided into three main parts. The thesis starts by exploring di�erent architectures of auto-association. These are evaluated in order to demonstrate the ability of nonlinear auto-association of neural networks with one nonlinear hidden layer as it is of great interest in terms of reduced computational complexity. It is shown that linear PCA lacks performance for novelty detection. The novel key study… CONTINUE READING

References

Publications referenced by this paper.
SHOWING 1-10 OF 134 REFERENCES

Auto-association by multilayer perceptrons and singular value decomposition

VIEW 16 EXCERPTS
HIGHLY INFLUENTIAL

Gaussian processes for machine learning

VIEW 8 EXCERPTS
HIGHLY INFLUENTIAL

MINIMUM VOLUME ENCLOSING ELLIPSOIDS

VIEW 9 EXCERPTS
HIGHLY INFLUENTIAL

Neural networks for pattern recognition

  • Christopher M Bishop
  • Clarendon press Oxford,
  • 1995
VIEW 20 EXCERPTS
HIGHLY INFLUENTIAL

Simplified neuron model as a principal component analyzer

  • Erkki Oja
  • Medicine, Mathematics
  • Journal of mathematical biology
  • 1982
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Reliability of Wind Turbines

VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Pattern recognition and machine learning, volume 4. springer

  • Christopher M Bishop
  • New York,
  • 2006
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Sandwich Materials for Wind Turbine Blades

VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL