Robust machine fault detection with independent component analysis and support vector data description

Ypma, Alexander; Tax, David M. J.; Duin, Rpw

doi:10.1109/nnsp.1999.788124

Cited by 38 publications

(23 citation statements)

References 7 publications

(6 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…support algorithms e.g. transform signals to frequency domain (like FFT) or reduce dimensionality of data (like PCA) [6]. A closer integration of the processing with hardware optimizes the signal processing chain and can lead to higher accuracy and lower communication costs.…”

Section: ) Local Processingmentioning

confidence: 99%

Servicing industrial machinery: Challenges using wireless identification and networked sensing systems

Fantana¹,

Riedel

2009

2009 Sixth International Conference on Networked Sensing Systems (INSS)

View full text Add to dashboard Cite

Abstract-Servicing industrial machinery and automation systems over their life targets at fast response and fast resolution. It requires skills, engineering knowledge and various data about the machine, its industrial environment, data from automation systems in the plant and historical information, which needs to be collected, correlated and analyzed. The advent of tiny smart devices such as RFID and networked wireless sensing nodes are promising and challenging for use in servicing industrial equipment. In this paper we identify fundamental challenges and requirements for establishing wireless networked sensing systems for industrial service applications. We further report on first design considerations for developing practical solutions and experiences from using prototypes in a test bed.

show abstract

Section: ) Local Processingmentioning

confidence: 99%

Servicing industrial machinery: Challenges using wireless identification and networked sensing systems

Fantana¹,

Riedel

2009

2009 Sixth International Conference on Networked Sensing Systems (INSS)

View full text Add to dashboard Cite

show abstract

“…Vibration was measured with 5 sensors mounted on a submersible pump operating in one normal and 3 abnormal states [14]. The data consists of the wavelet decomposition of the power spectrum.…”

Section: Datasets and Experimentsmentioning

confidence: 99%

Combining Fisher Linear Discriminants for Dissimilarity Representations

Pękalska

Skurichina

Duin

2000

Multiple Classifier Systems

View full text Add to dashboard Cite

Investigating a data set of the critical size makes a classification task difficult. Studying dissimilarity data refers to such a problem, since the number of samples equals their dimensionality. In such a case, a simple classifier is expected to generalize better than the complex one. Earlier experiments [9,3] confirm that in fact linear decision rules perform reasonably well on dissimilarity representations. For the Pseudo-Fisher linear discriminant the situation considered is the most inconvenient since the generalization error approaches its maximum when the size of a learning set equals the dimensionality [10]. However, some improvement is still possible. Combined classifiers may handle this problem better when a more powerful decision rule is found. In this paper, the usefulness of bagging and boosting of the Fisher linear discriminant for dissimilarity data is discussed and a new method based on random subspaces is proposed. This technique yields only a single linear pattern recognizer in the end and still significantly improves the accuracy.

show abstract

“…10], a kernel method, thus inherits all the related advantages of SVM. Since it was proposed, SVDD has been applied to various application problems, including image classification [39], remote sensing image analysis [2,23,24], medical image analysis [29], machine diagnostics [33,38], and multi-class classification problems [18,37], among others. Furthermore, SVDD is a preliminary step for support vector clustering [3,19,20].…”

Section: Introductionmentioning

confidence: 99%

Smoothly approximated support vector domain description

Zheng

2016

Pattern Recognition

View full text Add to dashboard Cite

Robust machine fault detection with independent component analysis and support vector data description

Cited by 38 publications

References 7 publications

Servicing industrial machinery: Challenges using wireless identification and networked sensing systems

Servicing industrial machinery: Challenges using wireless identification and networked sensing systems

Combining Fisher Linear Discriminants for Dissimilarity Representations

Smoothly approximated support vector domain description

Contact Info

Product

Resources

About