Optimal Detection of New Classes of Faults by an Invasive Weed Optimization Method

R. Razavi-Far; Vasile Palade; E. Zio

doi:10.1109/IJCNN.2014.6889887

Optimal Detection of New Classes of Faults by an Invasive Weed Optimization Method

R. Razavi-Far, Vasile Palade, E. Zio

Research output: Chapter in Book/Report/Conference proceeding › Chapter

22 Citations (Scopus)

Abstract

Proper detection of unknown patterns plays an important role in diagnosing new classes of faults. This can be done by incremental learning of novel information and updating the diagnostic system by appending newly trained fault classifiers in an ensemble design. We consider a new-class fault detector previously developed by the authors and based on thresholding the normalized weighted average of the outputs (NWAO) of the base classifiers in a multi-classifier diagnostic system. A proper tuning of the thresholds in the NWAO detector is necessary to achieve a satisfactory performance. This is done in this paper by specifically introducing a performance function and optimizing it within the necessary trade-off between new class false alarm and new class missed alarm rates, by means of an Invasive Weed Optimization (IWO) algorithm. The optimal NWAO detector is tested with respect to a set of simulated sensor faults in the doubly-fed induction generator (DFIG) of a wind turbine.

Original language	English
Title of host publication	International Joint Conference on Neural Networks, IJCNN 2014
Publisher	IEEE
Pages	91-98
Volume	Article number 6889887
ISBN (Print)	978-147991484-5
DOIs	https://doi.org/10.1109/IJCNN.2014.6889887
Publication status	Published - 3 Sept 2014

Bibliographical note

This conference paper is not yet available on the repository. The paper was given at the International Joint Conference on Neural Networks, IJCNN 2014; Beijing; China; 6 July 2014 through 11 July 2014.

Access to Document

10.1109/IJCNN.2014.6889887

Cite this

@inbook{058e3996649f48249e80d68bd2a14206,

title = "Optimal Detection of New Classes of Faults by an Invasive Weed Optimization Method",

abstract = "Proper detection of unknown patterns plays an important role in diagnosing new classes of faults. This can be done by incremental learning of novel information and updating the diagnostic system by appending newly trained fault classifiers in an ensemble design. We consider a new-class fault detector previously developed by the authors and based on thresholding the normalized weighted average of the outputs (NWAO) of the base classifiers in a multi-classifier diagnostic system. A proper tuning of the thresholds in the NWAO detector is necessary to achieve a satisfactory performance. This is done in this paper by specifically introducing a performance function and optimizing it within the necessary trade-off between new class false alarm and new class missed alarm rates, by means of an Invasive Weed Optimization (IWO) algorithm. The optimal NWAO detector is tested with respect to a set of simulated sensor faults in the doubly-fed induction generator (DFIG) of a wind turbine.",

author = "R. Razavi-Far and Vasile Palade and E. Zio",

note = "This conference paper is not yet available on the repository. The paper was given at the International Joint Conference on Neural Networks, IJCNN 2014; Beijing; China; 6 July 2014 through 11 July 2014.",

year = "2014",

month = sep,

day = "3",

doi = "10.1109/IJCNN.2014.6889887",

language = "English",

isbn = "978-147991484-5",

volume = "Article number 6889887",

pages = "91--98",

booktitle = "International Joint Conference on Neural Networks, IJCNN 2014",

publisher = "IEEE",

address = "United States",

}

TY - CHAP

T1 - Optimal Detection of New Classes of Faults by an Invasive Weed Optimization Method

AU - Razavi-Far, R.

AU - Palade, Vasile

AU - Zio, E.

N1 - This conference paper is not yet available on the repository. The paper was given at the International Joint Conference on Neural Networks, IJCNN 2014; Beijing; China; 6 July 2014 through 11 July 2014.

PY - 2014/9/3

Y1 - 2014/9/3

N2 - Proper detection of unknown patterns plays an important role in diagnosing new classes of faults. This can be done by incremental learning of novel information and updating the diagnostic system by appending newly trained fault classifiers in an ensemble design. We consider a new-class fault detector previously developed by the authors and based on thresholding the normalized weighted average of the outputs (NWAO) of the base classifiers in a multi-classifier diagnostic system. A proper tuning of the thresholds in the NWAO detector is necessary to achieve a satisfactory performance. This is done in this paper by specifically introducing a performance function and optimizing it within the necessary trade-off between new class false alarm and new class missed alarm rates, by means of an Invasive Weed Optimization (IWO) algorithm. The optimal NWAO detector is tested with respect to a set of simulated sensor faults in the doubly-fed induction generator (DFIG) of a wind turbine.

AB - Proper detection of unknown patterns plays an important role in diagnosing new classes of faults. This can be done by incremental learning of novel information and updating the diagnostic system by appending newly trained fault classifiers in an ensemble design. We consider a new-class fault detector previously developed by the authors and based on thresholding the normalized weighted average of the outputs (NWAO) of the base classifiers in a multi-classifier diagnostic system. A proper tuning of the thresholds in the NWAO detector is necessary to achieve a satisfactory performance. This is done in this paper by specifically introducing a performance function and optimizing it within the necessary trade-off between new class false alarm and new class missed alarm rates, by means of an Invasive Weed Optimization (IWO) algorithm. The optimal NWAO detector is tested with respect to a set of simulated sensor faults in the doubly-fed induction generator (DFIG) of a wind turbine.

U2 - 10.1109/IJCNN.2014.6889887

DO - 10.1109/IJCNN.2014.6889887

M3 - Chapter

SN - 978-147991484-5

VL - Article number 6889887

SP - 91

EP - 98

BT - International Joint Conference on Neural Networks, IJCNN 2014

PB - IEEE

ER -

Optimal Detection of New Classes of Faults by an Invasive Weed Optimization Method

Abstract

Bibliographical note

Access to Document

Fingerprint

Cite this