Advanced search
1 file | 965.65 KB Add to list

Mahalanobis classification system for quality classification of complex metallic turbine blades

Author
Organization
Abstract
The complex geometry of metallic components combined with the variety of possible damage features limits the application of conventional NDT technologies. For parts with complex geometric shapes relevant product quality assurance tools are needed. Process Compensated Resonance Testing (PCRT) is an advanced and sensitive non-destructive evaluation method. It employs Mahalanobis Taguchi System (MTS) to classify the components as Good/Bad by evaluating the variations on resonance frequencies in Mahalanobis space. However, the process of feature selection and threshold determination in MTS is questionable. In the present paper, a two-stage Mahalanobis Classification System (MCS) approach is proposed coupled with binary particle swarm optimization procedure. The proposed MCS approach is applied to equiaxed Nickel alloy first-stage turbine blades with various possible defects. The obtained results demonstrate the high classification accuracy and evidence of the superior performance of the proposed approach.
Keywords
MAHALANOBIS-TAGUCHI SYSTEM, PARTICLE SWARM OPTIMIZER

Downloads

  • (...).pdf
    • full text (Published version)
    • |
    • UGent only
    • |
    • PDF
    • |
    • 965.65 KB

Citation

Please use this url to cite or link to this publication:

MLA
Cheng, Liangliang, et al. “Mahalanobis Classification System for Quality Classification of Complex Metallic Turbine Blades.” PROCEEDINGS OF INTERNATIONAL CONFERENCE ON NOISE AND VIBRATION ENGINEERING (ISMA2020) / INTERNATIONAL CONFERENCE ON UNCERTAINTY IN STRUCTURAL DYNAMICS (USD2020), edited by W. Desmet et al., Katholieke Universiteit Leuven (Departement Werktuigkunde), 2020, pp. 2985–94.
APA
Cheng, L., Yaghoubi Nasrabadi, V., Van Paepegem, W., & Kersemans, M. (2020). Mahalanobis classification system for quality classification of complex metallic turbine blades. In W. Desmet, B. Pluymers, D. Moens, & S. Vandemaele (Eds.), PROCEEDINGS OF INTERNATIONAL CONFERENCE ON NOISE AND VIBRATION ENGINEERING (ISMA2020) / INTERNATIONAL CONFERENCE ON UNCERTAINTY IN STRUCTURAL DYNAMICS (USD2020) (pp. 2985–2994). Heverlee: Katholieke Universiteit Leuven (Departement Werktuigkunde).
Chicago author-date
Cheng, Liangliang, Vahid Yaghoubi Nasrabadi, Wim Van Paepegem, and Mathias Kersemans. 2020. “Mahalanobis Classification System for Quality Classification of Complex Metallic Turbine Blades.” In PROCEEDINGS OF INTERNATIONAL CONFERENCE ON NOISE AND VIBRATION ENGINEERING (ISMA2020) / INTERNATIONAL CONFERENCE ON UNCERTAINTY IN STRUCTURAL DYNAMICS (USD2020), edited by W. Desmet, B. Pluymers, D. Moens, and S. Vandemaele, 2985–94. Heverlee: Katholieke Universiteit Leuven (Departement Werktuigkunde).
Chicago author-date (all authors)
Cheng, Liangliang, Vahid Yaghoubi Nasrabadi, Wim Van Paepegem, and Mathias Kersemans. 2020. “Mahalanobis Classification System for Quality Classification of Complex Metallic Turbine Blades.” In PROCEEDINGS OF INTERNATIONAL CONFERENCE ON NOISE AND VIBRATION ENGINEERING (ISMA2020) / INTERNATIONAL CONFERENCE ON UNCERTAINTY IN STRUCTURAL DYNAMICS (USD2020), ed by. W. Desmet, B. Pluymers, D. Moens, and S. Vandemaele, 2985–2994. Heverlee: Katholieke Universiteit Leuven (Departement Werktuigkunde).
Vancouver
1.
Cheng L, Yaghoubi Nasrabadi V, Van Paepegem W, Kersemans M. Mahalanobis classification system for quality classification of complex metallic turbine blades. In: Desmet W, Pluymers B, Moens D, Vandemaele S, editors. PROCEEDINGS OF INTERNATIONAL CONFERENCE ON NOISE AND VIBRATION ENGINEERING (ISMA2020) / INTERNATIONAL CONFERENCE ON UNCERTAINTY IN STRUCTURAL DYNAMICS (USD2020). Heverlee: Katholieke Universiteit Leuven (Departement Werktuigkunde); 2020. p. 2985–94.
IEEE
[1]
L. Cheng, V. Yaghoubi Nasrabadi, W. Van Paepegem, and M. Kersemans, “Mahalanobis classification system for quality classification of complex metallic turbine blades,” in PROCEEDINGS OF INTERNATIONAL CONFERENCE ON NOISE AND VIBRATION ENGINEERING (ISMA2020) / INTERNATIONAL CONFERENCE ON UNCERTAINTY IN STRUCTURAL DYNAMICS (USD2020), Leuven, BELGIUM, 2020, pp. 2985–2994.
@inproceedings{8712796,
  abstract     = {{The complex geometry of metallic components combined with the variety of possible damage features limits the application of conventional NDT technologies. For parts with complex geometric shapes relevant product quality assurance tools are needed. Process Compensated Resonance Testing (PCRT) is an advanced and sensitive non-destructive evaluation method. It employs Mahalanobis Taguchi System (MTS) to classify the components as Good/Bad by evaluating the variations on resonance frequencies in Mahalanobis space. However, the process of feature selection and threshold determination in MTS is questionable. In the present paper, a two-stage Mahalanobis Classification System (MCS) approach is proposed coupled with binary particle swarm optimization procedure. The proposed MCS approach is applied to equiaxed Nickel alloy first-stage turbine blades with various possible defects. The obtained results demonstrate the high classification accuracy and evidence of the superior performance of the proposed approach.}},
  author       = {{Cheng, Liangliang and Yaghoubi Nasrabadi, Vahid and Van Paepegem, Wim and Kersemans, Mathias}},
  booktitle    = {{PROCEEDINGS OF INTERNATIONAL CONFERENCE ON NOISE AND VIBRATION ENGINEERING (ISMA2020) / INTERNATIONAL CONFERENCE ON UNCERTAINTY IN STRUCTURAL DYNAMICS (USD2020)}},
  editor       = {{Desmet, W. and Pluymers, B. and Moens, D. and Vandemaele, S.}},
  isbn         = {{9789082893113}},
  keywords     = {{MAHALANOBIS-TAGUCHI SYSTEM,PARTICLE SWARM OPTIMIZER}},
  language     = {{eng}},
  location     = {{Leuven, BELGIUM}},
  pages        = {{2985--2994}},
  publisher    = {{Katholieke Universiteit Leuven (Departement Werktuigkunde)}},
  title        = {{Mahalanobis classification system for quality classification of complex metallic turbine blades}},
  url          = {{http://past.isma-isaac.be/isma2020/}},
  year         = {{2020}},
}

Web of Science
Times cited: