Deep-learning-based crack detection with applications for the structural health monitoring of gas turbines

Mahtab Mohtasham Khani*, Sahand Vahidnia, Leila Ghasemzadeh, Y. Eren Ozturk, Mustafa Yuvalaklioglu, Selim Akin, Nazim Kemal Ure

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

57 Citations (Scopus)

Abstract

Gas turbine maintenance requires consistent inspections of cracks and other structural anomalies. The inspections provide information regarding the overall condition of the structures and yield information for estimating structural health and repair costs. Various image processing techniques have been used in the past to address the problem of automated visual crack detection with varying degrees of success. In this work, we propose a novel crack detection framework that utilizes techniques from both classical image processing and deep learning methodologies. The main contribution of this work is demonstrating that applying filters to image data in the pre-processing phase can significantly boost the classification performance of a convolutional neural network–based model. The developed architecture outperforms compared works by yielding a 96.26% classification accuracy on a data set of cracked surface images collected from gas turbines.

Original languageEnglish
Pages (from-to)1440-1452
Number of pages13
JournalStructural Health Monitoring
Volume19
Issue number5
DOIs
Publication statusPublished - 1 Sept 2020

Bibliographical note

Publisher Copyright:
© The Author(s) 2019.

Funding

https://orcid.org/0000-0003-4811-072X Mohtasham Khani Mahtab 1 * Vahidnia Sahand 1 * Ghasemzadeh Leila 1 * Ozturk Y Eren 2 Yuvalaklioglu Mustafa 2 Akin Selim 2 https://orcid.org/0000-0003-2660-2141 Ure Nazim Kemal 1 1 Istanbul Technical University, Istanbul, Turkey 2 General Electric, Istanbul, Turkey Mahtab Mohtasham Khani, Istanbul Technical University, Maslak, Sarıyer, 34467 Istanbul, Turkey. Email: [email protected] * These authors contributed equally to the article. 11 2019 1475921719883202 © The Author(s) 2019 2019 SAGE Publications Gas turbine maintenance requires consistent inspections of cracks and other structural anomalies. The inspections provide information regarding the overall condition of the structures and yield information for estimating structural health and repair costs. Various image processing techniques have been used in the past to address the problem of automated visual crack detection with varying degrees of success. In this work, we propose a novel crack detection framework that utilizes techniques from both classical image processing and deep learning methodologies. The main contribution of this work is demonstrating that applying filters to image data in the pre-processing phase can significantly boost the classification performance of a convolutional neural network–based model. The developed architecture outperforms compared works by yielding a 96.26% classification accuracy on a data set of cracked surface images collected from gas turbines. Convolutional neural network CNN image processing crack detection gas turbine machine learning deep learning classification computer vision structural health monitoring GE Energy https://doi.org/10.13039/100006774 edited-state corrected-proof Declaration of conflicting interests The author(s) declared no potential conflicts of interest with respect to the research, authorship, and/or publication of this article. Funding The author(s) disclosed receipt of the following financial support for the research, authorship, and/or publication of this article: This work was supported by the General Electric Power Department. ORCID iDs Mahtab Mohtasham Khani https://orcid.org/0000-0003-4811-072X Nazim Kemal Ure https://orcid.org/0000-0003-2660-2141

FundersFunder number
General Electric Power Department

    Keywords

    • CNN
    • Convolutional neural network
    • classification
    • computer vision
    • crack detection
    • deep learning
    • gas turbine
    • image processing
    • machine learning
    • structural health monitoring

    Fingerprint

    Dive into the research topics of 'Deep-learning-based crack detection with applications for the structural health monitoring of gas turbines'. Together they form a unique fingerprint.

    Cite this