A Novel Ensemble Model on Defects Identification in Aero-Engine Blade

Machine learning-based defect identification has emerged as a promising solution to improving the defect accuracy of the aero-engine blade. This solution adopts machine learning classifiers to classify the types of defects. These classifiers are trained to use features collected in ultrasonic echo signals. However, the current studies show the potential number of features, such as statistic values, for identifying defect reaches a number more than that offered by an ultrasonic echo signal. This necessitates multiple acquisitions of echo signal and increases manual effort, and the feature obtained from feature selection is sensitive to the characteristic of the classifier, which further increases the uncertainty of the classifier result. This paper proposes an ensemble learning technique that is only based on few features obtained from an echo signal and still achieves a high accuracy of defect identification as that in traditional machine learning, eliminating the need for multiple acquisitions of the echo signal. To this end, we apply two well-known ensemble learning classifiers and simultaneously compare three widely used machine learning models on defect identification of blades. The result shows that the proposed ensemble learning models outperform machine learning-based models with an equal number of features. In addition, the two-feature-based ensemble learning model reaches an accuracy close to that of multiple statistic features-based machine learning models, where features are obtained from multiple collections of the signal.

[1]  Patrick Flandrin,et al.  A complete ensemble empirical mode decomposition with adaptive noise , 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[2]  Jinwu Xu,et al.  Defects identification using the improved ultrasonic measurement model and support vector machines , 2020 .

[3]  Lei Zhang,et al.  Improved empirical mode decomposition based denoising method for lidar signals , 2014 .

[4]  Yoav Freund,et al.  A decision-theoretic generalization of on-line learning and an application to boosting , 1997, EuroCOLT.

[5]  A. Robert Calderbank,et al.  Lossless image compression using integer to integer wavelet transforms , 1997, Proceedings of International Conference on Image Processing.

[6]  S. Sambath,et al.  Automatic Defect Classification in Ultrasonic NDT Using Artificial Intelligence , 2011 .

[7]  Xian Cao,et al.  Two-sided ultrasonic surface rolling process of aeroengine blades based on on-machine noncontact measurement , 2020, Frontiers of Mechanical Engineering.

[8]  Wim Sweldens,et al.  The lifting scheme: a construction of second generation wavelets , 1998 .

[9]  F C Cruz,et al.  Efficient feature selection for neural network based detection of flaws in steel welded joints using ultrasound testing , 2017, Ultrasonics.

[10]  D. Thompson,et al.  Review of Progress in Quantitative Nondestructive Evaluation , 1982 .

[11]  Rui-Mei Zhao,et al.  Improved threshold denoising method based on wavelet transform , 2015, 2015 7th International Conference on Modelling, Identification and Control (ICMIC).

[12]  Bin Jiang,et al.  A Data-Driven Aero-Engine Degradation Prognostic Strategy , 2019, IEEE Transactions on Cybernetics.

[13]  Minoru Kurosawa,et al.  A linearization-based method of simultaneous position and velocity measurement using ultrasonic waves , 2015 .

[14]  Norden E. Huang,et al.  Complementary Ensemble Empirical Mode Decomposition: a Novel Noise Enhanced Data Analysis Method , 2010, Adv. Data Sci. Adapt. Anal..

[15]  M. G. Droubi,et al.  Acoustic emission method for defect detection and identification in carbon steel welded joints , 2017 .

[16]  Yong Huang,et al.  A Bayesian approach for sparse flaw detection from noisy signals for ultrasonic NDT , 2017 .

[17]  Ming-Yue Zhai,et al.  Seismic data denoising based on the fractional Fourier transformation , 2014 .

[19]  Mohammad Hossein Doost Mohammadi Improved Denoising Method for Ultrasonic Echo with Mother Wavelet Optimization and Best-Basis Selection , 2016 .

[20]  Yang Li,et al.  Inspection of butt welds for complex surface parts using ultrasonic phased array. , 2019, Ultrasonics.

[21]  Torsten Hothorn,et al.  Double-Bagging: Combining Classifiers by Bootstrap Aggregation , 2002, Pattern Recognit..

[22]  Abdullah Alsaeedi,et al.  Software Defect Prediction Using Supervised Machine Learning and Ensemble Techniques: A Comparative Study , 2019, Journal of Software Engineering and Applications.

[23]  Ke Chen,et al.  A quantified self-adaptive filtering method: effective IMFs selection based on CEEMD , 2018 .

[24]  Ergun Erçelebi Second generation wavelet transform-based pitch period estimation and voiced/unvoiced decision for speech signals , 2003 .

[25]  M. Hauser,et al.  Development of a method to characterize high-protein dairy powders using an ultrasonic flaw detector. , 2016, Journal of dairy science.

[26]  Ling Zhang,et al.  Research on Recognition of Nine Kinds of Fine Gestures Based on Adaptive AdaBoost Algorithm and Multi-Feature Combination , 2019, IEEE Access.

[27]  Liu Shuang,et al.  Coordinated bilateral ultrasonic surface rolling process on aero-engine blades , 2019, The International Journal of Advanced Manufacturing Technology.

[28]  William Q. Meeker,et al.  Detecting cracks in aircraft engine fan blades using vibrothermography nondestructive evaluation , 2014, Reliab. Eng. Syst. Saf..

[29]  Xue Li,et al.  Casting Blanks Cleanliness Evaluation Based on Ultrasonic Microscopy and Morphological Filtering , 2020, Metals.

[30]  Haiyang Zhan,et al.  Analysis of Aero-engine Performance and Selection Based on Fuzzy Comprehensive Evaluation , 2017 .