Non-destructive diagnostic of aircraft engine blades by Fuzzy Decision Tree

Abstract A new algorithm for non-destructive diagnosis based on signal classification is proposed. This algorithm permits classifying objects with different properties depending on signals characterizing the objects. In this paper, the algorithm is applied to diagnose blades of aircraft engine gas turbine according to vibration signal after a non-destructive shock excitation and to classify them as defective and faultless. Just like other signal classification algorithms, this algorithm consists of two steps that are signal preliminary transformation and classification. However, these steps are modified in the proposed algorithm. Unlike other algorithms, the fuzzy classifier is used in the classification step. The change of the classifier type causes modification of the preliminary transformation step because the attributes for the classification must be fuzzy. Therefore, fuzzification procedure is added into the step of preliminary transformation. The fuzzy classifier for the problem of aircraft engine blades diagnosis is ordered Fuzzy Decision Tree (oFDT) that is inducted by estimation of Cumulative Mutual Information. This induction has good efficiency for a small set of initial data. The accuracy of the classification of defective and faultless blades for the proposed algorithm is 98.5%, and oFDT for this classification is inducted based on 32 signals only. The comparison with other classification algorithms shows that oFDT based algorithm considered in this paper gives the best result for this problem.

[1]  Selcan Kaplan Berkaya,et al.  A survey on ECG analysis , 2018, Biomed. Signal Process. Control..

[2]  P. Geethanjali,et al.  DWT Based Detection of Epileptic Seizure From EEG Signals Using Naive Bayes and k-NN Classifiers , 2016, IEEE Access.

[3]  Nurhazimah Nazmi,et al.  A Review of Classification Techniques of EMG Signals during Isotonic and Isometric Contractions , 2016, Sensors.

[4]  Mislav Grgic,et al.  Independent comparative study of PCA, ICA, and LDA on the FERET data set , 2005, Int. J. Imaging Syst. Technol..

[5]  Peter Kipruto Chemweno,et al.  A review on lubricant condition monitoring information analysis for maintenance decision support , 2019, Mechanical Systems and Signal Processing.

[6]  Enrico Zio,et al.  Artificial intelligence for fault diagnosis of rotating machinery: A review , 2018, Mechanical Systems and Signal Processing.

[7]  Alex Alves Freitas,et al.  Automatic Design of Decision-Tree Induction Algorithms , 2015, SpringerBriefs in Computer Science.

[8]  Thomas Martin Deserno,et al.  Reliability estimation of healthcare systems using Fuzzy Decision Trees , 2016, 2016 Federated Conference on Computer Science and Information Systems (FedCSIS).

[9]  Jian Zhang,et al.  A pattern recognition technique for structural identification using observed vibration signals: Nonlinear case studies , 2008 .

[10]  Miroslav Kvassay,et al.  Electroencephalogram Signals Classification by Ordered Fuzzy Decision Tree , 2017, ICTERI.

[11]  Christian Cremona,et al.  Multivariate statistical analysis for early damage detection , 2013 .

[12]  Paul R. White,et al.  Fatigue crack diagnostics: A comparison of the use of the complex bicoherence and its magnitude , 2005 .

[13]  Ryszard Szczepanik.  EARLY DETECTION OF FATIGUE CRACKS IN TURBINE AERO-ENGINE ROTOR BLADES DURING FLIGHT , 2013 .

[14]  Gernot Kubin,et al.  Information Loss in Deterministic Signal Processing Systems , 2017 .

[15]  M. L. Dewal,et al.  Epileptic seizure detection using DWT based fuzzy approximate entropy and support vector machine , 2014, Neurocomputing.

[16]  Danilo Monarca,et al.  Ultrasonic waves for materials evaluation in fatigue, thermal and corrosion damage: A review , 2019, Mechanical Systems and Signal Processing.

[17]  K. I. Ramachandran,et al.  Automatic rule learning using decision tree for fuzzy classifier in fault diagnosis of roller bearing , 2007 .

[18]  Papia Ray,et al.  Fault detection, location and classification of a transmission line , 2017, Neural Computing and Applications.

[19]  Rajkumar Roy,et al.  Data Mining and Knowledge Reuse for the Initial Systems Design and Manufacturing: Aero-engine Service Risk Drivers , 2013 .

[20]  Ridha Djemal,et al.  Electroencephalography (EEG) signal processing for epilepsy and autism spectrum disorder diagnosis , 2017 .

[21]  Miroslav Hudec.  Fuzziness in Information Systems: How to Deal with Crisp and Fuzzy Data in Selection, Classification, and Summarization , 2016 .

[22]  Saeid Minaei,et al.  Fuzzy logic based classification of faults in mechanical differential , 2015 .

[23]  Nasser Kehtarnavaz,et al.  Real-Time Unsupervised Classification of Environmental Noise Signals , 2017, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

[24]  Hansa Rani Gupta,et al.  Power Spectrum Estimation using Welch Method for various Window Techniques , 2013 .

[25]  Sudhir Misra,et al.  Evaluating changes in fundamental cross-sectional mode of vibrations using a modified time domain for impact echo data , 2012 .

[26]  J. K. Roberge,et al.  Detection and characterization of blade/disk cracks in operational turbine engines , 2003, 2003 IEEE Aerospace Conference Proceedings (Cat. No.03TH8652).

[27]  Kim-Anh Lê Cao,et al.  Independent Principal Component Analysis for biologically meaningful dimension reduction of large biological data sets , 2012, BMC Bioinformatics.

[28]  Luiz Otávio Vilas Boas Oliveira,et al.  Real-Valued Negative Selection (RNS) for Classification Task , 2010, ICPR Contests.

[29]  Rahul Prabhu,et al.  System to monitor blade health in axial flow compressors , 2011, 2011 IEEE Conference on Prognostics and Health Management.

[30]  Gevork B. Gharehpetian,et al.  Classification and Discrimination Among Winding Mechanical Defects, Internal and External Electrical Faults, and Inrush Current of Transformer , 2018, IEEE Transactions on Industrial Informatics.

[31]  E. Alavi,et al.  Bladed disk crack detection through advanced analysis of blade time of arrival signal , 2012, 2012 IEEE Conference on Prognostics and Health Management.

[32]  Arsalane Zarghili,et al.  Comparative Study of PCA, ICA, LDA using SVM Classifier , 2014 .

[33]  Abdollah Bagheri,et al.  A nondestructive method for load rating of bridges without structural properties and plans , 2018 .

[34]  Kemal Polat,et al.  A novel data reduction method: Distance based data reduction and its application to classification of epileptiform EEG signals , 2008, Appl. Math. Comput..

[35]  Ilango Paramasivam,et al.  User localisation using wireless signal strength - an application for pattern classification using fuzzy decision tree , 2016, Int. J. Internet Protoc. Technol..

[36]  Hadi Salehi,et al.  Emerging artificial intelligence methods in structural engineering , 2018, Engineering Structures.

[37]  Iren Valova,et al.  Fuzzyfication of principle component analysis for data dimensionalty reduction , 2016, 2016 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE).

[38]  Hélène Welemane,et al.  NDT-based design of joint material for the detection of bonding defects by infrared thermography , 2018 .

[39]  Zhou Ji,et al.  A BOUNDARY-AWARE NEGATIVE SELECTION ALGORITHM , 2005 .

[40]  Pavel Potapov,et al.  On the loss of information in PCA of spectrum-images. , 2017, Ultramicroscopy.

[41]  Abdulhamit Subasi,et al.  EEG signal classification using PCA, ICA, LDA and support vector machines , 2010, Expert Syst. Appl..

[42]  Takehisa Yairi,et al.  A review on the application of deep learning in system health management , 2018, Mechanical Systems and Signal Processing.

[43]  Fabrizio D'Amico,et al.  A spectral analysis of ground-penetrating radar data for the assessment of the railway ballast geometric properties , 2017 .

[44]  Lijuan Cao,et al.  A comparison of PCA, KPCA and ICA for dimensionality reduction in support vector machine , 2003, Neurocomputing.