An ensemble classifier for vibration-based quality monitoring

Vibration-based quality monitoring of manufactured components often employs pattern recognition methods. Albeit developing several classification methods, they usually provide high accuracy for specific types of datasets, but not for general cases. In this paper, this issue has been addressed by developing a novel ensemble classifier based on the Dempster-Shafer theory of evidence. To deal with conflicting evidences, three remedies are proposed prior to combination: (i) selection of proper classifiers by evaluating the relevancy between the predicted and target outputs, (ii) devising an optimization method to minimize the distance between the predicted and target outputs, (iii) utilizing five different weighting factors, including a new one, to enhance the fusion performance. The effectiveness of the proposed framework is validated by its application to 15 UCI and KEEL machine learning datasets. It is then applied to two vibration-based datasets to detect defected samples: one synthetic dataset generated from the finite element model of a dogbone cylinder, and one real experimental dataset generated by collecting broadband vibrational response of polycrystalline Nickel alloy first-stage turbine blades. The investigation is made through statistical analysis in presence of different levels of noise-to-signal ratio. Comparing the results with those of four state-of-the-art fusion techniques reveals the good performance of the proposed ensemble method.

[1]  Galina L. Rogova,et al.  Combining the results of several neural network classifiers , 1994, Neural Networks.

[2]  Fuyuan Xiao,et al.  A Weighted Combination Method for Conflicting Evidence in Multi-Sensor Data Fusion , 2018, Sensors.

[3]  Marek Kurzynski,et al.  Optimal selection of ensemble classifiers using measures of competence and diversity of base classifiers , 2014, Neurocomputing.

[4]  Adam Krzyżak,et al.  Methods of combining multiple classifiers and their applications to handwriting recognition , 1992, IEEE Trans. Syst. Man Cybern..

[5]  Michele Meo,et al.  A Review of NDT/Structural Health Monitoring Techniques for Hot Gas Components in Gas Turbines , 2019, Sensors.

[6]  Fuyuan Xiao,et al.  Multi-sensor data fusion based on the belief divergence measure of evidences and the belief entropy , 2019, Inf. Fusion.

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

[8]  Richard K. Leach,et al.  X-ray computed tomography for additive manufacturing: a review , 2016 .

[9]  Fuyuan Xiao,et al.  A Novel Evidence Theory and Fuzzy Preference Approach-Based Multi-Sensor Data Fusion Technique for Fault Diagnosis , 2017, Sensors.

[10]  Witold Pedrycz,et al.  Aggregating multiple classification results using fuzzy integration and stochastic feature selection , 2010, Int. J. Approx. Reason..

[11]  Sankaran Mahadevan,et al.  An improved method to construct basic probability assignment based on the confusion matrix for classification problem , 2016, Inf. Sci..

[12]  M. Meo,et al.  A Nonlinear Ultrasonic Modulation Method for Crack Detection in Turbine Blades , 2020 .

[13]  Christophe Reboud,et al.  Real-Time NDT-NDE Through an Innovative Adaptive Partial Least Squares SVR Inversion Approach , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[14]  Ching Y. Suen,et al.  The Combination of Multiple Classifiers by A Neural Network Approach , 1995, Int. J. Pattern Recognit. Artif. Intell..

[15]  Francesco Ciampa,et al.  Recent Advances in Active Infrared Thermography for Non-Destructive Testing of Aerospace Components , 2018, Sensors.

[16]  James C. Bezdek,et al.  Decision templates for multiple classifier fusion: an experimental comparison , 2001, Pattern Recognit..

[17]  Xianguo Wu,et al.  Multi-classifier information fusion in risk analysis , 2020, Inf. Fusion.

[18]  Sean T. Gleeson,et al.  America Makes: National Additive Manufacturing Innovation Institute (NAMII) Project 1: Nondestructive Evaluation (NDE) of Complex Metallic Additive Manufactured (AM) Structures , 2014 .

[19]  Linghong Zhou,et al.  Feasibility study of a multi-criteria decision-making based hierarchical model for multi-modality feature and multi-classifier fusion: Applications in medical prognosis prediction , 2020, Inf. Fusion.

[20]  Glenn Shafer,et al.  Dempster's rule of combination , 2016, Int. J. Approx. Reason..

[21]  Anderson Rocha,et al.  Rank Aggregation for Pattern Classifier Selection in Remote Sensing Images , 2014, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[22]  W. Paepegem,et al.  Adaptive spectral band integration in flash thermography: Enhanced defect detectability and quantification in composites , 2020, Composites Part B: Engineering.

[23]  Hyung Jin Lim,et al.  Data-driven fatigue crack quantification and prognosis using nonlinear ultrasonic modulation , 2018, Mechanical Systems and Signal Processing.

[24]  Bogdan Gabrys,et al.  Classifier selection for majority voting , 2005, Inf. Fusion.

[25]  Hermann G. Matthies,et al.  Bayesian Parameter Determination of a CT-Test Described by a Viscoplastic-Damage Model Considering the Model Error , 2020, Metals.

[26]  Seong-Whan Lee,et al.  An information-theoretic strategy for constructing multiple classifier systems , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[27]  B. Goodlet,et al.  Process Compensated Resonance Testing Models for Quantification of Creep Damage in Single Crystal Nickel-based Superalloys , 2017 .

[28]  Thierry Denoeux,et al.  Classifier fusion in the Dempster-Shafer framework using optimized t-norm based combination rules , 2011, Int. J. Approx. Reason..

[29]  Wim Van Paepegem,et al.  Mahalanobis classification system (MCS) integrated with binary particle swarm optimization for robust quality classification of complex metallic turbine blades , 2021 .

[30]  Alexei Vinogradov,et al.  A real-time approach to acoustic emission clustering , 2013 .

[31]  Zhiyong Gao,et al.  Fault recognition using an ensemble classifier based on Dempster-Shafer Theory , 2020, Pattern Recognit..

[32]  Robert P. W. Duin,et al.  Support Vector Data Description , 2004, Machine Learning.

[33]  Luiz Eduardo Soares de Oliveira,et al.  Selecting and Combining Classifiers Based on Centrality Measures , 2020, Int. J. Artif. Intell. Tools.

[34]  Dirk Söffker,et al.  Does Classifier Fusion Improve the Overall Performance? Numerical Analysis of Data and Fusion Method Characteristics Influencing Classifier Fusion Performance , 2019, Entropy.

[35]  Moacir P. Ponti,et al.  Combining Classifiers: From the Creation of Ensembles to the Decision Fusion , 2011, SIBGRAPI Tutorials.

[36]  Luning Liu,et al.  A novel method to determine basic probability assignment in Dempster–Shafer theory and its application in multi-sensor information fusion , 2019, Int. J. Distributed Sens. Networks.

[37]  Gavin Brown.  An Information Theoretic Perspective on Multiple Classifier Systems , 2009, MCS.

[38]  Anton du Plessis,et al.  X-Ray Microcomputed Tomography in Additive Manufacturing: A Review of the Current Technology and Applications , 2018, 3D Printing and Additive Manufacturing.

[39]  Michael J. Pont,et al.  Application of Dempster-Shafer theory in condition monitoring applications: a case study , 2001, Pattern Recognit. Lett..

[40]  Mohamed A. Deriche,et al.  A New Technique for Combining Multiple Classifiers using The Dempster-Shafer Theory of Evidence , 2002, J. Artif. Intell. Res..