Integrated interval Mahalanobis classification system for the quality classification of turbine blades based on vibrational data incorporating measurement uncertainty
Restricted accessResearch articleFirst published online January, 2023
Integrated interval Mahalanobis classification system for the quality classification of turbine blades based on vibrational data incorporating measurement uncertainty
Measurements are not exactly accurate, and measurement errors could lead to a biased trained classifier, and finally to a wrong classification of the parts. This paper extends the recently proposed (Integrated) Mahalanobis Classification System with the concept of Interval Mahalanobis distance (IMD) in order to account for measurement uncertainty. This novel Integrated Interval Mahalanobis Classification System (IIMCS) is applied to an experimental case study of complex shaped metallic turbine blades with various damage types. The turbine blades have been vibrationally tested in a wide frequency range. The IIMCS selects a subset of optimal features that contribute the most to the system under the framework of Binary Particle Swarm Optimization, and determines the optimal decision threshold based on Particle Swarm Optimizer. A Monte Carlo method (MCM) is implemented to account for measurement uncertainty, and as such yields an indicator of reliability, implying the confidence level of the classification results. The obtained results illustrate a high performance of the IIMCS for classifying turbine blades based on vibrational response data with measurement uncertainty.
KalantariMRabbaniMEbadianM. A decision support system for order acceptance/rejection in hybrid MTS/MTO production systems. Appl Math Model2011; 35(3): 1363–1377.
4.
HuJZhangLLiangW. Dynamic degradation observer for bearing fault by MTS–SOM system. Mech Syst Signal Process2013; 36(2): 385–400.
5.
LeeY-CTengH-L. Predicting the financial crisis by Mahalanobis– Taguchi system–Examples of Taiwan’s electronic sector. Expert Syst with Applications2009; 36(414): 7469–7478.
6.
TaguchiGJugulumR. The Mahalanobis-Taguchi Strategy: a pattern technology system. Hoboken: John Wiley & Sons, 2002.
7.
KimC-WChangK-CKitauchiS, et al.A field experiment on a steel Gerber-truss bridge for damage detection utilizing vehicle-induced vibrations. Struct Health Monit2016; 15(2): 174–192.
8.
FriedmanJHSilvermanBW. Flexible parsimonious smoothing and additive modeling. Technometrics1989; 31(1): 3–21.
9.
WoodallWHKoudelikRTsuiK-L, et al.A review and analysis of the Mahalanobis—Taguchi system. Technometrics2003; 45(1): 1–15.
10.
PalAMaitiJ. Development of a hybrid methodology for dimensionality reduction in Mahalanobis–Taguchi system using Mahalanobis distance and binary particle swarm optimization. Expert Syst Appl2010; 37(2): 1286–1293.
11.
ReséNdizERull-FloresCA. Mahalanobis–Taguchi system applied to variable selection in automotive pedals components using Gompertz binary particle swarm optimization. Expert Syst Appl2013; 40(7): 2361–2365.
12.
ReséndizEMoncayo-MartínezLASolísG. Binary ant colony optimization applied to variable screening in the Mahalanobis–Taguchi system. Expert Syst Appl2013; 40(2): 634–637.
13.
El-BannaM. A novel approach for classifying imbalance welding data: Mahalanobis genetic algorithm (MGA). Int J Adv Manufacturing Technol2015; 77(1–4): 407–425.
14.
ReséndizELuisA. Moncayo-Martínez, and Georgina Solís. “Binary ant colony optimization applied to variable screening in the Mahalanobis–Taguchi system.” Expert Syst Appl2013; 402: 634–637.
15.
ChengLYaghoubiVVan PaepegemW, et al.Mahalanobis classification system (MCS) integrated with binary particle swarm optimization for robust quality classification of complex metallic turbine blades. Mech Syst Signal Processing2020; 146: 107060.
16.
ChengLYaghoubiVVan PaepegemW, et al.Quality inspection of complex-shaped metal parts by vibrations and an integrated Mahalanobis classification system. Struct Health Monit2020; 20(6): 3075.
17.
TaguchiGWuY. Introduction to off-line quality control. Nagaya, Japan: Central Japan Quality Control Assoc, 1979.
18.
SuC-THsiaoY-H. An evaluation of the robustness of MTS for imbalanced data. IEEE Trans Knowledge Data Engineering2007; 19(10): 1321–1332.
19.
LeeY-CTengH-L. Predicting the financial crisis by Mahalanobis–Taguchi system–examples of Taiwan’s electronic sector. Expert Syst Appl2009; 36(4): 7469–7478.
20.
KumarSChowTWPechtM. Approach to fault identification for electronic products using Mahalanobis distance. IEEE Trans Instrumentation Meas2009; 59(8): 2055–2064.
21.
El-BannaM. Modified Mahalanobis Taguchi system for imbalance data classification. Comput Intel Neurosci2017; 2017: 1–15.
22.
ChangZPLiYWFatimaN. A theoretical survey on Mahalanobis-Taguchi system. Measurement2019; 136: 501–510.
23.
ChangZPChengLSCuiLZ. Interval Choquet fuzzy integral multi-attribute decision making method based on Mahalanobis-Taguchi system. Cont Decisions2016; 31(1): 180–186.
24.
ChengLYaghoubiVPaepegemWV, et al.On the influence of reference Mahalanobis distance space for quality classification of complex metal parts using vibrations. Appl Sci2020; 10(23): 8620.
25.
RubinsteinRYKroeseDP. Simulation and the Monte Carlo method, Vol. 10. Hoboken, NJ: John Wiley & Sons, 2016.
26.
BichWCoxMGHarrisPM. Evolution of the ‘guide to the expression of uncertainty in measurement. Metrologia2006; 43(4): S161–S166.
27.
EberhartRKennedyJ. Particle swarm optimization. In: Proceedings of the IEEE international conference on neural networks, Perth, WA, Australia, 27 November–1 December 1995, 1995, pp. 1942–1948.
28.
KennedyJEberhartRC. A discrete binary version of the particle swarm algorithm. In: 1997 IEEE International conference on systems, man, and cybernetics Computational Cybernetics and Simulation, Orlando, FL, USA, 12–15 October 1997, IEEE, 1997, pp. 4104–4108.
29.
GouJLeiY-XGuoW-P, et al.A novel improved particle swarm optimization algorithm based on individual difference evolution. Appl Soft Computing2017; 57: 468–481.
30.
TooJAbdullahARMohd SaadN (2019, June). A new co-evolution binary particle swarm optimization with multiple inertia weight strategy for feature selection. Informatics6(2): 21. Multidisciplinary Digital Publishing Institute.
31.
LiuHWengQ. Enhancing temporal resolution of satellite imagery for public health studies: A case study of West NilevVirus outbreak in Los Angeles in 2007. Remote Sensing Environ2012; 117: 57–71.
32.
HearstMADumaisSTOsunaE, et al.Support vector machines. IEEE Intell Syst Their Appli1998; 13(4): 18–28.
33.
LiuJLiY-FZioE. A SVM framework for fault detection of the braking system in a high speed train. Mech Syst Signal Process2017; 87: 401–409.
34.
Hecht-NielsenR. Theory of the backpropagation neural network. In: Neural networks for perception. Boston: Academic Press; 1992, pp. 65–93.
35.
ZhangWLiCPengG, et al.A deep convolutional neural network with new training methods for bearing fault diagnosis under noisy environment and different working load. Mech Syst Signal Process2018; 100: 439–453.
36.
HeffernanJVJauriquiLBiedermannE, et al.Process compensated resonance testing models for quantification of creep damage in single crystal nickel-based superalloys. Mater Eval2017; 75(7): 941–952.
37.
LivingsRBiedermannEWangC, et al.Nondestructive evaluation of additive manufactured parts using process compensated resonance testing. In: Structural integrity of additive manufactured Parts. West Conshohocken, PA: ASTM International; 2020.
38.
KageyamaMOkajimaKMaesawaM, et al.X-ray phase-imaging scanner with tiled bent gratings for large-field-of-view nondestructive testing. NDT E Int2019; 105: 19–24.
39.
DafyddISharif KhodaeiZ. Analysis of barely visible impact damage severity with ultrasonic guided Lamb waves. Struct Health Monit2020; 19(4): 1104–1122.
40.
SereyVQuaegebeurNRenierMMicheauPMassonPCastaingsM. Selective generation of ultrasonic guided waves for damage detection in rectangular bars. Struct Health Monit2021; 20(3): 1156–1168.
