Industrial components and systems typically operate in an evolving environment characterized by modifications of the working conditions. Methods for diagnosing faults in components and systems must, therefore, be capable of adapting to the changings in the environment of operation. In this work, we propose a novel fault diagnostic method based on the compacted object sample extraction algorithm for fault diagnostics in an evolving environment from where unlabeled data are collected. The developed diagnostic method is shown able to correctly classify data taken from synthetic and real-world case studies.
XiaTDongYXiaoL, et al. Recent advances in prognostics and health management for advanced manufacturing paradigms. Reliab Eng Syst Saf2018; 178: 255–268.
2.
ChangSGaoLWangY. A review of integrated vehicle health management and prognostics and health management standards. In: Proceedings of the international conference on sensing, diagnostics, prognostics, and control (SDPC), Xi’an, China, 15–17 August 2018, pp.476–481. New York: IEEE.
3.
DongYXiaTFangX, et al. Prognostic and health management for adaptive manufacturing systems with online sensors and flexible structures. Comput Ind Eng2019; 133: 57–68.
4.
TingaTLoenderslootR. Aligning PHM, SHM and CBM by understanding the physical system failure behaviour. In: Proceedings of European conference of the prognostic and health management society, Nantes, 17 July 2014. Nantes: PHM Society.
5.
LeeJWuFZhaoW, et al. Prognostics and health management design for rotary machinery systems—reviews, methodology and applications. Mech Syst Signal Pr2014; 42: 314–334.
6.
ZioE. Prognostics and health management of industrial equipment. In: KadryS (ed.) Diagnostics and prognostics of engineering systems: methods and techniques. Hershey, PA: IGI Global, 2012, pp.333–356.
7.
LeiYYangBJiangX, et al. Applications of machine learning to machine fault diagnosis: a review and roadmap. Mech Syst Signal Pr2020; 138: 106587.
8.
ZhaoFTianZBechhoeferE, et al. An integrated prognostics method under time-varying operating conditions. IEEE T Reliab2015; 64(2): 673–686.
9.
BianLGebraeelN.Stochastic methodology for prognostics under continuously varying environmental profiles. Stat Anal Data Min2013; 6(3): 260–270.
10.
Razavi-FarRBaraldiPZioE. Dynamic weighting ensembles for incremental learning and diagnosing new concept class faults in nuclear power systems. IEEE T Nucl Sci2012; 59(5): 2520–2530.
11.
KolterJZMaloofMA. Dynamic weighted majority: an ensemble method for drifting concepts. J Mach Learn Res2007; 8: 2755–2790.
12.
ChenHTinoPRodanA, et al. Learning in the model space for cognitive fault diagnosis. IEEE T Neur Net Lear2014; 25(1): 124–136.
13.
ZliobaiteIBifetAPfahringerB, et al. Active learning with drifting streaming data. IEEE T Neur Net Lear2014; 25(1): 27–39.
14.
Ben-DavidSBlitzerJ. Analysis of representations for domain adaptation. Adv Neural Inf Process Syst2007; 19: 137–144.
DongMHeD. A segmental hidden semi-Markov model (HSMM)-based diagnostics and prognostics framework and methodology. Mech Syst Signal Pr2007; 21(5): 2248–2266.
17.
LiJZhangXZhouX, et al. Reliability assessment of wind turbine bearing based on the degradation-Hidden-Markov model. Renew Energy2019; 132: 1076–1087.
18.
LiFXuJ. A new prognostics method for state of health estimation of lithium-ion batteries based on a mixture of Gaussian process models and particle filter. Microelectron Reliab2015; 55(7): 1035–1045.
19.
KaramiMWangL. Fault detection and diagnosis for nonlinear systems: a new adaptive Gaussian mixture modeling approach. Energy Build2018; 166: 477–488.
20.
DyerKBCapoRPolikarR. COMPOSE: a semisupervised learning framework for initially labeled nonstationary streaming data. IEEE T Neur Net Lear2014; 25(1): 12–26.
21.
DyerKBPolikarR. Semi-supervised learning in initially labeled non-stationary environments with gradual drift. In: Proceedings of the international joint conference on neural networks (IJCNN), Brisbane, QLD, Australia, 10–15 June 2012, pp.1–9. New York: IEEE.
22.
BoseRPJCvan der AalstWMPZliobaiteI, et al. Dealing with concept drifts in process mining. IEEE T Neur Net Lear2014; 25(1): 154–171.
23.
PolikarRAlippiC. Guest editorial learning in nonstationary and evolving environments. IEEE T Neur Net Lear2014; 25(1): 9–11.
24.
HuYBaraldiPDi MaioF, et al. A compacted object sample extraction (COMPOSE)-based method for fault diagnostics in evolving environment. In: Proceedings of the prognostics and system health management conference (PHM), Beijing, China, 21–23 October 2015, pp.1–5. New York: IEEE.
KorbiczJ. Fault diagnosis: models, artificial intelligence, applications. Washington, DC: U.S. Government Printing Office, 2004.
29.
SamantaBAl-BalushiKR. Artificial neural network based fault diagnostics of rolling element bearings using time-domain features. Mech Syst Signal Pr2003; 17: 317–328.
30.
KunchevaLIFaithfullWJ. PCA feature extraction for change detection in multidimensional unlabeled data. IEEE T Neur Net Lear2014; 25(1): 69–80.
31.
VenkatasubramanianV. A review of process fault detection and diagnosis: part III: process history based methods. Comput Chem2003; 27: 293–311.
32.
LeiYLinJHeZ, et al. A review on empirical mode decomposition in fault diagnosis of rotating machinery. Mech Syst Signal Pr2013; 35(1–2): 108–126.
33.
LemosACaminhasWGomideF. Adaptive fault detection and diagnosis using an evolving fuzzy classifier. Inf Sci2013; 220: 64–85.
34.
SakthivelNRSugumaranVNairBB. Automatic rule learning using roughset for fuzzy classifier in fault categorization of mono-block centrifugal pump. Appl Soft Comput2012; 12(1): 196–203.
35.
RokachLHutterD. Automatic discovery of the root causes for quality drift in high dimensionality manufacturing processes. J Intell Manuf2011; 23(5): 1915–1930.
36.
HorstmannJSpahrHBujC, et al. Full-field speckle interferometry for non-contact photoacoustic tomography. Phys Med Biol2015; 60(10): 4045–4058.
37.
C C Aggarwal. Data streams: models and algorithms, vol. 31. Cham: Springer, 2007.
38.
GonçalvesPMde Carvalho SantosSGTBarrosRSM, et al. A comparative study on concept drift detectors. Expert Syst Appl2014; 41(18): 8144–8156.
39.
KunchevaLI. Change detection in streaming multivariate data using likelihood detectors. IEEE T Knowl Data En2013; 25: 1175–1180.
40.
DriesARückertU. Adaptive concept drift detection. Stat Anal Data Min2009; 2(5–6): 311–327.
41.
ZweigMHCampbellG. Receiver-operating characteristic (ROC) plots: a fundamental evaluation tool in clinical medicine. Clin Chem1993; 39(4): 561–577.
42.
EdelsbrunnerHMuckeEP. 3-dimensional alpha-shapes. ACM T Graphic1994; 13: 43–72.
LeiYZuoMJ. Gear crack level identification based on weighted K nearest neighbor classification algorithm. Mech Syst Signal Pr2009; 23(5): 1535–1547.
45.
XuZXuanJShiT, et al. A novel fault diagnosis method of bearing based on improved fuzzy ARTMAP and modified distance discriminant technique. Expert Syst Appl2009; 36(9): 11801–11807.
46.
WuS-DWuP-HWuC-W, et al. Bearing fault diagnosis based on multiscale permutation entropy and support vector machine. Entropy2012; 14(8): 1343–1356.
47.
BaraldiPCannarileFDi MaioF, et al. Hierarchical k-nearest neighbours classification and binary differential evolution for fault diagnostics of automotive bearings operating under variable. Reliab Eng Syst Saf2015; 56: 1–13.
48.
EmmanouilidisCHunterAMacIntyreJ, et al. Selecting features in neurofuzzy modelling by multiobjective genetic algorithms. In: Proceedings of the ninth international conference on artificial neural networks, ICANN 99 (Conf. Publ. No. 470), Edinburgh, 7–10 September 1999, vol. 2, pp.749–754. New York: IEEE.
49.
LangoneRAlzateCDe KetelaereB, et al. LS-SVM based spectral clustering and regression for predicting maintenance of industrial machines. Eng Appl Artif Intell2015; 37: 268–278.
50.
ChangCLinC. LIBSVM: a library for support vector machines. ACM T Intel Syst Tec2001; 2: 1–30.
51.
BaraldiPCannarileFDi MaioF, et al. Hierarchical k-nearest neighbours classification and binary differential evolution for fault diagnostics of automotive bearings operating under variable conditions. Eng Appl Artif Intell2016; 56: 1–13.
