An efficient maintenance policy allows for determining the current state of a system (diagnosis phase) and its future state (prognosis phase). We show in this paper that Markovian methods allow for obtaining many efficient indicators for the expert. To characterize the quality and robustness of these methods, we compared the Hidden Semi-Markov Model (HSMM) with the Hidden Markov Model (HMM). Several learning and decoding methods were included in the competition. A real case study was used as a particularly interesting working tool. The Remaining Useful Life (RUL) has also been included in this work.
RojkoA. Industry 4.0 concept: background and overview. Int J Interact Mob Technol2017; 11(5).
2.
ChiariniABelvedereVGrandoA. Industry 4.0 strategies and technological developments. An exploratory research from Italian manufacturing companies. Prod Plan Control2020;31(16): 1385–1398.
3.
AlcácerVCruz-MachadoV.Scanning the industry 4.0: A literature review on technologies for manufacturing systems. Eng Sci Technol Int J2019; 22(3): 899–919.
4.
SilvestriLForcinaAIntronaV, et al. Maintenance transformation through Industry 4.0 technologies: a systematic literature review. Comput Ind2020; 123: 103335.
5.
VrignatPKratzFAvilaM. Sustainable manufacturing, maintenance policies, prognostics and health management: a literature review. Reliabil Eng Syst Saf2022; 218: 108140.
6.
GouriveauRMedjaherKZerhouniN. From prognostics and health systems management to predictive maintenance 1: Monitoring and prognostics. John Wiley & Sons, 2016.
7.
OmriNAl MasryZMairotN, et al. Towards an adapted PHM approach: data quality requirements methodology for fault detection applications. Comput Ind2021; 127: 103414.
8.
CamposJSharmaPAlbanoM, et al. An open source framework approach to support condition monitoring and maintenance. Appl Sci2020; 10(18): 6360.
9.
JimenezJJMSchwartzSVingerhoedsR, et al. Towards multi-model approaches to predictive maintenance: a systematic literature survey on diagnostics and prognostics. J Manufact Syst2020; 56: 539–557.
10.
SoleimaniMCampeanFNeaguD. Diagnostics and prognostics for complex systems: A review of methods and challenges. Qual Reliabi Eng Int2021; 37(8): 3746–3778.
11.
TaheriEKolmanovskyIGusikhinO. Survey of prognostics methods for condition-based maintenance in engineering systems. arXiv preprint arXiv:1912.02708, 2019.
12.
ZhongKHanMHanB. Data-driven based fault prognosis for industrial systems: a concise overview. IEEE CAA J Autom Sin2020; 7(2): 330–345.
13.
ZontaTDa CostaCAda Rosa RighiR, et al. Predictive maintenance in the Industry 4.0: a systematic literature review. Comput Ind Eng2020; 150: 106889.
14.
BoulanouarSAhmedHRachidB, et al. Fuzzy prognosis system for decision making to vibrations monitoring in gas turbine. J Mech Eng2021; 71(2): 239–256.
15.
JiangQYanXHuangB. Review and perspectives of data-driven distributed monitoring for industrial plant-wide processes. Ind Eng Chem Res2019; 58(29): 12899–12912.
16.
Velasco-GallegoCLazakisI. RADIS: a real-time anomaly detection intelligent system for fault diagnosis of marine machinery. Expert Syst Appl2022; 204; 117634.
17.
DjeziriMBenmoussaSMouchawehMS, et al. Fault diagnosis and prognosis based on physical knowledge and reliability data: application to MOS field-effect transistor. Microelectron Reliabil2020; 110: 113682.
18.
NguyenTNPonciroliRKiblerT, et al. A physics-based parametric regression approach for feedwater pump system diagnosis. Ann Nucl Energy2022; 166: 108692.
19.
NyulásziLAndogaRButkaP, et al. Fault detection and isolation of an aircraft turbojet engine using a multi-sensor network and multiple model approach. Acta Polytechn Hung2018; 15(2): 189–209.
20.
Calderon-MendozaESchweitzerPWeberS. Kalman filter and a fuzzy logic processor for series arcing fault detection in a home electrical network. Int J Electric Power Energy Syst2019; 107: 251–263.
21.
GálvezADiez-OlivanASeneviratneD, et al. Fault detection and RUL estimation for railway HVAC systems using a hybrid model-based approach. Sustainability2021; 13(12): 6828.
22.
HongJHanLMiaoX, et al. Assessment based on support vector machine for rolling bearing grade-life. Journal of Beijing University of Aeronautics and Astronautics; 2010; 36(8): 896
23.
RausandMHoylandA. System reliability theory: models, statistical methods, and applications (Vol. 396). John Wiley & Sons, 2003.
24.
JimenezVJBouhmalaNGausdalAH. Developing a predictive maintenance model for vessel machinery. J Ocean Eng Sci2020; 5(4): 358–386.
25.
KimeraDNangoloFN. Predictive maintenance for ballast pumps on ship repair yards via machine learning. Transp Eng2020; 2: 100020.
26.
SharmaRDewanLChatterjiS. Fault diagnosis methods in dynamic systems: a. Int J Electron Electr Eng2015; 3(6): 465–471.
27.
SoualhiALamraouiMElyousfiB, et al. PHM SURVEY: Implementation of diagnostic methods for monitoring industrial systems. Energies2022; 15(19): 6909.
28.
DingSX. Advanced methods for fault diagnosis and fault-tolerant control. Berlin Heidelberg: Springer, 2021.
29.
Pourgol-MohammadMSalehpour-OskoueiF. Multi-criteria sensor placement determination in prognostics and health management using combined fault diagnosis, fault detection, and risk indexes. Proc I MechE, Part O: J Risk and Reliability2022; 237: 1234–1247.
30.
HuYLiuSLuH, et al. Online remaining useful life prognostics using an integrated particle filter. Proc I MechE, Part O: J Risk and Reliability2018; 232(6): 587–597.
31.
ShahinKISimonCWeberP, et al. Prognostic considering missing data: An input output hidden Markov model based solution. Proc I MechE, Part O: J Risk and Reliability2022; 237: 980–993.
32.
BukkapatnamSTAfrinKDaveD, et al. Machine learning and AI for long-term fault prognosis in complex manufacturing systems. CIRP Ann2019; 68(1): 459–462.
33.
EkanayakeTDewasurendraDAbeyratneS, et al. Model-based fault diagnosis and prognosis of dynamic systems: a review. Procedia Manuf2019; 30: 435–442.
34.
ZhouDYinHFuP, et al. Prognostics for state of health of lithium-ion batteries based on Gaussian process regression. Math Probl Eng2018; 2018: 8358025.
35.
KozłowskiEMazurkiewiczDŻabińskiT, et al. Machining sensor data management for operation-level predictive model, Expert Syst Appl2020; 159: 113600.
36.
ZhangNFouladiradMBarrosA, et al. Reliability and maintenance analysis of a degradation-threshold-shock model for a system in a dynamic environment. Appl Math Model2021; 91: 549–562.
37.
SarihHTchanganiAPMedjaherK, et al. Data preparation and preprocessing for broadcast systems monitoring in PHM framework. In 2019 6th international conference on control, decision and information technologies (CoDIT), 2019, pp.1444–1449. New York: IEEE.
RezaeianjouybariBShangY. Deep learning for prognostics and health management: State of the art, challenges, and opportunities. Measurement2020; 163: 107929.
40.
SinghVGangsarPPorwalR, et al. Artificial intelligence application in fault diagnostics of rotating industrial machines: a state-of-the-art review. J Intell Manuf2021; 341–30.
41.
ChenXVan HillegersbergJTopanE, et al. Application of data-driven models to predictive maintenance: Bearing wear prediction at TATA steel, Expert Syst Appl2021; 186: 115699.
42.
HagmeyerSMautheFZeilerP. Creation of publicly available data sets for prognostics and diagnostics addressing data scenarios relevant to industrial applications. Int J Progn Health Manage2021; 12(2): 1–20.
43.
AggabT. Pronostic des systèmes complexes par l’utilisation conjointe de modèle de Markov caché et d’observateur. PhD Thesis, Université d’Orléans, 2016.
44.
AngerC. Hidden semi-Markov models for predictive maintenance of rotating elements. PhD Thesis, Technische Universität, Darmstadt, 2018.
45.
DongHSLiuY. Semi-Markov models of inspection-based maintenance with empirical data from case studies on hydrant pumps. Proc I MechE, Part O: J Risk and Reliability2022; 238: 204–215.
46.
IslamMMProsvirinAEKimJM. Data-driven prognostic scheme for rolling-element bearings using a new health index and variants of least-square support vector machines. Mech Syst Signal Process2021; 160: 107853.
47.
BaruahPChinnamRB. HMMs for diagnostics and prognostics in machining processes. Int J Product Res2005; 43(6): 1275–1293.
48.
ZhouYRenHLiZ, et al. Anomaly detection based on a granular Markov model. Expert Syst Appl2022; 187: 115744.
49.
Tobon-MejiaDAMedjaherKZerhouniN, et al. Hidden Markov models for failure diagnostic and prognostic. In Prognostics and system health management confernece, 2011, pp.1–8. New York: IEEE.
50.
LiuTZhuKZengL. Diagnosis and prognosis of degradation process via hidden semi-Markov model. IEEE ASME Trans Mechatron2018; 23(3): 1456–1466.
51.
ZhaoWShiTWangL. Fault diagnosis and prognosis of bearing based on hidden Markov model with multi-features. Appl Math Nonlinear Sci2020; 5(1): 71–84.
52.
ParhizkarTStewartTHuangL, et al. Degradation and failure mechanisms of complex systems: principles. arXiv preprint arXiv:2109.12984, 2021.
YuS-Z. Hidden Semi-Markov models: theory, algorithms and applications. Morgan Kaufmann, 2015.
55.
KhalegheiAMakisV. Model parameter estimation and residual life prediction for a partially observable failing system. Nav Res Logist201562(3): 190–205.
56.
YuS-ZKobayashiH. Practical implementation of an efficient forward-backward algorithm for an explicit-duration hidden Markov model. IEEE Trans Signal Process2006; 54(5): 1947–1951.
57.
LingZ-HRichmondKYamagishiJ, et al. Integrating articulatory features into HMM-based parametric speech synthesis. IEEE Trans Audio Speech Lang Process2009; 17(6): 1171–1185.
58.
Nguyen-LeDHTaoQNguyenV-H, et al. A data-driven approach based on long short-term memory and hidden Markov model for crack propagation prediction. Eng Fract Mech2020; 235: 107085.
59.
ShahinKI. Dynamic probabilistic graphical model applied to the system health diagnosis, prognosis, and the remains useful life estimation. PhD Thesis, Université de Lorraine, 2020.
60.
Ruiz-SuarezSLeos-BarajasVMoralesJM. Hidden Markov and Semi-Markov models when and why are these models useful for classifying states in time series data?J Agric Biol Environ Stat2022; 27: 339–363.
61.
Chebel-MorelloBNicodJMVarnierC. From prognostics and health systems management to predictive maintenance 2: knowledge, reliability and decision. John Wiley & Sons, 2017
62.
HossainTAhadMRahmanA, et al. A method for sensor-based activity recognition in missing data scenario. Sensors2020; 20(14): 3811.
63.
HastieTTibshiraniRSherlockG, et al. Imputing missing data for gene expression arrays, Stanford Univ., 1999.
64.
ObaSSatoM-ATakemasaI, et al. A Bayesian missing value estimation method for gene expression profile data. Bioinformatics2003; 19(16): 2088–2096.
65.
TippingMEBishopCM. Probabilistic principal component analysis. J R Stat Soc B Stat Methodol1999; 61(3): 611–622.
66.
GrubbsFE. Procedures for detecting outlying observations in samples. Technometrics1969; 11(1): 1–21.
67.
CebeciZYıldızF. Unsupervised discretization of continuous variables in a chicken egg quality traits dataset. Turkish J Agric Food Sci Technol2017; 5(4): 315–320.
68.
JiangRKimMJMakisV. Maximum likelihood estimation for a hidden Semi-Markov model with multivariate observations. Qual Reliabil Eng Int2012; 28(7): 83–791.
69.
BobulskiJ. Selection of parameters of HMM. Pomiary Automatyka Kontrola2009; 55: 844–846.
70.
OliveiraJRennaFMantadelisT, et al. Adaptive sojourn time HSMM for heart sound segmentation. IEEE J Biomed Health Inform2018; 23(2): 642–649.
71.
NielsenF. Hierarchical clustering, in Introduction to HPC with MPI for data science. Springer, 2016, pp.195–211.
72.
NayakJNaikBBeheraH. Fuzzy C-means (FCM) clustering algorithm: a decade review from 2000 to 2014. Comput Intell2015; 2: 133–149.
73.
YangM-SLaiC-YLinC-Y. A robust EM clustering algorithm for Gaussian mixture models. Pattern Recognit2012; 45(11): 3950–3961.
74.
MacQueenJ. Some methods for classification and analysis of multivariate observations. In: Proceedings of the fifth Berkeley symposium on mathematical statistics and probability, Oakland, CA, 1967, vol. 1, no. 14, pp. 281–297.
75.
VesantoJAlhoniemiE. Clustering of the self-organizing map. IEEE Trans Neural Netw2000; 11(3): 586–600.
76.
SanguinettiGLaidlerJLawrenceND. Automatic determination of the number of clusters using spectral algorithms. In: IEEE workshop on machine learning for signal processing, 2005, pp.55–60. New York: IEEE.
77.
GuédonY. Exploring the state sequence space for hidden Markov and semi-Markov chains. Comput Stat Data Anal2007; 51(5): 2379–2409.
78.
NguyenN. An analysis and implementation of the hidden Markov model to technology stock prediction. Risks2017; 5(4): 62.
79.
PechtMGKangM. Prognostics and health management of electronics: fundamentals, machine learning, and the internet of things. John Wiley and Sons Ltd, 2018.
80.
SaxenaACelayaJBalabanE, et al. Metrics for evaluating performance of prognostic techniques. In: International conference on prognostics and health management, 2008, pp.1–17. New York: IEEE.
81.
MedjaherKTobon-MejiaDAZerhouniN. Remaining useful life estimation of critical components with application to bearings. IEEE Trans Reliabil2012; 61(2): 292–302.
