CThe aim of the paper is to develop ranking techniques for dynamic equipment based on its technical conditions, the estimation of recovered resource value and the determination of critical points of time after which equipment operation has to be terminated. Accelerometer data, cross-spectrum for wave analysis and a TOPSIS-based method have been used to achieve the goal. The most significant result of the work is a method of estimating the technical condition of the equipment, which allows: 1) to perform the transition to condition-based equipment maintenance by predicting non-normative work time; 2) to plan preventive repairs; 3) to select performers for repairs and maintenance of equipment based on objective estimates of work quality. The importance of the results is as follows: 1) the application of multi-criteria ranking method allowed to make ranking according to the technical condition of the equipment units for which condition monitoring groups of sensors are used; 2) it is shown that equipment condition changing is non-linear and there are areas of accelerated degradation; when the latter ones are reached, an accelerated condition deterioration is encountered; 3) the application of the technique on the data simultaneously taken from four sensors has shown its ability to conduct a comprehensive estimation without reference to a specific type of failure in conditions when the data from individual accelerometers give different information about the failure due to the different distance from the problem area. The verification of the proposed theoretical results is carried out on the basis of operating time data before a bearing failure, as well as monitoring data on the operation of wind turbine gearboxes.
T. J. Mi S. , Feng Y., Zheng H., Li Z., Gao Y.,“Integrated Intelligent Green Scheduling ofPredictive,” IEEE Access, vol. 8, pp. 45797-45812, 2020, doi: 10.1109/ACCESS.2020.2977667.
Q. Wang and J. Gao, “Research and application ofrisk and condition based maintenance taskoptimization technology in an oil transfer station,”J. Loss Prev. Process Ind., vol. 25, no. 6, pp. 1018-1027, Nov. 2012, doi: 10.1016/j.jlp.2012.06.002.
W. S. J. Tautz–Weinert J., “Using SCADA datafor wind turbine condition monitoring – a review,”IET Renew. Power Gener., vol. 11, no. 4, pp. 382-394, 2017, doi: 10.1049/iet-rpg.2016.0248.
H. Li et al., “Improving rail network velocity: Amachine learning approach to predictivemaintenance,” Transp. Res. Part C Emerg.Technol., vol. 45, pp. 17-26, Aug. 2014, doi:10.1016/j.trc.2014.04.013.
D. H. Wolpert and W. G. Macready, “No freelunch theorems for optimization,” IEEE Trans.Evol. Comput., vol. 1, no. 1, pp. 67-82, Apr. 1997,doi: 10.1109/4235.585893.
M. Sadiakhmatov, “Production planning model inthe conditions of changing demand with astochastic component.,” HS Anhalt, 2018.
G. L. Wang B., Lei Y., Yan T., Li N., “Recurrentconvolutional neural network: A new frameworkfor remaining useful life prediction of machinery,”Neurocomputing, vol. 379, pp. 117-129, 2020, doi: 10.1016/j.neucom.2019.10.064.
L. D. J., “Stupid Data Miner Tricks: Overfittingthe S&P 500,” J. Invest., vol. 16, no. 1, pp. 15-22,2007, doi: 10.3905/joi.2007.681820.
B. A. Santos P. , Maudes J., “Identifyingmaximum imbalance in datasets for fault diagnosisof gearboxes,” J. Intell. Manuf., vol. 29, no. 2, pp.333-351, 2018, doi: 10.1007/s10845-015-1110-0.
A. Paprotny and M. Thess, Realtime data mining:self-learning techniques for recommendationengines. Birke, 2013.
B. Wang, Y. Lei, N. Li, and N. Li, “A HybridPrognostics Approach for Estimating RemainingUseful Life of Rolling Element Bearings,” IEEETrans. Reliab., vol. 69, no. 1, pp. 401-412, Mar.2020, doi: 10.1109/TR.2018.2882682.
L. Mylnikov, B. Krause, M. Kütz, K. Bade, and I.Shmidt, Intelligent data analysis in themanagement of production systems (approachesand methods). Aachen: Shaker Verlag GmbH,2018.
K. Nishijima, S. Uenohara, and K. Furuya,“Evaluating Classification Methods in SnoreActivity Detection,” in Advances in IntelligentSystems and Computing, 2019, pp. 921-926.
K. V. F. Chernyshev S.A., “Vortex ring eigen-oscillations as a source of sound,” J. Fluid Mech.,vol. 341, pp. 19–57, 1997.
H. Zuo, K. Bi, and H. Hao, “A state-of-the-artreview on the vibration mitigation of windturbines,” Renew. Sustain. Energy Rev., vol. 121,p.109710, Apr. 2020, doi: 10.1016/j.rser.2020.109710.
N. Gebraeel, M. Lawley, R. Liu, and V.Parmeshwaran, “Residual Life Predictions FromVibration-Based Degradation Signals: A NeuralNetwork Approach,” IEEE Trans. Ind. Electron.,vol. 51, no. 3, pp. 694-700, Jun. 2004, doi: 10.1109/TIE.2004.824875.
M. Cinelli, S. R. Coles, and K. Kirwan, “Analysisof the potentials of multi criteria decision analysismethods to conduct sustainability assessment,”Ecol. Indic., vol. 46, pp. 138-148, Nov. 2014, doi: 10.1016/j.ecolind.2014.06.011.
J. S. Dyer, “Maut — Multiattribute UtilityTheory,” in Multiple Criteria Decision Analysis:State of the Art Surveys, New York: Springer-Verlag, pp. 265-292.
N. F. Matsatsinis and A. P. Samaras, “Brandchoice model selection based on consumers’multicriteria preferences and experts’ knowledge,”Comput. Oper. Res., vol. 27, no. 7–8, pp. 689–707, Jun. 2000, doi: 10.1016/S0305-0548(99)00114-8.
J. Xu, X. Ding, Y. Gong, N. Wu, and H. Yan,“Rotor imbalance detection and quantification inwind turbines via vibration analysis,” Wind Eng.,p.0309524X2199984,Mar. 2021, doi: 10.1177/0309524X21999841.
Z. Ma, M. Zhao, B. Li, and H. Fan, “A novel blinddeconvolution based on sparse subspace recodingfor condition monitoring of wind turbinegearbox,” Renew. Energy, vol. 170, pp. 141-162, Jun. 2021, doi: 10.1016/j.renene.2020.12.136.
P. Stoica and R. Moses, Spectral Analysis ofSignals, vol. 447. Upper Saddle River, NewJersey: Prentice Hall, Inc., 2005.
A. Labuda, “Daniell method for power spectraldensity estimation in atomic force microscopy,”Rev. Sci. Instrum., vol. 87, no. 3, 2016, doi: 10.1063/1.4943292.
T. Wang, Q. Han, F. Chu, and Z. Feng, “Vibrationbased condition monitoring and fault diagnosis ofwind turbine planetary gearbox: A review,” Mech.Syst. Signal Process., vol. 126, pp. 662–685, Jul.2019, doi: 10.1016/j.ymssp.2019.02.051.
O. Marchal, NOTES OF TIME SERIESANALYSIS, vol. 27. Department of Geology &Geophysics, Woods Hole OceanographicInstitution, 2015.
L. A. Mylnikov. Upravleniye proyektami isistemami v usloviyakh tsifrovoy ekonomiki.Perm: Izd-vo Perm. nats. issled. politekhn. un-ta.2021.
Z. Ma, W. Teng, Y. Liu, D. Wang, and A. Kusiak,“Application of the multi-scale envelopingspectrogram to detect weak faults in a wind turbinegearbox,” IET Renew. Power Gener., vol. 11, no.5, 2017, doi: 10.1049/iet-rpg.2016.0722.
N. Yang, S. Liu, J. Liu, and C. Li, “Assessment ofEquipment Operation State with ImprovedRandom Forest,” Int. J. Rotating Mach., vol. 2021, pp. 1-10, Mar. 2021, doi: 10.1155/2021/8813443.
Zwicky F., Discovery Invention, ResearchThrough the Morphological Approach. McMillan,1969.
N. Efimov, “Estimation model of the technicalcondition of dynamic equipment changes based onvibration data,” Anhalt University of AppliedSciences, 2021.
A. V. Seledkova, L. A. Mylnikov, and K. Bernd,“Forecasting characteristics of time series tosupport managerial decision making process inproduction-And-economic systems,” 2017, doi: 10.1109/SCM.2017.7970744.
L. A. Mylnikov. Statisticheskiye metodyintellektualnogo analiza dannykh. SPb.: BKhV-Peterburg, 2021.
·
This work is licensed under a
Creative Commons Attribution-ShareAlike 4.0 International License
