T present, a variety of research on the RUL prediction of parts have reported [6], and approaches of RUL prediction could be roughly grouped into three categories. The initial category will be the prediction technique according to physical models, which estimates the RUL of components in accordance with the degradation mechanism. Leser et al. [9] validated the crack growth modeling approach working with damage diagnosis data according to structural health monitoring, and also a probabilistic prediction of RUL is formed for any metallic, singleedge notch tension specimen using a fatigue crack increasing under mixedmode situations. Habib et al. [10] evaluated the anxiety of A310 aircraft wings for the duration of every loading cycle by means of a finite element evaluation, and they predicted the RUL of A310 wings applying the Paris Law strategy determined by linear elastic fracture mechanics. Chen et al. [11] created a novel computational modelling method for the prediction of crack development in load bearing orthopaedic alloys subjected to fatigue loading, which can predict the RUL of parts through the crack path. The second category could be the prediction system based on probability statistics, which match the failure information of parts to acquire the characteristic distribution of life by means of a statistical distribution model. Wang et al. [12] proposed a novel process depending on the threeparameterPublisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations.Copyright: 2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access write-up distributed below the terms and situations on the Inventive Commons Attribution (CC BY) license (https:// creativecommons.org/licenses/by/ four.0/).Appl. Sci. 2021, 11, 8482. https://doi.org/10.3390/apphttps://www.mdpi.com/journal/applsciAppl. Sci. 2021, 11,two ofWeibull distribution proportional hazards model to predict the RUL of rolling bearings, the model is able to generate precise RUL predictions for the tested bearings and outperforms the preferred twoparameter model. Pan et al. [13] proposed a remanufacturability evaluation scheme based on the average RUL on the structural arm, and created a complete evaluation by establishing the reliability parameter model from the structural arm. Xu et al. [14] discussed the influence of various distribution function values on the prediction benefits by analyzing different parameter estimation strategies, and established the RUL prediction model according to the failure data of components. Rong et al. [15] determined the typical helpful life in the pump truck boom based on the Weibull distribution function by using the failure information, and predicted the RUL on the boom by using the used time. The third category will be the datadriven prediction technique. Ren et al. [16] analyzed the timedomain and frequencydomain characteristics of rolling bearing vibration signals, and established the RUL prediction model of rolling bearing according to deep neural Piclamilast Biological Activity networks. Liu et al. [17] proposed an RUL prediction framework determined by various health state assessments that divide the whole bearing life into quite a few overall health states, where a local regression model may be built individually. Zio et al. [18] proposed a methodology for the estimation on the RUL of components determined by particle filtering. Sun et al. [19] employed support vector machines to build degradation models for bearing RUL prediction. Maio et al. [20] proposed a mixture of a relevance vector machine and model fitting as a prognostic procedure for estimati.
