Remaining useful life prediction for power-shift steering transmission based on fusion of multiple oil spectra

Abstract

Remaining useful life prediction is a critical issue to fault diagnosis and health management of power-shift steering transmission. Power-shift steering transmission wear, which leads to the increase of wear particles and severe wear afterwards, is a slow degradation process, which can be monitored by oil spectral analysis, but the actual degree of the power-shift steering transmission degradation is often difficult to evaluate. The main purpose of this article is to provide a more accurate remaining useful life prediction methodology for power-shift steering transmission compared to relying solely on an individual spectral oil data. Our methodology includes multiple degradation data fusion, degradation index construction, degradation modelling and remaining useful life estimation procedures. First, the robust kernel principal component analysis is used to reduce the data dimension, and the state space model is utilized to construct the wear degradation index. Then, the Wiener process-based degradation model is established based on the constructed degradation index, and the explicit formulas for several important quantities for remaining useful life estimation such as the probability density function and cumulative distribution function are derived. Finally, a case study is presented to demonstrate the applicability of the proposed methodology. The results show that the proposed remaining useful life prediction methodology can objectively describe the power-shift steering transmission degradation law, and the predicted remaining useful life has been extended as 65 Mh (38.2%) compared with specified maintenance interval. This will reduce the maintenance times of power-shift steering transmission life cycle and finally save the maintenance costs.

Studying truck transmission oils using the method of thermal-oxidative stability during vehicle operation

“…The issue of application of non-destructive methods is solved on the basis of analysis of oils for vehicles. Particular attention is paid to controlling dielectric permeability, electromagnetic inspection of oils and other diagnostic parameters of the lubricant state [4]. Urgency of conducting non-destructive oil control is determined by increasing efficiency of forming diagnostic databases for vehicle units.…”

A Unified System Residual Life Prediction Method Based on Selected Tribodiagnostic Data

“…Zhang et al [26] and Zhang et al [27] established the condition evaluation model of multiple wear components based on a support vector machine (SVM) approach and PCA, respectively, and the failure mode reorganization of different friction couplings was realized. In recent years, Yan et al [14] and Vališ et al [13] built a system degradation model based on selected oil field data with a stochastic diffusion process, for example, a Wiener process, to determine the real-time machine CM. A comprehensive review of the application of different approaches in machine degradation modeling and RL prediction based on oil field data can be found in [6] and the references therein.…”

“…The oil field data were obtained for the reliability analysis from a test (Figure 1.) of the PSST system [14], [15]. The PSST (Figure 2.)…”

“…We suppose that the degradation and failure of a PSST is governed by the oil spectral data of Fe and Cu, and this assumption is valid for every PSST tested, as we have analyzed in Section 3. The PSST is considered failed if one of the two selected oil field datasets exceed the predetermined threshold, in this case, 350 ppm for Fe and 20 ppm for Cu [14], [24]. The threshold is defined by using statistical analysis of historical failure data [24], [25].…”

“…The novelty of our approach lies in integrating oil field data in a unified degradation model, extending the models that have already been introduced in recent years [e.g., see Refs. [11]- [14]]. Here, an adaptive bivariate degradation model is established by utilizing the Wiener process with time scale transformations and the copula function to describe the correlation among the selected oil field data.…”