Prognostic modeling of predictive maintenance with survival analysis for mobile work equipment

Abstract

In recent years there is a data surge of industrial and business data. This posses opportunities and challenges at the same time because the wealth of information is usually buried in complex and frequently disconnected data sets. Predictive maintenance utilizes such data for developing prognostic and diagnostic models that allow the optimization of the life cycle of machine components. In this paper, we address the modeling of the prognostics of machine components from mobile work equipment. Specifically, we are estimating survival curves and hazard rates using parametric and non-parametric models to characterize time dependent failure probabilities of machine components. As a result, we find the presence of different types of censoring masking the presence of different populations that can cause severe problems for statistical estimators and the interpretations of results. Furthermore, we show that the obtained hazard functions for different machine components are complex and versatile and are best modeled via non-parametric estimators. However, notable exceptions for individual machine components can be found amenable for a Generalized-gamma and Weibull model.

AI for Automating Data Center Operations: Model Explainability in the Data Centre Context Using Shapley Additive Explanations (SHAP)

“…Most notably, existing works have often overlooked temporal changes in feature importance and the complex interactions between them [32][33][34]. Further, although methodologies such as time series and survival analysis have provided invaluable insights [35][36][37], capturing temporal issues has not been considered essential. In this paper, we adopt model explainability using SHAP and explore its application in the DC context.…”

Bayesian-based Component Lifetime Prediction Model Using Workshop and Telematics Data

“…The left-censored means that we cannot determine if it was t s at the nth observed time m n . Another type is right-censored, which means that t e cannot be determined at the nth observed time m n (Yang et al, 2022). In the maintenance records, the component was installed at m n , and replaced at m n+1 .…”

“…In mobility, faults are detected by maintenance records, but the use of maintenance records has the disadvantage that they are easily censored. There are parametric and non-parametric estimation methods for estimating the distribution of maintenance data to deal with censored characteristics, both methods are not simple and emphasize the importance of an accurate definition of the data (Yang, Kanniainen, Krogerus, & Emmert-Streib, 2022). Variability in operating and environmental conditions is particularly important in fleet management.…”

Leveraging Classical Statistical Methods for Sustainable Maintenance in Automotive Assembly Equipment

“…Statistical process control (SPC) techniques have been employed to monitor equipment performance and identify anomalies that could lead to potential failures using physical or softwareaided charts and statistical control methods to detect deviations from normal operation, facilitating timely maintenance interventions [22,23]. Weibull analysis, survival analysis, and other reliability models have been used to assess equipment degradation over time and forecast impending failures [24][25][26][27]. Studies have investigated the modeling of failure data to uncover underlying failure mechanisms and patterns [28].…”