Modeling Materials and Systems Control Team, Higher School of Technology, Moulay Ismail University, University Moulay Ismail, Meknès, Fès-Meknès, Morocco
Dr. Sabah Louragli
Modeling Materials and Systems Control Team, Higher School of Technology, Moulay Ismail University, University Moulay Ismail, Meknès, Fès-Meknès, Morocco
Predicting the Remaining Useful Life (RUL) of railway wheels is challenging because wheel–rail degradation is cumulative, stochastic, and influenced by operating conditions. This study evaluates a multi-indicator prognostic framework using real in-service measurements acquired with a CALIPRI C42 optical profilometer (NextSense GmbH, Graz, Austria). The database comprises 80 wheels from ten vehicles of the same rolling-stock type, monitored during five monthly measurement campaigns, and includes flange width (Fw), flange height (Fh), and the flange-gradient dimension (qR). The Gamma process and first-passage formulation are established tools; the contribution of this work is their common application to all three indicators on the same in-service fleet and the benchmarking of long-horizon probabilistic results against an AR(1) short-term predictor embedded in the First-Passage Auto-Regressive (FP-AR) framework using the same dataset. Median Gamma-based RUL values were 21.2–22.0 months for Fw, 13.7–17.6 months for Fh, and 5.7–9.5 months for qR, with qR showing the largest relative percentile dispersion. For one-step prediction, the FP-AR benchmark achieved global MAE/RMSE values of approximately 0.368/0.502 mm for Fw and 0.0187/0.0216 mm for Fh; qR was more difficult to predict, with global MAE/RMSE values of approximately 0.575/0.991 mm. Under the adopted intervention thresholds, these results identify qR as the most variable and operationally constraining indicator under the studied Fès–Marrakech service conditions. The proposed dual-model analysis therefore provides a position-specific, uncertainty-aware basis for comparing wheel-profile degradation indicators, while its maintenance implications remain fleet- and route-specific pending validation in additional operating contexts.
Building on previous work on wear law modeling, this paper focuses on the prediction of the remaining useful life (RUL) of a complex system, whose state is characterized by multivariate time-series data. Our study is framed within the context of predictive maintenance applied to rolling stock, particularly railway wheels. We propose an approach to estimate future wear based on the wear law, while using the Remaining Useful Life (RUL) prediction as a key performance indicator. We also evaluate the accuracy and reliability of the prediction model. We demonstrate the performance of RUL predictions for three factors (Flange height, Flange width, Flange gradient), with improvements of up to 8 % in the Mean Absolute Percentage Error (MAPE) for Flange width, a 60 % gain for Flange height, and 32 % for Flange gradient. These results highlight the generalizability and relevance of our approach.
The primary challenge confronting the railway industry is the accessibility of passenger and freight vehicles. Corrective maintenance remains widespread, which means that, without proper maintenance, equipment can be used beyond its optimum service life. This leads to increased breakdowns, operational inefficiencies and unforeseen repair costs. Moreover, most maintenance practices follow a periodic approach (systematic preventive maintenance), which fails to adequately consider the actual condition of components. For these reasons, this study aims to develop a predictive maintenance strategy using a failure database from 2023, which includes an analysis of 420 railway vehicles. The study aims to show the effectiveness of the analysis of reliability data based on the normal distribution. The results underline the importance of estimating the remaining useful life of critical components, in particular the wheels, as well as the implementation of predictive maintenance to ensure safety, optimize maintenance schedule and improve availability by guaranteeing the efficiency of maintenance operations.
The fatigue resistance of a monobloc ER8 steel wheel is evaluated using a stress-life ($\mathrm{S}-\mathrm{N}$) approach based on Basquin’s law, with local stresses calculated through Hertzian contact theory. A fatigue safety factor accounts for uncertainties related to loading conditions and material properties. The predicted number of cycles is converted into equivalent service distances. A wheel with a 445 mm radius and 135 mm tread width is analyzed under representative loads. The tread center is safe up to $5.1 \times 10^{6}$ cycles $(\approx 7120 \mathrm{~km})$, while the edge exhibits the shortest lifespan, approximately 2510 km. The combined approach of Hertzian contact analysis, $\mathrm{S}-\mathrm{N}$ modeling, and a fatigue safety factor provides a reliable methodology for predicting wheel fatigue life and planning maintenance operations.
Predictive maintenance of railway wheelsets requires remaining useful life (RUL) estimates and treatment of model limitations. This study develops a Gamma-process-informed XGBoost surrogate for an ONCF fleet of 444 vehicles, 3552 candidate wheel positions, and 14 inspection campaigns. Flange width (Fw), flange height (Fh), and flange steepness (qR) were measured using a CALIPRI C42 gauge. After date normalisation and series-level IQR filtering, 3296 candidate series remained per indicator; Gamma eligibility retained 2366 Fw, 1628 Fh, and 2445 qR series. RUL quantiles were evaluated from the discrete Gamma first-passage distribution, with Monte Carlo used only for convergence checking. Vehicle-level median RUL was 13 months for Fw, 3 months for Fh, and 7 months for qR. RUL below six months occurred for 25/402, 283/344, and 100/404 vehicles, respectively. Under vehicle-grouped five-fold cross-validation, surrogate-label reconstruction yielded Pearson r values of 0.968, 0.759, and 0.964, with MAEs of 4.16, 1.67, and 2.82 months. Ablation confirmed strong target-feature coupling, while calibration and bootstrap diagnostics revealed substantial uncertainty. The framework supports model-conditional fleet screening, not validated real-world RUL forecasting or automatic maintenance decisions, until prospective temporal validation links scores to maintenance outcomes.