This paper presents the use of proportional hazards regression models for predicting the Mean Time Between Failures (MTBF) of centrifugal pumps in the oil and gas industry. To that end, a dataset collected over 8 years including both design and operational variables from 675 pumps in an oil refinery was used to fit statistical models. Parametric and non-parametric transformations and restricted cubic splines were used to fit the covariates, thereby relaxing linearity assumptions and potentiating predictors with strong nonlinear effects on the outcome. Standard Principal Component Analysis (PCA) and sparse robust PCA methods were used for data reduction to simplify the fitted models and minimize overfitting. Models fitted with sparse robust PCA on non-parametrically transformed variables using an additive variance stabilizing (AVAS) method are suggested for further investigation. The complexity of the fitted models was reduced by 85% while at the same time providing for a more robust model as indicated by an improvement of the calibration slope from 0.830 to 0.936 with an essentially stable Akaike information criterion (AIC) (0.34% increase).

Rotating machinery belong to the category of major equipment in many large industries as oil refineries. When such assets are installed in an industrial plant, they are expected to perform with minimal faults and failures guaranteeing that the plant can be operated within pre-defined reliability, safety, availability, and performance specifications. This paper provides an insight into current practices when dealing with large fleets of rotating machines in an Industry 4.0 context and what opportunities and challenges are encountered towards improving their safe operation and reliability by taking advantage of the development of new technologies.

Bearing in mind that centrifugal pumps are the most common rotating machines in oil refineries, this paper is specially focused in this case, but its guidelines can be applied to all types of rotating equipment installed in an industrial plant.