Predictive reliability, or the ability to anticipate the failure probability of a system or component, is essential to extend the useful life of assets, prevent breakdowns, and minimize industrial incidents. Centrifugal pumps are among the most important assets in oil and gas applications, and their reliability is critical to operational availability and safety. As a result, predictive reliability strategies have increasingly been applied to these systems in recent years to enhance performance and reduce unplanned failures. Many studies have investigated the failure mechanisms of centrifugal pumps, and several time-to-failure predictive models have been developed, but the relative impact of the variables affecting their expected life is rarely quantified. Different methods often have significant variability in their results, due to method definitions, model behavior, and data-related factors like collinearity, sampling noise, and interactions. This paper addresses the issue by quantifying the influence of key variables through the application of four different methods. Three are based on statistical techniques: partial Likelihood Ratio (LR) χ2 analysis, Bayesian coefficient magnitudes, and the variable inclusion order in Lasso regression applied to a Cox Proportional Hazards Model (PHM). The fourth method employs a Machine Learning (ML) technique, permutation importance applied to a Random Survival Forest (RSF) model. As a robustness check of the RSF model, a gradient boosting survival model was fitted. SHAP values were also computed for both ML models and compared with permutation importance scores to assess the stability and consistency of variable-importance rankings. The procedure was implemented on a real-world dataset from an oil refinery, consisting of 675 pumps with a set of 27 potential predictors. Both ordinal and weighted rankings were computed, with weighted rankings providing deeper insights than ordinal rankings by capturing the relative differences between variables. Lasso and Bayesian Cox exhibited the highest variability in these rankings, while the RSF method showed the lowest variability (mean inter-quartile range: 2.7) and the strongest correlation (0.787) with the average ranking across models. Maintenance work orders consistently emerged as the most influential predictor of MTBF followed by pumped fluid, discharge pressure, and manufacturing year. To address variability, the Copeland–Llull voting method was applied to individual and aggregated rankings, reducing dispersion and improving robustness. Bootstrap resampling further quantified uncertainty and confirmed the stabilizing effect of this technique. Although minor changes occurred in variable ordering, key predictors remained dominant. Grouping variables into six categories revealed maintenance as the most impactful category followed by operating conditions. Overall, this approach enhances ranking stability and provides actionable insights for reliability analysis.

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).

The digital technologies accompanying Industry 4.0 have ushered in a new era in the management of industrial economic systems. The concept of the digital twin is at the heart of this transformation. Stemming from the convergence of advanced data analytics, Internet of Things (IoT) technologies, and virtual modelling and domain knowledge, digital twins were conceptualized to create virtual replicas of physical assets and systems. 

This book provides insights into how to approach and utilise data science tools, technologies, and methodologies related to artificial intelligence (AI) in industrial contexts. It explains the essence of distributed computing and AI technologies and their interconnections. It includes descriptions of various technology and methodology approaches and their purpose and benefits when developing AI solutions in industrial contexts. In addition, this book summarises experiences from AI technology deployment projects from several industrial sectors. Features:

• Presents a compendium of methodologies and technologies in industrial AI and digitalisation.

• Illustrates the sensor-to-actuation approach showing the complete cycle, which defines and differentiates AI and digitalisation.

• Covers a broad range of academic and industrial issues within the field of asset management.

• Discusses the impact of Industry 4.0 in other sectors.

• Includes a dedicated chapter on real-time case studies.

This book is aimed at researchers and professionals in industrial and software engineering, network security, AI and machine learning (ML), engineering managers, operational and maintenance specialists, asset managers, and digital and AI manufacturing specialists.

This paper proposes an assessment of features orientated to improve the accuracy of a hybrid model (HyM) used for detecting faults in a heating, ventilation, and air conditioning (HVAC) system. The HyM combines data collected by sensors embedded in the system with data generated by a physics-based model of the HVAC. The physics-based model includes sensors embedded in the real system and virtual sensors to represent the behaviour of the system when a failure mode (FM) is simulated. This fusion leads to improved maintenance actions to reduce the number of failures and predict the behaviour of the system. HyM can lead to improved fault detection and diagnostics (FDD) processes of critical systems, but multiple fault detection models are sometimes inaccurate. The paper assesses features extracted from synthetic signals. The results of the assessment are used to improve the accuracy of a multiple fault detection model developed in previous research. The assessment of features comprises the following: (1) generation of run-to-failure data using the physics-based model of the HVAC system; the FMs simulated in this paper are dust in the air filter, degradation of the CO2 sensor, degradation of the evaporator fan, and variations in the compression rate of the cooling system; (2) identification of the individual features that strongly distinguish the FM; (3) analysis of how the features selected vary when components degrade.