The demand for cost-effective, reliable and safe machinery operation requires accurate fault detection and classification to achieve an efficient maintenance strategy and increase performance. Furthermore, in strategic sectors such as the oil and gas industry, fault prediction plays a key role to extend component lifetime and reduce unplanned equipment thus preventing costly breakdowns and plant shutdowns. This paper presents the preliminary development of a simple and easy to implement machine learning (ML) model for early fault prediction of a centrifugal pump in the oil and gas industry. The data analysis is based on real-life historical data from process and equipment sensors mounted on the selected machinery. The raw sensor data, mainly from temperature, pressure and vibrations probes, are denoised, pre-processed and successively coded to train the model. To validate the learning capabilities of the ML model, two different algorithms—the Support Vector Machine (SVM) and the Multilayer Perceptron (MLP)—are implemented in KNIME platform. Based on these algorithms, potential faults are successfully recognized and classified ensuring good prediction accuracy. Indeed, results from this preliminary work show that the model allows us to properly detect the trends of system deviations from normal operation behavior and generate fault prediction alerts as a maintenance decision support system for operatives, aiming at avoiding possible incoming failures.

This paper presents the results of experimental and numerical research activities on a packed bed sensible thermal energy storage (TES) system. The TES consists of a cylindrical steel tank filled with small alumina beads and crossed by air used as the heat transfer fluid. Experimental tests were carried out while varying some operating parameters such as the mass flow rate, the inlet–outlet temperature thresholds and the aspect ratio (length over diameter). Numerical simulations were carried out using a one-dimensional model, specifically developed in the Matlab-Simulink environment and a 2D axisymmetric model based on the ANSYS-Fluent platform. Both models are based on a two-equation transient approach to calculate fluid and solid phase temperatures. Thermodynamic properties were considered to be temperature-dependent and, in the Computational Fluid Dynamics (CFD) model, variable porosity of the bed in the radial direction, thermal losses and the effective conductivity of the alumina beads were also considered. The simulation results of both models were compared to the experimental ones, showing good agreement. The one-dimensional model has the advantage of predicting the axial temperature distribution with a very low computational cost, but it does not allow calculation of the correct energy stored when the temperature distribution is strongly influenced by the wall. To overcome this problem a 2D CFD model was used in this work.

In the industrial domain, maintenance is essential to guarantee the correct operations, availability, and efficiency of machinery and systems. With the advent of Industry 4.0, solutions based on machine learning can be used for the prediction of future failures by exploiting historical failure data. Most of the time, these historical data have been collected by companies without a specific structure, schema, or even best practices, resulting in a potential loss of knowledge. In this paper, we analyze the historical data on maintenance alerts of the components of a revamping topping plant (referred to as RT2) belonging to the SARAS group. This analysis is done in collaboration with the ITALTELECO company, a partner of SARAS, that provided the necessary data. The pre-processing methodology to clean and fill these data and extract features useful for a prediction task will be shown. More in detail, we show the process to fill missing fields of these data to provide (i) a category for each fault by using simple natural language processing techniques and performing a clustering, and (ii) a data structure that can enable machine learning models and statistical approaches to perform reliable failure predictions. The data domain in which this methodology is applied is oil and gas, but it may be generalized and reformulated in various industrial and/or academic fields. The ultimate goal of our work is to obtain a procedure that is simple and can be applied to provide strategic support for the definition of an adequate maintenance plan.

The dependability assessment is a crucial activity for determining the availability, safety and maintainability of a system and establishing the best mitigation measures to prevent serious flaws and process interruptions. One of the most promising methodologies for the analysis of complex systems is Dynamic Reliability (also known as DPRA) with models that define explicitly the interactions between components and variables. Among the mathematical techniques of DPRA, Stochastic Hybrid Automaton (SHA) has been used to model systems characterized by continuous and discrete variables. Recently, a DPRA-oriented SHA modelling formalism, known as Stochastic Hybrid Fault Tree Automaton (SHyFTA), has been formalized together with a software library (SHyFTOO) that simplifies the resolution of complex models. At the state of the art, SHyFTOO allows analyzing the dependability of multistate repairable systems characterized by a reactive maintenance policy. Exploiting the flexibility of SHyFTA, this paper aims to extend the tools’ functionalities to other well-known maintenance policies. To achieve this goal, the main features of the preventive, risk-based and condition-based maintenance policies will be analyzed and used to design a software model to integrate into the SHyFTOO. Finally, a case study to test and compare the results of the different maintenance policies will be illustrated.

After the Seveso disaster occurred more than 40 years ago, there has been an increasing awareness of the potential impacts that similar accident events can occur in a wide range of process establishments, where the handling and production of hazardous substances pose a real threat to society and the environment. In these industrial sites denominated “Seveso sites,” the urgent need for an effective strategy emerged markedly to handle hazardous activities and to ensure safe conditions. Since then, the main challenging research issues have focused on how to prevent such accident events and how to mitigate their consequences leading to the development of many risk assessment methodologies. In recent years, researchers and practitioners have tried to provide useful overviews of the existing risk assessment methodologies proposing several reviews. However, these reviews are not exhaustive because they are either dated or focus only on one specific topic (e.g., liquefied natural gas, domino effect, etc.). This work aims to overcome the limitations of the current reviews by providing an up‐to‐date and comprehensive overview of the risk assessment methodologies for handling hazardous substances within the European industry. In particular, we have focused on the current techniques for hazards and accident scenarios identification, as well as probability and consequence analyses for both onshore and offshore installations. Thus, we have identified the research streams that have characterized the activities of researchers and practitioners over the years, and we have then presented and discussed the different risk assessment methodologies available concerning the research stream that they belong to.