Browsing by Department "#PLACEHOLDER_PARENT_METADATA_VALUE#"

Renewable energies have a fundamental role in sustainability, with wind power being one of the most important due to its low production costs. Modern wind turbines are becoming bigger and more complex, and their operation and maintenance must be as optimized as possible. In this context, supervisory control and data acquisition systems provide valuable information, but there is no precise methodology for their analysis. To overcome this need, a generalized methodology is proposed to determine the recognition of critical subsystems through alarm analysis and management. The proposed methodology defines each subsystem in a precise way, shows the indicators for the alarms, and presents a theoretical framework for its application using the quantity and activation times of alarms, along with the real downtime. It also considers the transition of states when the wind turbine is operationally inactive. To highlight the proposal’s novelty, the methodology is exemplified with a case study from the Southern Cone, applying the method through a data management and analysis tool. Four critical subsystems were found, with the alarms of wind vanes, anemometers, and emergency speeds being of relevance. The indicators and the graphical tools recommended helped guide the applied analysis.

The proportional hazards model (PHM) is a vital statistical procedure for condition-based maintenance that integrates age and covariates monitoring to estimate asset health and predict failure risks. However, when dealing with multi-covariate scenarios, the PHM faces interpretability challenges when it lacks coherent criteria for defining each covariate’s influence degree on the hazard rate. Hence, we proposed a comprehensive machine learning (ML) formulation with Interior Point Optimizer and gradient boosting to maximize and converge the logarithmic likelihood for estimating covariate weights, and a K-means and Gaussian mixture model (GMM) for condition state bands. Using real industrial data, this paper evaluates both clustering techniques to determine their suitability regarding reliability, remaining useful life, and asset intervention decision rules. By developing models differing in the selected covariates, the results show that although K-means and GMM produce comparable policies, GMM stands out for its robustness in cluster definition and intuitive interpretation in generating the state bands. Ultimately, as the evaluated models suggest similar policies, the novel PHM-ML demonstrates the robustness of its covariate weight estimation process, thereby strengthening the guidance for predictive maintenance decisions.

This article implements a hybrid Machine Learning (ML) model to classify stoppage events in a copper-crushing equipment, more specifically, a conveyor belt. The model combines Artificial Neural Networks (ANNs) and Support Vector Machines (SVMs) with Principal Component Analysis (PCA) to identify the type of stoppage event when they occur in an industrial sector that is significant for the Chilean economy. This research addresses the critical need to optimise maintenance management in the mining industry, highlighting the technological relevance and motivation for using advanced ML techniques. This study focusses on combining and implementing three ML models trained with historical data composed of information from various sensors, real and virtual, as well from maintenance reports that report operational conditions and equipment failure characteristics. The main objective of this study is to improve the efficiency when identifying the nature of a stoppage serving as a basis for the subsequent development of a reliable failure prediction system. The results indicate that this approach significantly increases information reliability, addressing the persistent challenges in data management within the maintenance area. With a classification accuracy of 96.2% and a recall of 96.3%, the model validates and automates the classification of stoppage events, significantly reducing dependency on interdepartmental interactions. This advancement eliminates the need for reliance on external databases, which have previously been prone to errors, missing critical data, or containing outdated information. By implementing this methodology, a robust and reliable foundation is established for developing a failure prediction model, fostering both efficiency and reliability in the maintenance process. The application of ML in this context produces demonstrably positive outcomes in the classification of stoppage events, underscoring its significant impact on industry operations.

Background Wildfires have caused significant damage in Chile, with critical infrastructure being vulnerable to extreme wildfires. Aim This work describes a methodology for estimating wildfire risk that was applied to an electrical substation in the wildland–urban interface (WUI) of Valparaíso, Chile. Methods Wildfire risk is defined as the product between the probability of a wildfire reaching infrastructure at the WUI and its consequences or impacts. The former is determined with event trees combined with modelled burn probability. Wildfire consequence is considered as the ignition probability of a proxy fuel within the substation, as a function of the incident heat flux using a probit expression derived from experimental data. The heat flux is estimated using modelled fire intensity and geometry and a corresponding view factor from an assumed solid flame. Key results The probability of normal and extreme fires reaching the WUI is of the order of 10−4 and 10−6 events/year, respectively. Total wildfire risk is of the order of 10−5 to 10−4 events/year Conclusions This methodology offers a comprehensive interpretation of wildfire risk that considers both wildfire likelihood and consequences. Implications The methodology is an interesting tool for quantitatively assessing wildfire risk of critical infrastructure and risk mitigation measures.

The problem of characterizing the passengers’ movement in a public transport system has been considered in the literature for analysis, simulation and optimization purposes. In particular, origindestination matrices are commonly used to describe the total number of passengers that travel between two points during a given time interval. In this paper, we propose to model the instantaneous rate of arrival of passengers for the origin-destination pairs of a metro system using point processes. More specifically, we apply the Expectation-Maximization algorithm to estimate the parameters of a Gaussian mixture intensity function for the daily flow of passengers using data from multiple days provided by EFE Valparaíso. The uncertainty in the parameter estimates is quantified computing standard errors and confidence intervals. Secondly, we quantitatively analyze the similarity of the obtained intensity functions among the different origin-destination pairs. In particular, we propose a dissimilarity index based on the Kullback-Leibler divergence and we apply this index in hierarchical agglomerative and partitioning methods to cluster origindestination pairs with similar daily flow of passengers. The obtained numerical results confirm expert knowledge about the passengers’ behavior in EFE Valparaíso metro system and, more interestingly, provide additional insights on the passengers’ behaviour for specific origin-destination pairs.