Ekhi Zugasti
YOU?
Author Swipe
View article: Navigating the Learning Landscape: A Case Study of Multisubject Problem-Based Learning in Computer Engineering Degree
Navigating the Learning Landscape: A Case Study of Multisubject Problem-Based Learning in Computer Engineering Degree Open
View article: Towards a Probabilistic Fusion Approach for Robust Battery Prognostics
Towards a Probabilistic Fusion Approach for Robust Battery Prognostics Open
Batteries are a key enabling technology for the decarbonization of transport and energy sectors. The safe and reliable operation of batteries is crucial for battery-powered systems. In this direction, the development of accurate and robust…
View article: Towards a Probabilistic Fusion Approach for Robust Battery Prognostics
Towards a Probabilistic Fusion Approach for Robust Battery Prognostics Open
Batteries are a key enabling technology for the decarbonization of transport and energy sectors. The safe and reliable operation of batteries is crucial for battery-powered systems. In this direction, the development of accurate and robust…
View article: A Methodology for Advanced Manufacturing Defect Detection through Self-Supervised Learning on X-ray Images
A Methodology for Advanced Manufacturing Defect Detection through Self-Supervised Learning on X-ray Images Open
In industrial quality control, especially in the field of manufacturing defect detection, deep learning plays an increasingly critical role. However, the efficacy of these advanced models is often hindered by their need for large-scale, an…
View article: Diagnostic spatio-temporal transformer with faithful encoding
Diagnostic spatio-temporal transformer with faithful encoding Open
View article: Best Practice Data Sharing Guidelines for Wind Turbine Fault Detection Model Evaluation
Best Practice Data Sharing Guidelines for Wind Turbine Fault Detection Model Evaluation Open
In this paper, a set of best practice data sharing guidelines for wind turbine fault detection model evaluation is developed, which can help practitioners overcome the main challenges of digitalisation. Digitalisation is one of the key dri…
View article: Best Practice Data Sharing Guidelines for Wind Turbine Fault Detection Model Evaluation
Best Practice Data Sharing Guidelines for Wind Turbine Fault Detection Model Evaluation Open
The digital era offers many opportunities to the wind energy industry and research community. Digitalisation is one of the key drivers for reducing costs and risks over the whole wind energy project life cycle. One of the largest challenge…
View article: Real-Time, Model-Agnostic and User-Driven Counterfactual Explanations Using Autoencoders
Real-Time, Model-Agnostic and User-Driven Counterfactual Explanations Using Autoencoders Open
Explainable Artificial Intelligence (XAI) has gained significant attention in recent years due to concerns over the lack of interpretability of Deep Learning models, which hinders their decision-making processes. To address this issue, cou…
View article: Towards a Probabilistic Error Correction Approach for Improved Drone Battery Health Assessment
Towards a Probabilistic Error Correction Approach for Improved Drone Battery Health Assessment Open
Health monitoring of remote critical infrastructure, such as offshore wind turbines, is complex and expensive.
\nFor the offshore energy sector, the accessibility for on-site asset inspection is hampered due to their harsh and
\nremote loc…
View article: Providing Proactiveness: Data Analysis Techniques Portfolios
Providing Proactiveness: Data Analysis Techniques Portfolios Open
Data analysis is of paramount importance in the management of proactive maintenance. This chapter provides a deep analysis of the different techniques that can be adopted when dealing with the automation of maintenance processes. In partic…
View article: Success Stories on Real Pilots
Success Stories on Real Pilots Open
This chapter describes success stories. The MANTIS architecture (Chapter 3) was implemented for a number of use cases on real pilots, and the techniques described in Chapters 4, 5, and 6 were experimented with in real settings. Results on …
View article: Methodology for data-driven predictive maintenance models design, development and implementation on manufacturing guided by domain knowledge
Methodology for data-driven predictive maintenance models design, development and implementation on manufacturing guided by domain knowledge Open
The 4th industrial revolution has connected machines and industrial plants, facilitating process monitoring and the implementation of predictive maintenance (PdM) systems that can save up to 60% of maintenance costs. Nowadays, most PdM res…
View article: Adaptable and Explainable Predictive Maintenance: Semi-Supervised Deep Learning for Anomaly Detection and Diagnosis in Press Machine Data
Adaptable and Explainable Predictive Maintenance: Semi-Supervised Deep Learning for Anomaly Detection and Diagnosis in Press Machine Data Open
Predictive maintenance (PdM) has the potential to reduce industrial costs by anticipating failures and extending the work life of components. Nowadays, factories are monitoring their assets and most collected data belong to correct working…
View article: Impregnation quality diagnosis in Resin Transfer Moulding by machine learning
Impregnation quality diagnosis in Resin Transfer Moulding by machine learning Open
View article: DA-DGCEx: Ensuring Validity of Deep Guided Counterfactual Explanations\n With Distribution-Aware Autoencoder Loss
DA-DGCEx: Ensuring Validity of Deep Guided Counterfactual Explanations\n With Distribution-Aware Autoencoder Loss Open
Deep Learning has become a very valuable tool in different fields, and no one\ndoubts the learning capacity of these models. Nevertheless, since Deep Learning\nmodels are often seen as black boxes due to their lack of interpretability,\nth…
View article: DA-DGCEx: Ensuring Validity of Deep Guided Counterfactual Explanations With Distribution-Aware Autoencoder Loss
DA-DGCEx: Ensuring Validity of Deep Guided Counterfactual Explanations With Distribution-Aware Autoencoder Loss Open
Deep Learning has become a very valuable tool in different fields, and no one doubts the learning capacity of these models. Nevertheless, since Deep Learning models are often seen as black boxes due to their lack of interpretability, there…
View article: Deep learning models for predictive maintenance: a survey, comparison, challenges and prospect
Deep learning models for predictive maintenance: a survey, comparison, challenges and prospect Open
Given the growing amount of industrial data spaces worldwide, deep learning solutions have become popular for predictive maintenance, which monitor assets to optimise maintenance tasks. Choosing the most suitable architecture for each use-…
View article: Interpreting Remaining Useful Life estimations combining Explainable Artificial Intelligence and domain knowledge in industrial machinery
Interpreting Remaining Useful Life estimations combining Explainable Artificial Intelligence and domain knowledge in industrial machinery Open
This paper presents the implementation and explanations of a remaining life estimator model based on machine learning, applied to industrial data. Concretely, the model has been applied to a bushings testbed, where fatigue life tests are p…
View article: Contrastive Explanations for a Deep Learning Model on Time-Series Data
Contrastive Explanations for a Deep Learning Model on Time-Series Data Open
In the last decade, with the irruption of Deep Learning
\n(DL), artificial intelligence has risen a step concerning previous years.
\nAlthough Deep Learning models have gained strength in many fields like
\nimage classification, speech rec…
View article: An Attribute Oriented Induction based Methodology for Data Driven Predictive Maintenance
An Attribute Oriented Induction based Methodology for Data Driven Predictive Maintenance Open
Attribute Oriented Induction (AOI) is a data mining algorithm used for extracting knowledge of relational data, taking into account expert knowledge. It is a clustering algorithm that works by transforming the values of the attributes and …
View article: A Big Data implementation of the MANTIS reference architecture for predictive maintenance
A Big Data implementation of the MANTIS reference architecture for predictive maintenance Open
This article presents the implementation of a reference architecture for cyber-physical systems to support condition-based maintenance of industrial assets. It also focuses on describing the data analysis approach to manage predictive main…
View article: Null is Not Always Empty: Monitoring the Null Space for Field-Level Anomaly Detection in Industrial IoT Environments
Null is Not Always Empty: Monitoring the Null Space for Field-Level Anomaly Detection in Industrial IoT Environments Open
Industrial environments have vastly changed sincethe conception of initial primitive and isolated networks. Thecurrent full interconnection paradigm, where connectivity be-tween different devices and the Internet has become a businessneces…