Ekhi Zugasti
Ekhi Zugasti has a total of 39 co-authors. Here are the top co-authors by number of shared publications:
- Oscar Serradilla
UPV/EHU
5 shared publications - Urko Zurutuza
Electronics and Computing Department, Data Analytics and Cybersecurity (DANZ) research group, Mondragon University, Arrasate-Mondragon, Spain
5 shared publications - Jose Ignacio Aizpurua
Department of Computer Science and Artificial Intelligence University of the Basque Country (EHU) Donostia‐San Sebastian Spain
3 shared publications - Ali Eftekhari Milani
TU Delft, Kluyverweg 1, Delft, 2629 HS, The Netherlands
2 shared publications - Ana Gómez González
University of Santiago de Compostela
2 shared publications - Carlos Cernuda
Electronics and Computer Science, Mondragon Unibertsitatea, Loramendi 4, 20500 Mondragon, Spain
2 shared publications
Latest Publications
- Open Access
- 26 March 2024
- Published by MDPI AG in Applied Sciences
- Vol. 14 (7) , 2785
A Methodology for Advanced Manufacturing Defect Detection through Self-Supervised Learning on X-ray Images
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, annotated datasets. Moreover, these datasets are mainly based on RGB images, which are very different from X-ray images. Addressing this limitation, our research proposes a methodology that incorporates domain-specific self-supervised pretraining techniques using X-ray imaging to improve defect detection capabilities in manufacturing products. We employ two pretraining approaches, SimSiam and SimMIM, to refine feature extraction from manufacturing images. The pretraining stage is carried out using an industrial dataset of 27,901 unlabeled X-ray images from a manufacturing production line. We analyze the performance of the pretraining against transfer-learning-based methods in a complex defect detection scenario using a Faster R-CNN model. We conduct evaluations on both a proprietary industrial dataset and the publicly available GDXray dataset. The findings reveal that models pretrained with domain-specific X-ray images consistently outperform those initialized with ImageNet weights. Notably, Swin Transformer models show superior results in scenarios rich in labeled data, whereas CNN backbones are more effective in limited-data environments. Moreover, we underscore the enhanced ability of the models pretrained with X-ray images in detecting critical defects, crucial for ensuring safety in industrial settings. Our study offers substantial evidence of the benefits of self-supervised learning in manufacturing defect detection, providing a solid foundation for further research and practical applications in industrial quality control.
- 26 March 2024
- Published by MDPI AG in Applied Sciences
- Vol. 14 (7) , 2785
Open AccessA Methodology for Advanced Manufacturing Defect Detection through Self-Supervised Learning on X-ray Images
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, annotated datasets. Moreover, these datasets are mainly based on RGB images, which are very different from X-ray images. Addressing this limitation, our research proposes a methodology that incorporates domain-specific self-supervised pretraining techniques using X-ray imaging to improve defect detection capabilities in manufacturing products. We employ two pretraining approaches, SimSiam and SimMIM, to refine feature extraction from manufacturing images. The pretraining stage is carried out using an industrial dataset of 27,901 unlabeled X-ray images from a manufacturing production line. We analyze the performance of the pretraining against transfer-learning-based methods in a complex defect detection scenario using a Faster R-CNN model. We conduct evaluations on both a proprietary industrial dataset and the publicly available GDXray dataset. The findings reveal that models pretrained with domain-specific X-ray images consistently outperform those initialized with ImageNet weights. Notably, Swin Transformer models show superior results in scenarios rich in labeled data, whereas CNN backbones are more effective in limited-data environments. Moreover, we underscore the enhanced ability of the models pretrained with X-ray images in detecting critical defects, crucial for ensuring safety in industrial settings. Our study offers substantial evidence of the benefits of self-supervised learning in manufacturing defect detection, providing a solid foundation for further research and practical applications in industrial quality control.
- 27 November 2023
- Published by Springer Nature
- p. 605-616
Towards Robust Defect Detection in Casting Using Contrastive Learning
- 27 November 2023
- Published by Springer Nature
- p. 605-616
Towards Robust Defect Detection in Casting Using Contrastive Learning
- Open Access
Best Practice Data Sharing Guidelines for Wind Turbine Fault Detection Model Evaluation
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 drivers for reducing costs and risks over the whole wind energy project life cycle. One of the largest challenges in successfully implementing digitalisation is the lack of data sharing and collaboration between organisations in the sector. In order to overcome this challenge, a new collaboration framework called WeDoWind was developed in recent work. The main innovation of this framework is the way it creates tangible incentives to motivate and empower different types of people from all over the world to share data and knowledge in practice. In this present paper, the challenges related to comparing and evaluating different SCADA-data-based wind turbine fault detection models are investigated by carrying out a new case study, the “WinJi Gearbox Fault Detection Challenge”, based on the WeDoWind framework. A total of six new solutions were submitted to the challenge, and a comparison and evaluation of the results show that, in general, some of the approaches (Particle Swarm Optimisation algorithm for constructing health indicators, performance monitoring using Deep Neural Networks, Combined Ward Hierarchical Clustering and Novelty Detection with Local Outlier Factor and Time-to-failure prediction using Random Forest Regression) appear to exhibit high potential to reach the goals of the Challenge. However, there are a number of concrete things that would have to have been done by the Challenge providers and the Challenge moderators in order to ensure success. This includes enabling access to more details of the different failure types, access to multiple data sets from more wind turbines experiencing gearbox failure, provision of a model or rule relating fault detection times or a remaining useful lifetime to the estimated costs for repairs, replacements and inspections, provision of a clear strategy for training and test periods in advance, as well as provision of a pre-defined template or requirements for the results. These learning outcomes are used directly to define a set of best practice data sharing guidelines for wind turbine fault detection model evaluation. The guidelines can be used by researchers in the sector in order to improve model evaluation and data sharing in the future.
Open AccessBest Practice Data Sharing Guidelines for Wind Turbine Fault Detection Model Evaluation
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 drivers for reducing costs and risks over the whole wind energy project life cycle. One of the largest challenges in successfully implementing digitalisation is the lack of data sharing and collaboration between organisations in the sector. In order to overcome this challenge, a new collaboration framework called WeDoWind was developed in recent work. The main innovation of this framework is the way it creates tangible incentives to motivate and empower different types of people from all over the world to share data and knowledge in practice. In this present paper, the challenges related to comparing and evaluating different SCADA-data-based wind turbine fault detection models are investigated by carrying out a new case study, the “WinJi Gearbox Fault Detection Challenge”, based on the WeDoWind framework. A total of six new solutions were submitted to the challenge, and a comparison and evaluation of the results show that, in general, some of the approaches (Particle Swarm Optimisation algorithm for constructing health indicators, performance monitoring using Deep Neural Networks, Combined Ward Hierarchical Clustering and Novelty Detection with Local Outlier Factor and Time-to-failure prediction using Random Forest Regression) appear to exhibit high potential to reach the goals of the Challenge. However, there are a number of concrete things that would have to have been done by the Challenge providers and the Challenge moderators in order to ensure success. This includes enabling access to more details of the different failure types, access to multiple data sets from more wind turbines experiencing gearbox failure, provision of a model or rule relating fault detection times or a remaining useful lifetime to the estimated costs for repairs, replacements and inspections, provision of a clear strategy for training and test periods in advance, as well as provision of a pre-defined template or requirements for the results. These learning outcomes are used directly to define a set of best practice data sharing guidelines for wind turbine fault detection model evaluation. The guidelines can be used by researchers in the sector in order to improve model evaluation and data sharing in the future.
- Open Access
- 14 March 2023
- Published by MDPI AG in Preprints.org
Best Practice Data Sharing Guidelines for Wind Turbine Fault Detection Model Evaluation
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 challenges in successfully implementing digitalisation is the lack of data sharing and collaboration between organisations in the sector. In order to overcome this challenge, a new collaboration method called WeDoWind was developed in recent work. The main innovation of this method is the way it creates tangible incentives to motivate and empower different types of people from all over the world to actually share data and knowledge in practice. In this present paper, the challenges related to comparing and evaluating different SCADA data based wind turbine fault detection models are investigated by carrying out a new case study, the "WinJi Gearbox Fault Detection Challenge", based on the WeDoWind Method. Six new solutions were submitted to the challenge, and a comparison and evaluation of the results show that, in general, some of the approaches (Particle Swarm Optimisation algorithm for constructing health indicators, performance monitoring using Deep Neural Networks, Combined Ward Hierarchical Clustering and Novelty Detection with Local Outlier Factor and Time-to-failure prediction using Random Forest Regression) appear to have a high potential to reach the goals of the Challenge. However, there are a number of concrete things that would have to have been done by the Challenge providers and the Challenge moderators in order to ensure success. This includes enabling access to more details of the different failure types, access to multiple data sets from more wind turbines experiencing gearbox failure, provision of a model or rule relating fault detection times or a remaining useful lifetime to the estimated costs for repairs, replacements and inspections, provision of a clear strategy for training and test periods in advance, as well as provision of a pre-defined template or requirements for the results. These learning outcomes are used directly to define a set of best practice data sharing guidelines for wind turbine fault detection model evaluation. They can be used by the sector in order to improve model evaluation and data sharing in the future.
- 14 March 2023
- Published by MDPI AG in Preprints.org
Open AccessBest Practice Data Sharing Guidelines for Wind Turbine Fault Detection Model Evaluation
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 challenges in successfully implementing digitalisation is the lack of data sharing and collaboration between organisations in the sector. In order to overcome this challenge, a new collaboration method called WeDoWind was developed in recent work. The main innovation of this method is the way it creates tangible incentives to motivate and empower different types of people from all over the world to actually share data and knowledge in practice. In this present paper, the challenges related to comparing and evaluating different SCADA data based wind turbine fault detection models are investigated by carrying out a new case study, the "WinJi Gearbox Fault Detection Challenge", based on the WeDoWind Method. Six new solutions were submitted to the challenge, and a comparison and evaluation of the results show that, in general, some of the approaches (Particle Swarm Optimisation algorithm for constructing health indicators, performance monitoring using Deep Neural Networks, Combined Ward Hierarchical Clustering and Novelty Detection with Local Outlier Factor and Time-to-failure prediction using Random Forest Regression) appear to have a high potential to reach the goals of the Challenge. However, there are a number of concrete things that would have to have been done by the Challenge providers and the Challenge moderators in order to ensure success. This includes enabling access to more details of the different failure types, access to multiple data sets from more wind turbines experiencing gearbox failure, provision of a model or rule relating fault detection times or a remaining useful lifetime to the estimated costs for repairs, replacements and inspections, provision of a clear strategy for training and test periods in advance, as well as provision of a pre-defined template or requirements for the results. These learning outcomes are used directly to define a set of best practice data sharing guidelines for wind turbine fault detection model evaluation. They can be used by the sector in order to improve model evaluation and data sharing in the future.
- Open Access
- 24 February 2023
- Published by MDPI AG in Applied Sciences
- Vol. 13 (5) , 2912
Real-Time, Model-Agnostic and User-Driven Counterfactual Explanations Using Autoencoders
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, counterfactual explanations have been proposed to elucidate the reasoning behind a model’s decisions by providing what-if statements as explanations. However, generating counterfactuals traditionally involves solving an optimization problem for each input, making it impractical for real-time feedback. Moreover, counterfactuals must meet specific criteria, including being user-driven, causing minimal changes, and staying within the data distribution. To overcome these challenges, a novel model-agnostic approach called Real-Time Guided Counterfactual Explanations (RTGCEx) is proposed. This approach utilizes autoencoders to generate real-time counterfactual explanations that adhere to these criteria by optimizing a multiobjective loss function. The performance of RTGCEx has been evaluated on two datasets: MNIST and Gearbox, a synthetic time series dataset. The results demonstrate that RTGCEx outperforms traditional methods in terms of speed and efficacy on MNIST, while also effectively identifying and rectifying anomalies in the Gearbox dataset, highlighting its versatility across different scenarios.
- 24 February 2023
- Published by MDPI AG in Applied Sciences
- Vol. 13 (5) , 2912
Open AccessReal-Time, Model-Agnostic and User-Driven Counterfactual Explanations Using Autoencoders
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, counterfactual explanations have been proposed to elucidate the reasoning behind a model’s decisions by providing what-if statements as explanations. However, generating counterfactuals traditionally involves solving an optimization problem for each input, making it impractical for real-time feedback. Moreover, counterfactuals must meet specific criteria, including being user-driven, causing minimal changes, and staying within the data distribution. To overcome these challenges, a novel model-agnostic approach called Real-Time Guided Counterfactual Explanations (RTGCEx) is proposed. This approach utilizes autoencoders to generate real-time counterfactual explanations that adhere to these criteria by optimizing a multiobjective loss function. The performance of RTGCEx has been evaluated on two datasets: MNIST and Gearbox, a synthetic time series dataset. The results demonstrate that RTGCEx outperforms traditional methods in terms of speed and efficacy on MNIST, while also effectively identifying and rectifying anomalies in the Gearbox dataset, highlighting its versatility across different scenarios.
- 1 January 2023
- Published by Research Publishing Services
- p. 1862-1868
Towards a Probabilistic Error Correction Approach for Improved Drone Battery Health Assessment
- 1 January 2023
- Published by Research Publishing Services
- p. 1862-1868
Towards a Probabilistic Error Correction Approach for Improved Drone Battery Health Assessment
- 2 March 2022
- Published by Taylor & Francis in International Journal of Computer Integrated Manufacturing
- Vol. 35 (12) , 1310-1334
Methodology for data-driven predictive maintenance models design, development and implementation on manufacturing guided by domain knowledge
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 research is carried out with expert systems and data-driven algorithms, but it is mainly focused on improving the results of reference simulation data sets. Hence, industrial requirements are not commonly addressed, and there is no guiding methodology for their implementation in real PdM use-cases. The objective of this work is to present a methodology for PdM application in industrial companies by combining data-driven techniques with domain knowledge. It defines sequentially ordered stages, steps and tasks to facilitate the design, development and implementation of PdM systems according to business and process characteristics. It also facilitates the collaboration among the required working profiles and defines deliverables. It is designed in a flexible and iterative way, combining standards, state-of-the-art methodologies and referent works of the field. Finally, the proposed methodology is validated on two use-cases: a bushing testbed and a press machine of the production line. These use-cases aim to facilitate, guide and speed up the implementation of the methodology on other PdM use-cases.
- 2 March 2022
- Published by Taylor & Francis in International Journal of Computer Integrated Manufacturing
- Vol. 35 (12) , 1310-1334
Methodology for data-driven predictive maintenance models design, development and implementation on manufacturing guided by domain knowledge
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 research is carried out with expert systems and data-driven algorithms, but it is mainly focused on improving the results of reference simulation data sets. Hence, industrial requirements are not commonly addressed, and there is no guiding methodology for their implementation in real PdM use-cases. The objective of this work is to present a methodology for PdM application in industrial companies by combining data-driven techniques with domain knowledge. It defines sequentially ordered stages, steps and tasks to facilitate the design, development and implementation of PdM systems according to business and process characteristics. It also facilitates the collaboration among the required working profiles and defines deliverables. It is designed in a flexible and iterative way, combining standards, state-of-the-art methodologies and referent works of the field. Finally, the proposed methodology is validated on two use-cases: a bushing testbed and a press machine of the production line. These use-cases aim to facilitate, guide and speed up the implementation of the methodology on other PdM use-cases.
- Top Cited Papers
- 18 January 2022
- Published by Springer Nature in Applied Intelligence
- Vol. 52 (10) , 10934-10964
Deep learning models for predictive maintenance: a survey, comparison, challenges and prospects
- 18 January 2022
- Published by Springer Nature in Applied Intelligence
- Vol. 52 (10) , 10934-10964
Top Cited PapersDeep learning models for predictive maintenance: a survey, comparison, challenges and prospects
- Open Access
- 11 August 2021
- Published by MDPI AG in Applied Sciences
- Vol. 11 (16) , 7376
Adaptable and Explainable Predictive Maintenance: Semi-Supervised Deep Learning for Anomaly Detection and Diagnosis in Press Machine Data
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 conditions. Thereby, semi-supervised data-driven models are relevant to enable PdM application by learning from assets’ data. However, their main challenges for application in industry are achieving high accuracy on anomaly detection, diagnosis of novel failures, and adaptability to changing environmental and operational conditions (EOC). This article aims to tackle these challenges, experimenting with algorithms in press machine data of a production line. Initially, state-of-the-art and classic data-driven anomaly detection model performance is compared, including 2D autoencoder, null-space, principal component analysis (PCA), one-class support vector machines (OC-SVM), and extreme learning machine (ELM) algorithms. Then, diagnosis tools are developed supported on autoencoder’s latent space feature vector, including clustering and projection algorithms to cluster data of synthetic failure types semi-supervised. In addition, explainable artificial intelligence techniques have enabled to track the autoencoder’s loss with input data to detect anomalous signals. Finally, transfer learning is applied to adapt autoencoders to changing EOC data of the same process. The data-driven techniques used in this work can be adapted to address other industrial use cases, helping stakeholders gain trust and thus promote the adoption of data-driven PdM systems in smart factories.
- 11 August 2021
- Published by MDPI AG in Applied Sciences
- Vol. 11 (16) , 7376
Open AccessAdaptable and Explainable Predictive Maintenance: Semi-Supervised Deep Learning for Anomaly Detection and Diagnosis in Press Machine Data
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 conditions. Thereby, semi-supervised data-driven models are relevant to enable PdM application by learning from assets’ data. However, their main challenges for application in industry are achieving high accuracy on anomaly detection, diagnosis of novel failures, and adaptability to changing environmental and operational conditions (EOC). This article aims to tackle these challenges, experimenting with algorithms in press machine data of a production line. Initially, state-of-the-art and classic data-driven anomaly detection model performance is compared, including 2D autoencoder, null-space, principal component analysis (PCA), one-class support vector machines (OC-SVM), and extreme learning machine (ELM) algorithms. Then, diagnosis tools are developed supported on autoencoder’s latent space feature vector, including clustering and projection algorithms to cluster data of synthetic failure types semi-supervised. In addition, explainable artificial intelligence techniques have enabled to track the autoencoder’s loss with input data to detect anomalous signals. Finally, transfer learning is applied to adapt autoencoders to changing EOC data of the same process. The data-driven techniques used in this work can be adapted to address other industrial use cases, helping stakeholders gain trust and thus promote the adoption of data-driven PdM systems in smart factories.
- 11 September 2020
- Published by Springer Nature
- p. 235-244
Contrastive Explanations for a Deep Learning Model on Time-Series Data
- 11 September 2020
- Published by Springer Nature
- p. 235-244
Contrastive Explanations for a Deep Learning Model on Time-Series Data