A One-class Classifier Based on a Hybrid Topology to Detect Faults in Power Cells

Jove, Esteban; Casteleiro‐Roca, José‐Luis; Quintián, Héctor; Zayas‐Gato, Francisco; Vercelli, Gianni; Calvo-Rolle, José Luís

doi:10.1093/jigpal/jzab011

Cited by 13 publications

(4 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…First, the data were used without any normalization process, NoNorm , then the data were normalized using a 0 to 1 criterion, Norm , and finally, the z-score method was applied (with a mean of 0 and a standard deviation of 1), Zscore [ 63 ]. The use of these normalization techniques, Zscore , in combination with one-class classification methods, has shown satisfactory results [ 64 ].…”

Section: Experiments Description (Setup) and Resultsmentioning

confidence: 99%

A Fault-Detection System Approach for the Optimization of Warship Equipment Replacement Parts Based on Operation Parameters

Michelena

López

Lamas-Lopez

et al. 2023

Sensors

Self Cite

View full text Add to dashboard Cite

Systems engineering plays a key role in the naval sector, focusing on how to design, integrate, and manage complex systems throughout their life cycle; it is therefore difficult to conceive functional warships without it. To this end, specialized information systems for logistical support and the sustainability of material solutions are essential to ensure proper provisioning and to know the operational status of the frigate. However, based on an architecture composed of a set of logistics applications, this information system may require highly qualified operators with a deep knowledge of the behavior of onboard systems to manage it properly. In this regard, failure detection systems have been postulated as one of the main cutting-edge methods to address the challenge, employing intelligent techniques for observing anomalies in the normal behavior of systems without the need for expert knowledge. In this paper, the study is concerned to the scope of the Spanish navy, where a complex information system structure is responsible for ensuring the correct maintenance and provisioning of the vessels. In such context, we hereby suggest a comparison between different one-class techniques, such as statistical models, geometric boundaries, or dimensional reduction to face anomaly detection in specific subsystems of a warship, with the prospect of applying it to the whole ship.

show abstract

Section: Experiments Description (Setup) and Resultsmentioning

confidence: 99%

A Fault-Detection System Approach for the Optimization of Warship Equipment Replacement Parts Based on Operation Parameters

Michelena

López

Lamas-Lopez

et al. 2023

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…The non supervised family of learning algorithm, named K-Means, is well known for clustering purposes [47,48]. This procedure defines a set of groups for the initial data set based on the number of groups selected by the user.…”

Section: K-meansmentioning

confidence: 99%

Intelligent One-Class Classifiers for the Development of an Intrusion Detection System: The MQTT Case Study

et al. 2022

Self Cite

View full text Add to dashboard Cite

The ever-increasing number of smart devices connected to the internet poses an unprecedented security challenge. This article presents the implementation of an Intrusion Detection System (IDS) based on the deployment of different one-class classifiers to prevent attacks over the Internet of Things (IoT) protocol Message Queuing Telemetry Transport (MQTT). The utilization of real data sets has allowed us to train the one-class algorithms, showing a remarkable performance in detecting attacks.

show abstract

“…A common solution consists of the use of renewable energy sources such as solar, wind, hydraulic or even ocean energy [20,11,7]. On the other hand, an interesting research line is focused on Proton-Exchange Membranes Fuel Cells (PEMFC) [21,19]. This technology can be efficiently used in micro-combined heat and power units (CHP) and electric vehicles [3,27].…”

Section: R a F T C O P Ymentioning

confidence: 99%

A Virtual Sensor for a Cell Voltage Prediction of a Proton-Exchange Membranes Based on Intelligent Techniques

Jove

Lozano

Manso

et al. 2021

Sustainable Smart Cities and Territories

Self Cite

View full text Add to dashboard Cite

The use of Proton-Exchange Membranes Fuel Cells is presented as a key alternative to face the increasing and concerning problems related to global warming. The international expansion of green policies, has resulted in the need of ensuring their quality and reliability performance. Although fuel cells can get to play a significant role, this technology is still under development, paying special attention to the problems related to gas starvation and degradation. In this context, the present work deals with the virtual sensor implementation of one of the voltage cells present in a stack, whose operation is subjected to several degradation cycles. The proposal predicts indirectly the voltage of one cell from the current state of the rest of the cells by means of an intelligent model.

show abstract

A One-class Classifier Based on a Hybrid Topology to Detect Faults in Power Cells

Cited by 13 publications

References 21 publications

A Fault-Detection System Approach for the Optimization of Warship Equipment Replacement Parts Based on Operation Parameters

A Fault-Detection System Approach for the Optimization of Warship Equipment Replacement Parts Based on Operation Parameters

Intelligent One-Class Classifiers for the Development of an Intrusion Detection System: The MQTT Case Study

A Virtual Sensor for a Cell Voltage Prediction of a Proton-Exchange Membranes Based on Intelligent Techniques

Contact Info

Product

Resources

About