Deep Learning-based Fault Detection, Classification, and Locating in Shipboard Power Systems

Senemmar, Soroush; Zhang, Jie

doi:10.1109/ests49166.2021.9512342

Cited by 15 publications

(5 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This paper introduces a cascading deep learning framework, grounded in signal processing, designed for the diagnosis of ITSCFs and the estimation of severity in the context of wind turbine Double-Fed Induction Generator (DFIG) systems. Such framework is built on top of our prior studies on complex systems monitoring and fault detection [9][10][11][12]. Initially, 16 operating modes of WT DFIG are identified and simulated using MATLAB.…”

Section: Research Objectivesmentioning

confidence: 99%

Inter-turn Short Circuit Fault Diagnosis and Severity Estimation for Wind Turbine Generators

Yan,

Senemmar,

Zhang

2024

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

While preventive maintenance is crucial in wind turbine operation, conventional condition monitoring systems face limitations in terms of cost and complexity when compared to innovative signal processing techniques and artificial intelligence. In this paper, a cascading deep learning framework is proposed for the monitoring of generator winding conditions, specifically to promptly detect and identify inter-turn short circuit faults and estimate their severity in real time. This framework encompasses the processing of high-resolution current signal samples, coupled with the extraction of current signal features in both time and frequency domains, achieved through discrete wavelet transform. By leveraging long short-term memory recurrent neural networks, our aim is to establish a cost-efficient and reliable condition monitoring system for wind turbine generators. Numeral experiments show an over 97% accuracy for fault diagnosis and severity estimation. More specifically, with the intrinsic feature provided by wavelet transform, the faults can be 100% identified by the diagnosis model.

show abstract

Section: Research Objectivesmentioning

confidence: 99%

Inter-turn Short Circuit Fault Diagnosis and Severity Estimation for Wind Turbine Generators

Yan,

Senemmar,

Zhang

2024

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

show abstract

“…Fault isolation: Fault isolation models predict attack types directly [25], [71], turning an anomaly-detection task into a classification task [35], [54]. Fault isolation requires an explicit definition of the types of faults expected in the system, which can be difficult to acquire [67].…”

Section: Rule-based Anomaly Detectionmentioning

confidence: 99%

Attributions for ML-based ICS Anomaly Detection: From Theory to Practice

Fung,

Zeng,

Bauer

2024

Proceedings 2024 Network and Distributed System Security Symposium

View full text Add to dashboard Cite

Industrial Control Systems (ICS) govern critical infrastructure like power plants and water treatment plants. ICS can be attacked through manipulations of its sensor or actuator values, causing physical harm. A promising technique for detecting such attacks is machine-learning-based anomaly detection, but it does not identify which sensor or actuator was manipulated and makes it difficult for ICS operators to diagnose the anomaly's root cause. Prior work has proposed using attribution methods to identify what features caused an ICS anomaly-detection model to raise an alarm, but it is unclear how well these attribution methods work in practice. In this paper, we compare state-of-the-art attribution methods for the ICS domain with real attacks from multiple datasets. We find that attribution methods for ICS anomaly detection do not perform as well as suggested in prior work and identify two main reasons. First, anomaly detectors often detect attacks either immediately or significantly after the attack start; we find that attributions computed at these detection points are inaccurate. Second, attribution accuracy varies greatly across attack properties, and attribution methods struggle with attacks on categorical-valued actuators. Despite these challenges, we find that ensembles of attributions can compensate for weaknesses in individual attribution methods. Towards practical use of attributions for ICS anomaly detection, we provide recommendations for researchers and practitioners, such as the need to evaluate attributions with diverse datasets and the potential for attributions in non-real-time workflows.

show abstract

“…SigFox, with its base stations strategically located globally, employs an unlicensed sub-GHz ISM frequency spectrum. Fog computing, an architecture facilitating remote collaboration, designates network edge devices as central repositories for data, processing, and applications, providing advantages like position perception and reduced latency [119]. This approach finds broad utility in diverse applications such as smart cities, smart grids, and smart cars.…”

Section: Nascent Technologies Of Massmentioning

confidence: 99%

Maritime Autonomous Surface Ships: A Review of Cybersecurity Challenges, Countermeasures, and Future Perspectives

Tabish,

Chaur-Luh

2024

IEEE Access

View full text Add to dashboard Cite

Maritime Autonomous Surface Ships (MASS) have brought a transformative wave in the marine industry, yielding unprecedented operational advancements and efficiency gains. However, this paradigm shift has concurrently raised substantial cybersecurity concerns that demand meticulous attention to mitigate the impact of attacks on MASS stability. This study presents a comprehensive examination of the cybersecurity landscape, shedding light on prevalent issues concerning the data independence, integrity, and connectivity of MASS. The effectiveness of existing defense strategies against both inbound and outbound cyberattacks, focusing on attack detection and classification, is rigorously scrutinized. This analysis encompasses regulatory frameworks, encryption methods, intrusion detection systems, and a systematic approach to identifying and categorizing cyber threats. Additionally, the study anticipates future developments in cyber threats and proposes innovative solutions to fortify MASS defenses against potential cybersecurity vulnerabilities. To align with cybersecurity standards, this paper integrates challenges, possible solutions, and future advancements in a structured and cohesive manner, ensuring a thorough understanding of the intricate cybersecurity ecosystem surrounding Maritime Autonomous Surface Ships.

show abstract

Deep Learning-based Fault Detection, Classification, and Locating in Shipboard Power Systems

Cited by 15 publications

References 12 publications

Inter-turn Short Circuit Fault Diagnosis and Severity Estimation for Wind Turbine Generators

Inter-turn Short Circuit Fault Diagnosis and Severity Estimation for Wind Turbine Generators

Attributions for ML-based ICS Anomaly Detection: From Theory to Practice

Maritime Autonomous Surface Ships: A Review of Cybersecurity Challenges, Countermeasures, and Future Perspectives

Contact Info

Product

Resources

About