DC-DC power converters play an important role in renewable energy systems, electrical vehicles, and battery chargers and so forth. DC-DC Buck converters are prone to faults due to age and unexpected accidents. As a re...
详细信息
ISBN:
(纸本)9781728170114
DC-DC power converters play an important role in renewable energy systems, electrical vehicles, and battery chargers and so forth. DC-DC Buck converters are prone to faults due to age and unexpected accidents. As a result, there is a high demand to improve the operation reliability and safety of power converters by using condition monitoring and fault diagnosis techniques. In this paper, data-driven and machine learning-based fault detection and faultclassification strategies are addressed for DC-DC Buck converters under disparate faulty scenarios of the parameters. A variety of algorithms such as principal component analysis, multi-linear principal component analysis, uncorrelated multi-linear principal component analysis, and Fast Fourier Transformation pre-processing based multi-linear principal component analysis and uncorrelated multi linear principal component analysis techniques are applied for faultclassification and diagnosis of the parameter faults in the DC-DC Buck converters. The effectiveness is demonstrated and discussed with details.
In modern industries, data-drivenfault detection and classification (FDC) systems can efficiently maintain industrial security and stability, while the security of the data-driven FDC system itself is rarely or even ...
详细信息
In modern industries, data-drivenfault detection and classification (FDC) systems can efficiently maintain industrial security and stability, while the security of the data-driven FDC system itself is rarely or even never considered. The security problem named adversarial vulnerability is the intrinsic of data-driven machine learning models, which will give incorrect predictions under the maliciously perturbed input data. This paper presents a work on this new security topic of the data-driven FDC systems, by 1) summarizing and comparing various recent and typical adversarial attack and defense methods for fault classifiers;2) proposing novel attack and defense techniques for unsupervised fault detectors;3) constructing a novel industrial adversarial security benchmark on FDC systems in the Tennessee-Eastman process (TEP) dataset;4) exploring and discussing which attack is most potentially threatening for FDC systems and which defense technique is most applicable to mitigate attacks. The results reveal unique security properties of FDC systems, mainly including 1) for fault classifiers, black-box attack is close to the attack strength of white-box FGSM and the universal transferable attack is not significantly stronger than random noise;2) weak adversarial training is excellent with high adversarial accuracy improvement and negligible clean accuracy decrease;3) fault detectors are intrinsically more robust, and can be well protected by strong adversarial training. More intriguing properties and profound insights are demonstrated in the paper. This pioneering work could guide researchers and practitioners in discovering and navigating the field of FDC system adversarial robustness, outlining the research directions and open problems.
暂无评论