Owing to the character of diversity and complexity, the compound fault diagnosis of rotating machinery under non-stationary operation has turned into a challenging task. In this paper, a novel method based on the optimal variational mode decomposition (OVMD) and 1.5-dimension envelope spectrum is proposed for detecting the compound faults of rotating machinery. In this method, compound fault signals are first decomposed by using OVMD containing optimal decomposition parameters, and several intrinsic mode components are obtained. Then, an adaptive selection method based on the weight factor (WF) is presented to choose two intrinsic mode components that contain the principal fault characteristic information. Finally, the 1.5-dimension envelope spectrum of the selected intrinsic mode components is utilized to extract the compound fault characteristic information of vibration signals. The performance of the proposed method is demonstrated by using the simulation signal and the experimental vibration signals collected from a rolling bearing and a gearbox with compound faults. The analysis results suggest that the proposed method is not only capable of detecting compound faults of a bearing and a gearbox, but can separate the characteristic signatures of compound faults. The research offers a new means for the compound fault diagnosis of rotating machinery.

No abstract

Deep learning (DL) models are inherently vulnerable to adversarial examples -maliciously crafted inputs to trigger target DL models to misbehave -which significantly hinders the application of DL in security-sensitive domains. Intensive research on adversarial learning has led to an arms race between adversaries and defenders. Such plethora of emerging attacks and defenses raise many questions: Which attacks are more evasive, preprocessing-proof, or transferable? Which defenses are more effective, utility-preserving, or general? Are ensembles of multiple defenses more robust than individuals? Yet, due to the lack of platforms for comprehensive evaluation on adversarial attacks and defenses, these critical questions remain largely unsolved.In this paper, we present the design, implementation, and evaluation of DEEPSEC, a uniform platform that aims to bridge this gap. In its current implementation, DEEPSEC incorporates 16 state-of-the-art attacks with 10 attack utility metrics, and 13 state-of-the-art defenses with 5 defensive utility metrics. To our best knowledge, DEEPSEC is the first platform that enables researchers and practitioners to (i) measure the vulnerability of DL models, (ii) evaluate the effectiveness of various attacks/defenses, and (iii) conduct comparative studies on attacks/defenses in a comprehensive and informative manner. Leveraging DEEPSEC, we systematically evaluate the existing adversarial attack and defense methods, and draw a set of key findings, which demonstrate DEEPSEC's rich functionality, such as (1) the trade-off between misclassification and imperceptibility is empirically confirmed;(2) most defenses that claim to be universally applicable can only defend against limited types of attacks under restricted settings;(3) it is not necessary that adversarial examples with higher perturbation magnitude are easier to be detected; (4) the ensemble of multiple defenses cannot improve the overall defense capability, but can improve the lower bound of the defense effectiveness of individuals. Extensive analysis on DEEPSEC demonstrates its capabilities and advantages as a benchmark platform which can benefit future adversarial learning research.

No abstract

No abstract