Purpose -The purpose of this paper is to detect gears' faults with an automatic decision-making process and find a reliable method to detect faults on gear systems using a composition of conventional methods. Design/methodology/approach -First, the vibration behavior of gears during engagement is investigated. Then, after studying different methods of fault detection using vibration signals analysis, a suitable method is proposed for the case of gears. For this purpose, a fuzzy model is employed based on available knowledge about fault detection of gears and results obtained from vibration behavior of gears. In the mentioned fuzzy model, a feature extracted from wavelet transform and also a couple of statistical indexes are used as fault criteria. Findings -Using fuzzy systems instead of numerous data in training the decision-making system and also utilizing available knowledge of gears' signals and information of fault effects can significantly simplify the decision-making process in auto-detecting gears faults, considering difficulty of laboratory set up, manufacturing and different faults creation, as well as, lack of sufficient data. Practical implications -In order to validate and enhance the proposed model, an empirical set up is manufactured and tested. Later on, the model is tested on another set of gears. Originality/value -Although the gears' faults were completely different from those of experimental set up, promising results in detecting faults were obtained. Moreover, it is shown that it is possible to determine the level of gears' health, as well as to estimate the gears' status, owing to fuzzy logic. This issue can be observed in the change of fault parameter while analyzing signals related to the fault growth in gears.
The increase of cyber attacks in both the numbers and varieties in recent years demands to build a more sophisticated network intrusion detection system (NIDS). These NIDS perform better when they can monitor all the traffic traversing through the network like when being deployed on a Software-Defined Network (SDN). Because of the inability to detect zeroday attacks, signature-based NIDS which were traditionally used for detecting malicious traffic are beginning to get replaced by anomaly-based NIDS built on neural networks. However, recently it has been shown that such NIDS have their own drawback namely being vulnerable to the adversarial example attack. Moreover, they were mostly evaluated on the old datasets which don't represent the variety of attacks network systems might face these days. In this paper, we present Reconstruction from Partial Observation (RePO) as a new mechanism to build an NIDS with the help of denoising autoencoders capable of detecting different types of network attacks in a low false alert setting with an enhanced robustness against adversarial example attack. Our evaluation conducted on a dataset with a variety of network attacks shows denoising autoencoders can improve detection of malicious traffic by up to 29% in a normal setting and by up to 45% in an adversarial setting compared to other recently proposed anomaly detectors.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.