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.
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.
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.
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.
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.
Hashemi, M. and Saeed Safizadeh, M. (2013), "Design of a fuzzy model based on vibration signal analysis to auto‐detect the gear faults", Industrial Lubrication and Tribology, Vol. 65 No. 3, pp. 194-201. https://doi.org/10.1108/00368791311311196Download as .RIS
Emerald Group Publishing Limited
Copyright © 2013, Emerald Group Publishing Limited