Abstract
A great investment is made in maintenance of machinery in any industry. A big percentage of this is spent both in workers and in materials in order to prevent potential issues with said devices. In order to avoid unnecessary expenses, this article presents an intelligent method to detect incipient faults. Particularly, this study focuses on bearings due to the fact that they are the mechanical elements that are most likely to break down. In this article, the proposed method is tested with data collected from a quasi-real industrial machine, which allows for the measurement of the behaviour of faulty bearings with incipient defects. In a second phase, the vibrations obtained from healthy and defective pieces are processed with a multiresolution analysis with the purpose of extracting the most interesting characteristics. Particularly, a Wavelet Packets Transform processing is carried out. Finally, these parameters are used as Genetic Neuro-Fuzzy inputs; this way, once it has been trained, it will indicate whether the analyzed mechanical element is faulty or not.
Highlights
Machinery is a fundamental part of any industry; any breakdown could imply an inoperative period of time and economic loss
The level 3 discrete wavelet transform (DWT) decomposition applied to the signal provides an eight characteristic coefficient vector, as it was explained in previous sections
Vibration signals of healthy and faulty mechanical elements were measured and a signal processing was accomplished, a Wavelet Packets Transform (WPT), as it was explained in previous sections
Summary
Machinery is a fundamental part of any industry; any breakdown could imply an inoperative period of time and economic loss. Analyzing critical components involves getting to know their internal state, which, in turn, allows for an early detection of incipient faults. One of the most critical elements in any industrial machine is rolling bearing, which means that anticipating any potential fault or breakdown is essential. In this sense, by knowing the normal state of the machinery, its monitoring could help to prevent a breakdown since any machinery would show a signal before failing. Condition monitoring allows for the detection of incipient faulty mechanical elements, which is why this method is such a widely explored research field.[1,2,3,4,5,6,7,8] An important aspect of this work is that the experimental laboratory bench used to collect data includes a radial load due to the fact that this is the most important force for which rolling bearings are designed
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
