AN ANALYSIS ON DIAGNOSTIC METHOD OF ROLLER BEARING FAULTS BASED ON AUDITORY SPECTRUM AND SPECTRAL CORRELATION
Journal Title: Topics in Intelligent Computing and Industry Design (ICID) - Year 2017, Vol 1, Issue 2
Abstract
Human auditory system possesses a desirable capacity for analyzing, processing and identifying signals. Whereas different types of rolling bearing faults cause different vibration noises, a new method based on early auditory model (EA model) is proposed for the diagnosis of rolling bearing faults. Firstly, according to characteristics of mechanical vibration signal, the EA model was established by simulating the human auditory system. Secondly, sample signals were processed by the EA model to build sets of auditory spectrums, the characteristics of which were extracted with the purpose of obtaining the characteristic auditory spectrums that reflected the overall characteristics of failure states, so as to further simplify the data. At last, based on spectral correlation, it applied integrated correlation coefficient to identify fault type. Experimental results show that the method is capable of extracting and distinguishing the overall characteristics of 12 types of rolling bearing fault states (four different degrees of faults and normal state of inner race, outer race and rolling element) with almost 100 percent accuracy possesses considerable feasibility an d certain potentialities in practical application.
Authors and Affiliations
Li Yungong, Xu Jinfang, Da Li, Zhang Qilin
Keywords
Related Articles
- EP ID EP409812
- DOI 10.26480/wsmce.01.2017.128.128
- Views 74
- Downloads 0
THE DESIGN OF VEHICLE HAZARD WARNING DEVICE
With the accident of Asphyxiation and death in the children’s car in recent years, the demand for this kind of dangerous alarm devices. The vehicle dangerous alarm device has both temperature and oxygen concentration mon...
DESIGN OF MULTI-LANGUAGE AUTOMATIC PLAYER SYSTEM
This paper is presented a design of system of multi-language automatic player, which is based on AT89S52 microcontroller and ISD4004. System hardware circuit is mainly composed of single-chip control circuit, liquid crys...
THE RESEARCH OF PREDICTING THE CERVICAL CANCER BASING ON BAYESIAN ALGORITHM
Cervical cancer remains a significant cause of mortality in low-income country. It is necessary to find a most effective machine learning algorithm to predict the cervical cancer. Our research attempts to help doctor to...
RESEARCH AND DEVELOPMENT OF STATIC LOAD TEST BENCH FOR EMU GEAR UNIT
The gear unit has been recently added to the list of the railway products that require compulsory certification according to China Railway Corporation. The test of the gear unit becomes much more important and urgent. It...
PERSONALIZED MUSIC RECOMMENDATION BASED ON CLUSTERING ALGORITHM
Aiming at the recommendation of music field, this paper proposes a music recommendation algorithm based on attribute selection and application clustering. Firstly, the recommended progress of music conduct in-depth analy...