Nhảy đến nội dung

Algorithm for Estimating Online Bearing Fault upon the Ability to Extract Meaningful Information from Big Data of Intelligent Structures


Quang Thịnh Trần, Sy Dzung Nguyen*, Tae-Il Seo

Source title: 
IEEE Transactions on Industrial Electronics, 2018 (ISI)
Academic year of acceptance: 

Bearing is an important machine detail participating in almost mechanical systems. Estimating online its operating condition to hold the initiative in exploiting the systems, therefore, is one of the most urgent requirements. In this paper we propose an Online Bearing Damage Identifying Method named ASSBDIM based on Adaptive Neuro-Fuzzy Inference System (ANFIS), Singular Spectrum Analysis (SSA) and Sparse Filtering (SF). It is an online process with offline and online phases. In the offline, by applying SSA and SF to the measured data stream typed big data with noise, both preprocessing data and extracting valuable information are implemented to build two offline-databases signed Off_DaB and Off_testDaB. The ANFIS identifies dynamic response of the mechanical system via the Off_DaB. Based on the Off_testDaB, the parameters of the ASSBDIM are then optimized. In the online, at each time, another database called On_DaB is built upon the way similar to the one for building the input space of the two offline-databases. The On_DaB participates as inputs of the ANFIS to estimate its outputs which are then compared with the corresponding encoded outputs to specify bearing real status at this time. Survey results based on different data sources showed the effectiveness of the proposed method.