Stability-based system for bearing fault early detection. (15th August 2017)

• Record Type: Journal Article
• Authors: Diaz, Moises; Henriquez, Patricia; Ferrer, Miguel A.; Pirlo, Giuseppe; Alonso, Jesus B.; Carmona-Duarte, Cristina; Impedovo, Donato
• Is Part Of: Expert systems with applications. Volume 79(2017)
• Page Start: 65
• Page End: 75
• Publication Date: 2017-08-15
• Subjects: Bearing fault detection -- Direct matching points -- Dynamic time warping -- Stability analysis; DTW Dynamic Time Warping -- DMP Direct Matching Points -- N Normal vibration signal -- OR Outer race -- IR Inner race -- B Balls -- b Ball diameters -- D Pitch diameters -- D Pitch diameters -- ΔP Local stability -- di Faulty severities -- τ Temporal frame -- nc Number of cycles -- fs Sampling rate -- frpm Rotation speed -- T Total duration of signal -- ψ Number of divisions of a recorder signal -- ν Number of total comparison -- H2 Hellinger distance -- g(x) Fault-free signal pdf -- f(x) Faulty signal pdf; Expert systems (Computer science) -- Periodicals; Systèmes experts (Informatique) -- Périodiques; Electronic journals; 006.33
• DOI: 10.1016/j.eswa.2017.02.030
• Languages: English
• ISSNs: 0957-4174

Abstract

Highlights: Novel Stability-based system for early bearing fault detection. Novel use of Dynamic Time Warping and Direct Matching Point techniques. Findings on continuous monitoring of vibration signals with low false alarms for faults Findings on two publicly available databases under several machining conditions. Abstract: This paper presents a new and straightforward system for bearing fault detection. The system computes the stability of two vibration signals by using the direct matching points (DMP) of an elastic and non-linear align function. It is able to find discriminant properties in the stability of fault-free and faulty bearing vibration signals from the early and late stages of the fault in critical bearing parts. Because training data constitutes one of the critical challenges in most expert and intelligent systems, one of the novelties of the proposed stability-based system is that it requires neither training nor fine-tuning. A significant impact on the robustness of the system is demonstrated using two publicly available vibration signal databases under several load conditions, with real faults, during multiple machine working states. Experimental results validate the use of the proposed stability-based system for predictive maintenance in bearings.