Mahalanobis Taguchi System (MTS) as a Prognostics Tool for Rolling Element Bearing Failures

In this paper, a novel Mahalanobis–Taguchi system (MTS)-based fault detection, isolation, and prognostics scheme is presented. The proposed data-driven scheme utilizes the Mahalanobis distance (MD)-based fault clustering and the progression of MD values over time. MD thresholds derived from the clustering analysis are used for fault detection and isolation. When a fault is detected, the prognostics scheme, which monitors the progression of the MD values, is initiated. Then, using a linear approximation, time to failure is estimated. The performance of the scheme has been validated via experiments performed on rolling element bearings inside the spindle headstock of a microcomputer numerical control (CNC) machine testbed. The bearings have been instrumented with vibration and temperature sensors and experiments involving healthy and various types of faulty operating conditions have been performed. The experiments show that the proposed approach renders satisfactory results for bearing fault detection, isolation, and prognostics. Overall, the proposed solution provides a reliable multivariate analysis and real-time decision making tool that (1) presents a single tool for fault detection, isolation, and prognosis, eliminating the need to develop each separately and (2) offers a systematic way to determine the key features, thus reducing analysis overhead. In addition, the MTS-based scheme is process independent and can easily be implemented on wireless motes and deployed for real-time monitoring, diagnostics, and prognostics in a wide variety of industrial environments.

Download Full-text

On-Line Tracking and Monitoring of Rolling Element Bearing Faults

Volume 8: 26th Conference on Mechanical Vibration and Noise ◽

10.1115/detc2014-35094 ◽

2014 ◽

Author(s):

S. Chatterton ◽

P. Borghesani ◽

P. Pennacchi ◽

A. Vania

Keyword(s):

Real Time ◽

Damage Index ◽

Vibration Signal ◽

Operating Conditions ◽

Rolling Element Bearing ◽

Simple Task ◽

Alarm Signaling ◽

Rolling Element ◽

On Line ◽

Element Bearing

Diagnostics of rolling element bearings is usually performed by the analysis of vibration signal using suitable signal analysis tools, such as the most used and simplest method, Envelope Analysis. This method is based on the identification of bearing damage frequency components in the so-called Square Envelope Spectrum. If the assessment of the bearing health is quite a simple task, the on-line monitoring and the real-time evaluation of the trend of a suitable damage index is a complex task to be performed in an automatic way. The damage index must be robust against variations of system operating conditions and external vibration sources to avoid misleading results. The damage index should be also simple to be evaluated in the case of real-time applications. In the paper, the case of a rolling element bearing in which the defect develops until a permanent failure is described as well as the algorithm implemented for alarm signaling.

Download Full-text

Improved effectiveness of vibration monitoring of rolling bearings in paper mills

Proceedings of the Institution of Mechanical Engineers Part J Journal of Engineering Tribology ◽

10.1243/1350650981541930 ◽

1998 ◽

Vol 212 (2) ◽

pp. 111-120 ◽

Cited By ~ 12

Author(s):

B Al-Najjar

Keyword(s):

Critical Role ◽

Paper Mill ◽

Operating Conditions ◽

Rolling Element Bearing ◽

Vibration Monitoring ◽

Paper Mills ◽

Bearing Failures ◽

Study Results ◽

Rolling Element ◽

Vibration Signature

Rolling element bearing failures in paper mill machines are considered in relation to their critical role in the machine function. The paper discusses these failures according to what becomes damaged and how, and relates them to the vibration spectra and their development over the lives of the bearings. Interpretations of some variations in the vibration signature, i.e. relating vibration amplitude changes and frequency shifts to the deterioration processes involved, are proposed and discussed. The literature was found mainly to confirm this analysis. A new approach to envelope alarming is presented and shown theoretically (logically) to offer later renewal with fewer failures, and therefore lower cost and higher productivity. Deficiencies in data coverage and quality, and the feedback of case study results, are discussed. A model to improve maintenance experience is proposed and discussed. Using vibration to monitor component conditions, the accurate prediction of remaining life requires (a) enough vibration measurements, (b) numerate records of operating conditions, (c) better discrimination between frequencies in the spectrum and (d) correlation of (b) and (c). This is because life prediction depends on the amplitudes of (and) the frequencies generated by the component damage. Much money could be saved because some of the present policies utilize as little as half of the useful life of a bearing.

Download Full-text

Rolling element bearing multi-fault diagnosis using morphological joint time–frequency adaptive kernel–based semi-smart framework

Journal of Vibration and Control ◽

10.1177/10775463211022878 ◽

2021 ◽

pp. 107754632110228

Author(s):

Sunil Lonare ◽

Neville Fernandes ◽

Aditya Abhyankar

Keyword(s):

Wavelet Transform ◽

Fault Detection ◽

Fault Location ◽

Operating Conditions ◽

Experimental Results ◽

Rolling Element Bearing ◽

Time Frequency ◽

Rolling Element ◽

Adaptive Kernel ◽

Element Bearing

The wavelet transform is a state of the art time–frequency analysis method for rolling element bearing localized fault detection, using vibration signals. When these localized faults are present at more than one location of bearing, it is called “multi-fault.” Using wavelet transform fault detection with high severity is possible, but this method fails to detect the presence of fault as well as the location of a fault in multi-fault case and when the fault severity is low. The identification of the fault location, in rolling element bearing when more than one location of bearing contains a localized fault, is very useful for further root cause analysis; therefore, multi-fault detection is a challenge today. In the present work, a new morphological joint time–frequency adaptive kernel–based semi-smart framework is developed to address this challenge. In morphological joint time–frequency adaptive kernel, the kernel will adapt itself by analyzing the basic morphology of the bearing under observation and by considering the location of a fault. The simulation and experimental results show that morphological joint time–frequency adaptive kernel–based framework is able to detect low severity single fault as well as the location of the localized fault on rolling element bearing in the multi-fault case. Experimental results also show that the morphological joint time–frequency adaptive kernel framework is independent of bearing dimensions as well as machine operating conditions.

Download Full-text

Detection of Rolling-Element Bearing Faults in Non-stationary Quasi-Parallel Machinery Using Residual Analysis Augmented by Neural Networks

International Journal of Prognostics and Health Management ◽

10.36001/ijphm.2021.v12i2.2915 ◽

2021 ◽

Vol 12 (2) ◽

Author(s):

Dustin Helm ◽

Markus Timusk

Keyword(s):

Fault Detection ◽

Operating Conditions ◽

Rolling Element Bearing ◽

Detection Scheme ◽

Bearing Faults ◽

Feature Vectors ◽

Gear Mesh ◽

Rolling Element ◽

Element Bearing ◽

The Relationship

This work proposes a methodology for the detection of rolling-element bearing faults in quasi-parallel machinery. In the context of this work, parallel machinery is considered to be any group of identical components of a mechanical system that are linked to operate on the same duty cycle. Quasi-parallel machinery can further be defined as two components not identical mechanically, but their operating conditions are correlated and they operate in the same environmental conditions. Furthermore, a new fault detection architecture is proposed wherein a feed-forward neural network (FFNN) is utilized to identify the relationship between signals. The proposed technique is based on the analysis of a calculated residual between feature vectors from two separate components. This technique is designed to reduce the effects of changes in the machines operating state on the condition monitoring system. When a fault detection system is monitoring multiple components in a larger system that are mechanically linked, signals and information that can be gleaned from the system can be used to reduce influences from factors that are not related to condition. The FFNN is used to identify the relationship between the feature vectors from two quasi-parallel components and eliminate the difference when no fault is present. The proposed method is tested on vibration data from two gearboxes that are connected in series. The gearboxes contain bearings operating at different speeds and gear mesh frequencies. In these conditions, a variety of rolling-element bearing faults are detected. The results indicate that improvement in fault detection accuracy can be achieved by using the additional information available from the quasi-parallel machine. The proposed method is directly compared to a typical AANN novelty detection scheme.

Download Full-text

A Novel Deep Learning Model for the Detection and Identification of Rolling Element-Bearing Faults

Sensors ◽

10.3390/s20185112 ◽

2020 ◽

Vol 20 (18) ◽

pp. 5112 ◽

Cited By ~ 3

Author(s):

Alex Shenfield ◽

Martin Howarth

Keyword(s):

Neural Network ◽

Neural Networks ◽

Real Time ◽

Operating Conditions ◽

Rolling Element Bearing ◽

Series Data ◽

Frequency Noise ◽

Bearing Faults ◽

Rolling Element ◽

Element Bearing

Real-time acquisition of large amounts of machine operating data is now increasingly common due to recent advances in Industry 4.0 technologies. A key benefit to factory operators of this large scale data acquisition is in the ability to perform real-time condition monitoring and early-stage fault detection and diagnosis on industrial machinery—with the potential to reduce machine down-time and thus operating costs. The main contribution of this work is the development of an intelligent fault diagnosis method capable of operating on these real-time data streams to provide early detection of developing problems under variable operating conditions. We propose a novel dual-path recurrent neural network with a wide first kernel and deep convolutional neural network pathway (RNN-WDCNN) capable of operating on raw temporal signals such as vibration data to diagnose rolling element bearing faults in data acquired from electromechanical drive systems. RNN-WDCNN combines elements of recurrent neural networks (RNNs) and convolutional neural networks (CNNs) to capture distant dependencies in time series data and suppress high-frequency noise in the input signals. Experimental results on the benchmark Case Western Reserve University (CWRU) bearing fault dataset show RNN-WDCNN outperforms current state-of-the-art methods in both domain adaptation and noise rejection tasks.

Download Full-text