Abstract The ability to forecast machinery failure is vital to reducing maintenance costs, operation downtime and safety hazards. Recent advances in condition monitoring technologies have given rise to a number of prognostic models that attempt to forecast machinery health based on condition data. This paper presents a novel approach for incorporating population characteristics information and suspended condition trending data of historical units into prognosis. The population characteristics information extracted from statistical failure distribution enables longer-range prognosis. The accurate modelling of suspended data is also found to be of great importance, since in practice machines are rarely allowed to run to failure and hence data are commonly suspended. The proposed model consists of a feed-forward neural network whose training targets are asset survival probabilities estimated using a variation of the Kaplan–Meier estimator and a degradation-based failure probability density function (PDF) estimator. The trained network is capable of estimating the future survival probabilities of an operating asset when a series of condition indices are inputted. The output survival probabilities collectively form an estimated survival curve. Pump vibration data were used for model validation. The proposed model was compared with two similar models that neglect suspended data, as well as with a conventional time series prediction model. The results support our hypothesis that the proposed model can predict more accurately and further ahead than similar methods that do not include population characteristics and/or suspended data in prognosis.

Intelligent condition-based prediction of machinery reliability

Rolling element bearing diagnosis based on singular value decomposition and composite squared envelope spectrum

Transfer learning for remaining useful life prediction of multi-conditions bearings based on bidirectional-GRU network

Remaining useful life prediction of roller bearings based on improved 1D-CNN and simple recurrent unit

https://re.public.polimi.it/bitstream/11311/1130114/1/MAC2PSD_v4_2_edited_final.pdf

A new method for the estimation of bearing health state and remaining useful life based on the moving average cross-correlation of power spectral density

The development of diagnostics for rolling element bearings (REBs) in recent years makes it possible to detect faults in bearings in real-time. Squared envelope analysis (SEA), in which the statistical characteristics of the squared envelope (SE) or the squared envelope spectrum (SES) are analysed, is widely recognized as both an effective and the simplest method. The most critical step of SEA is to find an optimal frequency band that contains the maximum defect information. The most commonly used approaches for selecting the optimal frequency band are derived from measuring the kurtosis of the SE or the SES. However, most methods fail to cope with the interference of a single or a few impulses in the corresponding domain. A new method is proposed in this paper called "PMFSgram", which just calculates the kurtosis of the SES in the range centred at the first two harmonics with a span of three times the modulation frequency rather than the entire SES of the band filtered signals. It is possible to avoid most of the interference from a small number of undesired impulses in the SES. PMFSgram uses several bandwidths from 1.5 times to 4.5 times the fault frequency and for each bandwidth has the same number of central frequencies. The frequency setting method is able to select an optimal frequency band containing most of the useful information with less noise. The performance of the new method is verified using synthesized signals and actual vibration data.

/pdf/a-novel-method-of-frequency-band-selection-for-squared-14s8u8lq2w.pdf

A Novel Method of Frequency Band Selection for Squared Envelope Analysis for Fault Diagnosing of Rolling Element Bearings in a Locomotive Powertrain.

Order tracking has been widely used to diagnose failures of variable speed rotating machines. The performance of the TOT (Time-Frequency Domain Tacholess Order Tracking) methods is based on the correct separation of the target component strictly related to the shaft rotation frequency. Currently, most of the methods have focused on obtaining the instantaneous frequency with accuracy. In this paper, a new TOT method has been proposed that combines the inverse short-time Fourier transform (ISTFT) with singular value decomposition (SVD). The target component closely related to the shaft rotation frequency is selected and filtered approximately in the time-frequency domain. Hence, the ISTFT is adopted to reverse the target component into the time domain. Next, SVD is used to refine the roughly filtered target component. Finally, the phase of the refined signal is extracted to resample the original signal. The performance of the method was tested using real vibration signals collected from a large-scale test rig of a high-speed train traction system.

https://www.mdpi.com/1424-8220/20/23/6924/pdf

A Tacholess Order Tracking Method Based on Inverse Short Time Fourier Transform and Singular Value Decomposition for Bearing Fault Diagnosis.

The application of Prognostics and Health Monitoring (PHM) concepts in rail vehicles is a rapidly growing field of research, and extensive efforts are being spent with the aim of improving the reliability and availability of railway systems and of substantially reducing maintenance costs by switching from time-based to event-driven maintenance policies. This paper is aimed at proving that effective PHM can be applied also on already existing rolling stocks. To do this, and focusing on bearings of the traction system, a prototype monitoring system, described in the paper, was developed and installed on a E464 locomotive. This regional train locomotive class, despite being recent since they were built between 1999 and 2015, is not equipped by any monitoring system for the bearings. The bearings have been monitored for about three years of service, during which the locomotive has undergone to a major maintenance and all the bearings of the traction system has been replaced. This allowed to examine them and to assess if damage indexes corresponded to actual faults. A huge amount of vibration data has been collected and it was possible to assess that the overall system cannot be considered as in stationary operation, neither when the train speed is constant nor when the same track is travelled. Many different techniques have been developed and tested with the aim of detecting bearing damages, considering that fault signals are heavily masked noise. The results are here described and it is shown that the introduced fault indexes are able to monitor the damage evolution in non-stationary conditions.

Lang Xu

Papers

Rolling element bearing diagnosis based on singular value decomposition and composite squared envelope spectrum

A new method for the estimation of bearing health state and remaining useful life based on the moving average cross-correlation of power spectral density

A Novel Method of Frequency Band Selection for Squared Envelope Analysis for Fault Diagnosing of Rolling Element Bearings in a Locomotive Powertrain.

A Tacholess Order Tracking Method Based on Inverse Short Time Fourier Transform and Singular Value Decomposition for Bearing Fault Diagnosis.

Diagnostics of Bearings in Rolling Stocks: Results of Long Lasting Tests for a Regional Train Locomotive