Deep Learning-based Health Indicator for Better Bearing RUL Prediction

2021 ◽  
Vol 263 (6) ◽  
pp. 493-498
Author(s):  
Taewan Kim ◽  
Seungchul Lee
Keyword(s):  
Domain Knowledge ◽  
Health Indicators ◽  
Remaining Useful Life ◽  
Data Driven ◽  
Health State ◽  
Health Indicator ◽  
Prognostic Performance ◽  
High Level ◽  
Processing Techniques ◽  
Signal Processing Techniques

The prognostic performance of data-driven approaches closely depends on the features extracted from the measurement. For a high level of prognostic performance, features must be carefully designed to represent the machine's health state well and are generally obtained by signal processing techniques. These features are themselves used as health indicators (HI) or used to construct HIs. However, many conventional HIs are heavily relying on the type of machine components and expert domain knowledge. To solve these drawbacks, we propose a fully data-driven method, that is, the adversarial autoencoder-based health indicator (AAE-HI) for remaining useful life (RUL) prediction. Accelerated degradation tests of bearings collected from PRONOSTIA were used to validate the proposed AAE-HI method. It is shown that our proposed AAE-HI can autonomously find monotonicity and trendability of features, which will capture the degradation progression from the measurement. Therefore, the performance of AAE-HI in RUL prediction is promising compared with other conventional HIs.

scholarly journals Thresholded ConvNet ensembles: neural networks for technical forecasting

2020 ◽  
Vol 32 (18) ◽  
pp. 15249-15262
Author(s):  
Sid Ghoshal ◽  
Stephen Roberts
Keyword(s):  
Neural Networks ◽  
Domain Knowledge ◽  
Deep Neural Network ◽  
State Of The Art ◽  
Financial Time Series ◽  
Visual Representations ◽  
Financial Time ◽  
Subjective Form ◽  
Processing Techniques ◽  
Signal Processing Techniques

Abstract Much of modern practice in financial forecasting relies on technicals, an umbrella term for several heuristics applying visual pattern recognition to price charts. Despite its ubiquity in financial media, the reliability of its signals remains a contentious and highly subjective form of ‘domain knowledge’. We investigate the predictive value of patterns in financial time series, applying machine learning and signal processing techniques to 22 years of US equity data. By reframing technical analysis as a poorly specified, arbitrarily preset feature-extractive layer in a deep neural network, we show that better convolutional filters can be learned directly from the data, and provide visual representations of the features being identified. We find that an ensemble of shallow, thresholded convolutional neural networks optimised over different resolutions achieves state-of-the-art performance on this domain, outperforming technical methods while retaining some of their interpretability.

scholarly journals Constructing a Reliable Health Indicator for Bearings Using Convolutional Autoencoder and Continuous Wavelet Transform

2020 ◽  
Author(s):  
Mohammadreza Kaji ◽  
Jamshid Parvizian ◽  
Hans Wernher van de Venn
Keyword(s):  
Wavelet Transform ◽  
Continuous Wavelet Transform ◽  
Degradation Process ◽  
Remaining Useful Life ◽  
Data Driven ◽  
Maintenance Cost ◽  
Continuous Wavelet ◽  
Health Indicator ◽  
Failure Data ◽  
Convolutional Autoencoder

Estimating the remaining useful life (RUL) of components is a crucial task to enhance the reliability, safety, productivity, and to reduce maintenance cost. In general, predicting the RUL of a component includes constructing a health indicator (HI) to infer the current condition of the component, and modelling the degradation process, to estimate the future behavior. Although many signal processing and data-driven based methods were proposed to construct the HI, most of the existing methods are based on manual feature extraction techniques, and need the prior knowledge of experts, or rely on a large amount of failure data. Therefore, in this study, a new data-driven method based on the convolutional autoencoder (CAE) is presented to construct the HI. For this purpose, the continuous wavelet transform (CWT) technique is used to convert the raw acquired vibrational signals into a two-dimensional image; then, the CAE model, which learns the healthy operation data distribution, is used to construct the HI. The proposed method is tested on a benchmark bearing dataset and compared with several other traditional HI construction models. Experimental results indicate that the constructed HI exhibits a monotonically increasing degradation trend and has a good performance to detect incipient faults.

scholarly journals A data-driven framework for remaining useful life estimation

2017 ◽  
Vol 55 (5) ◽  
pp. 557 ◽  
Author(s):  
Hoa Dinh Nguyen
Keyword(s):  
Data Processing ◽  
Health Management ◽  
Remaining Useful Life ◽  
Data Driven ◽  
Life Estimation ◽  
Search Experiment ◽  
Useful Life ◽  
Structural Health Management ◽  
Processing Techniques ◽  
Data Library

Remaining useful life (RUL) estimation is one of the most common tasks in the field of prognostics and structural health management. The aim of this research is to estimate the remaining useful life of an unspecified complex system using some data-driven approaches. The approaches are suitable for problems in which a data library of complete runs of a system is available. Given a non-complete  run of the system, the RUL can be predicted  using these approaches. Three main RUL prediction algorithms, which cover centralized data processing, decentralize data processing, and  in-between, are introduced and evaluated using the data of PHM’08 Challenge Problem. The methods involve the use of some other data processing techniques including wavelets denoise and similarity search. Experiment results show that all of the approaches  are effective in performing RUL prediction.

scholarly journals A Reliable Health Indicator for Fault Prognosis of Bearings

Sensors ◽  
2018 ◽  
Vol 18 (11) ◽  
pp. 3740 ◽  
Author(s):  
Bach Duong ◽  
Sheraz Khan ◽  
Dongkoo Shon ◽  
Kichang Im ◽  
Jeongho Park ◽  
...  
Keyword(s):  
Wavelet Packet ◽  
Health Indicators ◽  
Remaining Useful Life ◽  
Poor Correlation ◽  
Discrete Wavelet ◽  
Health Indicator ◽  
Vibration Acceleration ◽  
Discrete Wavelet Packet Transform ◽  
Acceleration Signal ◽  
Gradient Based

Estimation of the remaining useful life (RUL) of bearings is important to avoid abrupt shutdowns in rotary machines. An important task in RUL estimation is the construction of a suitable health indicator (HI) to infer the bearing condition. Conventional health indicators rely on features of the vibration acceleration signal and are predominantly calculated without considering its non-stationary nature. This often results in an HI with a trend that is difficult to model, as well as random fluctuations and poor correlation with bearing degradation. Therefore, this paper presents a method for constructing a bearing’s HI by considering the non-stationarity of the vibration acceleration signals. The proposed method employs the discrete wavelet packet transform (DWPT) to decompose the raw signal into different sub-bands. The HI is extracted from each sub-band signal, smoothened using locally weighted regression, and evaluated using a gradient-based method. The HIs showing the best trends among all the sub-bands are iteratively accumulated to construct an HI with the best trend over the entire life of the bearing. The proposed method is tested on two benchmark bearing datasets. The results show that the proposed method yields an HI that correlates well with bearing degradation and is relatively easy to model.

Data Driven Prognostics for Rotating Machinery

2013 ◽  
pp. 120-133 ◽  
Author(s):  
Eric Bechhoefer
Keyword(s):  
Detection Threshold ◽  
Remaining Useful Life ◽  
Condition Based Maintenance ◽  
Data Driven ◽  
Health Indicator ◽  
Damage State ◽  
Condition Indicators ◽  
Gear Fault ◽  
Useful Life ◽  
Threshold Setting

A prognostic is an estimate of the remaining useful life of a monitored part. While diagnostics alone can support condition based maintenance practices, prognostics facilitates changes to logistics which can greatly reduce cost or increase readiness and availability. A successful prognostic requires four processes: 1) feature extraction of measured data to estimate damage; 2) a threshold for the feature, which, when exceeded, indicates that it is appropriate to perform maintenance; 3) given a future load profile, a model that can estimate the remaining useful life of the component based on the current damage state; and 4) an estimate of the confidence in the prognostic. This chapter outlines a process for data-driven prognostics by: describing appropriate condition indicators (CIs) for gear fault detection; threshold setting for those CIs through fusion into a component health indicator (HI); using a state space process to estimate the remaining useful life given the current component health; and a state estimate to quantify the confidence in the estimate of the remaining useful life.

scholarly journals Constructing a Reliable Health Indicator for Bearings Using Convolutional Autoencoder and Continuous Wavelet Transform

2020 ◽  
Vol 10 (24) ◽  
pp. 8948
Author(s):  
Mohammadreza Kaji ◽  
Jamshid Parvizian ◽  
Hans Wernher van de Venn
Keyword(s):  
Wavelet Transform ◽  
Continuous Wavelet Transform ◽  
Degradation Process ◽  
Remaining Useful Life ◽  
Data Driven ◽  
Maintenance Cost ◽  
Continuous Wavelet ◽  
Health Indicator ◽  
Failure Data ◽  
Convolutional Autoencoder

Estimating the remaining useful life (RUL) of components is a crucial task to enhance reliability, safety, productivity, and to reduce maintenance cost. In general, predicting the RUL of a component includes constructing a health indicator (HI) to infer the current condition of the component, and modelling the degradation process in order to estimate the future behavior. Although many signal processing and data-driven methods have been proposed to construct the HI, most of the existing methods are based on manual feature extraction techniques and require the prior knowledge of experts, or rely on a large amount of failure data. Therefore, in this study, a new data-driven method based on the convolutional autoencoder (CAE) is presented to construct the HI. For this purpose, the continuous wavelet transform (CWT) technique was used to convert the raw acquired vibrational signals into a two-dimensional image; then, the CAE model was trained by the healthy operation dataset. Finally, the Mahalanobis distance (MD) between the healthy and failure stages was measured as the HI. The proposed method was tested on a benchmark bearing dataset and compared with several other traditional HI construction models. Experimental results indicate that the constructed HI exhibited a monotonically increasing degradation trend and had good performance in terms of detecting incipient faults.

scholarly journals Predicting Remaining Useful Life Based on Hilbert–Huang Entropy with Degradation Model

2019 ◽  
Vol 2019 ◽  
pp. 1-11 ◽  
Author(s):  
Yuhuang Zheng
Keyword(s):  
Health Management ◽  
Detection Threshold ◽  
Prediction Method ◽  
Remaining Useful Life ◽  
Health State ◽  
Health Indicator ◽  
Degradation Model ◽  
Vibration Signals ◽  
Current Health ◽  
Useful Life

Prognostics health management (PHM) of rotating machinery has become an important process for increasing reliability and reducing machine malfunctions in industry. Bearings are one of the most important equipment parts and are also one of the most common failure points. To assess the degradation of a machine, this paper presents a bearing remaining useful life (RUL) prediction method. The method relies on a novel health indicator and a linear degradation model to predict bearing RUL. The health indicator is extracted by using Hilbert–Huang entropy to process horizontal vibration signals obtained from bearings. We present a linear degradation model to estimate RUL using this health indicator. In the training phase, the degradation detection threshold and the failure threshold of this model are estimated by the distribution of 600 bootstrapped samples. These bootstrapped samples are taken from the six training sets. In the test phase, the health indicator and the model are used to estimate the bearing’s current health state and predict its RUL. This method is suitable for the degradation of bearings. The experimental results show that this method can effectively monitor bearing degradation and predict its RUL.

scholarly journals Adapting Approximate Entropy as a Health Indicator of Rotating Machinery for Estimation of Remaining Useful Life

2019 ◽  
Vol 11 (1) ◽  
Author(s):  
Cody Walker
Keyword(s):  
Health Monitoring ◽  
Health Indicators ◽  
Approximate Entropy ◽  
Remaining Useful Life ◽  
Frequency Content ◽  
Health Indicator ◽  
Vibration Signals ◽  
Early Results ◽  
Useful Life ◽  
Significant Attention

Despite significant attention to online health monitoring and prognostics of bearings, many common health indicators are not sensitive to early stages of degradation. This research investigates the use of approximate entropy (ApEn), previously developed for fault diagnostics, as a health indicator for prognostics. ApEn quantifies the regularity of a signal; as bearings degrade, the frequency content of vibration signals changes and affects the ApEn as the vibration becomes more chaotic. Early results suggest ApEn supports earlier degradation detection and more predictable progression from fault to failure. This research focuses on optimizing parameters of the ApEn calculation to provide guidance across a variety of bearing types, sizes, and geometries in both steady-state and transient operation.

Sign in / Sign up

Export Citation Format

Share Document