Data Augmentation for Roller Bearing Health Indicator Estimation Using Multi-Channel Frequency Data Representations

2021 ◽  
Author(s):  
Jacob Hendriks ◽  
Patrick Dumond
Keyword(s):  
Data Augmentation ◽  
Roller Bearing ◽  
Health Indicators ◽  
Remaining Useful Life ◽  
Failure Data ◽  
Data Representations ◽  
Masking Noise ◽  
Augmentation Techniques ◽  
Added Benefit ◽  
Useful Life

Abstract This paper demonstrates various data augmentation techniques that can be used when working with limited run-to-failure data to estimate health indicators related to the remaining useful life of roller bearings. The PRONOSTIA bearing prognosis dataset is used for benchmarking data augmentation techniques. The input to the networks are multi-dimensional frequency representations obtained by combining the spectra taken from two accelerometers. Data augmentation techniques are adapted from other machine learning fields and include adding Gaussian noise, region masking, masking noise, and pitch shifting. Augmented datasets are used in training a conventional CNN architecture comprising two convolutional and pooling layer sequences with batch normalization. Results from individually separating each bearing’s data for the purpose of validation shows that all methods, except pitch shifting, give improved validation accuracy on average. Masking noise and region masking both show the added benefit of dataset regularization by giving results that are more consistent after repeatedly training each configuration with new randomly generated augmented datasets. It is shown that gradually deteriorating bearings and bearings with abrupt failure are not treated significantly differently by the augmentation techniques.

scholarly journals Development of a Novel Methodology for Remaining Useful Life Prediction of Industrial Slurry Pumps in the Absence of Run to Failure Data

Sensors ◽  
2021 ◽  
Vol 21 (24) ◽  
pp. 8420
Author(s):  
Muhammad Mohsin Khan ◽  
Peter W. Tse ◽  
Amy J.C. Trappey
Keyword(s):  
Life Prediction ◽  
Prediction Models ◽  
Remaining Useful Life ◽  
Condition Based Maintenance ◽  
Vibration Signals ◽  
The Core ◽  
Failure Data ◽  
Periodic Maintenance ◽  
Useful Life ◽  
Nonlinear Autoregressive

Smart remaining useful life (RUL) prognosis methods for condition-based maintenance (CBM) of engineering equipment are getting high popularity nowadays. Current RUL prediction models in the literature are developed with an ideal database, i.e., a combination of a huge “run to failure” and “run to prior failure” data. However, in real-world, run to failure data for rotary machines is difficult to exist since periodic maintenance is continuously practiced to the running machines in industry, to save any production downtime. In such a situation, the maintenance staff only have run to prior failure data of an in operation machine for implementing CBM. In this study, a unique strategy for the RUL prediction of two identical and in-process slurry pumps, having only real-time run to prior failure data, is proposed. The obtained vibration signals from slurry pumps were utilized for generating degradation trends while a hybrid nonlinear autoregressive (NAR)-LSTM-BiLSTM model was developed for RUL prediction. The core of the developed strategy was the usage of the NAR prediction results as the “path to be followed” for the designed LSTM-BiLSTM model. The proposed methodology was also applied on publically available NASA’s C-MAPSS dataset for validating its applicability, and in return, satisfactory results were achieved.

scholarly journals Prediction of remaining useful life for lithium-ion battery with multiple health indicators

2021 ◽  
Vol 23 (1) ◽  
pp. 176-183
Author(s):  
Chun Su ◽  
Hongjing Chen ◽  
Zejun Wen
Keyword(s):  
Lithium Ion ◽  
Health Indicators ◽  
Primary Energy ◽  
Remaining Useful Life ◽  
Generalized Regression Neural Network ◽  
Current Voltage ◽  
Remaining Capacity ◽  
Li Ion ◽  
Useful Life ◽  
Multiple Health

Lithium-ion (Li-ion) battery has become a primary energy form for a variety of engineering equipments. To ensure the equipments’ reliability, it is crucial to accurately predict Liion battery’s remaining capacity as well as its remaining useful life (RUL). In this study, we propose a novel method for Li-ion battery’s online RUL prediction, which is based on multiple health indicators (HIs) and can be derived from the battery’s historical operation data. Firstly, four types of indirect HIs are built according to the battery’s operation current, voltage and temperature data respectively. On this basis, a generalized regression neural network (GRNN) is presented to estimate the battery’s remaining capacity, and the nonlinear autoregressive approach (NAR) is applied to predict the battery’s RUL based on the estimated capacity value. Furthermore, to reduce the interference, twice wavelet denoising are performed with different thresholds. A case study is conducted with a NASA battery dataset to demonstrate the effectiveness of the method. The result shows that the proposed method can obtain Li-ion batteries’ RUL effectively.

scholarly journals Heat Exchanger Fouling and Estimation of Remaining Useful Life

2021 ◽  
Vol 5 (1) ◽  
Author(s):  
Tutpol Ardsomang ◽  
J. Wesley Hines ◽  
Belle R. Upadhyaya
Keyword(s):  
Heat Exchanger ◽  
Process Management ◽  
Remaining Useful Life ◽  
Path Model ◽  
Empirical Modeling ◽  
Data Driven ◽  
Transfer Resistance ◽  
Failure Data ◽  
Real Process ◽  
Useful Life

One of the challenges in data-driven prognostics is the availability of degradation data for application to prognostic methods. In real process management settings, failure data are not often available due to the high costs of unplanned breakdowns. This research presents a data-driven (empirical) modeling approach for characterizing the degradation of a heat exchanger (HX) and to estimate the Remaining Useful Life (RUL) of its design operation. The Autoassociative Kernel Regression (AAKR) modeling was applied to predict the effect of fouling on the heat transfer resistance. The result indicates that AAKR model is an effective method to capture the HX fouling in the dynamic process. The AAKR residuals were fused to develop a prognostic parameter which was used to develop a General Path Model (GPM) with Bayesian updating. The results demonstrate the successful application of this approach for the heat exchanger RUL prediction.

scholarly journals Self-Organizing Representation Learning

2021 ◽  
Author(s):  
noureddine kermiche
Keyword(s):  
Data Augmentation ◽  
Representation Learning ◽  
Self Organization ◽  
Learning Methods ◽  
Self Organizing Maps ◽  
Output Layer ◽  
Data Representations ◽  
Augmentation Techniques ◽  
Using Data ◽  
Self Organizing

Using data augmentation techniques, unsupervised representation learning methods extract features from data by training artificial neural networks to recognize that different views of an object are just different instances of the same object. We extend current unsupervised representation learning methods to networks that can self-organize data representations into two-dimensional (2D) maps. The proposed method combines ideas from Kohonen’s original self-organizing maps (SOM) and recent development in unsupervised representation learning. A ResNet backbone with an added 2D <i>Softmax</i> output layer is used to organize the data representations. A new loss function with linear complexity is proposed to enforce SOM requirements of winner-take-all (WTA) and competition between neurons while explicitly avoiding collapse into trivial solutions. We show that enforcing SOM topological neighborhood requirement can be achieved by a fixed radial convolution at the 2D output layer without having to resort to actual radial activation functions which prevented the original SOM algorithm from being extended to nowadays neural network architectures. We demonstrate that when combined with data augmentation techniques, self-organization is a simple emergent property of the 2D output layer because of neighborhood recruitment combined with WTA competition between neurons. The proposed methodology is demonstrated on SVHN and CIFAR10 data sets. The proposed algorithm is the first end-to-end unsupervised learning method that combines data self-organization and visualization as integral parts of unsupervised representation learning.

scholarly journals Outlier Modeling in Gear Bearing Using Autoencoder for Remaining Useful Life Prediction

2019 ◽  
Author(s):  
Sunny Singh ◽  
Praneet Shiv ◽  
Atif Ahmed
Keyword(s):  
Life Prediction ◽  
Health Management ◽  
Health Indicators ◽  
Remaining Useful Life ◽  
System Failure ◽  
Mechanical Signal ◽  
Long Time ◽  
Data Points ◽  
Useful Life ◽  
Bearing System

In this paper, we introduce the Prognostics and Health Management of gear bearing system using autoencoder neural networks. Bearings and gears are the most common mechanical components in rotating machines, and their health conditions are of great concern in practice. This study presents an outlier modeling method for forecasting the gear bearing system failure using the health indicators constructed from mechanical signal processing and modeling. Outlier modeling aims to find patterns in data that are significantly different from what is defined as normal. In the unsupervised outlier modeling setting, prior labels about the anomalousness of data points are not available. In such cases, the most common techniques for scoring data points for outlyingness include distance-based methods density-based methods, and linear methods. The conventional outlier modeling methods have been used for a long time to detect anomalous observations in data. However, this paper shows that autoencoders are a very competitive technique compared to other existing methods. The developed method is demonstrated using the IMS bearing data from NASA Acoustics and Vibration Database.

scholarly journals Prediction of Remaining Useful Life of Wind Turbine Bearings under Non-Stationary Operating Conditions

Energies ◽  
2018 ◽  
Vol 11 (12) ◽  
pp. 3318 ◽  
Author(s):  
Lixiao Cao ◽  
Zheng Qian ◽  
Hamid Zareipour ◽  
David Wood ◽  
Ehsan Mollasalehi ◽  
...  
Keyword(s):  
Wind Turbine ◽  
Wind Turbines ◽  
Wavelet Packet ◽  
Health Indicators ◽  
Degradation Process ◽  
Remaining Useful Life ◽  
Operating Conditions ◽  
Support Vector ◽  
Useful Life ◽  
Artificial Neural Network Ann

Wind-powered electricity generation has grown significantly over the past decade. While there are many components that might impact their useful life, the gearbox and generator bearings are among the most fragile components in wind turbines. Therefore, the prediction of remaining useful life (RUL) of faulty or damaged wind turbine bearings will provide useful support for reliability evaluation and advanced maintenance of wind turbines. This paper proposes a data-driven method combining the interval whitenization method with a Gaussian process (GP) algorithm in order to predict the RUL of wind turbine generator bearings. Firstly, a wavelet packet transform is used to eliminate noise in the vibration signals and extract the characteristic fault signals. A comprehensive analysis of the real degradation process is used to determine the indicators of degradation. The interval whitenization method is proposed to reduce the interference of non-stationary operating conditions to improve the quality of health indicators. Finally, the GP method is utilized to construct the model which reflects the relationship between the RUL and health indicators. The method is assessed using actual vibration datasets from two wind turbines. The prediction results demonstrate that the proposed method can reduce the effect of non-stationary operating conditions. In addition, compared with the support vector regression (SVR) method and artificial neural network (ANN), the prediction accuracy of the proposed method has an improvement of more than 65.8%. The prediction results verify the effectiveness and superiority of the proposed method.

Semi-Supervised Learning With Co-Training for Data-Driven Prognostics

2011 ◽  
Author(s):  
Chao Hu ◽  
Byeng D. Youn ◽  
Taejin Kim
Keyword(s):  
Remaining Useful Life ◽  
Training Data ◽  
Data Driven ◽  
Individual Data ◽  
Data Set ◽  
Failure Data ◽  
Rich Information ◽  
Useful Life ◽  
Engineered Systems ◽  
Systems Failure

Traditional data-driven prognostics often requires a large amount of failure data for the offline training in order to achieve good accuracy for the online prediction. However, in many engineered systems, failure data are fairly expensive and time-consuming to obtain while suspension data are readily available. In such cases, it becomes essentially critical to utilize suspension data, which may carry rich information regarding the degradation trend and help achieve more accurate remaining useful life (RUL) prediction. To this end, this paper proposes a co-training-based data-driven prognostic algorithm, denoted by Coprog, which uses two individual data-driven algorithms with each predicting RULs of suspension units for the other. The confidence of an individual data-driven algorithm in predicting the RUL of a suspension unit is quantified by the extent to which the inclusion of that unit in the training data set reduces the sum square error (SSE) in RUL prediction on the failure units. After a suspension unit is chosen and its RUL is predicted by an individual algorithm, it becomes a virtual failure unit that is added to the training data set. Results obtained from two case studies suggest that Coprog gives more accurate RUL predictions compared to any individual algorithm without the consideration of suspension data and that Coprog can effectively exploit suspension data to improve the accuracy in data-driven prognostics.

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.

scholarly journals Outlier Modeling in Gear Bearing Using Autoencoder for Remaining Useful Life Prediction

2019 ◽  
Author(s):  
Sunny Singh ◽  
Praneet Shiv ◽  
Atif Ahmed
Keyword(s):  
Life Prediction ◽  
Health Management ◽  
Health Indicators ◽  
Remaining Useful Life ◽  
System Failure ◽  
Mechanical Signal ◽  
Long Time ◽  
Data Points ◽  
Useful Life ◽  
Bearing System

In this paper, we introduce the Prognostics and Health Management of gear bearing system using autoencoder neural networks. Bearings and gears are the most common mechanical components in rotating machines, and their health conditions are of great concern in practice. This study presents an outlier modeling method for forecasting the gear bearing system failure using the health indicators constructed from mechanical signal processing and modeling. Outlier modeling aims to find patterns in data that are significantly different from what is defined as normal. In the unsupervised outlier modeling setting, prior labels about the anomalousness of data points are not available. In such cases, the most common techniques for scoring data points for outlyingness include distance-based methods density-based methods, and linear methods. The conventional outlier modeling methods have been used for a long time to detect anomalous observations in data. However, this paper shows that autoencoders are a very competitive technique compared to other existing methods. The developed method is demonstrated using the IMS bearing data from NASA Acoustics and Vibration Database.

Sign in / Sign up

Export Citation Format

Share Document