scholarly journals Data-driven remaining useful life prediction based on domain adaptation

2021 ◽  
Vol 7 ◽  
pp. e690
Author(s):  
Bin cheng Wen ◽  
Ming qing Xiao ◽  
Xue qi Wang ◽  
Xin Zhao ◽  
Jian feng Li ◽  
...  
Keyword(s):  
Test Data ◽  
Health Management ◽  
Domain Adaptation ◽  
Current Data ◽  
Remaining Useful Life ◽  
Operating Conditions ◽  
Training Data ◽  
Data Driven ◽  
Target Domain ◽  
Useful Life

As an important part of prognostics and health management, remaining useful life (RUL) prediction can provide users and managers with system life information and improve the reliability of maintenance systems. Data-driven methods are powerful tools for RUL prediction because of their great modeling abilities. However, most current data-driven studies require large amounts of labeled training data and assume that the training data and test data follow similar distributions. In fact, the collected data are often variable due to different equipment operating conditions, fault modes, and noise distributions. As a result, the assumption that the training data and the test data obey the same distribution may not be valid. In response to the above problems, this paper proposes a data-driven framework with domain adaptability using a bidirectional gated recurrent unit (BGRU). The framework uses a domain-adversarial neural network (DANN) to implement transfer learning (TL) from the source domain to the target domain, which contains only sensor information. To verify the effectiveness of the proposed method, we analyze the IEEE PHM 2012 Challenge datasets and use them for verification. The experimental results show that the generalization ability of the model is effectively improved through the domain adaptation approach.

A Copula-Based Sampling Method for Data-Driven Prognostics and Health Management

2013 ◽  
Author(s):  
Zhimin Xi ◽  
Rong Jing ◽  
Pingfeng Wang ◽  
Chao Hu
Keyword(s):  
Sampling Method ◽  
Failure Time ◽  
Health Management ◽  
Remaining Useful Life ◽  
Training Data ◽  
Data Driven ◽  
Prognostics And Health Management ◽  
Statistical Relationship ◽  
Cooling Fans ◽  
On Line

This paper develops a Copula-based sampling method for data-driven prognostics and health management (PHM). The principal idea is to first build statistical relationship between failure time and the time realizations at specified degradation levels on the basis of off-line training data sets, then identify possible failure times for on-line testing units based on the constructed statistical model and available on-line testing data. Specifically, three technical components are proposed to implement the methodology. First of all, a generic health index system is proposed to represent the health degradation of engineering systems. Next, a Copula-based modeling is proposed to build statistical relationship between failure time and the time realizations at specified degradation levels. Finally, a sampling approach is proposed to estimate the failure time and remaining useful life (RUL) of on-line testing units. Two case studies, including a bearing system in electric cooling fans and a 2008 IEEE PHM challenge problem, are employed to demonstrate the effectiveness of the proposed methodology.

scholarly journals Transfer Learning with Deep Recurrent Neural Networks for Remaining Useful Life Estimation

2018 ◽  
Vol 8 (12) ◽  
pp. 2416 ◽  
Author(s):  
Ansi Zhang ◽  
Honglei Wang ◽  
Shaobo Li ◽  
Yuxin Cui ◽  
Zhonghao Liu ◽  
...  
Keyword(s):  
Neural Networks ◽  
Transfer Learning ◽  
Recurrent Neural Networks ◽  
Prediction Models ◽  
Learning Algorithm ◽  
Remaining Useful Life ◽  
Operating Conditions ◽  
Training Data ◽  
Good Prediction ◽  
Useful Life

Prognostics, such as remaining useful life (RUL) prediction, is a crucial task in condition-based maintenance. A major challenge in data-driven prognostics is the difficulty of obtaining a sufficient number of samples of failure progression. However, for traditional machine learning methods and deep neural networks, enough training data is a prerequisite to train good prediction models. In this work, we proposed a transfer learning algorithm based on Bi-directional Long Short-Term Memory (BLSTM) recurrent neural networks for RUL estimation, in which the models can be first trained on different but related datasets and then fine-tuned by the target dataset. Extensive experimental results show that transfer learning can in general improve the prediction models on the dataset with a small number of samples. There is one exception that when transferring from multi-type operating conditions to single operating conditions, transfer learning led to a worse result.

A Stochastic Asset Life Prediction Method for Large Fleet Datasets in Big Data Environment

2015 ◽  
Author(s):  
Behrad Bagheri ◽  
David Siegel ◽  
Wenyu Zhao ◽  
Jay Lee
Keyword(s):  
Monte Carlo ◽  
Big Data ◽  
Evaluation Method ◽  
Health Management ◽  
Prediction Method ◽  
Remaining Useful Life ◽  
Data Driven ◽  
Engineering System ◽  
Useful Life ◽  
Data Environment

Preventing catastrophic failures is the most important task of prognostics and health management approaches in industry where Remaining Useful Life (RUL) prediction plays a significant role to schedule required preventive actions. Regarding recent advances and trends in data analysis and in Big Data environment, industries with such foreseeing approach are able to maintain their fleet of assets more efficiently with higher assurance. To address this requirement, several physics-based and data-driven methods have been developed to predict the remaining useful life of various engineering systems. In current paper, we present a simple, yet accurate stochastic method for data-driven RUL prediction of complex engineering system. The approach is constructed based on selecting the most significant parameters from raw data by using the improved distance evaluation method as feature selection algorithms. Subsequently, the health value of units is assessed by logistic regression and the assessment output is used in a Monte Carlo simulation to estimate the remaining useful life of the desired system. During Monte Carlo iterations, several features are extracted to help filtering less accurate estimations and improve the overall prediction accuracy. The proposed algorithm is validated in two ways. First of all, the accuracy of RUL prediction is measured by applying the method to 2008 PHM data challenge gas-turbine dataset. Subsequently, gradual changes in RUL prediction of a particular test unit are measured to verify the behavior of the algorithm upon availability of additional historical data.

scholarly journals Physics Based Deep Learning Technique for Prognostics

2019 ◽  
Vol 11 (1) ◽  
Author(s):  
Khaled Akkad
Keyword(s):  
Pattern Recognition ◽  
Deep Learning ◽  
Health Management ◽  
Recognition Performance ◽  
Remaining Useful Life ◽  
Data Driven ◽  
Prognostics And Health Management ◽  
Learning Technique ◽  
Useful Life

Remaining useful life (RUL) estimation is one of the most important aspects of prognostics and health management (PHM). Various deep learning (DL) based techniques have been developed and applied for the purposes of RUL estimation. One limitation of DL is the lack of physical interpretations as they are purely data driven models. Another limitation is the need for an exceedingly large amount of data to arrive at an acceptable pattern recognition performance for the purposes of RUL estimation. This research is aimed to overcome these limitations by developing physics based DL techniques for RUL prediction and validate the method with real run-to-failure datasets. The contribution of the research relies on creating hybrid DL based techniques as well as combining physics based approaches with DL techniques for effective RUL prediction.

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.

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 Adaptive Degradation Prognostic Reasoning by Particle Filter with a Neural Network Degradation Model for Turbofan Jet Engine

Data ◽  
2018 ◽  
Vol 3 (4) ◽  
pp. 49 ◽  
Author(s):  
Faisal Khan ◽  
Omer Eker ◽  
Atif Khan ◽  
Wasim Orfali
Keyword(s):  
Neural Network ◽  
Particle Filter ◽  
Health Management ◽  
Cost Effective ◽  
Remaining Useful Life ◽  
Operating Conditions ◽  
Data Driven ◽  
Prediction Errors ◽  
Degradation Model ◽  
Jet Engine

In the aerospace industry, every minute of downtime because of equipment failure impacts operations significantly. Therefore, efficient maintenance, repair and overhaul processes to aid maximum equipment availability are essential. However, scheduled maintenance is costly and does not track the degradation of the equipment which could result in unexpected failure of the equipment. Prognostic Health Management (PHM) provides techniques to monitor the precise degradation of the equipment along with cost-effective reliability. This article presents an adaptive data-driven prognostics reasoning approach. An engineering case study of Turbofan Jet Engine has been used to demonstrate the prognostic reasoning approach. The emphasis of this article is on an adaptive data-driven degradation model and how to improve the remaining useful life (RUL) prediction performance in condition monitoring of a Turbofan Jet Engine. The RUL prediction results show low prediction errors regardless of operating conditions, which contrasts with a conventional data-driven model (a non-parameterised Neural Network model) where prediction errors increase as operating conditions deviate from the nominal condition. In this article, the Neural Network has been used to build the Nominal model and Particle Filter has been used to track the present degradation along with degradation parameter.

scholarly journals Cross-Condition and Cross-Platform Remaining Useful Life Estimation Via Adversarial-Based Domain Adaptation

2021 ◽  
Author(s):  
Dongdong Zhao ◽  
Feng Liu
Keyword(s):  
Domain Adaptation ◽  
Remaining Useful Life ◽  
Supervised Machine Learning ◽  
Target Domain ◽  
Feature Extractor ◽  
Supervised Methods ◽  
Cross Platform ◽  
Useful Life ◽  
Detection Mechanisms ◽  
The Impact

Abstract Supervised machine learning is a traditionally remaining useful life (RUL) estimation tool, which requires a lot of prior knowledge. For the situation lacking labeled data, supervised methods are invalid for the issue of domain shift in data distribution. In this paper, a adversarial-based domain adaptation (ADA) architecture with convolution neural networks (CNN) for RUL estimation of bearings under different conditions and platforms, referred to as ADACNN, is proposed. Specifically, ADACNN is trained in source labeled data and fine-tunes to similar target unlabeled data via an adversarial training and parameters shared mechanism. Besides a feature extractor and source domain regressive predictor, ADACNN also includes a domain classifier that tries to guide feature extractor find some domain-invariant features, which differents with traditional methods and belongs to a unsupervised learning in target domain, which has potential application value and far-reaching significance in academia. In addition, according to different first predictive time (FPT) detection mechanisms, we also explores the impact of different FPT detection mechanisms on RUL estimation performance. Finally, according to extensive experiments, the results of RUL estimation of bearing in cross-condition and cross-platform prove that ADACNN architecture has satisfactory generalization performance and great practical value in industry.

Data Driven Approach to Analyzing The Impact of Power Plant Cycling on Air Preheater Degradation and Remaining Useful Life

2021 ◽  
Author(s):  
Himanshu Sharma ◽  
Veronica Adetola ◽  
Laurentiu Marinovici ◽  
Herbert T. Schaef
Keyword(s):  
Power Plant ◽  
Operation Time ◽  
Remaining Useful Life ◽  
Operating Conditions ◽  
Dew Point ◽  
Data Driven ◽  
Air Preheater ◽  
Operational Life ◽  
Useful Life ◽  
The Impact

Abstract Due to the increased penetration of renewable energy generation sources, and fluctuations of the oil and gas prices, modern coal burning power plants deal with increased variability in the demand for power generation. These varying demands result in their intermittent under-capacity operation (cycling). Periodical ramping down and back up to follow the daily power demands causes damages to the plant components reducing its operational life. In this paper we analyze the impact of cycling on a rotary Ljungstrom air preheater (APH) unit installed at a coal fire power plant in the US. An inefficient air preheater can significantly impact boiler performance. Due to the repeated boiler’s hot-cold start, the APH experiences fluctuating operating conditions that result in accelerated degradation mechanisms, such as dew-point corrosion, fouling/deposition plugging, and air heater leakage. The analysis in this paper utilizes field data related to APH basket replacement, and the number of cycles experienced by the boiler to model the life expectancy of the baskets. The data-driven model enables preventive maintenance strategies for the APH by predicting how long the APH baskets will last in a probabilistic sense. The analysis showed that an increase in cycling for a fixed operation time can reduce the APH basket remaining useful life by about 30%.

FUZZY BRIDGED REFINEMENT DOMAIN ADAPTATION: LONG-TERM BANK FAILURE PREDICTION

2013 ◽  
Vol 12 (01) ◽  
pp. 1350003 ◽  
Author(s):  
VAHID BEHBOOD ◽  
JIE LU ◽  
GUANGQUAN ZHANG
Keyword(s):  
Test Data ◽  
Prediction Models ◽  
Predictive Accuracy ◽  
Domain Adaptation ◽  
Failure Prediction ◽  
Bank Failure ◽  
Training Data ◽  
Support Vector ◽  
Target Domain

Machine learning methods, such as neural network (NN) and support vector machine, assume that the training data and the test data are drawn from the same distribution. This assumption may not be satisfied in many real world applications, like long-term financial failure prediction, because the training and test data may each come from different time periods or domains. This paper proposes a novel algorithm known as fuzzy bridged refinement-based domain adaptation to solve the problem of long-term prediction. The algorithm utilizes the fuzzy system and similarity concepts to modify the target instances' labels which were initially predicted by a shift-unaware prediction model. The experiments are performed using three shift-unaware prediction models based on nine different settings including two main situations: (1) there is no labeled instance in the target domain; (2) there are a few labeled instances in the target domain. In these experiments bank failure financial data is used to validate the algorithm. The results demonstrate a significant improvement in the predictive accuracy, particularly in the second situation identified above.

Sign in / Sign up

Export Citation Format

Share Document