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 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 Deep Learning with Dynamically Weighted Loss Function for Sensor-Based Prognostics and Health Management

Sensors ◽  
2020 ◽  
Vol 20 (3) ◽  
pp. 723 ◽  
Author(s):  
Divish Rengasamy ◽  
Mina Jafari ◽  
Benjamin Rothwell ◽  
Xin Chen ◽  
Grazziela P. Figueredo
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Loss Function ◽  
Short Term Memory ◽  
Health Management ◽  
Remaining Useful Life ◽  
Loss Functions ◽  
Pressure System ◽  
Failure Data ◽  
Prognostic And Health Management

Deep learning has been employed to prognostic and health management of automotive and aerospace with promising results. Literature in this area has revealed that most contributions regarding deep learning is largely focused on the model’s architecture. However, contributions regarding improvement of different aspects in deep learning, such as custom loss function for prognostic and health management are scarce. There is therefore an opportunity to improve upon the effectiveness of deep learning for the system’s prognostics and diagnostics without modifying the models’ architecture. To address this gap, the use of two different dynamically weighted loss functions, a newly proposed weighting mechanism and a focal loss function for prognostics and diagnostics task are investigated. A dynamically weighted loss function is expected to modify the learning process by augmenting the loss function with a weight value corresponding to the learning error of each data instance. The objective is to force deep learning models to focus on those instances where larger learning errors occur in order to improve their performance. The two loss functions used are evaluated using four popular deep learning architectures, namely, deep feedforward neural network, one-dimensional convolutional neural network, bidirectional gated recurrent unit and bidirectional long short-term memory on the commercial modular aero-propulsion system simulation data from NASA and air pressure system failure data for Scania trucks. Experimental results show that dynamically-weighted loss functions helps us achieve significant improvement for remaining useful life prediction and fault detection rate over non-weighted loss function predictions.

scholarly journals A New Data-Driven Approach for Power IGBT Remaining Useful Life Estimation Based On Feature Reduction Technique and Neural Network

Electronics ◽  
2020 ◽  
Vol 9 (10) ◽  
pp. 1571
Author(s):  
Adla Ismail ◽  
Lotfi Saidi ◽  
Mounir Sayadi ◽  
Mohamed Benbouzid
Keyword(s):  
Neural Network ◽  
Accelerated Aging ◽  
Principal Component ◽  
Life Time ◽  
Time Domain Analysis ◽  
Energy System ◽  
Remaining Useful Life ◽  
Feature Reduction ◽  
Operating Conditions ◽  
Useful Life

The insulated gate bipolar transistor (IGBT) is a crucial component of power converters (PCVs) and is commonly used in several PCVs topologies. On the other hand, the investigation and the study of the IGBT component show several changes within its behavior and lifetime, while this component is highly influenced by the operating conditions. Indeed, the monitoring of this component is necessary to minimize unexpected downtime of the wind energy system (WES). However, an accurate prediction of IGBTs remaining useful life (RUL) is the key enabler for life-time-optimized operation. Consequently, this work proposes a new prognostic approach for online IGBTs monitoring that adopts the time-domain analysis to extract useful information that is used as an input in the generation of the health indicator. Moreover, this approach is based on combining both of principal component analysis (PCA) technique and the feedforward neural network (FFNN) technique. PCA is used to reduce features extracted from IGBTs and the FFNN is implemented to achieve online regression of the trend parameter obtained from the PCA technique. To investigate and evaluate the performance of our idea we used the NASA Ames Laboratory Prognostics Center of Excellence IGBTs accelerated aging database. Finally, the achieved results clearly show the strength of the new trend parameter for IGBTs RUL prediction. The most notable strong correlation within the proposed approach is in relation to accuracy value, with an acceptable average accuracy rate of 60.4%.

scholarly journals A Stochastic Deterioration Process Based Approach for Micro Switches Remaining Useful Life Estimation

2019 ◽  
Vol 9 (3) ◽  
pp. 613
Author(s):  
Bangcheng Zhang ◽  
Yubo Shao ◽  
Zhenchen Chang ◽  
Zhongbo Sun ◽  
Yuankun Sui
Keyword(s):  
Kalman Filter ◽  
Health Management ◽  
Remaining Useful Life ◽  
Degradation Model ◽  
Time Prediction ◽  
Model Based ◽  
Stochastic Parameters ◽  
Deterioration Process ◽  
Useful Life ◽  
Posterior Estimation

Real-time prediction of remaining useful life (RUL) is one of the most essential works inprognostics and health management (PHM) of the micro-switches. In this paper, a lineardegradation model based on an inverse Kalman filter to imitate the stochastic deterioration processis proposed. First, Bayesian posterior estimation and expectation maximization (EM) algorithm areused to estimate the stochastic parameters. Second, an inverse Kalman filter is delivered to solvethe errors in the initial parameters. In order to improve the accuracy of estimating nonlinear data,the strong tracking filtering (STF) method is used on the basis of Bayesian updating Third, theeffectiveness of the proposed approach is validated on an experimental data relating tomicro-switches for the rail vehicle. Additionally, it proposes another two methods for comparisonto illustrate the effectiveness of the method with an inverse Kalman filter in this paper. Inconclusion, a linear degradation model based on an inverse Kalman filter shall deal with errors inRUL estimation of the micro-switches excellently.

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.

Remaining useful life prediction for lithium-ion batteries using particle filter and artificial neural network

2019 ◽  
Vol 120 (2) ◽  
pp. 312-328 ◽  
Author(s):  
Wei Qin ◽  
Huichun Lv ◽  
Chengliang Liu ◽  
Datta Nirmalya ◽  
Peyman Jahanshahi
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Particle Filter ◽  
Prediction Accuracy ◽  
Lithium Ion ◽  
Remaining Useful Life ◽  
Content Type ◽  
Public Data ◽  
Useful Life ◽  
Artificial Neural

Purpose With the promotion of lithium-ion battery, it is more and more important to ensure the safety usage of the battery. The purpose of this paper is to analyze the battery operation data and estimate the remaining life of the battery, and provide effective information to the user to avoid the risk of battery accidents. Design/methodology/approach The particle filter (PF) algorithm is taken as the core, and the double-exponential model is used as the state equation and the artificial neural network is used as the observation equation. After the importance resampling process, the battery degradation curve is obtained after getting the posterior parameter, and then the system could estimate remaining useful life (RUL). Findings Experiments were carried out by using the public data set. The results show that the Bayesian-based posterior estimation model has a good predictive effect and fits the degradation curve of the battery well, and the prediction accuracy will increase gradually as the cycle increases. Originality/value This paper combines the advantages of the data-driven method and PF algorithm. The proposed method has good prediction accuracy and has an uncertain expression on the RUL of the battery. Besides, the method proposed is relatively easy to implement in the battery management system, which has high practical value and can effectively avoid battery using risk for driver safety.

Sign in / Sign up

Export Citation Format

Share Document