Remaining Useful Life Prediction of an Aircraft Turbofan Engine Using Deep Layer Recurrent Neural Networks

Thakkar, Unnati Rajeshkumar; Chaoui, Hicham

doi:10.3390/act11030067

Cited by 19 publications

(9 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Pattern recognition applications are beginning to make greater use of neural networks as a result of the excellent capabilities offered by these systems [42]. A variety of neural models, including as backpropagation networks, high-order neural networks, time delays, and recurrent neural networks, can be quite helpful [43].…”

Section: A Conceptualizationmentioning

confidence: 99%

“…Back-propagation algorithms frequently face the challenge of dealing with the appearance of local minima. In addition to these difficulties, neural networks also face issues regarding the rate at which they learn new information as well as the design that they employ [41][42][43]. In addition to that, they have issues with modularity and size.…”

Section: A Conceptualizationmentioning

confidence: 99%

See 1 more Smart Citation

Threats From Unintentional Insiders: An Assessment of an Organization’s Readiness Using Machine Learning

2022

View full text Add to dashboard Cite

Today's organisations are facing a number of challenges, one of the most significant of which is ensuring the safety of their digital data. This is as a result of the fact that they are frequently faced with internal and external threats that can put the data they have been entrusted with in jeopardy of being compromised. As a result of this, this study investigates the dimension of threats associated to unintentional internal user of an organisation and utilises NARX to model and test a detection scheme associated to the menace. In addition, this study aims to provide a better understanding of the current state of the threat landscape. The data adopted for this research is primarily a "user activity logs" dataset from CERT (release version r4.2). From the data, the study conceptualized "Access", "Motivation", and "Action" to be the key dimensions influencing "insider", whereas "Intent", "+Action", "Method", and "knowledge" are the key dimension influencing "threats". Experimental analyses conducted by NARX within several numbers of partitions of the data point to a good detection capacity, with the greatest value of R 2 coming in at 0.97. This indicates that NARX was able to detect the crucial dimension that was formulated for by the research to be the detections parameter of an inadvertent insider threat when operating under the best partition. In light of these findings, organisations can use the proposed approach to assess their preparedness for Insider attacks.

show abstract

Section: A Conceptualizationmentioning

confidence: 99%

Section: A Conceptualizationmentioning

confidence: 99%

Threats From Unintentional Insiders: An Assessment of an Organization’s Readiness Using Machine Learning

2022

View full text Add to dashboard Cite

show abstract

“…16 Thakkar et al proposed an RUL estimation technique based on deep RNN to calculate the RUL of turbofan engines based on complete historical data. 17 Li et al made the first attempt to use event vision data collected by event-based cameras for intelligent mechanical fault diagnosis designed an event data augmentation method to improve the robustness of the model, and further proposed a deep representation clustering method to improve the fault pattern identification of different machines. 18 Zhou et al developed a dual-thread gated recurrent unit (GRU) that uses a two-thread learning strategy to mine information in data and state differences between adjacent data, thus improving the performance of RUL prediction.…”

Section: Introductionmentioning

confidence: 99%

“…Thakkar et al. proposed an RUL estimation technique based on deep RNN to calculate the RUL of turbofan engines based on complete historical data 17 . Li et al.…”

Section: Introductionmentioning

confidence: 99%

An unsupervised subdomain adversarial network for remaining useful life estimation under various conditions

Wen,

Lyu,

Chen

2023

Quality & Reliability Eng

View full text Add to dashboard Cite

Domain adaptation is a transfer learning method that is widely applied for remaining useful life (RUL) prediction under different operating conditions. However, current RUL prediction methods based on domain adaptation only consider minimizing degradation feature differences, while ignoring the correlation between features and labels, which may result in significant errors in the mapping relationship between the two learned by the model, and thus reduce the accuracy of prediction. To address this issue, this paper proposes an unsupervised subdomain adversarial network (USDAN) for RUL estimation under various conditions. On the basis of traditional domain adversarial adaptation networks, the network uses temporal convolutional networks to construct the feature extractor to learn the long‐term dependencies between degradation data, and a multilinear conditioning scheme is designed to combine the features and subdomain labels as input features to the domain discriminator. Finally, with backpropagation and gradient reversal, the feature extractor is prompted to generate cross‐domain invariant features that are correlated with the labels, improving the prediction accuracy and enhancing the transferability of the network. In the experimental section, the public turbofan engine degradation dataset is used to validate the effectiveness of the network, and the comparison with other approaches demonstrates its advantages.

show abstract

“…The hybrid approach combines the advantages of both model-based and data-driven approaches. It uses data where system knowledge is lacking and uses physics where data is lacking [37], which results in improved prediction accuracy and a corresponding reduction in computing time. But it also has the disadvantages of both model-based and data-driven approaches, such as the need for in-depth knowledge of the system and the need for large amounts of data.…”

Section: Hybrid-based Techniquesmentioning

confidence: 99%

Remaining Useful Life Prediction of Proton Exchange Membrane Fuel Cells Using Genetic Algorithm Based Nonlinear Autoregressive Exogenous Network

Shen¹

View full text Add to dashboard Cite

The proton exchange membrane fuel cell (PEMFC) is one of the most promising clean energy sources with characteristics like high energy conversion, no electrolyte leakage, and low operational temperature. However, it is difficult to build a mathematical model because the system consists of a complex nonlinear system. In the meantime, accurate estimation of the remaining useful life (RUL) of fuel cells plays an important role in improving the safety and lifetime of fuel cells. A joint prediction method based on genetic algorithm (GA) and nonlinear autoregressive neural network with external input (NARX) is proposed. The method was designed to predict the RUL of the proton exchange membrane fuel cell. GA is used to optimize the initial weights and biases of the NARX neural network. Then, the historical voltage evolution under rated current conditions is used to train the NARX network, where the trained model is used to predict the voltage evolution under ripple conditions. Integrating the GA-NARX algorithm leads to the improvement of convergence speed and the prediction accuracy of the algorithm. This integrated algorithm obtains better estimation accuracy compared to the NARX network by itself. The proposed method was compared with the genetic algorithm-based backpropagation neural network (GA-BPNN) and genetic algorithm-based time delay neural network (GA-TDNN). The proposed method is validated with the IEEE PHM 2014 Data Challenge dataset and the results showed that the method has better prediction accuracy compared to other ANN algorithms.

show abstract

Remaining Useful Life Prediction of an Aircraft Turbofan Engine Using Deep Layer Recurrent Neural Networks

Cited by 19 publications

References 36 publications

Threats From Unintentional Insiders: An Assessment of an Organization’s Readiness Using Machine Learning

Threats From Unintentional Insiders: An Assessment of an Organization’s Readiness Using Machine Learning

An unsupervised subdomain adversarial network for remaining useful life estimation under various conditions

Remaining Useful Life Prediction of Proton Exchange Membrane Fuel Cells Using Genetic Algorithm Based Nonlinear Autoregressive Exogenous Network

Contact Info

Product

Resources

About