RUL prediction for IMA based on deep regression method

Gao, Zehai; Ma, Cunbao; Luo, Yige

doi:10.1109/iwcia.2017.8203556

Cited by 9 publications

(14 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In Table II, the most commonly used state-of-the-art machine learning algorithms are Support Vector Regressor (SVR) [12], [13] , Random Forest (RF) [14], Deep Convolutional Neural Network (DCNN) [15], Long Short-Term Memory (LSTM) [6], [16], [17] and Neural Network (NN) [18]. We observe inconsistency in model comparison, similarly to the findings in [8] [10] and [11].…”

Section: Current Methodologies In Aerospace Prognostic Algorithms Evaluationsupporting

confidence: 53%

“…Similarly, Li et al [15] compare DCNN for RUL prediction to four different NN architectures while Zhao et al [18] compare their proposed NN architecture to only Discriminating Shapelet Extraction (DSE). Furthermore, Zaidan et al [19] and Gao et al [12] utilise Bayesian Hierarchical and SVR Models respectively for gas turbine engine prognostics but did not compare their methods to other models.…”

Section: Current Methodologies In Aerospace Prognostic Algorithms Evaluationmentioning

confidence: 99%

See 1 more Smart Citation

An Intelligent Toolkit for Benchmarking Data-Driven Aerospace Prognostics

Rengasamy

Mase

Rothwell

et al. 2019

2019 IEEE Intelligent Transportation Systems Conference (ITSC)

View full text Add to dashboard Cite

Machine Learning (ML) has been largely employed to sensor data for predicting the Remaining Useful Life (RUL) of aircraft components with promising results. A review of the literature, however, has revealed a lack of consensus regarding evaluation metrics adopted, the state-of-the-art methods employed for performance comparison, the approaches to address data overfitting, and statistical tests to assess results' significance. These weaknesses in methodological approaches to experimental design, results evaluation, comparison and reporting of findings can result in misleading outcomes and ultimately produce less effective predictors. Arbitrary choices of approaches for novel method's evaluation, the potential bias that can be introduced, and the lack of systematic replication and comparison of outcomes might affect the findings reported and misguide future research. For further advances in this area, there is therefore an urgent need for appropriate benchmarking methodologies to assist evaluating novel methods and to produce fair performance rankings. In this paper we introduce an opensource, extensible benchmarking library to address this gap in aerospace prognosis. The library will assist researchers to conduct a proper and fair evaluation of their novel ML RUL predictive models. In addition, it will assist stimulating better practices and a more rigorous experimental design approach across the field. Our library contains 13 state-of-the-art ML methods, 12 metrics for algorithm performance evaluation and tests for statistical significance. To demonstrate the library's functionalities, we apply it to gas turbine engine prognostic datasets.

show abstract

Section: Current Methodologies In Aerospace Prognostic Algorithms Evaluationsupporting

confidence: 53%

Section: Current Methodologies In Aerospace Prognostic Algorithms Evaluationmentioning

confidence: 99%

An Intelligent Toolkit for Benchmarking Data-Driven Aerospace Prognostics

Rengasamy

Mase

Rothwell

et al. 2019

2019 IEEE Intelligent Transportation Systems Conference (ITSC)

View full text Add to dashboard Cite

show abstract

“…Compact representation of data in DAE is used for dimensional reduction. Subsequently, the Sarkar et al [13] Deep autoencoder Crack detection in aircraft's multi-layer composite sub-elements Gao et al [14] Deep denoising autoencoder remaining useful life prediction in integrated modular avionics.…”

Section: A Deep Autoencodersmentioning

confidence: 99%

“…Gao et al [14] utilizes a combination of stacked denoising autoencoders [27] (SDAE) and Support Vector Machine (SVM) to predict the Remaining Useful Life (RUL) of integrated modular avionics (IMA). Degradation of IMA is typically caused by the wearing out of electronics that lead to electromigration and time-dependent dielectric breakdown -the root cause of intermittent faults (IF) in IMA.…”

Section: A Deep Autoencodersmentioning

confidence: 99%

Deep Learning Approaches to Aircraft Maintenance, Repair and Overhaul: A Review

Rengasamy

Morvan

Figueredo

2018

2018 21st International Conference on Intelligent Transportation Systems (ITSC)

View full text Add to dashboard Cite

The use of sensor technology constantly gathering aircrafts' status data has promoted the rapid development of data-driven solutions in aerospace engineering. These methods assist, for instance, with determining appropriate actions for aircraft maintenance, repair and overhaul (MRO). Challenges however are found when dealing with such large amounts of data. Identifying patterns, anomalies and faults disambiguation, with acceptable levels of accuracy and reliability are examples of complex problems in this area. Experiments using deep learning techniques, however, have demonstrated its usefulness in assisting on the analysis aircraft health data. The purpose of this paper therefore is to conduct a survey on deep learning architectures and their application in aircraft MRO. Although deep learning in general is not yet largely exploited for aircraft health, from our search, we identified four main architectures employed to MRO, namely, Deep Autoencoders, Long Short-Term Memory, Convolutional Neural Networks and Deep Belief Networks. For each architecture, we review their main concepts, the types of problems to which these architectures are employed to, the type of data used and their outcomes. We also discuss how research in this area can be advanced by identifying current research gaps and outlining future research opportunities.

show abstract

“…Resulting from the increasing scale of integration and complex interaction between functions and resources, a new series of problems arise, which brings new requirements for the security of avionics systems [3]. Many researches are committed to guarantee the safety of IMA by virtue of structural optimization and redundancy design [4], [5]. However, quite few studies focus on the remaining useful life (RUL) prediction of IMA.…”

Section: Introductionmentioning

confidence: 99%

Enhanced Online Sequential Parallel Extreme Learning Machine and its Application in Remaining Useful Life Prediction of Integrated Modular Avionics

Gao

Zhang

et al. 2019

IEEE Access

Self Cite

View full text Add to dashboard Cite

Integrated modular avionics is one of the most advanced systems which has been widely applied in modern aircraft. The performance of integrated modular avionics deeply impacts flight mission. Remaining useful life prediction is the critical manner which can efficiently improve the safety and reliability of aircraft. Since integrated modular avionics is a real-time system, the prediction algorithm should have fast learning speed to satisfy the real-time requirement. In this paper, an enhanced online sequential method is proposed to predict the remaining useful life of integrated modular avionics. Firstly, this paper proposes an online sequential network which is based on the architecture of parallel layer network. Secondly, to enhance the learning capability, this paper adopts the extreme learning machine denosing autoencoder to determine the input weights of the network. Thirdly, an adaptive forgetting factor is added to further improve the performance of the proposed method. The effectiveness and the superiority of the proposed method are verified in comparison with three online sequential algorithms on the standard datasets. Finally, a degradation model is built to depict the deteriorated process of integrated modular avionics. The prediction results confirms that the proposed method can effectively address remaining useful life of integrated modular avionics.INDEX TERMS Integrated modular avionics, parallel layer network, remaining useful life, degradation model.

show abstract

RUL prediction for IMA based on deep regression method

Cited by 9 publications

References 13 publications

An Intelligent Toolkit for Benchmarking Data-Driven Aerospace Prognostics

An Intelligent Toolkit for Benchmarking Data-Driven Aerospace Prognostics

Deep Learning Approaches to Aircraft Maintenance, Repair and Overhaul: A Review

Enhanced Online Sequential Parallel Extreme Learning Machine and its Application in Remaining Useful Life Prediction of Integrated Modular Avionics

Contact Info

Product

Resources

About