Rare Failure Prediction via Event Matching for Aerospace Applications

Burnaev, Evgeny

doi:10.1109/cirsyssim.2019.8935598

Cited by 6 publications

(4 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…failure data are limited in real-world industrial scenarios due to three major reasons: (i) rare (yet adverse) failures; (ii) over-protective maintenance and replacement regimes; (iii) highly reliable equipment [3], [4]. This causes training datasets to be imbalanced, which makes it difficult for data-driven algorithms to estimate model parameters from degradation patterns and characterise system performance for prognostics modelling [4].…”

Section: Introductionmentioning

confidence: 99%

A Methodology for Prognostics Under the Conditions of Limited Failure Data Availability

et al. 2019

View full text Add to dashboard Cite

When failure data are limited, data-driven prognostics solutions underperform since the number of failure data samples is insufficient for training prognostics models effectively. In order to address this problem, we present a novel methodology for generating failure data which allows training datasets to be augmented so that the number of failure data samples is increased. In contrast to existing data generation techniques which duplicate or randomly generate data, the proposed methodology is capable of generating new and realistic failure data samples. The methodology utilises the conditional generative adversarial network and auxiliary information pertaining to failure modes to control and direct the failure data generation process. The theoretical foundation of the methodology in a non-parametric setting is presented and we show that it holds in practice using empirical results. The methodology is evaluated in a real-world case study involving the prediction of air purge valve failures in heavy-trucks. Two prognostics models are developed using the gradient boosting machine and random forest classifiers. When these models are trained on the augmented training dataset, they outperformed the best solution previously proposed in the literature for the case study by a large margin. More specifically, costs due to breakdowns and false alarms are reduced by 44%. INDEX TERMS Equipment prognostics, expert knowledge, generative modeling, limited failure data, physics of failure.

show abstract

Section: Introductionmentioning

confidence: 99%

A Methodology for Prognostics Under the Conditions of Limited Failure Data Availability

et al. 2019

View full text Add to dashboard Cite

show abstract

“…However, it needs larger data samples and a longer processing time to achieve higher performance [42]. Advances have been made to tackle slightly rare event predictions, especially in the aerospace domain, using machine learning approaches [1,43,44]. Deep learning models have also been developed for rare event predictions.…”

Section: Related Workmentioning

confidence: 99%

“…Changchang et al [45] combined multiple DL algorithms for aircraft prognostic and health management. In fact, Burnaev et al [46] pointed out that many aircraft predictive maintenance solutions are built on basic threshold settings that detect trivial errors on specific components. On the other hand, the threshold-setting strategy is prone to producing high false-positive rates, which lowers model confidence.…”

Section: Related Workmentioning

confidence: 99%

A rare failure detection model for aircraft predictive maintenance using a deep hybrid learning approach

Dangut

Jennions

King

et al. 2022

Neural Comput & Applic

View full text Add to dashboard Cite

The use of aircraft operation logs to develop a data-driven model to predict probable failures that could cause interruption poses many challenges and has yet to be fully explored. Given that aircraft is high-integrity assets, failures are exceedingly rare. Hence, the distribution of relevant log data containing prior signs will be heavily skewed towards the typical (healthy) scenario. Thus, this study presents a novel deep learning technique based on the auto-encoder and bidirectional gated recurrent unit networks to handle extremely rare failure predictions in aircraft predictive maintenance modelling. The auto-encoder is modified and trained to detect rare failures, and the result from the auto-encoder is fed into the convolutional bidirectional gated recurrent unit network to predict the next occurrence of failure. The proposed network architecture with the rescaled focal loss addresses the imbalance problem during model training. The effectiveness of the proposed method is evaluated using real-world test cases of log-based warning and failure messages obtained from the fleet database of aircraft central maintenance system records. The proposed model is compared to other similar deep learning approaches. The results indicated an 18% increase in precision, a 5% increase in recall, and a 10% increase in G-mean values. It also demonstrates reliability in anticipating rare failures within a predetermined, meaningful time frame.

show abstract

“…In contrast, rare failure is typically one-of-a-kind, and hence it becomes difficult to learn temporal patterns using traditional machine learning approaches. That is why many aircraft predictive maintenance models are based on simple "threshold" monitoring rules capable of detecting only simple faults and, consequently, having high false-positive rates (FPR) [7]. Hence, it is vital to provide an accurate prediction of failures and, at the same time, have a very low FPR.…”

Section: Introductionmentioning

confidence: 99%

Application of deep reinforcement learning for extremely rare failure prediction in aircraft maintenance

Dangut

Jennions

King

et al. 2022

Mechanical Systems and Signal Processing

View full text Add to dashboard Cite

Rare Failure Prediction via Event Matching for Aerospace Applications

Cited by 6 publications

References 24 publications

A Methodology for Prognostics Under the Conditions of Limited Failure Data Availability

A Methodology for Prognostics Under the Conditions of Limited Failure Data Availability

A rare failure detection model for aircraft predictive maintenance using a deep hybrid learning approach

Application of deep reinforcement learning for extremely rare failure prediction in aircraft maintenance

Contact Info

Product

Resources

About