Browsing by Author "King, Steve"

Now showing 1 - 6 of 6
  • Thumbnail Image
    ItemOpen Access
    Aircraft system-level diagnosis with emphasis on maintenance decisions
    (SAGE, 2021-10-26) Skliros, Christos; Ali, Fakhre; King, Steve; Jennions, Ian
    This paper proposes a diagnostic technique that can predict component degradation for a number of complex systems. It improves and clarifies the capabilities of a previously proposed diagnostic approach, by identifying the degradation severity of the examined components, and uses a 3D Principal Component Analysis approach to provide an explanation for the observed diagnostic accuracy. The diagnostic results are then used, in a systematic way, to influence maintenance decisions. Having been developed for the Auxiliary Power Unit (APU), the flexibility and power of the diagnostic methodology is shown by applying it to a completely new system, the Environmental Control System (ECS). A major conclusion of this work is that the proposed diagnostic approach is able to correctly predict the health state of two aircraft systems, and potentially many more, even in cases where different fault combinations result in similar fault patterns. Based on the engineering simulation approach verified here, a diagnostic methodology suitable from aircraft conception to retirement is proposed.
  • Thumbnail Image
    ItemOpen Access
    Application of data analytics for predictive maintenance in aerospace: an approach to imbalanced learning.
    (2021-05) Dangut, Maren David; Jennions, Ian K.; King, Steve
    The use of aircraft operational logs to predict potential failure that may lead to disruption poses many challenges and has yet to be fully explored. These logs are captured during each flight and contain streamed data from various aircraft subsystems relating to status and warning indicators. They may, therefore, be regarded as complex multivariate time-series data. Given that aircraft are high-integrity assets, failures are extremely rare, and hence the distribution of relevant data containing prior indicators will be highly skewed to the normal (healthy) case. This will present a significant challenge in using data-driven techniques to 'learning' relationships/patterns that depict fault scenarios since the model will be biased to the heavily weighted no-fault outcomes. This thesis aims to develop a predictive model for aircraft component failure utilising data from the aircraft central maintenance system (ACMS). The initial objective is to determine the suitability of the ACMS data for predictive maintenance modelling. An exploratory analysis of the data revealed several inherent irregularities, including an extreme data imbalance problem, irregular patterns and trends, class overlapping, and small class disjunct, all of which are significant drawbacks for traditional machine learning algorithms, resulting in low-performance models. Four novel advanced imbalanced classification techniques are developed to handle the identified data irregularities. The first algorithm focuses on pattern extraction and uses bootstrapping to oversample the minority class; the second algorithm employs the balanced calibrated hybrid ensemble technique to overcome class overlapping and small class disjunct; the third algorithm uses a derived loss function and new network architecture to handle extremely imbalanced ratios in deep neural networks; and finally, a deep reinforcement learning approach for imbalanced classification problems in log- based datasets is developed. An ACMS dataset and its accompanying maintenance records were used to validate the proposed algorithms. The research's overall finding indicates that an advanced method for handling extremely imbalanced problems using the log-based ACMS datasets is viable for developing robust data-driven predictive maintenance models for aircraft component failure. When the four implementations were compared, deep reinforcement learning (DRL) strategies, specifically the proposed double deep State-action-reward-state-action with prioritised experience reply memory (DDSARSA+PER), outperformed other methods in terms of false-positive and false-negative rates for all the components considered. The validation result further suggests that the DDSARSA+PER model is capable of predicting around 90% of aircraft component replacements with a 0.005 false-negative rate in both A330 and A320 aircraft families studied in this research
  • Thumbnail Image
    ItemOpen Access
    Application of deep reinforcement learning for extremely rare failure prediction in aircraft maintenance
    (Elsevier, 2022-02-08) Dangut, Maren David; Jennions, Ian K.; King, Steve; Skaf, Zakwan
    The use of aircraft operational logs to predict potential failure that may lead to disruption poses many challenges and has yet to be fully explored. Given that aircraft are high-integrity assets, failures are extremely rare, and hence the distribution of relevant log data containing prior indicators will be highly skewed to the normal (healthy) case. This will present a significant challenge in using data-driven techniques because the model will be biased to the heavily weighted no-fault outcomes. This paper presents a novel approach for predicting unscheduled aircraft maintenance action based on deep reinforcement learning techniques using aircraft central maintenance system logs. The algorithm transforms the rare failure prediction problem into a sequential decision-making process that is optimised using a reward system that penalises proposed predictions that result in a false diagnosis and preferentially favours predictions that result in the right diagnosis. The validation data is directly associated with the physical health aspects of the aircraft components. The influence of extremely rare failure prediction on the proposed method is analysed. The effectiveness of the new approach is verified by comparison with previous studies, cost-sensitive and oversampling methods. Performance was evaluated based on G-mean and false-positives rates. The proposed approach shows the superior performance of 20.3% improvement in G-mean and 97% reduction in false-positive rate.
  • Thumbnail Image
    ItemOpen Access
    A deep-learning-based approach for aircraft engine defect detection
    (MDPI, 2023-02-01) Upadhyay, Anurag; Li, Jun; King, Steve; Addepalli, Sri
    Borescope inspection is a labour-intensive process used to find defects in aircraft engines that contain areas not visible during a general visual inspection. The outcome of the process largely depends on the judgment of the maintenance professionals who perform it. This research develops a novel deep learning framework for automated borescope inspection. In the framework, a customised U-Net architecture is developed to detect the defects on high-pressure compressor blades. Since motion blur is introduced in some images while the blades are rotated during the inspection, a hybrid motion deblurring method for image sharpening and denoising is applied to remove the effect based on classic computer vision techniques in combination with a customised GAN model. The framework also addresses the data imbalance, small size of the defects and data availability issues in part by testing different loss functions and generating synthetic images using a customised generative adversarial net (GAN) model, respectively. The results obtained from the implementation of the deep learning framework achieve precisions and recalls of over 90%. The hybrid model for motion deblurring results in a 10× improvement in image quality. However, the framework only achieves modest success with particular loss functions for very small sizes of defects. The future study will focus on very small defects detection and extend the deep learning framework to general borescope inspection.
  • Thumbnail Image
    ItemOpen Access
    Framework for anomaly detection of flight-crew deviation from standard operating procedures: a data analytics approach.
    (Cranfield University, 2022-05) Igenewari, Vivian Rowoli; King, Steve; Jennions, Ian K.
    Deviations from Standard Operating Procedure form a significant part of aviation incidents today involving loss of lives and other related costs. Previous work tailored towards detecting procedure deviations in flight operations have primarily been rule-based. The current method being used by airlines to detect operational, component fault and crew action anomalies within flight data is a rule-based Exceedance Detection technique which is only able to flag up known flight abnormalities. Lately, Anomaly Detection methods have been introduced to find, not just known, but unknown anomalies that deviate from the expected normal flight profile. There is a need to explore flight data using anomaly detection methods to detect subtle underlying misunderstandings of the flight crew in relation to deviations from laid down procedures which do not lead to incidents, under most conditions, or are hard to detect by the state-of-the-art method. However, these detection methods are limited in the type of anomalies they can find when implemented individually on heterogeneous flight dataset thereby missing critical anomalous flight incidents. In this work, Flight Data Recorder data of a fleet from a United Kingdom airline and a structurally similar publicly available dataset from the National Aeronautics & Space Administration are used. This study proposes a framework integrating an Ensemble anomaly detection technique (combining individual anomaly detection techniques into a single method) and a Case Based Reasoning system. The findings reveal that combining existing anomaly detection methods into an Ensemble can detect a wider variety of anomalies that were not flagged by individual methods. Also, the proposed reasoning design aims to filter for procedure deviations from the pool of anomalous incidents detected by the Ensemble. Detecting these procedure deviations is not just aimed at complementing crew training, improving procedures, and understanding automation design to put in place mitigation strategies but also to aid accident investigations by informing of accident flights with procedure deviations that may have been contributing factors.
  • Thumbnail Image
    ItemOpen Access
    A rare failure detection model for aircraft predictive maintenance using a deep hybrid learning approach
    (Springer, 2022-03-26) Dangut, Maren David; Jennions, Ian K.; King, Steve; Skaf, Zakwan
    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.