Aircraft Engine Gas-Path Monitoring and Diagnostics Framework Based on a Hybrid Fault Recognition Approach

Pérez-Ruiz, Juan Luis; Tang, Yu; Loboda, Igor

doi:10.3390/aerospace8080232

Cited by 18 publications

(18 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Table 7 summarises the blind-test-case metric results from other known diagnostic methods using the ProDiMES software for evaluation. Regularized Extreme Learning Machines-Sparse Representation Classification (RELM-SRC) method [33] has the best diagnostic performance, which provides a kappa coefficient of 0.685. The kappa coefficient of the proposed method in this paper is 0.731, which is 0.046, larger than the kappa coefficient provided by the RELM-SRC method.…”

Section: Discussionmentioning

confidence: 99%

Convolutional Neural Network Denoising Auto-Encoders for Intelligent Aircraft Engine Gas Path Health Signal Noise Filtering

Zhao

Sampath

2023

Journal of Engineering for Gas Turbines and Power

View full text Add to dashboard Cite

Removing noise from health signals is critical in gas path diagnostics of aircraft engines. An efficient noise filtering/denoising method should remove noise without using future data points, preserve important changes, and promote accurate diagnostics without time delay. Machine Learning (ML)-based methods are promising for high fidelity, accuracy, and computational efficiency under the motivation of Intelligent Engines. However, previous ML-based denoising methods are rarely applied in actual engineering practice because they cannot accommodate time series and cannot effectively capture important changes or are limited by the time delay problem. This paper proposes a Convolutional Neural Network Denoising Autoencoder (CNN-DAE) method to build a denoising autoencoder structure. In this structure, a convolutional operation is used to accommodate time series, and causal convolution is introduced to solve the problem of using future data points. The proposed denoising method is evaluated against NASA's Propulsion Diagnostic Method Evaluation Strategy (ProDiMES) software. It has been proved that the proposed method can accommodate time series, remove noise for improved denoising accuracy and preserve the important changes for enhanced diagnostic information. NASA's blind test case results show that Kappa Coefficient of a common diagnostic method using the processed data is 0.731 and is at least 0.046 higher than the other diagnostic methods in the open literature. Processing health signals using the proposed method would significantly promote accurate diagnostics without time delay. The proposed method could support intelligent condition monitoring systems by exploiting historical information for improved denoising and diagnostic performance.

show abstract

Section: Discussionmentioning

confidence: 99%

Convolutional Neural Network Denoising Auto-Encoders for Intelligent Aircraft Engine Gas Path Health Signal Noise Filtering

Zhao

Sampath

2023

Journal of Engineering for Gas Turbines and Power

View full text Add to dashboard Cite

show abstract

“…Zhao et al confirmed better performance provided by Soft Extreme Learning Machine (SELM) and Improved SELM (ISELM) [24]. To improve numerical stability, a regularization term is often used in ELM diagnostic systems [25][26][27]. Liu et al introduced the optimized ELM based on restricted Boltzmann machine [28] to predict the EGT trend in Auxiliary Power Unit (APU) with the improved stability of ELM solutions when some input parameters are correlated.…”

Section: Introductionmentioning

confidence: 97%

Extreme Learning Machine-Based Diagnostics for Component Degradation in a Microturbine

Menga¹,

Mothakani²,

Giorgi³

et al. 2022

Preprint

View full text Add to dashboard Cite

Micro turbojets are used for propelling radio-controlled aircraft, aerial targets and personal air vehicles. When compared to full-scale engines, they are characterized by relatively low efficiency and durability. In this context, the degraded performance of gas path components could lead to an unacceptable reduction in the overall engine performance. In this work, a data-driven model based on a conventional Artificial Neural Network (ANN) and an extreme learning machine (ELM) was used for estimating the performance degradation of the micro turbojet. The training datasets containing the performance data of the engine with degraded components were generated using the validated GSP model and the Monte Carlo approach. In particular, compressor and turbine performance degradation were simulated for three different flight regimes. It was confirmed that component degradation has a higher impact in flight than at sea level. Finally, the datasets were used in the training and testing process of the ELM algorithm with four different input vectors. Two vectors had an extensive number of virtual sensors, and the other two were reduced to just fuel flow and Exhaust Gas Temperature. Even with the small number of sensors, the high prediction accuracy of ELM was maintained for takeoff and cruise but was slightly worse for variable flight conditions.

show abstract

“…Here, the data sparsity related to snapshot data leads to difficulties distinguishing between faults and random scatter. Depending on the faulty component and the severity of the fault, it may take multiple data points to detect a fault [4][5][6]. Consequently, several flights might be carried out until fault detection increasing the risk of collateral damage.…”

Section: Introductionmentioning

confidence: 99%

Steady-State Fault Detection with Full-Flight Data

et al. 2022

View full text Add to dashboard Cite

Aircraft engine condition monitoring is a key technology for increasing safety and reducing maintenance expenses. Current engine condition monitoring approaches use a minimum of one steady-state snapshot per flight. Whilst being appropriate for trending gradual engine deterioration, snapshots result in a detrimental latency in fault detection. The increased availability of non-mandatory data acquisition hardware in modern airplanes provides so-called full-flight data sampled continuously during flight. These datasets enable the detection of engine faults within one flight by deriving a statistically relevant set of steady-state data points, thus, allowing the application of machine-learning approaches. It is shown that low-pass filtering before steady-state detection significantly increases the success rate in detecting steady-state data points. The application of Principal Component Analysis halves the number of relevant dimensions and provides a coordinate system of principal components retaining most of the variance. Consequently, clusters of data points with and without engine fault can be separated visually and numerically using a One-Class Support Vector Machine. High detection rates are demonstrated for various component faults and even for a minimum instrumentation suite using synthesized datasets derived from full-flight data of commercially operated flights. In addition to the tests conducted with synthesized data, the algorithm is verified based on operational in-flight measurements providing a proof-of-concept. Consequently, the availability of continuously sampled in-flight measurements combined with machine-learning methods allows fault detection within a single flight.

show abstract

Aircraft Engine Gas-Path Monitoring and Diagnostics Framework Based on a Hybrid Fault Recognition Approach

Cited by 18 publications

References 26 publications

Convolutional Neural Network Denoising Auto-Encoders for Intelligent Aircraft Engine Gas Path Health Signal Noise Filtering

Convolutional Neural Network Denoising Auto-Encoders for Intelligent Aircraft Engine Gas Path Health Signal Noise Filtering

Extreme Learning Machine-Based Diagnostics for Component Degradation in a Microturbine

Steady-State Fault Detection with Full-Flight Data

Contact Info

Product

Resources

About