| 1. |
- Arias Chao, Manuel, et al.
(author)
-
Aircraft Engine Run-to-Failure Dataset under Real Flight Conditions for Prognostics and Diagnostics
- 2021
-
In: Data. - : MDPI. - 2306-5729. ; 6:1, s. 5-5
-
Journal article (peer-reviewed)abstract
- A key enabler of intelligent maintenance systems is the ability to predict the remaining useful lifetime (RUL) of its components, i.e., prognostics. The development of data-driven prognostics models requires datasets with run-to-failure trajectories. However, large representative run-to-failure datasets are often unavailable in real applications because failures are rare in many safety-critical systems. To foster the development of prognostics methods, we develop a new realistic dataset of run-to-failure trajectories for a fleet of aircraft engines under real flight conditions. The dataset was generated with the Commercial Modular Aero-Propulsion System Simulation (CMAPSS) model developed at NASA. The damage propagation modelling used in this dataset builds on the modelling strategy from previous work and incorporates two new levels of fidelity. First, it considers real flight conditions as recorded on board of a commercial jet. Second, it extends the degradation modelling by relating the degradation process to its operation history. This dataset also provides the health, respectively, fault class. Therefore, besides its applicability to prognostics problems, the dataset can be used for fault diagnostics.
|
|
| 2. |
- Arias Chao, Manuel, et al.
(author)
-
Fusing physics-based and deep learning models for prognostics
- 2022
-
In: Reliability Engineering & System Safety. - : Elsevier. - 0951-8320 .- 1879-0836. ; 217
-
Journal article (peer-reviewed)abstract
- Physics-based and data-driven models for remaining useful lifetime (RUL) prediction typically suffer from two major challenges that limit their applicability to complex real-world domains: (1) the incompleteness of physics-based models and (2) the limited representativeness of the training dataset for data-driven models. Combining the advantages of these two approaches while overcoming some of their limitations, we propose a novel hybrid framework for fusing the information from physics-based performance models with deep learning algorithms for prognostics of complex safety-critical systems. In the proposed framework, we use physics-based performance models to infer unobservable model parameters related to a system’s components health by solving a calibration problem. These parameters are subsequently combined with sensor readings and used as input to a deep neural network, thereby generating a data-driven prognostics model with physics-augmented features. The performance of the hybrid framework is evaluated on an extensive case study comprising run-to-failure degradation trajectories from a fleet of nine turbofan engines under real flight conditions. The experimental results show that the hybrid framework outperforms purely data-driven approaches by extending the prediction horizon by nearly 127%. Furthermore, it requires less training data and is less sensitive to the limited representativeness of the dataset as compared to purely data-driven approaches. Furthermore, we demonstrated the feasibility of the proposed framework on the original CMAPSS dataset, thereby confirming its superior performance.
|
|
| 3. |
- Bajarunas, Kristupas, et al.
(author)
-
Health index estimation through integration of general knowledge with unsupervised learning
- 2024
-
In: Reliability Engineering & System Safety. - : Elsevier. - 0951-8320 .- 1879-0836. ; 251
-
Journal article (peer-reviewed)abstract
- Accurately estimating a Health Index (HI) from condition monitoring data (CM) is essential for reliable and interpretable prognostics and health management (PHM) in complex systems. In most scenarios, complex systems operate under varying operating conditions and can exhibit different fault modes, making unsupervised inference of an HI from CM data a significant challenge. Hybrid models combining prior knowledge about degradation with deep learning models have been proposed to overcome this challenge. However, previously suggested hybrid models for HI estimation usually rely heavily on system-specific information, limiting their transferability to other systems. In this work, we propose an unsupervised hybrid method for HI estimation that integrates general knowledge about degradation into the convolutional autoencoder’s model architecture and learning algorithm, enhancing its applicability across various systems. The effectiveness of the proposed method is demonstrated in two case studies from different domains: turbofan engines and lithium batteries. The results show that the proposed method outperforms other competitive alternatives, including residual-based methods, in terms of HI quality and their utility for Remaining Useful Life (RUL) predictions. The case studies also highlight the comparable performance of our proposed method with a supervised model trained with HI labels.
|
|
| 4. |
- Baptista, Marcia Lourenco, et al.
(author)
-
A self-organizing map and a normalizing multi-layer perceptron approach to baselining in prognostics under dynamic regimes
- 2021
-
In: Neurocomputing. - : Elsevier. - 0925-2312 .- 1872-8286. ; 456, s. 268-287
-
Journal article (peer-reviewed)abstract
- When the influence of changing operational and environmental conditions is not factored out, it can be dificult to observe a clear deterioration path. This can significantly affect the task of prognostics and other analytic operations. To address this issue, it is necessary to baseline the data, typically by first finding the operating regimes and then normalizing the data within each regime. In this paper, we propose the use of machine learning techniques to perform baselining. A self-organizing map identifies the regimes, and a multi-layer perceptron normalizes the data based on the detected regimes. Tests are performed on the C-MAPSS data. The approach is capable of producing similar results to classical methods without the need to specify in advance the number of regimes and the explicit computation of the statistical properties of a hold-out dataset. Importantly, the techniques can be integrated into a deep learning system to perform prognostics in a single pass.
|
|
| 5. |
- Baptista, Marcia L., et al.
(author)
-
More effective prognostics with elbow point detection and deep learning
- 2021
-
In: Mechanical systems and signal processing. - : Elsevier. - 0888-3270 .- 1096-1216. ; 146
-
Journal article (peer-reviewed)abstract
- Prior to failure, most systems exhibit signs of changed characteristics. The early detection of this change is important to remaining useful life estimation. To have the ability to detect the inflection point or “elbow point” of an asset, i.e. the point of the degradation curve that marks the transition from nominal to faulty condition, can enable more sophisticated prognostics because this divide and conquer tactic allows the prediction to focus on the window before failure when significant changes are being expected. In this work, we compare prognostics with and without change point detection. We use different recurrent neural network techniques (standard recurrent neural network, long short-term memory and gated recurrent unit) to find the elbow point location. The actual estimation of the remaining time to failure is based on the echo state network, a state-of-the-art approach in prognostics. Two different experiments are performed on simulated data obtained from NASA Ames prognostics repository. We first compare the performance of the elbow point detectors based on recurrent neural networks against three baseline models: the Z-test, multi-layer perceptron and random forests. Results indicate that recurrent neural networks can outperform the baseline approaches. In the second experiment, the best elbow detection model, the gated recurrent unit, is integrated within an echo state network, with a significant increase in overall performance in terms of remaining useful life estimation.
|
|
| 6. |
- Baptista, Marcia L., et al.
(author)
-
Relation between prognostics predictor evaluation metrics and local interpretability SHAP values
- 2022
-
In: Artificial Intelligence. - : Elsevier. - 0004-3702 .- 1872-7921. ; 306
-
Journal article (peer-reviewed)abstract
- Maintenance decisions in domains such as aeronautics are becoming increasingly dependent on being able to predict the failure of components and systems. When data-driven techniques are used for this prognostic task, they often face headwinds due to their perceived lack of interpretability. To address this issue, this paper examines how features used in a data-driven prognostic approach correlate with established metrics of monotonicity, trendability, and prognosability. In particular, we use the SHAP model (SHapley Additive exPlanations) from the field of eXplainable Artificial Intelligence (XAI) to analyze the outcome of three increasingly complex algorithms: Linear Regression, Multi-Layer Perceptron, and Echo State Network. Our goal is to test the hypothesis that the prognostics metrics correlate with the SHAP model's explanations, i.e., the SHAP values. We use baseline data from a standard data set that contains several hundred run-to-failure trajectories for jet engines. The results indicate that SHAP values track very closely with these metrics with differences observed between the models that support the assertion that model complexity is a significant factor to consider when explainability is a consideration in prognostics.
|
|
| 7. |
- Bektas, Oguz, et al.
(author)
-
A neural network filtering approach for similarity-based remaining useful life estimation
- 2019
-
In: The International Journal of Advanced Manufacturing Technology. - : Springer. - 0268-3768 .- 1433-3015. ; 101:1-4, s. 87-103
-
Journal article (peer-reviewed)abstract
- The role of prognostics and health management is ever more prevalent with advanced techniques of estimation methods. However, data processing and remaining useful life prediction algorithms are often very different. Some difficulties in accurate prediction can be tackled by redefining raw data parameters into more meaningful and comprehensive health level indicators that will then provide performance information. Proper data processing has a significant importance on remaining useful life predictions, for example, to deal with data limitations or/and multi-regime operating conditions. The framework proposed in this paper considers a similarity-based prognostic algorithm that is fed by the use of data normalisation and filtering methods for operational trajectories of complex systems. This is combined with a data-driven prognostic technique based on feed-forward neural networks with multi-regime normalisation. In particular, the paper takes a close look at how pre-processing methods affect algorithm performance. The work presented herein shows a conceptual prognostic framework that overcomes challenges presented by short-term test datasets and that increases the prediction performance with regards to prognostic metrics.
|
|
| 8. |
- Bektas, Oguz, et al.
(author)
-
A neural network framework for similarity-based prognostics
- 2019
-
In: MethodsX. - : Elsevier. - 1258-780X .- 2215-0161. ; 6, s. 383-390
-
Journal article (peer-reviewed)abstract
- Prognostic performance is associated with accurately estimating remaining useful life. Difficulty in accurate prognostic applications can be tackled by processing raw sensor readings into more meaningful and comprehensive health condition indicators that will then provide performance information for remaining useful life estimations. To that end, typically, multiple tasks on data pre-processing and predictions have to be carried out such that tasks can be assessed using different methodological aspects. However, incompatible methods may result in poor performance and consequently lead to undesirable error rates.The present research evaluates data training and prediction stages. A data-driven prognostic method based on a feed-forward neural network framework is first defined to calculate the performance of a complex system. Then, the health indicators are used in a similarity based remaining useful life estimation method. This framework presents a conceptual prognostic protocol that overcomes challenges presented by multi-regime condition monitoring data.
|
|
| 9. |
- Bektas, Oguz, et al.
(author)
-
Reconstructing secondary test database from PHM08 challenge data set
- 2018
-
In: Data in Brief. - : Elsevier. - 2352-3409. ; 21, s. 2464-2469
-
Journal article (peer-reviewed)abstract
- In this data article, a reconstructed database, which provides information from PHM08 challenge data set, is presented. The original turbofan engine data were from the Prognostic Center of Excellence (PCoE) of NASA Ames Research Center (Saxena and Goebel, 2008), and were simulated by the Commercial Modular Aero-Propulsion System Simulation (C-MAPSS) (Saxena et al., 2008). The data set is further divided into "training", "test" and "final test" subsets. It is expected from collaborators to train their models using “training” data subset, evaluate the Remaining Useful Life (RUL) prediction performance on “test” subset and finally, apply the models to the “final test” subset for competition. However, the "final test" results can only be submitted once by email to PCoE. Before the results are sent for performance evaluation, in order to pre-validate the dataset with true RUL values, this data article introduces reconstructed secondary datasets derived from the noisy degradation patterns of original trajectories. Reconstructed database refers to data that were collected from the training trajectories. Fundamentally, it is formed of individual partial trajectories in which the RUL is known as a ground truth. Its use provides a robust validation of the model developed for the PHM08 data challenge that would otherwise be ambiguous due to the high-risk of one-time submission. These data and analyses support the research data article “A Neural Network Filtering Approach for Similarity-Based Remaining Useful Life Estimations” (Bektas et al., 2018).
|
|
| 10. |
- Chao, Manuel Arias, et al.
(author)
-
Hybrid deep fault detection and isolation : Combining deep neural networks and system performance models
- 2019
-
In: International Journal of Prognostics and Health Management. - : PHM Society. - 2153-2648. ; 10:11
-
Journal article (peer-reviewed)abstract
- With the increased availability of condition monitoring data on the one hand and the increased complexity of explicit system physics-based models on the other hand, the application of data-driven approaches for fault detection and isolation has recently grown. While detection accuracy of such approaches is generally very good, their performance on fault isolation often suffers from the fact that fault conditions affect a large portion of the measured signals thereby masking the fault source. To overcome this limitation, we propose a hybrid approach combining physical performance models with deep learning algorithms. Unobserved process variables are inferred with a physics-based performance model to enhance the input space of a data-driven diagnostics model. The resulting increased input space gains representation power enabling more accurate fault detection and isolation. To validate the effectiveness of the proposed method, we generate a condition monitoring dataset of an advanced gas turbine during flight conditions under healthy and four faulty operative conditions based on the Aero-Propulsion System Simulation (C-MAPSS) dynamical model. We evaluate the performance of the proposed hybrid methodology in combination with two different deep learning algorithms: deep feed forward neural networks and Variational Autoencoders, both of which demonstrate a significant improvement when applied within the hybrid fault detection and diagnostics framework. The proposed method is able to outperform pure data-driven solutions, particularly for systems with a high variability of Manuel Arias Chao et al. This is an open-access article distributed under the terms of the Creative Commons Attribution 3.0 United States License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. operating conditions. It provides superior results both for fault detection as well as for fault isolation. For the fault isolation task, it overcomes the smearing effect that is commonly observed in pure data-driven approaches and enables a precise isolation of the affected signal. We also demonstrate that deep learning algorithms provide a better performance on the fault detection tas
|
|
