Turbofan Engine Degradation Research Articles

An unsupervised subdomain adversarial network for remaining useful life estimation under various conditions

AbstractDomain adaptation is a transfer learning method that is widely applied for remaining useful life (RUL) prediction under different operating conditions. However, current RUL prediction methods based on domain adaptation only consider minimizing degradation feature differences, while ignoring the correlation between features and labels, which may result in significant errors in the mapping relationship between the two learned by the model, and thus reduce the accuracy of prediction. To address this issue, this paper proposes an unsupervised subdomain adversarial network (USDAN) for RUL estimation under various conditions. On the basis of traditional domain adversarial adaptation networks, the network uses temporal convolutional networks to construct the feature extractor to learn the long‐term dependencies between degradation data, and a multilinear conditioning scheme is designed to combine the features and subdomain labels as input features to the domain discriminator. Finally, with backpropagation and gradient reversal, the feature extractor is prompted to generate cross‐domain invariant features that are correlated with the labels, improving the prediction accuracy and enhancing the transferability of the network. In the experimental section, the public turbofan engine degradation dataset is used to validate the effectiveness of the network, and the comparison with other approaches demonstrates its advantages.

Research on combination of periodic inspection and data-driven maintenance system of turbofan engine

In the field of aviation, turbofan engine is a crucial high-precision component of an aircraft which requires rigorous maintenance to ensure the running stability, safety, and efficiency. To reduce the high cost of general maintenance, the system of combination of periodic inspection and Data-driven maintenance is a meaningful research trend. In this pattern, the engine's condition study over sensor data serves as the foundation for the maintenance, to meet the safety requirements, improved sensor data processing and interpretation and precise prediction model plays important role. In this study, Long Short-Term Memory (LSTM) architecture was used to estimate RUL (remaining useful life) and support periodic inspection. The experiments were taken by using the dataset of FD001 and FD003 in Turbofan engine degradation dataset that contains operating and degradation information of several turbofan engines. After being analysed by different evaluation methods, the algorithm is capable to discover the features that hidden among sensor data, which indicates that the model has promising results for predictive maintenance. Therefore, the Data-driven maintenance structure that integrated with LSTM architecture is proposed as an application method. Furthermore, considering all aspects of the real application, management tools, Kubernetes and Kubeflow are introduced in this paper. Finally, regularly scheduled inspection is introduced, with the help of estimated RUL, inspection can be applied by parts rather than removing engine for overhaul and replacement of all parts including parts in good condition.

A metric for assessing and optimizing data-driven prognostic algorithms for predictive maintenance

Prognostic Health Management aims to predict the Remaining Useful Life (RUL) of degrading components/systems utilizing monitoring data. These RUL predictions form the basis for optimizing maintenance planning in a Predictive Maintenance (PdM) paradigm. We here propose a metric for assessing data-driven prognostic algorithms based on their impact on downstream PdM decisions. The metric is defined in association with a decision setting and a corresponding PdM policy. We consider two typical PdM decision settings, namely component ordering and/or replacement planning, for which we investigate and improve PdM policies that are commonly utilized in the literature. All policies are evaluated via the data-based estimation of the long-run expected maintenance cost per unit time, using monitored run-to-failure experiments. The policy evaluation enables the estimation of the proposed metric. We employ the metric as an objective function for optimizing heuristic PdM policies and algorithms’ hyperparameters. The effect of different PdM policies on the metric is initially investigated through a theoretical numerical example. Subsequently, we employ four data-driven prognostic algorithms on a simulated turbofan engine degradation problem, and investigate the joint effect of prognostic algorithm and PdM policy on the metric, resulting in a decision-oriented performance assessment of these algorithms.

A Lightweight and Adaptive Knowledge Distillation Framework for Remaining Useful Life Prediction

For prognostics and health management of industrial systems, machine remaining useful life (RUL) prediction is an essential task. While deep learning-based methods have achieved great successes in RUL prediction tasks, large-scale neural networks are still difficult to deploy on edge devices owing to the constraints of memory capacity and computing power. In this paper, we propose a lightweight and adaptive knowledge distillation (KD) framework to alleviate this problem. Firstly, multiple teacher models are compressed into a student model through KD to improve the industrial prediction accuracy. Secondly, a dynamic exiting method is studied to enable an adaptive inference on the distilled student model. Finally, we develop a reparameterization scheme to further lessen the student network. Experiments on two turbofan engine degradation datasets and a bearing degradation dataset demonstrate that our method significantly outperforms the state-of-the-art KD methods and enables the distilled model with an adaptive inference ability.

A denoising semi-supervised deep learning model for remaining useful life prediction of turbofan engine degradation

A denoising semi-supervised deep learning model for remaining useful life prediction of turbofan engine degradation

Attention and Long Short-Term Memory Network for Remaining Useful Lifetime Predictions of Turbofan Engine Degradation

Machine Prognostics and Health Management (PHM) is often concerned with the prediction of the Remaining Useful Lifetime (RUL) of assets. Accurate real-time RUL predictions enable equipment health assessment and maintenance planning. In this work, we propose a Long Short-Term Memory (LSTM) network combined with global Attention mechanisms to learn RUL relationships directly from time-series sensor data. We use the NASA Commercial Modular Aero- Propulsion System Simulation (C-MAPPS) datasets to assess the performance of our proposed method. We compare our approach with current state-of-the-art methods on the same datasets and show that our results yield competitive results. Moreover, our method does not require previous degradation knowledge, and attention weights can be used to visualise temporal relationships between inputs and predicted outputs.

Stacking-based ensemble learning for remaining useful life estimation

Excessive and untimely maintenance prompts economic losses and unnecessary workload. Therefore, predictive maintenance models are developed to estimate the right time for maintenance. In this study, predictive models that estimate the remaining useful life of turbofan engines have been developed using deep learning algorithms on NASA’s turbofan engine degradation simulation dataset. Before equipment failure, the proposed model presents an estimated timeline for maintenance. The experimental studies demonstrated that the stacking ensemble learning and the convolutional neural network (CNN) methods are superior to the other investigated methods. While the convolution neural network (CNN) method was superior to the other investigated methods with an accuracy of 93.93%, the stacking ensemble learning method provided the best result with an accuracy of 95.72%.

LSTM Inefficiency in Long-Term Dependencies Regression Problems

Recurrent neural networks (RNNs) are an excellent fit for regression problems where sequential data are the norm since their recurrent internal structure can analyse and process data for long. However, RNNs are prone to the phenomenal vanishing gradient problem (VGP) that causes the network to stop learning and generate poor prediction accuracy, especially in long-term dependencies. Originally, gated units such as long short-term memory (LSTM) and gated recurrent unit (GRU) were created to address this problem. However, VGP was and still is an unsolved problem, even in gated units. This problem occurs during the backpropagation process when the recurrent network weights tend to vanishingly reduce and hinder the network from learning the correlation between temporally distant events (long-term dependencies), that results in slow or no network convergence. This study aims to provide an empirical analysis of LSTM networks with an emphasis on inefficiency in long-term dependencies convergence because of VGP. Case studies on NASA’s turbofan engine degradation are examined and empirically analysed.

Optimizing the Parameters of Long Short-Term Memory Networks Using the Bees Algorithm

Improving the performance of Deep Learning (DL) algorithms is a challenging problem. However, DL is applied to different types of Deep Neural Networks, and Long Short-Term Memory (LSTM) is one of them that deals with time series or sequential data. This paper attempts to overcome this problem by optimizing LSTM parameters using the Bees Algorithm (BA), which is a nature-inspired algorithm that mimics the foraging behavior of honey bees. In particular, it was used to optimize the adjustment factors of the learning rate in the forget, input, and output gates, in addition to cell candidate, in both forward and backward sides. Furthermore, the BA was used to optimize the learning rate factor in the fully connected layer. In this study, artificial porosity images were used for testing the algorithms; since the input data were images, a Convolutional Neural Network (CNN) was added in order to extract the features in the images to feed into the LSTM for predicting the percentage of porosity in the sequential layers of artificial porosity images that mimic real CT scan images of products manufactured by the Selective Laser Melting (SLM) process. Applying a Convolutional Neural Network Long Short-Term Memory (CNN-LSTM) yielded a porosity prediction accuracy of 93.17%. Although using Bayesian Optimization (BO) to optimize the LSTM parameters mentioned previously did not improve the performance of the LSTM, as the prediction accuracy was 93%, adding the BA to optimize the same LSTM parameters did improve its performance in predicting the porosity, with an accuracy of 95.17% where a hybrid Bees Algorithm Convolutional Neural Network Long Short-Term Memory (BA-CNN-LSTM) was used. Furthermore, the hybrid BA-CNN-LSTM algorithm was capable of dealing with classification problems as well. This was shown by applying it to Electrocardiogram (ECG) benchmark images, which improved the test set classification accuracy, which was 92.50% for the CNN-LSTM algorithm and 95% for both the BO-CNN-LSTM and BA-CNN-LSTM algorithms. In addition, the turbofan engine degradation simulation numerical dataset was used to predict the Remaining Useful Life (RUL) of the engines using the LSTM network. A CNN was not needed in this case, as there was no feature extraction for the images. However, adding the BA to optimize the LSTM parameters improved the prediction accuracy in the testing set for the LSTM and BO-LSTM, which increased from 74% to 77% for the hybrid BA-LSTM algorithm.

Self-Attention Transformer-Based Architecture for Remaining Useful Life Estimation of Complex Machines

Meaningful feature extraction from multivariate time-series data is still challenging since it takes into account the correlation between pairs of sensors as well as the temporal information of each time-series. Meanwhile, the huge industrial system has evolved into a data-rich environment, resulting in the rapid development and deployment of deep learning for machine RUL prediction. RUL (Remaining Useful Life) examines a system's behavior over the course of its lifetime, that is, from the last inspection to when the system's performance deteriorates beyond a certain point. RUL has been addressed using Long-Short-Term Memory (LSTM) and Convolution Neural Network (CNN), particularly in complex tasks involving high-dimensional nonlinear data. The main focus, however, has been on degradation data. In 2021, a new realistic run-to-failure turbofan engine degradation dataset was released, which differs significantly from the simulation dataset. The key difference is that each cycle's flight duration varies, so the existing deep technique will be ineffective at predicting the RUL for real-world degradation data. We present a Self-Attention Transformer-Based Encoder model to address this problem. The encoder with the time-stamp encoder layer works in parallel to extract features from various sensors at various time stamps. Self-attention enables efficient processing of extended sequences and focuses on key elements of the input time series. Self-attention is used in the proposed Transformer model to access global characteristics from diverse time-series representations. Under real-world flight conditions, we conduct tests on turbofan engine degradation data using variable-length input. The proposed approach for estimating RUL of turbofan engines appears to be efficient based on empirical results.

A deep learning-based conditional system health index method to reduce the uncertainty of remaining useful life prediction

Many recent data-driven studies have used sensor profile data for prognostics and health management (PHM). However, existing data-driven PHM techniques are vulnerable to three types of uncertainty: sensor noise inherent to the sensor profile data, uncertainty regarding the current health status diagnosis caused by monitoring a single health index (HI), and uncertainty in predicting the remaining useful life (RUL), which is affected by unpredictable changes in system operating conditions and the future external environment. This study proposes a deep conditional health index extraction network (DCHIEN) for PHM to effectively manage these three types of uncertainty. DCHIEN is a model that combines a stacked denoising autoencoder that extracts high-level features robust to sensor noise with a feed-forward neural network that produces an HI based on user-defined monitoring conditions. This approach supports system health monitoring using the conditional HI, as well as prognostics using RUL interval predictions. Extensive experiments were conducted using NASA’s turbofan engine degradation dataset. The results show that the proposed method achieves a superior RUL prediction performance compared to state-of-the-art methods and that uncertainties can be effectively managed.

A deep learning framework for sensor-equipped machine health indicator construction and remaining useful life prediction

Prognostic and health management (PHM) effectively reduces the economic loss of sensor-equipped machine downtime caused by under-maintenance and the waste of resources resulted from over-maintenance. The remaining useful life (RUL) prediction is the most critical step in PHM. However, accurate RUL prediction in a multiple sensors data environment faces challenges and difficulties. In this paper, we firstly consider the change point where the sensor-equipped machine drifts from a health state (initial stage) to the degradation stage, and combine the deep learning model with the change point to construct the health indicator (HI). Then, a long short-term memory model combined with an attention mechanism (LSTM_Att) is used to iteratively predict the future HI. Additionally, the predicted RUL distribution of the studied sensor-equipped machine is estimated using the similarity method based on the HI data of historical multiple sensor-equipped machines. Then, the confidence interval of RUL is obtained. Finally, the proposed method is verified on the publicly available turbofan engine degradation data set. The experimental results show that the proposed method outperforms the state-of-art benchmark methods.

Shock-Loading-Based Reliability Modeling with Dependent Degradation Processes and Random Shocks

In general, a system deteriorates due to internal physical degradation and external random shocks. Previous studies mainly focused on establishing dependent competing risk models to evaluate mutual effects of degradation processes and random shocks affecting system health. However, there is a lack of consideration about the magnitude of impacts caused by random shocks on degradation processes. Thus, a shock-loading-based degradation model is proposed to classify the magnitude of impacts from random shocks on degradation processes based on the threshold of the cumulative shock loading. Copula methods are utilized to derive joint reliability function from multiple marginal distributions of degradation processes. Two numerical examples are utilized to demonstrate the reliability prediction performance of the proposed model. First, a simulated example is used. The second example employs the turbofan engine degradation data from the NASA Prognostic Data Repository to show the performance of the proposed shock-loading-based degradation process and its corresponding system reliability model.

Investigating the Efficiencies of Fusion Algorithms for Accurate Equipment Monitoring and Prognostics

Recent findings suggest the need for optimal condition monitoring due to increasing counter-productive issues ranging from threats to life, malware, and hardware failures. Several prognostic schemes have been reported across many disciplines; however, the issues of sensor data discrepancy emanating from varying loading and operating conditions of cyber-physical system (CPS) components still remain a challenging factor. Nonetheless, a significant part of these prognostic schemes comprises a sensor/feature fusion module for comprehensive health indicator (HI) construction. This study investigates the prowess of unsupervised fusion algorithms for constructing optimal HI construction on two publicly available datasets—a simulated turbofan engine degradation experiment and an actual production plant condition monitoring dataset. The fusion efficiencies of the algorithms were evaluated using standard metrics for prognostic parameter assessments. The results show that the autoencoder is more reliable for real-life applications, including cases with uniform degradation patterns and the more complex scenarios with irregular degradation paths in the sensor measurements/features, and is expected to direct continued research for improved multi-sensor-based prognostics and health management of industrial equipment.

A Deep Learning Model for Remaining Useful Life Prediction of Aircraft Turbofan Engine on C-MAPSS Dataset

In the era of industry 4.0, safety, efficiency and reliability of industrial machinery is an elementary concern in trade sectors. The accurate remaining useful life (RUL) prediction of an equipment in due time allows us to effectively plan the maintenance operation and mitigate the downtime to raise the revenue of business. In the past decade, data driven based RUL prognostic methods had gained a lot of interest among the researchers. There exist various deep learning-based techniques which have been used for accurate RUL estimation. One of the widely used technique in this regard is the long short-term memory (LSTM) networks. To further improve the prediction accuracy of LSTM networks, this paper proposes a model in which effective pre-processing steps are combined with LSTM network. C-MAPSS turbofan engine degradation dataset released by NASA is used to validate the performance of the proposed model. One important factor in RUL predictions is to determine the starting point of the engine degradation. This work proposes an improved piecewise linear degradation model to determine the starting point of deterioration and assign the RUL target labels. The sensors data is pre-processed using the correlation analysis to choose only those sensors measurement which have a monotonous behavior with RUL, which is then filtered through a moving median filter. The updated RUL labels from the degradation model together with the pre-processed data are used to train a deep LSTM network. The deep neural network when combined with dimensionality reduction and piece-wise linear RUL function algorithms achieves improved performance on aircraft turbofan engine sensor dataset. We have tested our proposed model on all four sub-datasets in C-MAPSS and the results are then compared with the existing methods which utilizes the same dataset in their experimental work. It is concluded that our model yields improvement in RUL prediction and attains minimum root mean squared error and score function values.

An Unsupervised Noisy Sample Detection Method for Deep Learning-Based Health Status Prediction

Due to rough environment or data-acquisition equipment failure, the machine monitoring data may be contaminated with noise, which may lead to the generation of noisy samples. For the widely used deep learning-based prediction model, some noisy samples (with low-intensity noise) may improve model generalization while some noisy samples (with high-intensity noise) may hamper the prediction models. To detect the noisy samples that hamper the prediction models, an unsupervised noisy sample detection method is proposed, thereby promoting the accuracy of the deep learning-based prediction model. First, the transforming model with an attention mechanism is built to transform the multivariate input sequences of samples to attention weight vectors, which are related to the prediction task. Then, a clustering method without hyperparameters is proposed to cluster these attention weight vectors and the hierarchy of clusters is created. Afterward, the noisy samples that hamper the prediction models are detected and removed based on the clustering thresholds, and a prediction model with higher prediction accuracy can thus be obtained. The effectiveness of the proposed method is verified using a simulated turbofan engine degradation dataset and a real milling machine monitoring dataset. The results show that the prediction errors for the two datasets have been reduced by 13.44% and 12.97% on average after removing the noisy samples detected by the proposed method. The comparison results show that the proposed method outperforms other methods in terms of improving the prediction accuracy.

Data-driven prognostics method for turbofan engine degradation using hybrid deep neural network

Data-driven prognostics method for turbofan engine degradation using hybrid deep neural network

Проверка значимости случайного эффекта для винеровской деградационной модели

This paper considers the Wiener degradation model with random effects. Random-effect models take into account the unit-to-unit variability of the degradation index. It is assumed that a random parameter has a truncated normal distribution. During the research, the expression for the maximum likelihood estimates and the reliability function has been obtained. Two statistical tests have been proposed to reveal the existence of random effects in degradation data corresponding to the Wiener degradation model. The first test is a well-known likelihood ratio test, and the second one is based on the variance estimate of the random parameter. These tests have been compared in terms of power with the Monte-Carlo simulation method. The result of the research has shown that the criterion based on the variance estimate of the random parameter is more powerful than the likelihood ratio test in the case of the considered pairs of competing hypotheses. An example of the analysis using the proposed tests for the turbofan engine degradation data has been considered. The data set includes the measurements recorded from 18 sensors for 100 engines. Before constructing the degradation model, the single degradation index has been obtained using the principal component method. The hypothesis of the random effect insignificance in the model has been rejected for both tests. It has been shown that the random-effect Wiener degradation model describes the failure time distribution more accurately than the fixed-effect Wiener degradation model.

ER rule classifier with an optimization operator recommendation

It is difficult for many classic classification methods to consider expert experience and classify small-sample datasets well. The evidential reasoning rule (ER rule) classifier can solve these problems. The ER rule has strong processing and comprehensive analysis abilities for diversified mixed information and can solve problems with expert experience effectively. Moreover, the initial parameters of the classifier constructed based on the ER rule can be set according to empirical knowledge instead of being trained by a large number of samples, which can help the classifier classify small-sample datasets well. However, the initial parameters of the ER rule classifier need to be optimized, and choosing the best optimization algorithm is still a challenge. Considering these problems, the ER rule classifier with an optimization operator recommendation is proposed in this paper. First, the initial ER rule classifier is constructed based on training samples and expert experience. Second, the adjustable parameters are optimized, in which the optimization operator recommendation strategy is applied to select the best algorithm by partial samples, and then experiments with full samples are carried out. Finally, a case study on a turbofan engine degradation simulation dataset is carried out, and the results indicate that the ER rule classifier has a higher classification accuracy than other classic classifiers, which demonstrates the capability and effectiveness of the proposed ER rule classifier with an optimization operator recommendation.

Two-phase degradation modeling and remaining useful life prediction using nonlinear wiener process

Remaining useful life (RUL) is an essential part of prognostic and health management, which can be employed to enhance the reliability and reduce the maintenance cost. For many products, due to the change of external operating conditions and internal mechanisms, their degradation trajectories tend to exhibit two-phase patterns. In the current method, linear Wiener process is used in each phase for degradation modeling and RUL prediction. In practice, the degradation process of each phase exhibits nonlinear characteristics, where using linear Wiener process to establish two-phase model is often inadequate. In this paper, a novel approach for two-phase degrading product is proposed. A degradation model using nonlinear Wiener process is adopted to characterize the two-phase degradation trajectory firstly. The maximum likelihood estimation (MLE) is used to estimate the unknown parameters of proposed model and Bayesian method is employed for updating the parameters. Taking into account the randomness of the initial state transition to the changing state and the variability in different units degradation, the approximate analytical solution of RUL under the concept of the first passage time is derived. Finally, the effectiveness of the proposed RUL prediction method is demonstrated through a simulation study and a turbofan engine degradation dataset.