Figure 1 - available via license: Creative Commons Attribution 4.0 International
Content may be subject to copyright.
Source publication
The accurate prediction of airplane engine failure can provide a reasonable decision basis for airplane engine maintenance, effectively reducing maintenance costs and reducing the incidence of failure. According to the characteristics of the monitoring data of airplane engine sensors, this work proposed a remaining useful life (RUL) prediction mode...
Contexts in source publication
Context 1
... LSTM network extracts the internal relationship of long time series through the input gate, output gate and the forgetting gate, which is effective in dealing with a long-term dependence problem. Its basic unit structure diagram is shown in Figure 1. As can be seen from the figure above, the stacked values of a t−1 and x t are copied into four copies, and they are input into different doors. ...
Context 2
... Figure 1, i t , f t and o t respectively represent the operation results of the input gate, forget gate and output gate; W f , W i , W c and W o respectively represent the weight matrix of each part; b is the bias vector of each part; σ and tanh represent sigmoid function and hyperbolic tangent function respectively; h t represents for output; C t represents the candidate value of the current cell state; C t represents the updated cell status value. ...
Similar publications
Intelligent transportation systems (ITS) play an important role in the quality of life of citizens in any metropolitan city. Despite various policies and strategies incorporated to increase the reliability and quality of service, public transportation authorities continue to face criticism from commuters largely due to irregularities in bus arrival...
Citations
... Long short-term memory neural network (LSTM) basic unit structure diagram[28]. ...
... In order to deal with the problem of hinge deformation of the aircraft braking system, Wang et al. further explored spatial transient patterns on the thermal pattern comparison results based on eddy current pulse thermal imaging by constructing principal component analysis to obtain better fault diagnosis results [19]. Ji et al. proposed a remaining service life prediction model based on principal component analysis and bidirectional long short-term memory neural network, which shows better prediction accuracy in engine failure prediction compared to other types of methods [20]. Support vector machine (SVM) is a binary classification model. ...
With the development of modern aviation technology, how to ensure the stability of the air cargo process and how to ensure the safety of the aircraft has always been one of the important issues of concern to the air transport industry. During actual transportation, aircraft often lose control due to their own mechanical failures or system failures. In order to solve this problem, based on a comprehensive survey of relevant literature on aircraft fault diagnosis, a classification and introduction of related research was conducted based on different data-driven methods. This review is expected to provide a useful reference for research on aircraft fault diagnosis.
... Rosa et al. [29] introduced a generic fault prognosis framework employing LSTM-based autoencoder feature learning methods, emphasizing the semi-supervised extrapolation of reconstruction errors to address imbalanced data in an industrial context. Ji et al. [30] proposed a hybrid model for accurate airplane engine failure prediction, integrating principal component analysis (PCA) for feature extraction and BiLSTM for learning the relationship between the sensor data and RUL. Peng et al. [31] introduced a dual-channel LSTM neural network model for predicting the RUL of machinery, addressing challenges related to noise impact in complex operations and diverse abnormal environments. ...
The accurate estimation of the remaining useful life (RUL) for aircraft engines is essential for ensuring safety and uninterrupted operations in the aviation industry. Numerous investigations have leveraged the success of the attention-based Transformer architecture in sequence modeling tasks, particularly in its application to RUL prediction. These studies primarily focus on utilizing onboard sensor readings as input predictors. While various Transformer-based approaches have demonstrated improvement in RUL predictions, their exclusive focus on temporal attention within multivariate time series sensor readings, without considering sensor-wise attention, raises concerns about potential inaccuracies in RUL predictions. To address this concern, our paper proposes a novel solution in the form of a two-stage attention-based hierarchical Transformer (STAR) framework. This approach incorporates a two-stage attention mechanism, systematically addressing both temporal and sensor-wise attentions. Furthermore, we enhance the STAR RUL prediction framework by integrating hierarchical encoder–decoder structures to capture valuable information across different time scales. By conducting extensive numerical experiments with the CMAPSS datasets, we demonstrate that our proposed STAR framework significantly outperforms the current state-of-the-art models for RUL prediction.
... Rosa et al. [27] introduced a generic fault prognosis framework employing LSTM-based autoencoder feature learning methods, emphasizing semi-supervised extrapolation of reconstruction errors to address imbalanced data in an industrial context. Ji et al. [28] proposed a hybrid model for accurate airplane engine failure prediction, integrating principal component analysis (PCA) for feature extraction and BiLSTM for learning the relationship between sensor data and RUL. Peng et al. [29] introduced a dual-channel LSTM neural network model for predicting the RUL of machinery, addressing challenges related to noise impact in complex operations and diverse abnormal environments. ...
Accurate estimation of Remaining Useful Life (RUL) for aircraft engines is essential for ensuring safety and uninterrupted operations in the aviation industry. Numerous investigations have leveraged the success of attention-based Transformer architecture in sequence modeling tasks, particularly in its application to RUL prediction. These studies primarily focus on utilizing onboard sensor readings as input predictors. While various Transformer-based approaches have demonstrated improvement in RUL predictions, their exclusive focus on temporal attention within multivariate time series sensor readings, without considering sensor-wise attention, raises concerns about potential inaccuracies in RUL predictions. To address this concern, our paper proposes a novel solution in the form of a two-stage attention based hierarchical transformer (STAR) frame-work. This approach incorporates a two-stage attention mechanism, systematically addressing both temporal and sensor-wise attentions. Furthermore, we enhance the STAR RUL prediction framework by integrate hierarchical encoder-decoder structures to capture valuable information across different time scales. By conducting extensive numerical experiments with the CMAPSS datasets, we demonstrate that our proposed STAR framework significantly outperforms current state-of-the-art models for RUL prediction.
... PCA is used in [113] to conduct a data reduction process to lower the dimensionality of a dataset used for aircraft engine diagnostics. The dimensionality reduction capabilities of PCA are also employed in [114] with the goal of predicting the Remaining Useful Life (RUL) of airplane engines. ...
Maintenance is crucial for aircraft engines because of the demanding conditions to which they are exposed during operation. A proper maintenance plan is essential for ensuring safe flights and prolonging the life of the engines. It also plays a major role in managing costs for aeronautical companies. Various forms of degradation can affect different engine components. To optimize cost management, modern maintenance plans utilize diagnostic and prognostic techniques, such as Engine Health Monitoring (EHM), which assesses the health of the engine based on monitored parameters. In recent years, various EHM systems have been developed utilizing computational techniques. These algorithms are often enhanced by utilizing data reduction and noise filtering tools, which help to minimize computational time and efforts, and to improve performance by reducing noise from sensor data. This paper discusses the various mechanisms that lead to the degradation of aircraft engine components and the impact on engine performance. Additionally, it provides an overview of the most commonly used data reduction and diagnostic and prognostic techniques.
... The possible volume of data collected at all stages of the GTE LC is measured by terabytes or, in some cases, petabytes. Therefore, an actual task is to process these data to design the predictive models at the stage of GTE testing [33,34]. ...
The task of choosing the modes and duration of life tests of complex technical objects, such as aircraft engines, is a complex and difficult-to-formalize task. Experimental optimization of the parameters of life tests of complex technical objects is costly in terms of material and time resources, which makes such an approach to the choice of test parameters practically difficult. The problem of life test optimization for gas turbine engines on the basis of the engine life cycle information support and statistical modeling is discussed. Within the framework of the research, the features of the optimization of life tests based on simulation modeling of the life cycle of gas turbine engines were studied. The criterion of the efficiency of the life tests was introduced, and this characterized the predicted effect (technical and economic) of the operation of a batch of engines, the reliability of which was confirmed by life tests; a method of complex optimization of resource tests in the life cycle system was developed. An objective function was formed for the complex optimization of life tests based on life cycle simulation. The principles of formation and refinement of the simulation model of the life cycle for the optimization of life tests were determined. A simulation model of the main stages of the life cycle of an auxiliary gas turbine engine was developed. A study was performed on the influence of the quality of the production of “critical” engine elements, the system of engine acceptance and shipment, as well as the effect of a range of parameters of the engine loading mode on the efficiency of the life tests of an auxiliary gas turbine engine. The optimal parameters of periodic life tests of an auxiliary gas turbine engine were determined by simulation modeling in the life cycle system, which made it possible to increase the equivalence of tests by several times and reduce their duration in comparison with the program of serial tests.
... Wu et al. [20] calculated power values on a sensitive frequency band (SFB) of bearings as a degradation indicator. Ji et al. [21] used a principal component analysis (PCA) for feature extraction to eliminate useless information and noise. Zhang et al. [22] translated the multi-dimension sensor data of aircraft engines to the dimensionless health index using a single-layer perceptron called a data generator. ...
Prognostic and health management (PHM) of plastic gears has attracted attention due to an increasing performance of plastic gears, uncovering potential applications in the industry, especially in vehicle transmissions. Meanwhile, health indicator (HI) construction and remaining useful life (RUL) estimation are two key elements to efficiently perform PHM. In this paper, a health indicator generator (HIG) based on an artificial neural network (ANN) is constructed. The HIG is learned from training data extracted from plastic gears’ raw vibration data using the Fourier decomposition method (FDM) in a sensitive frequency band (SFB) and labeled using a change-point detection algorithm (CDA). Three prediction strategies, including linear regression (LR), estimation of parameters for Weibull distribution (EWD), HI combined average RUL (HI-ARUL), are deployed using HI generated from HIG to predict the RUL of the plastic gear. The results show that the generated HI is sensitive to the early failure of plastic gears and is capable of applying an efficient and precise diagnosis method, which can be performed during the whole working time of plastic gear with prediction errors smaller than 7%.
... By calculating the cumulative contribution of the features, an acceptable threshold kpca is determined for selecting the desirable features using Equation (22). All of the features calculated by KPCA are ranked in descending order of the contribution rate of each feature, and when the first q features' cumulative contribution rate T reaches this threshold kpca , the first q features are formed into a new optimal feature set. ...
... By calculating the cumulative contribution of the features, an acceptable threshold σ kpca is determined for selecting the desirable features using Equation (22). All of the features calculated by KPCA are ranked in descending order of the contribution rate of each feature, and when the first q features' cumulative contribution rate η T reaches this threshold σ kpca , the first q features are formed into a new optimal feature set. ...
Remaining useful life prediction is one of the essential processes for machine system prognostics and health management. Although there are many new approaches based on deep learning for remaining useful life prediction emerging in recent years, these methods still have the following weaknesses: (1) The correlation between the information collected by each sensor and the remaining useful life of the machinery is not sufficiently considered. (2) The accuracy of deep learning algorithms for remaining useful life prediction is low due to the high noise, over-dimensionality, and non-linear signals generated during the operation of complex systems. To overcome the above weaknesses, a general deep long short memory network-based approach for mechanical remaining useful life prediction is proposed in this paper. Firstly, a two-step maximum information coefficient method was built to calculate the correlation between the sensor data and the remaining useful life. Secondly, the kernel principal component analysis with a simple moving average method was designed to eliminate noise, reduce dimensionality, and extract nonlinear features. Finally, a deep long short memory network-based deep learning method is presented to predict remaining useful life. The efficiency of the proposed method for remaining useful life prediction of a nonlinear degradation process is demonstrated by a test case of NASA’s commercial modular aero-propulsion system simulation data. The experimental results also show that the proposed method has better prediction accuracy than other state-of-the-art methods.
... LSTM is a kind of recurrent neural network (RNN) with a special structure. Compared with the traditional RNN, the hidden layer unit in LSTM is a linear self-cyclic memory block, which contains three gate structures, which allows the gradient to pass through a long sequence, solves the vanishing gradient problem, and overcomes the shortcomings of the RNN model [25]. The basic structural unit of the LSTM network is shown in Figure 4. ...
Electrostatic probe diagnosis is the main method of plasma diagnosis. However, the traditional diagnosis theory is affected by many factors, and it is difficult to obtain accurate diagnosis results. In this study, a long short-term memory (LSTM) approach is used for plasma probe diagnosis to derive electron density (Ne) and temperature (Te) more accurately and quickly. The LSTM network uses the data collected by Langmuir probes as input to eliminate the influence of the discharge device on the diagnosis that can be applied to a variety of discharge environments and even space ionospheric diagnosis. In the high-vacuum gas discharge environment, the Langmuir probe is used to obtain current–voltage (I–V) characteristic curves under different Neand Te. A part of the data input network is selected for training, the other part of the data is used as the test set to test the network, and the parameters are adjusted to make the network obtain better prediction results. Two indexes, namely, mean squared error (MSE) and mean absolute percentage error (MAPE), are evaluated to calculate the prediction accuracy. The results show that using LSTM to diagnose plasma can reduce the impact of probe surface contamination on the traditional diagnosis methods and can accurately diagnose the underdense plasma. In addition, compared with Te, the Ne diagnosis result output by LSTM is more accurate.
... Deep RNNs based on long short-term memory networks (LSTM) have also shown excellent results with regard to the prognostics problem [7,8,10,36,42]. Therefore, we also adopted a deep LSTM architecture as an RNN model. ...
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.
