Search

In order to maximise fuel cell reliability of operation and useful life span, an accurate online health assessment of the fuel cell system is essential. Existing algorithms for fault detection in fuel cell systems are based on sensing elements, control methods, and statistical/probabilistic models. In this paper, an artificial neural network (ANN) will be developed to detect and classify faults in proton-exchange membrane (PEM) fuel cell systems. As the ANN model developed within the PEM system relies on the input and output current and voltage, additional sensing devices are not required within the system. Based on an experimental setup using a 3-kW fuel cell system, it was found that the proposed model was able to detect faults associated with the reduction/increase of fuel pressure, H 2 consumption rate, and voltage regulation changes in the dc-dc converter with >90% accuracy. In the proposed model, historical data is required to train and validate the ANN algorithm, but after this is complete, no human intervention is required afterward. [Display omitted] • An ANN-based algorithm for identifying faults in PEM fuel cells. • Voltage regulation of dc-dc converters, fuel pressure, and hydrogen consumption rate can be detected. • A 3-kW fuel cell system was used to demonstrate the effectiveness of the ANN model. • The detection accuracy rate is always over 90% for all seven types of faults considered. • Performance of the ANN algorithm is compared with that of classical methods. [ABSTRACT FROM AUTHOR]

Modeling and recognizing events in complex systems through machine learning techniques is a challenging task. Especially if the model is constrained to be explainable and interpretable, while ensuring high levels of accuracy. In this paper, we adopt a bilinear logistic regression model in which the parameters are trained in a data-driven fashion on a real-world dataset of power grid failure data. The bilinear white-box model – grounded on a specific neural architecture – has been proven effective in classifying faulty states with a performance comparable to several classifiers in technical literature. Additionally, the low computational complexity of the bilinear model, in terms of the number of free parameters, allows gaining insights into the fault phenomenon correlating the events that impact the power grid (exogenous causes) with its constitutive characteristics, thence eliciting the relational information hidden in the data. The proposed model is also able to estimate a vulnerability vector that can be associated, as a suitable characteristic "label", to power grid components, opening the way, as will be deeply demonstrated in the following, not only to predictive maintenance programs or condition monitoring tasks but also to risk assessment and scenario analyses in line with the explainable AI paradigm. • Introduced a bilinear logistic regression model trained on real-world power grid failure data for grid reliability assessment. • Emphasized the role of explainable AI in power grid analysis, highlighting the interpretability of the proposed model. • Developed a method to estimate a vulnerability vector for power grid components and a deep analysis related to the computed weight correlation matrix. • Stressed the importance of semantic specification in modeling complex systems. [ABSTRACT FROM AUTHOR]

The photovoltaic (PV) array is the most sensible element in PV plants, which is subject to different type of faults and defects. Thus, to keep these plants working efficiently they should be monitored and protected carefully. Some faults if they are not detected and isolated promptly they may lead to hazardous risks. The diagnosis of PV systems is widely addressed and recently machine learning (ML) and deep leaning (DL) methods drawn the attention of many researchers. Most applications of ML methods are based on the use of the I–V curves measurement, as enough information and features can be extracted from the curves, to detect and classify faults. These methods showed their capability to classify some faults, like line to line, degradation, disconnected PV modules, partial shading effect, and bypass diode faults. Another approach is based on the use of thermal or electroluminescence images of PV modules/arrays to detect and identify defects, such as hot spot, snails crack, and others. In this paper, different ML and ensemble learning (EL) methods are evaluated for fault diagnosis of PV arrays. The focus is mainly on the detection and classification of some complex faults that may affect the PV arrays, i.e., multiple faults, and faults with similar I–V curves, that are not evaluated before. The results showed the ability of the methods developed to detect faults with very good accuracy (classification rate = number of classified instances/total instances), within 99%, while the classification faults is done with an acceptable accuracy, within 81.73%. Through this study it is shown when really ML and EL methods should be used, and some recommendations, challenges and future directions in this topic are presented. [ABSTRACT FROM AUTHOR]

The low fault current contribution from inverter-interfaced distributed generators (IIDGs) and bidirectional flow of current in the power networks introduces protection challenges when islanded. The existing fault detection scheme based on the transient monitoring function (TMF) fails under such scenarios. A new decentralised machine learning (ML) based fault detection and classification scheme is proposed in this paper using terminal voltage information of IIDG (v o−abc). TMF of v o−abc , along with the zero sequence component of v o−abc , is utilised for training and testing of ensemble bagged trees ML algorithm. The proposed scheme is implemented inside each IIDG, and hence, it does not require communication. It is validated on a modified CIGRE test benchmark microgrid for all shunt faults at various locations with different loading, fault resistances, and inception angles. The accuracy of detection and classification of fault (DCF) during fault cases with unbalanced loads, noise, harmonic loads, and no-fault scenarios such as load and DG switching proves the effectiveness of the proposed method with varying scenarios. The performance of the proposed scheme is found to be superior when compared with the existing threshold based TMF and Hilbert–Huang transform (HHT) based techniques considering accuracy, dependability, security, and response time. • Queries by all the reviewer 3 are addressed in details. • Made suitable changes to the introduction to bring in more clarity. [ABSTRACT FROM AUTHOR]

Deep learning-based incipient fault diagnostic techniques have achieved surprisingly well in wind turbines. Due to component failures, wind turbines must undergo active maintenance, substantially influencing revenue and power generation. Unfortunately, there are consistently uneven data distributions between samples with faults and those without faults, resulting in incorrect fault classification. Wind turbine fault classification has a significant data imbalance problem, compromising learning attention for majority and minority classes. Machine learning methodologies based on Generative Adversarial Networks (GAN), over-sampling, and under-sampling techniques for generating synthetic data have been widely employed to address the imbalance data problem. However, the traditional synthetic minority oversampling technique (SMOTE) accomplishes oversampling using linear interpolation between close minority class samples, which could be confusing, subpar, and indistinguishable from the majority class. This study suggests combining over and under-sampling using adaptive SMOTE and edited nearest neighbors (ASMOTE-ENN) that incorporate over-sampling with adaptive SMOTE and under-sampling with ENN to improve the quality of the generated samples. With this resampling technique, noise in an imbalanced dataset is reduced on three levels by using an adaptive nearest neighbor selection algorithm to find the nearest neighbors that are visible. Then use SMOTE to create samples that precisely fall into the minority class, and later use the ENN technique to eliminate instances that contribute to noise afterwards. Resampling data created by combining over- and under-sampling approaches to match the data distribution over all classes is the foundation of the suggested method's efficacy. A hybrid ensemble method is used for effective classification, including boosting, bagging, and stacking techniques. The original unbalanced and balanced data using the ASMOTE-ENN algorithm were classified using the proposed hybrid ensemble method. The classification results show that the proposed strategy is more accurate than a few imbalanced fault diagnosis techniques. • To gain complete knowledge, characteristics of SCADA data are obtained using data analysis. • We present the adaptive SMOTE-ENN algorithm-based data resampling technique to deal with imbalanced data. • Create a hybrid ensemble classification technique to identify faulty and no-fault events effectively. • The results demonstrate that the suggested method outperforms the most popular ML techniques. [ABSTRACT FROM AUTHOR]

Residential air-conditioning systems are subject to soft faults, which can reduce their efficiency, capacity, and life expectancy, without being detected by the occupants. Early detection and diagnosis of faults could potentially be done by using machine learning (ML) on measurable features of the air-conditioner, such as refrigerant temperatures and pressures. This paper describes a novel approach to applying ML, which is to train a fault classifier using data from one system, and apply it to different systems. If this is effective, it can significantly reduce the cost of widescale application of ML fault classification. The support vector machine (SVM) algorithm was used. An additional question for practical application is whether the number of sensors required for input feature measurement can be reduced. This work also tests the feature reduction effect, in combination with applying an ML classifier trained on one system, to classify faults in two other systems. The results are disappointing, showing that fault classification is poor when the SVM classifier is trained on a different system than it is applied to. However, with additional work, this method has potential for improvement, possibly to a point where it can be a viable approach for field deployment. [ABSTRACT FROM AUTHOR]

Highlights • A complementary fault classification stage for Thermal NDT-E of electrofusion PE joints. • Combined heat pulsing, IR imaging, and machine learning for classification accuracy. • The ovality diagnosis was more accurate than unalignment fault. • GLMNet (93.75%) was the best classifier, followed by Random Forests (84.21%) and k-means (70.37%). Abstract The capability of conveniently classifying the fault types in the electrofusion joints can certainly increase the security of polyethylene gas pipelines. Therefore in the current study, we use machine learning to push the horizons of our recent thermal pulsing and IR thermography method, to identify ovality versus unalignment faults. To do so, we extend our experimental IR-thermography data bank and then apply k -means, Random Forests and GLMNet algorithms in a two stage approach. The overall classification accuracy for k -means and Random Forests were 70.37% and 84.21% respectively; GLMNet could successfully outperform the others with a classification accuracy of 93.75%. [ABSTRACT FROM AUTHOR]

The fault classification of chemical processes based on supervised learning generally demands for enough labeled fault samples, which represents a big challenge for practical engineering issues. In the industrial field, when capturing an appearance of process abnormities, human operators usually take account of correlations of relevant variables so as to locate process variables associated with the abnormity before further classifying or diagnosing the corresponding faults. In this context, accurate abnormity localizations can be an effective help for classifying the fault type. Nowadays, deep learning based fault classifications have been extensively studied and widely circulated in the literature. However, the existing approaches rarely concern the supporting role of abnormity locations for fault classifications. Motivated by this observation, this paper proposes a multi-task learning (MTL) based convolutional neural network (CNN) model for concurrent abnormity locations and fault classifications for chemical processes. Specifically, fault samples are labeled with both abnormal variable locations and fault categories before constructing a multi-task learning CNN classifier performing an auxiliary task, abnormity locations, and a primary task, fault classifications. In addition, dynamic task weights are assigned to facilitate task contributions. This method can enjoy effectively reducing the necessary amounts of labeled fault samples in achieving satisfactory fault classification performances. Experiments are carried out on the TE process simulation platform and an industrial coal gasification plant along with comparisons with conventional fault classification methods, verifying the effectiveness of the proposed method. • A CNN model based on multi-task learning is proposed to better adapt to fault diagnosis of chemical industrial processes. • An adaptive multitask learning algorithm is proposed to balance the multi-task training process effectively. • Abnormity locations can improve the accuracy of fault classification and the convergence of the overall network training. • Abnormity locations task branches can share tags to the primary task thus reducing the impact of insufficient fault labels. • Future potentiality: Since MTL method doesn't require architectural constraints, it can be applied to other neural networks. [ABSTRACT FROM AUTHOR]

• Fault classification and localization are carried out in a photovoltaic system. • A multi-output scalable machine- and deep-learning approach is developed. • A 50% reduction in the number of sensors needed per string is achieved. • Deep Learning models are more resilient to noise and are more accurate. • Accuracy up to 99.98% and cross-entropy loss as low as 0.002 are attained. Fault classification and localization are imperative to maintaining an efficient photovoltaic (PV) system. Due to the environmental factors that PV systems function in, they can be prone to multiple types of fault conditions such as string-to-string (SS), string-to-ground (SG), and open-circuit faults (OC). If left undetected, these faults can lead to power loss and eventually system failures. To help mitigate such outcomes, this paper presents an approach to detect, classify, and locate SS, SG, and OC faults using multi-output deep learning (DL) algorithms: convolutional neural networks (CNN), long short-term memory (LSTM), and bi-directional long short-term memory (Bi-LSTM) networks. The proposed approach reduces the number of sensors needed per string by 50% compared to the previous approaches in the literature. It also allows for increased scalability and the development of a multi-label dataset through an uncoupled modeling scheme. Fault classification and location are achieved with accuracies of 99.94% and 99.54%, respectively. Further, a comparison is conducted among the proposed DL and conventional machine learning algorithms using multiple evaluation metrics. The proposed method is validated by testing multiple datasets and adding noise. The results obtained reflect high reliability and demonstrate the effectiveness and scalability of the proposed multi-output DL approach. [ABSTRACT FROM AUTHOR]

Attention Mechanism has become very popular in the field of mechanical fault diagnosis in recent years and has become an important technique for scholars to study and apply. The introduction of Attention Mechanism can help models achieve efficient resource allocation, improve the remote information capture capability of models, and significantly improve the performance of models for various equipment health management tasks (fault classification, life prediction, etc.) The application of Attention Mechanism in machinery has achieved fruitful research results, but there is a lack of related reviews. In order to facilitate later scholars to quickly grasp the Attention Mechanism and select the appropriate technique, this paper reviews the relevant research and applications of Attention Mechanism in Intelligent Fault Diagnosis of Machinery. Based on the methods proposed in the collected literature, this paper classifies and analyzes them from multiple perspectives to help readers grasp the development status and trends in this field. We divide the collected technologies into three categories: Recurrent-based, Convolution-based, and Self-attention-based. We describe each attention technique and its application scenarios in detail. Finally, we summarize the advantages and disadvantages of various AM techniques, and further discuss the possible future directions of attention mechanisms in the mechanistic field. The purpose of this paper is to provide a comprehensive reference for researchers and to help them find further research directions. [ABSTRACT FROM AUTHOR]

Faults in transmission lines can cause several problems to transmission utilities. An adequate diagnosis of such events can improve service restoration time and, consequently, asset availability. This work proposes a machine learning-based approach to diagnose transmission line faults. The oscillography files of the fault case are processed and applied to four different classifiers, which must identify: phases involved, electrical nature, impedance level, and, fault cause. The method, which is inherently robust regarding signal noise and lack of synchronization between relays, combines Decision Trees, feature engineering, and optimization to perform the fault diagnosis based only on relay measures. It was tested in two fault data sets, one containing 24,000 faults generated using a Real Time Digital Simulator and another one with 46 real faults. The results obtained were very promising, with accuracy values close to 100% for involved phase and fault nature, 90% for impedance level, and 80% for fault cause. [Display omitted] • A ML approach is proposed for comprehensive fault diagnosis in transmission lines. • Fault phases, nature, impedance, and cause are inferred from oscillographs. • The approach is very robust regarding noise and lack of synchronism between relays. • It relies on very few adjustable parameters. Most internal parameters are optimized. • Results on RTDS simulated and real fault cases are provided. [ABSTRACT FROM AUTHOR]

• Various types of faults are classified by the proposed optimal intelligent method. • Wavelet packet transform is used successfully to extracts the set of features. • A ELM classifier based fault detection method is proposed for binary classification of fault and non-fault conditions. • Equilibrium optimizer algorithm is applied to enhance the ELM classifier performance. A novel intelligent scheme using the wavelet packet transform (WPT) and extreme learning machine (ELM) is proposed for fault event classification in the grid-connected photovoltaic (PV) system. The WPT is applied for preprocessing the cycle of the post-fault voltage samples at the point of common coupling (PCC) measurement to get the normalized logarithmic energy entropy (NLEE). The ELM is applied to classify the different fault cases. To enhance the performance of ELM for faults classification, a hybrid optimization mechanism based on an equilibrium optimization algorithm (EOA) is proposed to optimize the selection of input feature subset and the number of ELM hidden nodes. Furthermore, to evaluate the proposed scheme's performance, a comprehensive evaluation was conducted on a 250 kW grid-connected photovoltaic system. From simulation, the classification accuracy is recorded to be 100% under the no-noise condition, while at the signal-to-noise ratios (SNR) of 30, 35, and 40 dB, the accuracies are 98.96, 99.04, and 99.36%, respectively. Moreover, the practical performance of the EOA-ELM classifier is validated using IEEE 34 bus system. The obtained results validate the effectiveness of the proposed scheme in terms of robustness against measurement noise, computation time, and detection accuracy. [ABSTRACT FROM AUTHOR]

• Propose a stacking based data-driven model, to identify the fault type and location in a distribution system, including PV units and their stochastic nature. • All types of faults including faulty phase or phases, along with the no fault conditions (NF) are classified in three-phase test distribution systems with superior performance. • Detect low and high impedance faults. • Develop a straightforward yet accurate approach which requires only voltage measurements in some buses to identify and determine the type and location of the fault (without the need to further preprocessing stage of the input data). • Enhance the accuracy of the predictions comparing to individual machine learning models. This paper proposes an ensemble learning-based method to determine the type and location of faults in a smart distribution network. The employed scheme is a stacking based method that consists of two main levels, each of which includes one or more independent classifiers. In the structure of the proposed method for first level, multiclass support vector machine, K-nearest neighbors and random forest models are exploited. Also, for the next (final) level, which is also called meta-classifier, a random forest based model has been used, which itself is a kind of ensemble learning method. In order to supply the data used to feed the model, the voltage and current measurements in some buses and lines have been used. The proposed model is tested using the data related to all different types and location of faults and operating conditions in the IEEE 123-bus network. Besides, the model is implemented on another distribution test system to consider wider range and specs for fault parameters and also to comprise with other methods applied to it; high impedance faults are also regarded in this part. The obtained results show the appropriate accuracy of the proposed model and its better performance than other considered methods. [ABSTRACT FROM AUTHOR]

As support to fault location algorithms, this paper presents a new method for detecting and classifying faults in active distribution networks using the energy moving averages of the current signals measured at the feeder head. A proposal for updating the energy thresholds for fault detection is introduced, aiming to achieve higher sensitivity in fault detection, especially for scenarios with high penetration levels of distributed generation (DG). Since the power injected by DG can rapidly change, this proposal is essential for maintaining the fault detection method's reliability. Also, the fault classification is based on an analytical approach, making it possible to be easily applied to different operating scenarios of a distribution system. Thus, its potential for real-world implementation is higher when compared to classifiers based on supervised learning algorithms. Performance tests on the IEEE 34-node test feeder showed that this method is reliable for detecting and classifying different fault types, with diverse generation-load scenarios and noisy signals. • Detection thresholds are adaptive to increase detection sensitivity. • Fault classification is based on a simple analytical approach. • The method uses only the current measurements at the feeder head to diagnose faults. • The method is applicable for active distribution networks. [ABSTRACT FROM AUTHOR]

Abstract: This article studies if machine faults can be effectively determined in a reduced dimensional space. When faults occur in machines, machine vibration signals will deviate from its normal signal pattern. Such changes can be reflected in the features constructed from the machine signals. In this article, 13-dimension feature data set is constructed to represent different health conditions of machines, and unsupervised learning algorithms are introduced to deal with feature data sets for feature extraction and fault classification. A weighted local and global regressive mapping (WLGRM) algorithm is proposed for machine fault classification. Two synthetic fault data sets and two experimental data sets are employed to validate the effectiveness of the proposed approach. Comparative analysis with other unsupervised learning algorithms, such as local and global regressive mapping, locality preserving projection, Isomap, principal component analysis, and Sammon mapping, are reported. The results show that different machine faults can be classified, the degree of fault severity can be captured, and WLGRM can achieve better performance than other algorithms in most cases of machine fault classification. [Copyright &y& Elsevier]

Abstract: This paper proposes a new approach based on combined Wavelet Transform-Extreme Learning Machine (WT-ELM) technique for fault section identification (whether the fault is before or after the series capacitor as observed from the relay point), classification and location in a series compensated transmission line. This method uses the samples of fault currents for half cycle duration from the inception of fault. The features of fault currents are extracted by first level decomposition of the current samples using discrete wavelet transform (DWT) and the extracted features are applied as inputs to ELMs for fault section identification, classification and location. The feasibility of the proposed method has been tested on a 400kV, 300km series compensated transmission line for all the ten types of faults using MATLAB simulink. On testing 28,800 fault cases with varying fault resistance, fault inception angle, fault distance, load angle, percentage compensation level and source impedance, the performance of the proposed method has been found to be quite promising. The results also indicate that the proposed method is robust to wide variation in system and operating conditions. [Copyright &y& Elsevier]

Abstract: This paper proposes two approaches based on wavelet transform-support vector machine (WT-SVM) and wavelet transform-extreme learning machine (WT-ELM) for transmission line protection. These methods uses fault current samples for half cycle from the inception of fault. The features of the line currents are extracted by first level decomposition of the current samples using discrete wavelet transform (DWT) and extracted features are applied as inputs to SVM and ELM for faulted phase detection, fault classification, location and discrimination between fault and switching transient condition. The feasibility of the proposed methods have been tested on a 240-kV, 225-km transmission line for all the 10 types of fault using MATLAB Simulink. Upon testing on 9600 fault cases with varying fault resistance, fault inception angle, fault distance, pre-fault power level, and source impedances, the performance of the proposed methods are quite promising. The performance of the proposed methods is compared in terms of classification accuracy and fault location error. The results indicate that SVM based approach is accurate compared to ELM based approach for fault classification. For fault location, the maximum error is less with SVM than ELM and the mean error of SVM is slightly higher than ELM. [Copyright &y& Elsevier]

The Auxiliary Power Unit (APU) is an integral part of an aircraft, providing electrical and pneumatic power to various on-board sub-systems. APU failure results in delay or cancellation of a flight, accompanied by the imposition of hefty fines from the regional authorities. Such inadvertent situations can be avoided by continuously monitoring the health of the system and reporting any incipient fault to the MRO (Maintenance Repair and Overhaul) organization. Generally, enablers for such health monitoring techniques are embedded during a product's design. However, a situation may arise where only the critical components are regularly monitored, and their status presented to the operator. In such cases, efforts can be made during service to incorporate additional health monitoring features using the already installed sensing mechanisms supplemented by maintenance data or by instrumenting the system with appropriate sensors. Due to the inherently critical nature of aircraft systems, it is necessary that instrumentation does not interfere with a system's performance and does not pose any safety concerns. One such method is to install non-intrusive vibroacoustic sensors such that the system integrity is maintained while maximizing system fault diagnostic knowledge. To start such an approach, an in-depth literature survey is necessary as this has not been previously reported in a consolidated manner. Therefore, this paper concentrates on auxiliary power units, their failure modes, maintenance strategies, fault diagnostic methodologies, and their acoustic signature. The recent trend in APU design and requirements, and the need for innovative fault diagnostics techniques and acoustic measurements for future aircraft, have also been summarized. Finally, the paper will highlight the shortcomings found during the survey, the challenges, and prospects, of utilizing sound as a source of diagnostics for aircraft auxiliary power units. [ABSTRACT FROM AUTHOR]

The rapid development of photovoltaic (PV) technology and the growing number and size of PV power plants require increasingly efficient and intelligent health monitoring strategies to ensure reliable operation and high energy availability. Among the various techniques, Artificial Neural Network (ANN) has exhibited the functional capacity to perform the identification and classification of PV faults. In the present review, a systematic study on the application of ANN and hybridized ANN models for PV fault detection and diagnosis (FDD) is conducted. For each application, the targeted PV faults, the detectable faults, the type and amount of data used, the model configuration and the FDD performance are extracted, and analyzed. The main trends, challenges and prospects for the application of ANN for PV FDD are extracted and presented. • Applications of ANN techniques and hybrid application for PV FDD are summarized. • Detectable PV faults with ANN technique and diagnosis performance are investigated. • Reported public PV database of 1D data and 2D images are summarized. • Common trends for the selection of model for different PV faults are identified. • Challenges and prospects for PV FDD using ANN techniques are presented. [ABSTRACT FROM AUTHOR]

• Proposed a deep learning based CNN model for fault classification in Power System distribution network integrated with distributed generators (DGs). • In this proposed work, fault classification is done without any pre-processing or feature engineering steps. • All types of fault in 3-phase power system network including no-fault is classified using proposed model with superior performance. • Proposed model is compared with conventional machine learning methods for fault classification in terms of both performance and computational cost. • The performance of proposed model is also tested on a mixed transmission line and distribution network with PV as DG. Fault detection is the critical stage of the relaying system and their successful completion in minimum time is expected for fault clearance. With the increasing usage of distributed generators (DGs) in a distribution network, the conventional relaying methods are becoming inappropriate due to changing fault current levels. This paper presents a deep learning algorithm i.e. Convolutional Neural Network (CNN) customized for fault classification in the distributed networks integrated with DGs. This is first time that CNN has been used for fault detection using raw and sampled-data of three-phase voltage and current signals of various fault classes and no-fault class. The 10-fold cross-validation is used to demonstrate the performance of the proposed model in terms of different metrics such as accuracy, sensitivity, specificity, precision, and F1 score. The proposed model has attended an average 10-fold cross-validation accuracy of 99.52% for all the tested fault cases. This featureless proposed method has been compared with conventional approaches from literature and has shown better performance in terms of accuracy and computation burden. Further, a similar fault study is conducted on a mixed transmission line and distribution network with PV as DG using the proposed method and found performance accuracy of 99.92% and 99.97%, respectively. [ABSTRACT FROM AUTHOR]

The development of airborne sensor monitoring and artificial intelligence technologies provides effective tools for precise prognostic and health management (PHM) of aircraft. This paper presents a PHM model which combines multiple deep learning algorithms for condition assessment, fault classification, sensor prediction, and remaining useful life (RUL) estimation of aircraft systems. A long short-term memory (LSTM) based recurrent network is used to predict multiple multivariate time series of sensors, and deep belief network (DBN) is applied to assess system condition and classify faults of aircraft systems. Then, the RUL can be estimated through the integration of condition assessment and sensor prediction. Finally, the proposed algorithm is validated experimentally using NASA's C-MAPSS dataset, and the results showed a lower error rate and deviation than traditional models. [ABSTRACT FROM AUTHOR]