Remaining Useful Life Estimation Approach Research Articles

A novel spatio-temporal characteristic extraction network for bearing remaining useful life prediction

Abstract Remaining useful life (RUL) is an important index indicating the health status of equipment, which has attracted extensive attention. Nevertheless, many existing RUL prediction methods encounter difficulties in effectively capturing comprehensive degradation features hidden in the data. Moreover, within real-world industrial scenarios, noisy signals are inevitably collected in the raw signals, thereby posing a big challenge to the precision of RUL predictions. To address the aforementioned problems, a robust RUL estimation approach based on degradation intrinsic mode functions (IMFs) selection and spatio-temporal feature regression is developed in this paper. The former addresses the issue of deep learning models struggling to extract degradation features of rolling bearings due to interference factors in vibration signals, while the latter resolves the problem of incomplete degradation features extracted by traditional RUL models under complex operating conditions. Firstly, complete ensemble empirical mode decomposition with adaptive noise is adopted to process the raw signals, separating components with degradation features, ineffective components, and noise. Subsequently, an IMFs selection method employing fast dynamic time warping and cosine coefficients is designed to obtain the valuable degradation features. Finally, a spatio-temporal feature extraction network is presented to comprehensively and effectively capture both spatial and temporal features within the chosen degradation IMFs, achieving the prediction of RUL with high accuracy and strong robustness. The experimental part containing two case studies has validated the effectiveness and superiority of the proposed method.

Fatigue assessment of bridges using interacting filtering approach with sub-structured predictor model based on current health

Fatigue estimation for critical structures necessitates comprehensive monitoring, which, in turn, requires dense instrumentation and models that heavily rely on computational resource models that heavily rely on computational resources. However, the fatigue vulnerability of different segments within the infrastructure can be considered to adopt a cost-effective substructure-based monitoring approach, minimizing the need for extensive instrumentation or complex models. However, estimating or instrumenting the substructure boundary adds to the complexity. In addition, conventional fatigue estimation approaches often assume constant structural health, disregarding the unknown current health status of aging structures. To overcome this limitation, a novel substructure-based fatigue life estimation approach is developed, incorporating an interacting ensemble-particle filter that considers the current health status while remaining robust against boundary forces. Numerical experiments validate the proposed approach on a simulated reinforced concrete box girder bridge, utilizing a 3D beam model that accounts for dynamic interaction with vehicles. A parametric analysis investigates the relationships between fatigue damage and factors such as surface roughness, vehicle speed, vehicle weight, and vehicle category, aiming to identify dominant stimuli. The results demonstrate an accurate estimation of health parameters and remaining useful life (RUL). Furthermore, a novel decomposed approach for RUL estimation is developed, enabling the mapping of traffic information to fatigue damage without requiring costly simulations. A case study highlights the practical applicability of the approach, focusing on a reinforced concrete box girder bridge in Himachal Pradesh, India.

Remaining useful life prediction considering degradation interactions of subsea Christmas tree: A multi-stage modeling approach

Interactions exist in the performance degradation of the systems because of uneven distribution of working pressures of components. Actually, even the same two components have different degradation processes under the natural degradation or external impact. For a complex system, even if single degradation process of components is known, it is still difficult to evaluate its overall performance. The remaining useful life (RUL) of the system is also tough to estimate due to the effects of interactions. This paper contributed a multi-stage model-based RUL estimation approach considering interactions. The framework of the approach is based on Bayesian networks (BNs). On the one hand, BNs is used to identify and match the system degradation stage, and on the other hand, it is used to deal with the uncertainty of parameters in the RUL estimation. Multi-stage degradation and interaction coefficients are the two most important tasks to complete the RUL estimation considering interactions. The RUL are obtained from the time difference from healthy operation to failure. An electro-hydraulic subsea Christmas tree is adopted to demonstrate the proposed approach. The results show that the approach can effectively evaluate the system performance and RUL under the influence of interactions.

Improved Particle Swarm Optimization-Extreme Learning Machine Modeling Strategies for the Accurate Lithium-ion Battery State of Health Estimation and High-adaptability Remaining Useful Life Prediction

To ensure the secure and stable operation of lithium-ion batteries, the state of health (SOH) and the remaining useful life (RUL) are the critical state parameters of lithium-ion batteries, which need to be estimated precisely. A joint SOH and RUL estimation approach based on an improved Particle Swarm Optimization Extreme Learning Machine (PSO-ELM) is proposed in this paper. The approach adopts Pearson coefficients to screen multivariate information of the discharge process as health indicators and uses them as inputs to enable accurate estimation of SOH and RUL prediction of lithium-ion batteries on the basis of the PSO-ELM model. The validity of the model is demonstrated by the NASA lithium-ion battery data set: the maximum root mean square error (RMSE) of the SOH estimation of the tested battery is 0.0033, the maximum RMSE of its RUL prediction is 0.0082, and the maximum absolute error of RUL prediction is one cycle number. In comparison with the prediction results of the traditional extreme learning machine, the optimized model proposed in this paper estimates the SOH of lithium-ion batteries and RUL with relatively high accuracy.

Temporal convolution-based transferable cross-domain adaptation approach for remaining useful life estimation under variable failure behaviors

Many data-driven models normally assume that the training and test data are independent and identically distributed to predict the remaining useful life (RUL) of industrial machines. However, different failure models caused by variable failure behaviors may lead to a domain shift. Meanwhile, conventional methods lack comprehensive attention to temporal information, resulting in a limitation. To handle the aforementioned challenges, a transferable cross-domain approach for RUL estimation is proposed. The hidden features are extracted adaptively by a temporal convolution network in which residual self-attention is able to fully consider the contextual degradation information. Furthermore, a new cross-domain adaption architecture with the contrastive loss and multi-kernel maximum mean discrepancy is designed to learn the domain invariant features. The effectiveness and superiority of the proposed method are proved by the case study on IEEE PHM challenge 2012 bearing dataset and the comparison with other methods.

A data-driven approach based on deep neural networks for lithium-ion battery prognostics

Remaining useful life estimation is gaining attention in many real-world applications to alleviate maintenance expenses and increase system reliability and efficiency. Deep learning approaches have recently provided a significant improvement in the estimation of remaining useful life (RUL) and degradation progression concerning machinery prognostics. This research presents a new data-driven approach for RUL estimation using a hybrid deep neural network that combines CNN, LSTM, and classical neural networks. The presented CNN–LSTM neural network aims to extract the spatio-temporal relations in multivariate time series data and capture nonlinear characteristics to achieve better RUL prediction accuracy. To improve the proposed model's performance, PSO is handled to simultaneously optimize the hyperparameters of the network consisting of the number of epochs, the number of convolutional and LSTM layers, the size of units (or filters) in each convolutional, and LSTM layers. Besides, the proposed model in this paper, called the CNN–LSTM–PSO, realizes the multi-step-ahead prediction. In the experimental studies, the popular lithium-ion battery dataset presented by NASA is selected to verify the CNN–LSTM–PSO approach. The experimental consequences revealed that the presented CNN–LSTM–PSO model gives better results than other state-of-the-art machine learning techniques and deep learning approaches considering various performance criteria.

Spatiotemporal non-negative projected convolutional network with bidirectional NMF and 3DCNN for remaining useful life estimation of bearings

Remaining useful life (RUL) estimation for bearings is crucial in guaranteeing the reliability of rotating machinery. With the rapid development of information science, deep-learning-based RUL estimation has become more appealing as it can automatically establish the mapping relationship between the monitored data and the degradation states through feature learning. Vibration analysis via time–frequency representation (TFR) has shown great advantages for the detection of bearing damage in deep-learning-based prognostics. However, the following two problems remain: 1) insufficient or ineffective utilization of the data feature information, and 2) the requirement for huge computational resources, which still present challenges for the accuracy and efficiency of TFR-based prognostics. A novel RUL estimation approach called spatiotemporal non-negative projected convolutional network (SNPCN) is hence proposed. The approach can fully learn the spatiotemporal degradation features of bearing TFRs with high computational efficiency. In detail, the continuous wavelet transform (CWT) was applied as a TFR analysis method to reveal the nonstationary properties of the bearing degradation signals. Then, a newly proposed bidirectional non-negative matrix factorization (BiNMF) method was used to obtain the low-rank eigenmatrices of the TFRs and greatly compress the calculations in TFR-based prognostics. A three-dimensional convolutional neural network (3DCNN) was next constructed to learn the spatiotemporal degradation features in adjacent BiNMF eigenmatrices and construct the mapping relationship between the bearing RUL and current monitored data. Experiments on the PRONOSTIA platform demonstrate the feasibility and superiority of the proposed SNPCN-based bearing RUL estimation approach.

Remaining useful life estimation via transformer encoder enhanced by a gated convolutional unit

Remaining Useful Life (RUL) estimation is a fundamental task in the prognostic and health management (PHM) of industrial equipment and systems. To this end, we propose a novel approach for RUL estimation in this paper, based on deep neural architecture due to its great success in sequence learning. Specifically, we take the Transformer encoder as the backbone of our model to capture short- and long-term dependencies in a time sequence. Compared with convolutional neural network based methods, there is no limitation from the kernel size for a complete receptive field of all time steps. While compared with recurrent neural network based methods, we develop our model based on dot-product self-attention, enabling it to fully exploit parallel computation. Moreover, we further propose a gated convolutional unit to facilitate the model’s ability of incorporating local contexts at each time step, for the attention mechanism used in the Transformer encoder makes the output high-level features insensitive to local contexts. We conduct experiments on the C-MAPSS datasets and show that, the performance of our model is superior or comparable to those of other existing methods. We also carry out ablation studies and demonstrate the necessity and effectiveness of each component used in the proposed model.

Multiscale deep bidirectional gated recurrent neural networks based prognostic method for complex non-linear degradation systems

Reliable estimation of the remaining useful life (RUL) of complex engineered systems plays a vital role in avoiding undue maintenance situations while guaranteeing system safety. However, efficient tracking of RUL often gets hampered by the prerequisite for prior knowledge regarding degradation characteristics of critical components, which are not available in most cases. Additionally, machine learning techniques face difficulties in adapting and modeling degradation trends in the presence of equipment’s complex working environments. To address these issues, we present a novel data-driven feature learning approach based on a multi-scale deep bidirectional gated recurrent neural network (MDBGRU). The MDBGRU network can: i) automatically learns both local and global information in addition to temporal variations in the multivariate sensor data; ii) capture salient discriminative features characterizing the system complexity; iii) overcome the pre-expertise requirement on multiple sub-components of the system; and iv) curb shortcomings of machine learning methods. Extensive experiments are performed on the C-MAPSS dataset to evaluate the prognostic capability of the proposed method. Compared with the existing works, our network attains enhanced prediction accuracy with an overall improvement of 13.54%, suggesting this as a new and promising RUL estimation approach.

Predicting Remaining Useful Life using Time Series Embeddings based on Recurrent Neural Networks

We consider the problem of estimating the remaining useful life (RUL) of a system or a machine from sensor data. Many approaches for RUL estimation based on sensor data make assumptions about how machines degrade. Additionally, sensor data from machines is noisy and often suffers from missing values in many practical settings. We propose Embed-RUL: a novel approach for RUL estimation from sensor data that does not rely on any degradation-trend assumptions, is robust to noise, and handles missing values. Embed-RUL utilizes a sequence-to-sequence model based on Recurrent Neural Networks (RNNs) to generate embeddings for multivariate time series subsequences. The embeddings for normal and degraded machines tend to be different, and are therefore found to be useful for RUL estimation. We show that the embeddings capture the overall pattern in the time series while filtering out the noise, so that the embeddings of two machines with similar operational behavior are close to each other, even when their sensor readings have significant and varying levels of noise content. We perform experiments on publicly available turbofan engine dataset and a proprietary real-world dataset, and demonstrate that Embed-RUL outperforms the previously reported state-of-the-art (Malhotra, TV, et al., 2016) on several metrics.

Estimation of Bearing Remaining Useful Life Based on Multiscale Convolutional Neural Network

Bearing remaining useful life (RUL) prediction plays a crucial role in guaranteeing safe operation of machinery and reducing maintenance loss. In this paper, we present a new deep feature learning method for RUL estimation approach through time frequency representation (TFR) and multiscale convolutional neural network (MSCNN). TFR can reveal nonstationary property of a bearing degradation signal effectively. After acquiring time-series degradation signals, we get TFRs, which contain plenty of useful information using wavelet transform. Owing to high dimensionality, the size of these TFRs is reduced by bilinear interpolation, which are further regarded as inputs for deep learning models. Here, we introduce an MSCNN model structure, which keeps the global and local information synchronously compared to a traditional convolutional neural network (CNN). The salient features, which contribute for RUL estimation, can be learned automatically by MSCNN. The effectiveness of the presented method is validated by the experiment data. Compared to traditional data-driven and different CNN-based feature extraction methods, the proposed method shows enhanced performance in the prediction accuracy.

An Adaptive Remaining Useful Life Estimation Approach for Newly Developed System Based on Nonlinear Degradation Model

As the central component of prognostic and health management (PHM) field, remaining useful life (RUL) estimation approaches based on degradation modeling have played an extremely significant role in recent years. For the newly developed systems working in complex environments, the associated degradation processes not only lack historical data and prior information but also have strong nonlinearity and three-source variability. Therefore, this paper proposes an adaptive RUL estimation approach for the newly developed system based on a nonlinear model. Specifically, a general nonlinear Wiener-process-based degradation model is established to simultaneously characterize three-source variability and nonlinearity, and the associated RUL distribution is derived with an explicit form. In order to utilize the condition monitoring (CM) data of the service system up to date, we present a parameter estimation method based on the expectation maximization algorithm to adaptively estimate and update the model parameters online. As such, the RUL distribution can be updated once the new CM data are available. Finally, the effectiveness and superiority of the proposed method are demonstrated by the numerical example an empirical study for battery data. The results show that the proposed method can provide accurate and robust RUL prediction for the newly developed system.

Auxiliary Particle Filtering-Based Estimation of Remaining Useful Life of IGBT

Insulated gate bipolar transistor (IGBT) has been widely used in diverse power electronics systems. As IGBT is one of the most vulnerable components in power electronics converter, remaining useful life ( RUL ) estimation of this switch has become highlight of the research in recent years. This RUL estimation helps in schedule maintenance based on health status of IGBT to avoid the unexpected failure of converters. However, there has been commonly a large variance in RUL estimation due to presence of random noise, which leads to erroneous result in IGBT prognosis. To reduce this variance in RUL estimation, particle filter methods including sequential importance sampling and sequential importance resampling have been employed recently. Still, these methods lead to nonnegligible estimation variance due to degeneracy and impoverishment of samples. In this paper, RUL estimation approach based on auxiliary particle filter (APF) is proposed. The proposed method will sufficiently reduce estimation variance by increasing dimensionality of samples as well as by sustaining diversity in samples. In addition, a simple slope-based method is proposed to identify the region when the degradation is evident in IGBT. An APF method is applied when the IGBTs under test enter this region. This step is able to reduce variation in RUL estimation and computation cost. The performance of the proposed RUL estimation method is theoretically and experimentally verified.

Conception and implementation of a data-driven prognostics algorithm for safety–critical systems

Complex engineering systems suffer from internal wears and tears that cannot be measured by sensors. Sudden failure of such systems is hazardous and may endanger human life. To avoid sudden failures, a prognostics system that takes multivariate sensor data and infers system health and then projects the inferred system health into future based on damage progression for remaining useful life (RUL) estimation in real time is needed. Logisticians, engineers, project managers, and others can also benefit from prognostics information to improve performance and reduce cost. Our contribution in this paper is to present a data-driven prognostics approach for RUL estimation of aircraft turbofan engines that run onboard in real time. Kalman filter and neural network are used together to infer system health from several sensor readings. The inferred system health is then projected by another neural network till the end of life for RUL calculation. The algorithm is implemented on Raspberry Pi 2 single-board computer running Windows 10 Internet of Things Core to enable efficient development and deployment of onboard prognostics applications. Data from PHM08 data challenge competition are used for algorithm development and testing. The results show the applicability of this approach for RUL estimation onboard in real time.

Remaining useful life estimation in heterogeneous fleets working under variable operating conditions

The availability of condition monitoring data for large fleets of similar equipment motivates the development of data-driven prognostic approaches that capitalize on the information contained in such data to estimate equipment Remaining Useful Life (RUL). A main difficulty is that the fleet of equipment typically experiences different operating conditions, which influence both the condition monitoring data and the degradation processes that physically determine the RUL. We propose an approach for RUL estimation from heterogeneous fleet data based on three phases: firstly, the degradation levels (states) of an homogeneous discrete-time finite-state semi-markov model are identified by resorting to an unsupervised ensemble clustering approach. Then, the parameters of the discrete Weibull distributions describing the transitions among the states and their uncertainties are inferred by resorting to the Maximum Likelihood Estimation (MLE) method and to the Fisher Information Matrix (FIM), respectively. Finally, the inferred degradation model is used to estimate the RUL of fleet equipment by direct Monte Carlo (MC) simulation. The proposed approach is applied to two case studies regarding heterogeneous fleets of aluminium electrolytic capacitors and turbofan engines. Results show the effectiveness of the proposed approach in predicting the RUL and its superiority compared to a fuzzy similarity-based approach of literature.

Remaining useful life estimation using an inverse Gaussian degradation model

The use of degradation data to estimate the remaining useful life (RUL) has gained great attention with the widespread use of prognostics and health management on safety critical systems. Accurate RUL estimation can prevent system failure and reduce the running risks since the efficient maintenance service could be scheduled in advance. In this paper, we present a degradation modeling and RUL estimation approach by using available degradation data for a deteriorating system. An inverse Gaussian process with the random effect is firstly used to characterize the degradation process of the system. Expectation maximization algorithm is then adopted to estimate the model parameters, and the random parameters in the degradation model are updated by Bayesian method, which makes the estimated RUL able to be real-time updated in terms of the fresh degradation data. Our proposed method can capture the latest condition of the system by means of updating degradation data continuously, and obtain the explicit expression of RUL distribution. Finally, a numerical example and a practical case study are provided to show that the presented approach can effectively model degradation process for the individual system and obtain better results for RUL estimation.

Degradation data-driven approach for remaining useful life estimation

Remaining useful life (RUL) estimation is termed as one of the key issues in prognostics and health management (PHM). To achieve RUL estimation for individual equipment, we present a degradation data-driven RUL estimation approach under the collaboration between Bayesian updating and expectation maximization (EM) algorithm. Firstly, we utilize an exponential-like degradation model to describe equipment degradation process and update stochastic parameters in the model via Bayesian approach. Based on the Bayesian updating results, both probability distribution of the RUL and its point estimation can be derived. Secondly, based on the monitored degradation data to date, we give a parameter estimation approach for non-stochastic parameters in the degradation model and prove that the obtained estimation is unique and optimal in each iteration. Finally, a numerical example and a practical case study for global positioning system (GPS) receiver are provided to show that the presented approach can model degradation process and achieve RUL estimation effectively and generate better results than a previously reported approach in literature.

A degradation path-dependent approach for remaining useful life estimation with an exact and closed-form solution

Remaining useful life (RUL) estimation is regarded as one of the most central components in prognostics and health management (PHM). Accurate RUL estimation can enable failure prevention in a more controllable manner in that effective maintenance can be executed in appropriate time to correct impending faults. In this paper we consider the problem of estimating the RUL from observed degradation data for a general system. A degradation path-dependent approach for RUL estimation is presented through the combination of Bayesian updating and expectation maximization (EM) algorithm. The use of both Bayesian updating and EM algorithm to update the model parameters and RUL distribution at the time obtaining a newly observed data is a novel contribution of this paper, which makes the estimated RUL depend on the observed degradation data history. As two specific cases, a linear degradation model and an exponential-based degradation model are considered to illustrate the implementation of our presented approach. A major contribution under these two special cases is that our approach can obtain an exact and closed-form RUL distribution respectively, and the moment of the obtained RUL distribution from our presented approach exists. This contrasts sharply with the approximated results obtained in the literature for the same cases. To our knowledge, the RUL estimation approach presented in this paper for the two special cases is the only one that can provide an exact and closed-form RUL distribution utilizing the monitoring history. Finally, numerical examples for RUL estimation and a practical case study for condition-based replacement decision making with comparison to a previously reported approach are provided to substantiate the superiority of the proposed model.