Remaining Useful Life Prediction Research Articles

A novel two-stage method via adversarial strategy for remaining useful life prediction of bearings under variable conditions

It is critical to accurately predict the remaining useful life (RUL) of rolling bearings to avoid severe accidents and financial losses in the industry. Nevertheless, accurately determining the initial prediction time (IPT) continues to pose a challenge, and significant differences in the data distribution of bearings under different operating conditions are frequently overlooked. To deal with these problems, we propose a novel two-stage method based on the adversarial strategy for RUL prediction of bearings under variable conditions. Firstly, we create reliable health indicators in an unsupervised manner by recording the coded characteristics of the bearing’s state of health. Secondly, an adaptive threshold method based on rate-of-change (ATMROC) is developed to perform accurate health state classification. Finally, we propose a RUL prediction network based on the attention depth-gated recurrent unit with domain invariance (DIADGRU) to handle the inconsistent distribution of degradation features under different operating conditions. Experiments of RUL prediction on PHM2012 and XITU-SY datasets are implemented, and the promising results validate the effectiveness of the proposed method.

Intelligent fatigue damage tracking and prognostics of composite structures utilizing raw images via interpretable deep learning

In recent years, prognostics gained attention in various industries by optimizing maintenance, boosting operational efficiency, and preventing costly downtime. Central to prognostics is the Remaining Useful Life (RUL), representing the critical time before system failure. Deep learning advancements facilitate RUL forecasting by extracting features from diverse data formats such as time series, images, or sequences thereof, in one, two, or three dimensions, respectively. Yet, predicting RUL from image sequences often relies heavily on resource-intensive techniques like digital image correlation, complicating data acquisition. To address challenges with high-dimensional data and unreliable models, this study introduces ISTRUST, an innovative Transformer-based architecture. ISTRUST (Interpretable Spatiotemporal TRansformer for Understanding STructures) tackles the dual challenges posed by high-dimensional data and the black-box nature of existing models. Leveraging Transformers’ attention mechanism, ISTRUST breaks down the spatiotemporal domain, effectively realizing interpretable RUL predictions under uncertainty using only sparse raw image sequences as input. Evaluated on fatigue-loaded composite samples showcasing crack propagation, ISTRUST interprets the relation between cracks and RUL via the attention mechanism. The results substantiate its capacity to interpret and clarify instances in which predictions may exhibit variability in accuracy. Through the attention mechanism, a strong correlation between the model’s spatiotemporal focus and the RUL predictions is established, making it, to the best of our knowledge, the first model to provide interpretable stochastic RUL predictions directly from sequential images of this nature.

A remaining useful life prediction method based on DATCN-PSOSEN for turbofan engines

Abstract Turbofan engine is a crucial operational component of aircraft. Remaining useful life (RUL) prediction is important for the stable and reliable operation of the turbofan engine. High-dimensional and large-capacity monitoring data of turbofan engines pose a considerable challenge to accurate RUL prediction. A novel approach based on dual-attention temporal convolutional network (DATCN) and particle swarm optimization with selective ensemble (PSOSEN) is proposed in this paper. In the first stage, DATCN is utilized to explore the internal correlations among various input features and different time steps in monitoring data, highlighting the degradation information from two dimensions. In the second stage, PSOSEN is developed to prune base models, excluding the ones with poor performance and assigning varying weights to the others, leading to selectively ensembled prediction results. The experimental results on the C-MAPSS aero-engine degradation dataset validate the effectiveness of the proposed DATCN-PSOSEN method and show improvements of RUL prediction accuracy by 14.2% compared with other methods.

Unsupervised health indicator construction by a new Gaussian-student’s t-distribution mixture model and its application

The equipment’s remaining useful life (RUL) must be accurately estimated to guarantee its reliable operation. As a crucial part of data-driven RUL prediction, the health indicator (HI) construction method employing the distribution discrepancies can represent the variation trend of health conditions. However, the existing Gaussian mixture model based HI construction method cannot accurately estimate the long-tail distribution characteristics in some degradation data. Moreover, it cannot comprehensively mine the distribution characteristics of degradation data by leveraging different types of distributions. A novel Gaussian-student’s t-distribution mixture model (GSMM) that simultaneously considers Gaussian distribution and student’s t-distribution is developed in this work to estimate the distributions of normal and degradation data. Next, the distribution contact ratio metric (DCRM) is applied to measure the discrepancies between the baseline distribution of normal data and the distributions of test data at different moments. The bearing HI can be constructed with the acquired DCRMs. Finally, the effectiveness and merit of the developed HI construction approach are validated by two bearing life-cycle datasets. The experimental results illustrate that the GSMM-based HI performs better than other classical and state-of-the-art HIs. Additionally, the constructed HI is more suitable for bearing RUL prediction.

Joint estimation of SOH and RUL for lithium batteries based on variable frequency and model integration

The safe and stable operation of lithium-ion batteries in electric vehicles is crucial. Aiming at the problems of a large workload of online estimation and prediction and inability to weigh the whole life cycle of the battery in the joint estimation of SOH (State of Health) and RUL (Remaining Useful Life) for traditional lithium-ion batteries, this paper proposes an optimization scheme for the joint analysis of SOH-RUL. First, the article extracts suitable health features. It utilizes an integrated Extreme Learning Machine (ELM) to estimate the SOH of the battery and inputs the estimates into a Regression Vector Machine (RVM) model for RUL prediction. To better cope with the phenomenon of "sudden capacity change" in batteries, this paper divides the entire life cycle into the early and late stages. A lower estimation frequency and model integration are employed in the early stage.In contrast, the estimation frequency and model integration are increased later to balance speed and safety in total life cycle estimation. Finally, validation was performed on the NASA and CALCE datasets, comparing the effect of constant estimated frequency and model integration with that of varying estimated frequency and model integration at different aging stages. The RMSE of SOH estimation error for both datasets is within 2% during the early and late stages, and the SOH estimation error for the entire lifecycle is within 2%. The absolute RUL prediction error for the NASA dataset is below five times; for the CALCE dataset, it is below 20 times in most cases.

Sparse Graph Structure Fusion Convolutional Network for Machinery Remaining Useful Life Prediction

Effective prediction of machinery remaining useful life (RUL) is prominent to achieve intelligent preventive maintenance in manufacturing systems. In this paper, a sparse graph structure fusion convolutional network (SGSFCN) is proposed for more accurate end-to-end RUL prediction of machine. A novel node-level graph structure called time series shapelet distance graph (TSSDG) is designed to convert the time series to node feature. The SGSFCN model is proposed to learn degradation information from the graph structure. In SGSFCN, a sparse graph structure (SGS) layer and a fusion graph structure (FGS) layer preceding the graph convolutional network (GCN) are designed to learn the SGS from node representation and fuse the original graph structure, enabling the graph structure and node update iteratively in subsequent layers. Concurrently, a bidirectional long short-term memory network (BiLSTM) layer is integrated to capture the global temporal dependencies. The method is validated by two test rig data, and results demonstrate that the proposed method offers significantly higher prediction accuracy of RUL compared to several state-of-art methods.

Remaining useful life prediction method for cross- condition tools based on parallel fusion

Abstract The current tool remaining useful life (RUL) prediction models do not fully consider the importance of signals from different sensors and the differences in working conditions, which leads to a decline in the model’s robust performance under new conditions. This paper introduces a novel cross-condition RUL prediction approach that integrates parallel fusion, transfer learning, and deep learning. Considering the characteristics of different data sources, correlated signals are initially selected using correlation analysis and dynamic time warping (DTW). Subsequently, multi-scale Depthwise Separable Convolution and multi-attention mechanisms are combined to capture the importance of features at various scales. Finally, a dynamic domain adaptation technique is employed to adjust the importance weights of conditional distribution discrepancy and marginal distribution discrepancy, enabling the model to adapt to cross-condition scenarios.

Uncertainty Quantification In The Prediction of Remaining Useful Life Considering Multiple Failure Modes

Abstract Despite the substantive literature on remaining useful life (RUL) prediction, less attention is paid to the influence of epistemic uncertainty and aleatory uncertainty in multiple failure behaviors in the accuracy of RUL. The research question in this study was: can uncertainties be quantified in predicting the RUL of systems with multiple failure modes? The first objective was to quantify the uncertainties in the prediction of RUL, considering known multiple failure modes. This objective used vibration data from accelerated degradation experiments of rolling element bearings. The second objective was to calculate the uncertainties in the prediction of RUL, considering the multiple failure modes as unknown. The experimental data used in this objective was from run-to-failure tests of Li-ion batteries. An analysis was performed on how the uncertainties affect the RUL prediction in systems with known multiple failure modes and systems where the multiple failure modes were unknown. A Bayesian neural network was used to quantify epistemic and aleatory uncertainty while predicting RUL. The results of the qualitative uncertainties on RUL in systems with multiple failure modes were presented and discussed. Also, the study yielded an RUL uncertainty quantification model for multiple failure modes. The proposed framework's performance in the RUL prediction was demonstrated. Finally, the epistemic and aleatory uncertainties were quantified in the system's RUL. It was shown that systems that fail due to the same failure mode tend to have similar uncertainty values over time. The results in this paper may lead to the design of more reliable systems that exhibit multiple failure modes.

Air turbine starter remaining useful life prediction for bearing based on an improved temporal convolutional network

The air turbine starter (ATS) is an equipment employed for initiating aircraft engines, in which rolling bearings play a central role. Predicting the remaining useful life (RUL) of rolling bearings constitutes a challenging task within the domain of prognostics and health management (PHM). Improving computational efficiency to predict the RUL of bearings is a core problem addressed in this paper, and thus, this paper introduces the parallel causal convolutional hierarchical dilated temporal convolutional network (HD-TCN). HD-TCN effectively captures long-term temporal dependencies and significantly enhances computational efficiency compared to serial convolutional recurrent neural networks (RNNs). In addition, the introduction of the feature data stacking (FDS) module allows features from different hierarchical levels and dimensions to participate in the prediction task, ensuring both computational efficiency and prediction accuracy. To consolidate the extracted multidimensional features, the network incorporates the matrix multiplication dimensionality reduction transformation (MMDRT) module, which reduces the dimensionality of the data and further improves the computational efficiency as well. The introduction of the MMDRT module resulted in reductions of 43.4% in root mean square error (RMSE). The proposed method achieved reductions in RMSE by 38.3% and 46.4% compared to the transformer and long short-term memory (LSTM) models, respectively. Finally, the effectiveness of the proposed method is validated using the XJTU-SY data set and civil aircraft bearing components RUL prediction test bench bearing data. The results show that the proposed approach can predict the RUL of bearings with high accuracy.

Bearing RUL prediction and fault diagnosis system based on parallel multi-scale MIMT lightweight model

Abstract In actual industrial production, the importance of safety production is increasingly prominent, and the degradation and failure of machinery and equipment are potential sources of safety hazards. Therefore, there is a growing trend towards real-time monitoring, prediction, and diagnosis of industrial equipment to prevent unpredictable impacts on life and property safety caused by sudden failures. To address this issue, this paper proposes a real-time degradation anomaly detection based on parallel multiscale autoencoders and a lightweight model of parallel multiscale multi-input multi-task for bearing Remaining Useful Life (RUL) prediction and fault diagnosis systems. Firstly, the multiscale autoencoder method is used to simulate actual working conditions and reconstruct the original vibration signals to build abnormal degradation detection intervals. The [0, $\mu$ +3$\sigma$] interval is utilized to judge abnormal degradation based on reconstruction errors, and the First Predict Timepoint (FPT) is determined adaptively. Secondly, a method for constructing dimensionless auxiliary datasets is proposed, which adopts a multi-input form based on deep separable convolution for feature extraction of original vibration signals, kurtosis, and peak values to improve the prediction and diagnosis performance of the lightweight model. Finally, a multi-task output method combining clustering and regression is employed to achieve RUL prediction and fault diagnosis of bearings. The proposed method overcomes the problems existing in traditional bearing RUL prediction and diagnosis methods and possesses theoretical innovation and engineering practicality. Validation on two bearing datasets confirms the effectiveness of the proposed method.

Remaining useful life prognostics of bearings based on convolution attention networks and enhanced transformer

Rolling bearings are critical components of industrial equipment, and predicting their remaining useful life (RUL) is a challenging task. This article proposes a new end-to-end model (MDSCT) to achieve efficient and accurate prediction of bearing RUL. MDSCT uses the raw vibration signals collected by sensors for prediction, without relying on a large amount of prior knowledge. The feature extraction backbone of this model is composed of an MDSC attention module that integrates multiple parallel depth-wise separable convolutions and an efficient attention mechanism, combined with a tansformer encoder (PPSformer) optimized using patch embedding and probesparse self attention techniques. They are respectively used to capture local subtle features and global dependent features in degraded signals. This article also proposes an improved adaptive activation function AdaptH_Swish to enhance the model's ability to model nonlinear relationships. To comprehensively verify the comprehensive performance of the model, this paper conducted detailed ablation and comparative experiments using two standard datasets, PHM2012 and XJTU-SY. The experimental results not only confirm the rationality and efficiency of the model structure design, but also demonstrate significant advantages in three evaluation indicators compared to various existing methods, fully demonstrating the high generalization and strong robustness of the MDSCT model in bearing RUL prediction tasks.

A novel dynamic predictive maintenance framework for gearboxes utilizing nonlinear Wiener process

Abstract In the context of advancing industrial automation, gearboxes, as pivotal components in power transmission systems, have a direct bearing on the operational efficiency and safety of the entire machinery. This study introduces a novel dynamic predictive maintenance framework for gearboxes using a nonlinear Wiener process. Comprehensive experiments validate the framework, demonstrating significant reductions in maintenance costs and improvements in reliability. First, a full-life degradation experiment was executed on the gearbox, leveraging the root mean square (RMS) value of the vibration signal as an indicator of system degradation. Subsequently, the signals from four vibration sensors were synthesized and normalized through Kernel Principal Component Analysis (KPCA), thereby enabling a more nuanced representation of the gearbox's degradation profile. The degradation trajectory was then modeled using a nonlinear Wiener process framework. The Wiener process's parameters and state variables were iteratively refined utilizing an online filtering algorithm grounded in Bayesian inference. This facilitated the derivation of the probability density function for the remaining useful life (RUL), thereby enabling a robust prediction of the gearbox's RUL. Finally, to minimize maintenance costs per unit of time, an optimization model for dynamic maintenance decision-making was formulated. The optimal maintenance timing was ascertained by solving this model. The empirical findings of this investigation demonstrate the efficacy of the proposed approach in executing dynamic predictive maintenance for gearboxes. This research endeavors to furnish novel theoretical underpinnings and pragmatic directives for the field of predictive maintenance in the context of gearboxes.

MSTAN: multi-scale spatiotemporal attention network with adaptive relationship mining for remaining useful life prediction in complex systems

Abstract In the era of smart manufacturing and advanced industrial systems, the high degree of integration and intelligence of equipment demands higher reliability and safety from systems. Existing methods often rely on historical data for Remaining Useful Life (RUL) prediction to achieve Prognostic and Health Management (PHM). However, the internal units of complex equipment exhibit significant spatial correlation and temporal diversity, making PHM for complex equipment a multidimensional challenge involving both temporal and spatial information, thereby severely limits the effectiveness of RUL prediction for complex systems. Addressing these challenges, this study introduces a multi-scale spatiotemporal attention network with adaptive relationship mining, specifically designed for the remaining useful life (RUL) prediction of such equipment. The core of the proposed method lies in the multi-scale feature perception module, which adeptly extracts varied scale features from multidimensional sensor data. Following this, an innovative adaptive relationship mining module is integrated to uncover multi-order coupling relationships between diverse sensors, enhancing the model’s predictive accuracy. Furthermore, a spatiotemporal attention module is employed to discern and emphasize crucial spatiotemporal correlations. To validate the effectiveness and superiority of the proposed method, the Commercial Modular Aero-propulsion System Simulation (C-MAPSS) dataset is employed for comprehensive performance evaluation, the IEEE 2012 PHM bearing dataset is also adopted to demonstrate the generalization and robustness of the proposed method. The results not only show a notable improvement over existing methods but also offer a more intuitive understanding through visual representations, marking a significant stride in enhancing the safety and efficiency of complex systems.

Machine cross-domain remaining useful life prediction via contrastive adversarial variational recurrent method

The performance degradation process of the machine is non-stationary which varies with the operating environment and is reflected as a temporal shift phenomenon. Models or methods that assume the test and training sets have the same distribution will no longer be suitable for solving problems where domain shifts exist. This brings new challenges for accurately evaluating the machine’s remaining useful life (RUL). This paper studies a contrastive adversarial variational recurrent method for machine RUL prediction under different service conditions. In this new approach, the variational recurrent networks are developed to extract distribution features and latent spaces of raw data, meanwhile, the adversarial strategies are applied to enable the learning of domain-invariant features to make the model achieve cross-domain task processing. To supervise the learning process of the model to learn more mutual information between the extracted features and the raw input data, a contrastive loss is also introduced in the proposed method. Sufficient experiments were conducted to verify the feasibility and superiority of the suggested approach, including 12 sets of cross-scenario tests on the turbofan engine dataset C-MAPSS from NASA. Experimental findings confirm that the proposed method performs satisfactorily and competitively even compared to current state-of-the-art works.

Remaining Useful Life Prediction of Rolling Bearings Based on Adaptive Continuous Deep Belief Networks and Improved Kernel Extreme Learning Machine

ABSTRACTRolling bearings are crucial components in a wide variety of machinery. Monitoring their conditions and predicting their remaining useful life (RUL) is vital to prevent unexpected breakdowns, optimize maintenance schedules, and reduce operational costs. This article proposes an approach based on adaptive continuous deep belief networks (ACDBN) and improved kernel extreme learning machine (KELM) to predict the RUL of rolling bearings. In the proposed approach, the ACDBN model is used for extracting hidden fault features and the distance between the initial health state and the real‐time degradation state is used to construct a health indicator (HI). Then, a hybrid kernel extreme learning machine prediction model optimized by the sparrow search algorithm (SSA‐KELM) is proposed to estimate the RUL using the extracted HIs. The SSA is used to find the optimal parameters of the KELM model. The proposed method has been assessed using existing bearing datasets. The obtained results indicate that the proposed method successfully improves RUL prediction accuracy compared to existing approaches in the literature.

Predictive framework for remaining useful life of roller bearings: Utilizing fractional generalized Pareto degradation model in performance evaluation

Research on predictive frameworks for the Remaining Useful Life (RUL) of mechanical systems is limited. This study proposes a comprehensive RUL prediction framework for roller bearings, integrating early failure assessment, adaptive failure threshold determination, and an adaptive drift fractional-order Pareto degradation model. To tackle data insufficiency, multi-sensor fusion combines time-domain, frequency-domain, and time–frequency features. The framework normalizes the health indicator (HI) using Mahalanobis distance and a sigmoid function, and employs the MD-CUSUM technique for early fault detection. Dynamic threshold updating is achieved through BOX-COX transformation and Chebyshev inequality, establishing confidence intervals. The model demonstrates significant results: lowest RMSE of 5.4267, MAE of 3.7857, highest SOR of 0.90936, HD of 0.93543, PICP of 57.143%, and the narrowest MPIW of 9.45, showing enhanced accuracy and reduced uncertainty. Validation with the XJTU-SY bearing dataset confirms improved performance.

Remaining useful life prediction based on time-series features and conformalized quantile regression

Abstract The remaining useful life (RUL) prediction is a key task in the field of prognostics and health management (PHM) and plays a crucial role in preventive maintenance tasks. Traditional prediction methods have mostly focused on point prediction issues, neglecting the uncertain factors in the prediction task, thus failing to ensure the credibility of the prediction. In light of this, this paper focuses on improving the accuracy of point prediction models for RUL and interval prediction issues, proposing the introduction of multi-scale convolutional neural networks (MCNN), decomposed time-sequential linear layers (DL), and conformal quantile regression (CQR) techniques into the RUL prediction task of aero-engines. The aim is to provide timely and accurate failure warnings for aero engines, effectively ensure their reliability and safety, and reduce maintenance costs throughout their life cycle. In response to the limitations of current point prediction models in capturing the temporal features of life data, a MCNN-DL-based RUL prediction model is proposed to capture life data's long-term trends and local variations for precise point predictions. Furthermore, an interval estimation approach for RUL is presented, which integrates the MCNN-DL model with CQR to account for prediction uncertainty. Finally, the method in this paper is verified using the CMAPSS dataset, and the results show that the method has achieved excellent results in both RUL point prediction and interval prediction tasks.

A novel unsupervised adaptive density-based clustering filter for remaining useful life prediction of bearings

Abstract Constructing the health indicator (HI) and predicting the remaining useful life (RUL) are essential steps in bearing health management. Some prediction methods depend on prior information about HIs, especially when these indicators are generated by deep learning models. However, acquiring such prior information can be challenging in practical applications. This paper introduces a novel unsupervised adaptive density-based clustering filter (UADCF) for RUL prediction of bearings, which operates without the need for prior knowledge. Firstly, a post-hoc interpretation HI model (PIHIM) is proposed to characterize the deep learning constructed HIs from the perspective of what the deep learning has done. Then, leveraging the classical density-based clustering algorithm, we introduce the UADCF for unsupervised estimation of model parameters, which can dynamically adjust density parameters based on the current conditions. Finally, we develop a prediction framework combining PIHIM and UADCF, enabling unsupervised RUL prediction of bearings. The experimental studies validate the effectiveness of the proposed method.

A Novel Hybrid Approach for Remaining Useful Life (RUL) and Short-Term Capacity Prediction of Batteries

Lithium-ion battery management requires an accurate determination of the batteries’ remaining usable lives. A novel hybrid method used for the RUL and short-term capacity prediction of batteries is presented in this manuscript. The proposed technique is combined with a White Shark Optimizer (WSO) with the Multi-kernel Support Vector Machine (MSVM); therefore, it is called the WSO-MSVM technique. The major goal of this WSO-MSVM method is to attain effective future capacities and RUL forecast for the Lithium-Ion Battery (LIB) with reliable management of uncertainty. The hybrid technique solves the difficulty of forecasting the RUL of LIB. This proposal trains the WSO-MSVM model using the LIB data. The trained model is utilized to forecast the capacity and RUL of LIBs. In this proposed system, capacity, current, and voltage are considered in the discharge operation. The proposed technique validates good reliability and prediction accuracy with this suitable mechanism. Compared to the existing techniques like artificial neural network (ANN), ant lion optimizer-optimized artificial neural network, and adaptive network-based fuzzy inference system, the proposed technique shows fewer errors under charge and discharge conditions. In addition, the uncertainty intervals of the proposed WSO-MSVM technique for the predicted RUL may include the actual remaining life of the battery. The proposed technique’s charging error is lower the other exciting methods.

Prediction of Remaining Useful Life of Aero-engines Based on CNN-LSTM-Attention

Accurately predicting the remaining useful life (RUL) of aircraft engines is crucial for maintaining financial stability and aviation safety. To further enhance the prediction accuracy of aircraft engine RUL, a deep learning-based RUL prediction method is proposed. This method possesses the potential to strengthen the recognition of data features, thereby improving the prediction accuracy of the model. First, the input features are normalized and the CMAPSS (Commercial Modular Aero-Propulsion System Simulation) dataset is utilized to calculate the RUL for aircraft engines. After extracting attributes from the input data using a convolutional neural network (CNN), the extracted data are input into a long short-term memory (LSTM) network model, with the addition of attention mechanisms to predict the RUL of aircraft engines. Finally, the proposed aircraft engine model is evaluated and compared through ablation studies and comparative model experiments. The results indicate that the CNN-LSTM-Attention model exhibits superior prediction performance for datasets FD001, FD002, FD003, and FD004, with RMSEs of 15.977, 14.452, 13.907, and 16.637, respectively. Compared with CNN, LSTM, and CNN-LSTM models, the CNN-LSTM model demonstrates better prediction performance across datasets. In comparison with other models, this model achieves the highest prediction accuracy on the CMAPSS dataset, showcasing strong reliability and accuracy.