Remaining Useful Life Estimation Research Articles

Remaining Useful-Life Prediction of the Milling Cutting Tool Using Time–Frequency-Based Features and Deep Learning Models

The milling machine serves an important role in manufacturing because of its versatility in machining. The cutting tool is a critical component of machining because it is responsible for machining accuracy and surface finishing, impacting industrial productivity. Monitoring the cutting tool’s life is essential to avoid machining downtime caused due to tool wear. To prevent the unplanned downtime of the machine and to utilize the maximum life of the cutting tool, the accurate prediction of the remaining useful life (RUL) cutting tool is essential. Different artificial intelligence (AI) techniques estimate the RUL of cutting tools in milling operations with improved prediction accuracy. The IEEE NUAA Ideahouse dataset has been used in this paper for the RUL estimation of the milling cutter. The accuracy of the prediction is based on the quality of feature engineering performed on the unprocessed data. Feature extraction is a crucial phase in RUL prediction. In this work, the authors considers the time–frequency domain (TFD) features such as short-time Fourier-transform (STFT) and different wavelet transforms (WT) along with deep learning (DL) models such as long short-term memory (LSTM), different variants of LSTN, convolutional neural network (CNN), and hybrid models that are a combination of CCN with LSTM variants for RUL estimation. The TFD feature extraction with LSTM variants and hybrid models performs well for the milling cutting tool RUL estimation.

RUL prediction for bivariate degradation process considering individual differences

Remaining useful life (RUL), is essential for prediction and health management. Because of unit-to-unit heterogeneity in degradation, it is intractable to perform precise degradation trajectories of an individual bivariate individual system. First, for predicting the RUL of an individual system, the parameter in the nonlinear transformation path of the degradation model is proposed as an indicator to characterize the heterogeneity of the degradation process, which is used for accurate degradation prediction. Furthermore, a prediction method based on this improved degradation model is presented for the RUL estimation of degrading systems. An improved parameter updating way based on the Bayesian approach is developed for parameter posterior estimation. The proposed prediction method is illustrated and validated through a publicly available GaAs lasers dataset and a practical degrading system case data. The results show that the new method is superior to the conventional method in prediction accuracy.

Method for Forecasting the Remaining Useful Life of a Furnace Transformer Based on Online Monitoring Data

Implementing the concept of a “smart furnace transformer” should stipulate its information support throughout its life cycle. This requires improving techniques for estimating the transformer’s health and forecasting its remaining useful life (RUL). A brief review of the problem being solved has shown that the known RUL estimation techniques include processing the results of measuring the facility state parameters using various mathematical methods. Data processing techniques (deep learning, SOLA, etc.) are used, but there is no information on their application in online monitoring systems. Herewith, fast (shock) changes in the resource caused by the failures and subsequent recoveries of the facility’s health have not been considered. This reduces the RUL forecasting accuracy for the repairable equipment, including transformers. It is especially relevant to consider the impact of sudden state changes when it comes to furnace transformers due to a cumulative wear effect determined by their frequent connections to the grid (up to 100 times a day). The proposed approach is based on calculating the RUL by analytical dependencies, considering the failures and recoveries of the facility state. For the first time, an engineering RUL forecasting technique has been developed, based on the online diagnostic monitoring data results provided in the form of time series. The equipment’s relative failure tolerance index, calculated with analytical dependencies, has first been used in RUL forecasting. As a generalized indicator, a relative failure tolerance index considering the facility’s state change dynamics has been proposed. The application of the RUL forecasting technique based on the results of dissolved gas analysis of a ladle furnace unit’s transformer is demonstrated. The changes in the transformer state during the operation period from 2014 to 2022 have been studied. The RUL was calculated in the intensive aging interval; the winding dismantling results were demonstrated, which confirmed developing destructive processes in the insulation. The key practical result of the study is reducing accidents and increasing the service life of the arc and ladle furnace transformers. The techno-economic effect aims to ensure process continuity and increase the metallurgical enterprise’s output (we cannot quantify this effect since it depends on the performance of a particular enterprise). It is recommended to use the technique to forecast the RUL of repairable facilities equipped with online monitoring systems.

Remaining Useful Life Estimation Based on Detection of Explosive Changes: Analysis of Bearing Vibration

The monitoring of condition variables for maintenance purposes is a growing trend amongst researchers and practitioners where decisions are based on degradation levels. The two approaches in Condition-Based Maintenance (CBM) are diagnosing the level of degradation (diagnostics) or predicting when a certain level of degradation will be reached (prognostics). Using diagnostics determines when it is necessary to perform maintenance, but it rarely allows for estimation of future degradation. In the second case, prognostics does allow for degradation and failure prediction, however, its major drawback lies in when to perform the analysis, and exactly what information should be used for predictions. This encumbrance is due to previous studies that have shown that degradation variable could undergo a change that misleads these calculations. This paper addresses the issue of identifying explosive changes in condition variables, using Control Charts, to determine when to perform a new model fitting in order to obtain more accurate Remaining Useful Life (RUL) estimations. The diagnostic-prognostic methodology allows for discarding pre-change observations to avoid contamination in condition prediction. In addition the performance of the integration methodology is compared against adaptive autoregressive (AR) models. Results show that using only the observations acquired after the out-of-control signal produces more accurate RUL estimations.

Time Series-Based Sensor Selection and Lightweight Neural Architecture Search for RUL Estimation in Future Industry 4.0

Industry 4.0 is the current development trend in manufacturing technology. Regarding prognostic and health management (PHM) systems, a major task is to predict the remaining useful life (RUL) of a machine. To have precise RUL information, massive sensors should be involved, which leads to the dramatic cost of sensor network construction. Therefore, many sensor selection methods have been proposed to remove the redundant sensors under a certain constraint of RUL estimation. However, those approaches do not consider time-series sensing data, which is an intrinsic feature of mechanical signals. Therefore, the current research suffers from sensor under-killing problems due to the pessimistic consideration. To solve this problem, this work first considers the time-series sensing data to propose an integrated group-based valuable sensor selection algorithm by using the Least Absolute Shrinkage and Selection Operator (LASSO) property. In addition, to reduce the computing and hardware overhead, we further propose a heuristic neural architecture search (NAS) method to reduce the number of neurons in each neural network for further RUL estimation. To verify the proposed approaches, we use the Commercial Modular Aero-Propulsion System Simulation (C-MAPSS) dataset and utilize the PHM score to evaluate the performance of RUL estimation. Compared with the conventional methods, the proposed sensor selection method can reduce the PHM score by 9% to 99% with fewer sensors. On the other hand, the proposed NAS method can reduce the number of neurons by 86% to 89% and reduce the PHM score by 17% to 79% compared with the traditional NAS approaches.

A Physics-Constrained Bayesian neural network for battery remaining useful life prediction

In order to predict the remaining useful life (RUL) of lithium-ion batteries, a capacity degradation model may be developed using either simplified physical laws or machine learning-based methods. It is observed that even though degradation models based on simplified physical laws are easy to implement, they may result in large error in the application of failure prognostics. While data-driven prognostics models can provide more accurate degradation forecasting, they may require a large volume of training data and may invoke predictions inconsistent with physical laws. It is also very challenging for existing methods to predict the RUL at the early stages of battery life. In this paper, we propose a Bayesian physics-constrained neural network for battery RUL prediction by overcoming limitations of the current methods. In the proposed method, a neural differential operator is learned from the first 100 cycles of data. The neural differential operator is modeled with a Bayesian neural network architecture that separates the fixed history dependence from the time dependence to isolate epistemic uncertainty quantification. Using the battery dataset presented in the paper by Severson et al. as an example, we compare our proposed method with a simplified physics-based degradation forecasting model and two data-driven prognostics models. The results show that the proposed physics-constrained neural network can provide more accurate RUL estimation than the other methods with the same group of training data. Most importantly, the proposed method allows for RUL prediction at earlier stages of the battery life cycle.

Remaining Useful Life Estimation Using Fault to Failure Transformation in Process Systems

The remaining useful life (RUL) plays a significant role in the predictive maintenance of process systems. In recent years, data-driven approaches have been used to estimate the RUL. However, without a deeper understanding of process systems and their failure mechanisms, it is challenging to estimate the RUL for process systems. This demands an approach that integrates data with mechanistic understanding. This article proposes a model to estimate the RUL of process systems in real time by monitoring the system's fault condition. The fault is modeled using real-time observed data, while the progression of fault to failure is modeled using mechanistic understanding. These steps are carried out using a novel mixed model combining machine learning-based autonomous fault diagnosis with root cause analysis and a statistical degradation model. The autonomous RUL estimation method is then developed as a self-learning model. A fault dictionary is developed to store the fault patterns and failure margin for different failure conditions. The proposed approach is benchmarked using the Tennessee Eastman process.

Dynamic predictive maintenance for multiple components using data-driven probabilistic RUL prognostics: The case of turbofan engines

The increasing availability of condition-monitoring data for components/systems has incentivized the development of data-driven Remaining Useful Life (RUL) prognostics in the past years. However, most studies focus on point RUL prognostics, with limited insights into the uncertainty associated with these estimates. This limits the applicability of such RUL prognostics to maintenance planning, which is per definition a stochastic problem. In this paper, we therefore develop probabilistic RUL prognostics using Convolutional Neural Networks. These prognostics are further integrated into maintenance planning, both for single and multiple components. We illustrate our approach for aircraft turbofan engines. The results show that the optimal replacement time for the engines is close to the lower bound of the 99% confidence interval of the RUL estimates. We also show that our proposed maintenance approach leads to a cost reduction of 53% compared to a traditional Time-based maintenance strategy. Moreover, compared with the ideal case when the true RUL is known in advance (perfect RUL prognostics), our approach leads to a limited number of failures. Overall, this paper proposes an end-to-end framework for data-driven predictive maintenance for multiple components, and showcases the potential benefits of data-driven predictive maintenance on cost and reliability.

A data driven methodology for upscaling remaining useful life predictions: From single- to multi-stiffened composite panels

In this paper we execute a complex test campaign to develop a novel methodology for the Remaining Useful Life (RUL) estimation of complex multi-stiffened composite aeronautical panels utilizing Machine Learning models trained with Structural Health Monitoring (SHM) data from hierarchically simpler elements, i.e., single-stiffened panels. Distributed Fiber Optical sensors (DFOS) are employed to monitor the panels’ behavior undergoing variable amplitude compression-compression fatigue after multiple impacts. A data processing methodology is first applied to the DFOS data, to both alleviate the effect of the variable loading conditions on the monitored strain and ease the computational burden. In this upscaling endeavor, an advanced strain-based Health Indicator (HI) based on Genetic algorithms, created and validated on the single-stiffened panel data, is utilized as the prognostic feature for the RUL estimations of the multi-stiffened panels. The HI displays favorable characteristics in terms of monotonicity and prognosability which are highly desirable for more accurate RUL estimations. For the prognostic task, standard machine learning models are trained using the historical degradation data of the single-stiffened panels and a similarity analysis is performed to enhance the accuracy when predicting the RUL of the multi-stiffened panels. Despite the increased structural complexity of the multi-stiffened panels, we demonstrate that the RUL is able to be predicted with reasonable accuracy. The present work paves the road for upscaling and applying prognostic methodologies to more complex structures beyond simple coupons or generic elements.

Remaining Useful Life Estimation of Spindle Bearing Based on Bearing Load Calculation and Off-Line Condition Monitoring

Spindles are key components of machine tools. An efficient estimation of the spindle condition and its prognosis can improve production efficiency and quality due to predictive maintenance planning. This paper proposes a method for predicting the remaining useful life (RUL) of machine tool spindle bearings using a combined calculation and experimental approach. The calculation model based on the ISO 281 standard uses monitored real loading conditions caused by the machining process and the machine tool operation. The model enables the updated calculation of the spindle lifetime L10h using real load distribution. Since the operation hours of the spindle are also monitored, the remaining useful life (RUL) of the spindle can be calculated. This RUL value is corrected using a bearing condition assessment based on the effective value of the vibration velocity RMS according to the ISO 20816 standard and measured data from the machine tool control system. The proposed method is tested on two different spindle types featuring three pieces of every type. The experimental results of six spindles are compared and validated with a concurrent blind evaluation conducted by a skilled expert. The validation shows a very good match of the proposed method and the expert opinion. The method combining a calculation of the spindle lifetime using monitored real load distribution and subsequent result correction using vibration signal enables the implementation of a full automated estimation of the spindle RUL.

Accurate long-term prognostics of proton exchange membrane fuel cells using recurrent and convolutional neural networks

Estimating the remaining useful life (RUL) of proton exchange membrane fuel cells (PEMFCs) is key to predicting and increasing their durability. This paper investigates six deep learning techniques – long short-term memory (LSTM) networks, gated recurrent units (GRU), 1-D convolutional neural network (CNN)-LSTMs, 1D–CNN–GRUs, 1D–CNN–Bidirectional-LSTMs, and 1D–CNN–Bidirectional-GRUs – for RUL and long-term degradation trend prediction for a five-cell PEMFC stack operated with and without current ripples. The hyperparameters of all models are optimized for minimum root-mean-square error (RMSE) of the stack voltage using tree-structured Parzen estimators (TPE) with hyperband pruning. The obtained prediction results are benchmarked using the coefficient of determination (R2), RMSE, and mean absolute percentage error (MAPE) in stack voltage predictions and relative error (RE) in RUL estimates. The comparative analysis for models trained on 50% datasets reveals that the best R2, RMSE, MAPE, and RE of 98.87E-2, 1.258E-3, 0.285E-1, and 0.0425E-1 are offered by the LSTM model for the stack without current ripples. Further, for the stack with current ripples, the best R2, RMSE, MAPE, and RE of 99.482E-2, 1.77E-3, 0.444E-1, and 0.089E-1 are exhibited by the 1D–CNN–Bidirectional-GRU model. The LSTM model also reveals excellent transfer learning performance on the stack with current ripples with the best R2, RMSE, MAPE, and RE of 98.91E-2, 2.455E-3, 0.362E-1, and 0.044E-1, respectively.

Controlled physics-informed data generation for deep learning-based remaining useful life prediction under unseen operation conditions

Limited availability of representative time-to-failure (TTF) trajectories either limits the performance of deep learning (DL)-based approaches on remaining useful life (RUL) prediction in practice or even precludes their application. Generating synthetic data that is physically plausible is a promising way to tackle this challenge. In this study, a novel hybrid framework combining the controlled physics-informed data generation approach with a deep learning-based prediction model for prognostics is proposed. In the proposed framework, a new controlled physics-informed generative adversarial network (CPI-GAN) is developed to generate synthetic degradation trajectories that are physically interpretable and diverse. Five basic physics constraints are proposed as the controllable settings in the generator. A physics-informed loss function with penalty is designed as the regularization term, which ensures that the changing trend of system health state recorded in the synthetic data is consistent with the underlying physical laws. Then, the generated synthetic data is used as input of the DL-based prediction model to obtain the RUL estimations. The proposed framework is evaluated based on new Commercial Modular Aero-Propulsion System Simulation (N-CMAPSS), a turbofan engine prognostics dataset where a limited availability of TTF trajectories is assumed. The experimental results demonstrate that the proposed framework is able to generate synthetic TTF trajectories that are consistent with underlying degradation trends. The generated trajectories enable to significantly improve the accuracy of RUL predictions.

Remaining Useful Lifetime Prediction Based on Extended Kalman Particle Filter for Power SiC MOSFETs.

Nowadays, the performance of silicon-based devices is almost approaching the physical limit of their materials, which have difficulty meeting the needs of modern high-power applications. The SiC MOSFET, as one of the important third-generation wide bandgap power semiconductor devices, has received extensive attention. However, numerous specific reliability issues exist for SiC MOSFETs, such as bias temperature instability, threshold voltage drift, and reduced short-circuit robustness. The remaining useful life (RUL) prediction of SiC MOSFETs has become the focus of device reliability research. In this paper, a RUL estimation method using the Extended Kalman Particle Filter (EPF) based on an on-state voltage degradation model for SiC MOSFETs is proposed. A new power cycling test platform is designed to monitor the on-state voltage of SiC MOSFETs used as the failure precursor. The experimental results show that the RUL prediction error decreases from 20.5% of the traditional Particle Filter algorithm (PF) algorithm to 11.5% of EPF with 40% data input. The life prediction accuracy is therefore improved by about 10%.

RUL Estimation for Rolling Bearings Using Augmented Quaternion-Based Least Mean P-Power With Correntropy Induced Metric Under Framework of Sparsity

Accurate remaining useful life (RUL) estimation of rolling bearings can significantly improve the safety, availability, reliability and productivity of a rotating machinery system. In this article, a new approach of RUL estimation for rolling bearings based upon the fractional-order spatiotemporal sparse low-rank matrix (FST-SLRM) and augmented quaternion least mean p-power with correntropy induced metric (AQLMP-CIM) is originally proposed. Specifically, the proposed approach includes three modules: the construction of the fused health indicator, which fuses the classical features and spectral kurtosis derived indices; the decomposition of the static and dynamic components, the fused health indicator time series (FHITS) is decomposed by the FST-SLRM algorithm, thus low- and high- frequency trend components (i.e., LFCs, HFCs) are obtained, respectively; and the prognostics of degradation trajectory and RUL estimation, the degradation trajectories are obtained by the AQLMP-CIM algorithm via integrating the predicted LFC and HFC, and the RUL is eventually acquired. Two experimental cases are conducted on run-to-failure fatigue test of rolling bearings, the results demonstrate that the proposed approach is able to achieve better performance compared with state-of-the-art benchmarks.

A spatiotemporal feature learning-based RUL estimation method for predictive maintenance

Studies that apply deep learning (DL) methods to maintenance support systems have achieved many successes because degradation patterns and remaining useful life (RUL) of critical equipment can be described and predicted by DL techniques. However, mining spatial and temporal dependencies from multivariate sensor signals and fusing spatiotemporal features sufficiently are challenging tasks. In this proposal, a novel signal-level DL framework containing three layers called STRUL is proposed for end-to-end RUL estimation. The first data segmentation layer is designed based on the sliding window manner which makes STRUL work directly on raw signals. Then, in the information extraction layer, two feature extractors based on the convolutional neural network are used synchronously to learn spatial and temporal features from each time series. The last information aggregation layer is designed to fuse features so that the holistic spatiotemporal features can be learned and further contribute to RUL prediction. The proposed STRUL model achieves better comprehensive performance on RUL estimation tasks than existing models, which has been verified by two case studies.

Self-Supervised Learning for data scarcity in a fatigue damage prognostic problem

With the increasing availability of data for Prognostics and Health Management (PHM), Deep Learning (DL) techniques are now the subject of considerable attention for this application, often achieving more accurate Remaining Useful Life (RUL) predictions. However, one of the major challenges for DL techniques resides in the difficulty of obtaining large amounts of labelled data on industrial systems. To overcome this lack of labelled data, an emerging learning technique is considered in our work: Self-Supervised Learning, a sub-category of unsupervised learning approaches. This paper aims to investigate whether pre-training DL models in a self-supervised way on unlabelled sensors data can be useful for RUL estimation with only Few-Shots Learning, i.e. with scarce labelled data. In this research, a fatigue damage prognostics problem is addressed, through the estimation of the RUL of aluminum alloy panels (typical of aerospace structures) subject to fatigue cracks from strain gauge data. Synthetic datasets composed of strain data are used allowing to extensively investigate the influence of the dataset size on the predictive performance. Results show that the self-supervised pre-trained models are able to significantly outperform the non-pre-trained models in downstream RUL prediction task, and with less computational expense, showing promising results in prognostic tasks when only limited labelled data is available.

To Charge or to Sell? EV Pack Useful Life Estimation via LSTMs, CNNs, and Autoencoders

Electric vehicles (EVs) are spreading fast as they promise to provide better performance and comfort, but above all, to help face climate change. Despite their success, their cost is still a challenge. Lithium-ion batteries are one of the most expensive EV components, and have become the standard for energy storage in various applications. Precisely estimating the remaining useful life (RUL) of battery packs can encourage their reuse and thus help to reduce the cost of EVs and improve sustainability. A correct RUL estimation can be used to quantify the residual market value of the battery pack. The customer can then decide to sell the battery when it still has a value, i.e., before it exceeds the end of life of the target application, so it can still be reused in a second domain without compromising safety and reliability. This paper proposes and compares two deep learning approaches to estimate the RUL of Li-ion batteries: LSTM and autoencoders vs. CNN and autoencoders. The autoencoders are used to extract useful features, while the subsequent network is then used to estimate the RUL. Compared to what has been proposed so far in the literature, we employ measures to ensure the method’s applicability in the actual deployed application. Such measures include (1) avoiding using non-measurable variables as input, (2) employing appropriate datasets with wide variability and different conditions, and (3) predicting the remaining ampere-hours instead of the number of cycles. The results show that the proposed methods can generalize on datasets consisting of numerous batteries with high variance.

Integrated machine learning and probabilistic degradation approach for vessel electric motor prognostics

In the transition towards more sustainable ships, electric motors (EM) are being used in ship propulsion systems to reduce emissions and increase efficiency. The safe operation of ships is crucial, and prognostics and health management applications have emerged as effective solutions to transit towards monitored reliable systems. In this context, this paper presents a probabilistic EM prognostics model integrating data-driven operational models and physics-informed degradation models. Firstly, motor torque and winding temperature are estimated through connected machine learning models, which are based on operational and meteorological data. Operational and meteorological variables drive the EM degradation model and enable the analysis of EM degradation under different operational and environmental conditions. Subsequently, EM remaining useful life (RUL) is predicted within a probabilistic Monte-Carlo approach combining the thermal-stress model along with the associated uncertainties. The methodology is tested on a real case study of the OV Ryvingen vessel, with collected data during voyages along the Norwegian coast. Results confirm the validity of the designed RUL model showing that, under normal operation conditions, the degradation is mild, and the temperature measurement errors are important for RUL estimation.

A Novel Remaining Useful Estimation Model to Assist Asset Renewal Decisions Applied to the Brazilian Electric Sector

Assets deteriorate over time, as well as being covered, corroded, or becoming old in less obvious ways. Maintenance can extend the remaining useful life (RUL) of an asset system, but sooner or later it must surely be replaced. In this study, we propose a new RUL estimation methodology to assist in decision making for the maintenance and replacement of assets from prioritizing equipment in a renovation plan. Our methodology uses advanced data analysis techniques that consider multiple competing criteria with the goal of maximizing values of the asset throughout its life cycle, while considering the rules of remuneration and service quality of the current regulation, as well as the values at risk according to the decisions and actions taken. Experimental results with real datasets show the efficiency of the proposed approach. Finally, this work also presents the development of an analytical tool to optimize asset renewal decisions applying the RUL estimation methodology proposed and its application to the Brazilian electric sector.

Demonstration of a Response Time Based Remaining Useful Life (RUL) Prediction for Software Systems

Prognostic and Health Management (PHM) has been widely applied to hardware systems in the electronics and non-electronics domains but has not been explored for software. While software does not decay over time, it can degrade over release cycles. Software health management is confined to diagnostic assessments that identify problems, whereas prognostic assessment potentially indicates when in the future a problem will become detrimental. Relevant research areas such as software defect prediction, software reliability prediction, predictive maintenance of software, software degradation, and software performance prediction, exist, but all of these represent diagnostic models built upon historical data – none of which can predict an RUL for software. This paper addresses the application of PHM concepts to software systems for fault predictions and RUL estimation. Specifically, this paper addresses how PHM can be used to make decisions for software systems such as version update/upgrade, module changes, system re-engineering, rejuvenation, maintenance scheduling, budgeting, and total abandonment. This paper presents a method to prognostically and continuously predict the RUL of a software system based on usage parameters (e.g., the numbers and categories of releases) and performance parameters (e.g., response time). The model developed has been validated by comparing actual data, with the results that were generated by predictive models. Statistical validation (regression validation, and k-fold cross validation) has also been carried out. A case study, based on publicly available data for the Bugzilla application is presented. This case study demonstrates that PHM concepts can be applied to software systems and RUL can be calculated to make system management decisions.