Search

In many settings, fleets of assets must perform series of missions with in-between finite breaks. For such fleets, a widely used maintenance strategy is the fleet selective maintenance (FSM). Under resource constraints, the FSM problem selects an optimal subset of feasible maintenance actions to be performed on a subset of components to minimise the maintenance cost while ensuring high system reliability during the upcoming mission. The majority of extant FSMP models are focussed on traditional physics-based reliability models. With recent advances in Machine Learning (ML) and Deep Learning (DL) algorithms, data-driven methods have shown accuracy in predicting remaining useful life (RUL). This paper proposes a predictive FSM strategy for fleets of complex and large multicomponent systems. It relies on a concurrent ML/DL and optimisation approach where a clustering algorithm is used to determine the health states of components and a probabilistic RUL prognostics model is used for component reliability assessment. An optimisation model is developed to solve the predictive FSM problem to ensure high reliability of all systems within the fleet. An efficient two-phase solution approach is developed to solve this complex optimisation problem. Numerical experiments show the validity of the approach and highlight the improved maintenance plans achieved. [ABSTRACT FROM AUTHOR]

The remaining useful life (RUL) prediction based on deep learning obtains certain prediction results by training model with deterministic parameters. However, this method ignores the error range of parameter estimation, resulting in the inability to fully characterise the uncertainty. Therefore, a RUL prediction method based on anomaly correction is proposed. Firstly, to address the problem of RMS deviating from the degradation trajectory caused by external random factors, this paper proposes an adaptive time window anomaly correction strategy with sliding windows are used to construct degenerate slope. Secondly, to solve the problem of prediction result errors caused by changing random factors, this paper considers heteroscedasticity in prognosis and constructs a probability density function library to dynamically match the probability distribution. Then, aiming at the mean value as the prediction result may lead to overconfidence, a probability-based weighted enhanced method is proposed to improve the prediction accuracy. Finally, two datasets are used to verify the effectiveness and superiority of the proposed method. [ABSTRACT FROM AUTHOR]

Advanced reactor designers are looking to maximize the system capacity factor to make advanced reactors more economically competitive and meet the projected energy demand. To achieve this goal, we propose a Dynamic Operation and Maintenance Optimization (DyOMO) framework to perform system-level predictive maintenance (PdM) using a dynamic Bayesian network and component-specific PdM using deep neural networks. At the system level, DyOMO detects the presence of anomalous phenomena, determines the most influential degradation mode, and estimates the remaining useful life (RUL) distribution for the system. At the component level, DyOMO summarizes the health state of key system components, determines the presence of an anomaly using a feedforward neural network, and predicts component RUL using a Bayesian neural network. To evaluate the overall performance of DyOMO, normal operations of a Pebble-Bed High-Temperature Gas-cooled Reactor (PB-HTGR) were simulated with realistic component degradation for the steam turbine and steam generator. Across the 20 independent reactor life simulations, it was found that maintenance was always performed before any safety limits were violated and before a component failed. Specifically, the system-level PdM suggested maintenance on the steam generator once the steam pressure approached its safety limit, and the component-specific PdM suggested maintenance on the steam turbine once the turbine blade hardness degraded. The results indicate that through the continuous monitoring of the system and individual components, the DyOMO framework improves safety and increases the availability of the reactor when compared to traditional maintenance philosophies. [ABSTRACT FROM AUTHOR]

Bearings, essential in industrial rotating machinery, undergo progressive wear over time. This degradation occurs in multiple stages with varying rates, characteristic changes, and information content, presenting challenges for accurate remaining useful life (RUL) prediction. Existing methods do not account for the impact of multi-stage degradation characteristic differences on the prediction model, leading to significant prediction errors. This paper presents a novel dynamic feedback mechanism-driven approach based on multi-stage degradation characteristics. The method introduces a trend detection technique to segment monitoring data into distinct degradation stages. By continuously updating the parameters of the degradation model, the model accurately identifies transition points between stages. In a key innovation, a dynamic feedback mechanism is established between multi-stage features and multi-scale parameters, integrated with a multi-scale densely connected temporal convolutional network (TCN) prediction model. This mechanism enables adaptive adjustments to dilation rates and kernel sizes in response to feature variations across different stages, facilitating the precise extraction of stage-specific degradation patterns. Experimental validation using the XJTU-SY and SMU bearing datasets confirms that the proposed method outperforms existing approaches in terms of degradation feature extraction and multi-stage adaptive prediction, showcasing its practical applicability and superior performance in complex industrial settings.. [ABSTRACT FROM AUTHOR]

Predicting the remaining useful life (RUL) of rolling bearings is crucial for industrial machinery maintenance, non-destructive testing and evaluation (NDT). To address the challenges posed by noise interference and redundant information, this paper proposes a novel approach utilising residual attention networks and multi-scale feature extraction. The method enhances feature extraction by combining shallow and deep convolutional layers while employing bidirectional LSTM to capture both short-term and long-term dependencies in time series data. The incorporation of a residual attention fusion module further enhances the model’s ability to focus on important features, ensuring more stable training and better prediction performance. After validation on PHM2012, IMS, and laboratory self-constructed datasets, the proposed model demonstrates superior performance compared to existing methods, significantly reducing prediction errors. The practical application of this work lies in its potential integration into industrial predictive maintenance systems, providing a solid foundation for expanding predictive maintenance strategies in complex real-world industrial environments. [ABSTRACT FROM AUTHOR]

Deep learning techniques play a crucial role in predicting the remaining useful life (RUL) of mechanical equipment. Nevertheless, obtaining a substantial number of labeled samples is a challenge, and the prediction accuracy tends to decline when the labeled samples are insufficient. Moreover, existing RUL prediction methods usually extract the degradation characteristics only from one single domain, which is insufficient for a high-accuracy prediction. To address these challenges, a time-frequency synchronization contrastive learning-driven (TFSCL) multi-sensor remaining useful life prediction model is proposed. The proposed TFSCL utilizes a large amount of unlabeled data for model pre-training and key feature extraction, and it introduces a novel time-frequency fusion contrastive loss function to optimize the pre-training process. It employs a dual-channel structure at the sensor and timestamp levels, incorporating an attention mechanism that adaptively adjusts sensor feature weights, enabling more accurate extraction of critical information while effectively mitigating interference from irrelevant data. To validate the effectiveness of the proposed TFSCL, two case studies are conducted, with different labeling ratios being used. The experimental results demonstrate that even with lower labeling ratios, the proposed TFSCL model still achieves a satisfactory prediction effect and outperforms other advanced methods. [ABSTRACT FROM AUTHOR]

Prognosis and Health Management (PHM) is crucial for ensuring the reliable operation of structural components, such as bracing members. Despite this, limited study exists for the RUL estimation of civil engineering components. This paper presents a nested framework utilizing the Least Square Support Vector Regression (LS-SVR) for accurately predicting the Remaining Useful Life (RUL) of axially loaded members. The framework addresses the challenges of sparse data and multidimensional damage-sensitive features (DSFs) by employing a two-stage process. In the first stage, DSFs are forecasted using one-dimensional mapping, providing essential inputs for the second stage, where axial stiffness degradation is predicted using LS-SVR. The proposed framework is validated through an experimental study on axially loaded members subjected to low-cycle fatigue. To enhance model performance, simulated data generated from an OpenSees model is combined with the experimental data. The nested LS-SVR framework demonstrates superior performance compared to traditional methods, achieving high accuracy in RUL estimation as evidenced by the Root Mean Square Error (RMSE) and Mean Absolute Error (MAE) metrics. The framework's ability to forecast axial stiffness degradation, a critical indicator of structural health, makes it a valuable tool for real-time assessment of structural component RUL. By integrating this framework with real-time monitoring systems, proactive maintenance strategies can be implemented, leading to safer and more efficient structural health management. [ABSTRACT FROM AUTHOR]

Machining tools are vital components of intelligent manufacturing systems whose state and remaining useful life (RUL) determine product quality. Specifically, the wearing of tool reduces its capability of production yield and diminishes product quality. Therefore, a capability-based RUL prediction approach is proposed in this paper to thoroughly evaluate the state and RUL of machining tools. First, the connotation of tool capability is discussed, and a framework for quality assurance capability-based RUL prediction is proposed. Product quality, which can be used to assess the capability of tool, is modelled and expanded to consider non-geometric dimensioning and tolerancing (non-GD&T) features based on the classic geometric dimensioning and tolerancing (GD&T) system. Second, a physics-based model of process is developed to estimate the non-GD&T features and calculate tool wear. Third, a hybrid data-driven and physics-based model is developed to quantitatively assess the capability of tool based on the comprehensive quality estimation. Finally, a case study of rolling machining tool is carried out to verify the effectiveness and proactiveness of the proposed framework, and the final result highlights its rationality and accuracy in estimating the RUL of machining tools with better interpretation. [ABSTRACT FROM AUTHOR]

To function effectively, nuclear power plants rely on the effective filtration of air, water, and process fluids, examples of which include inlet sea water, reactor coolant, plant drinking water, and moderator purification. Filtration assets degrade over time, which impairs their filtering performance and reduces the flow rate. Being able to determine the remaining useful life (RUL) of a filter could result in benefits, particularly when moving from a time-based to a condition-based maintenance strategy that would optimize the filter replacement procedure and reduce early replacement of filters that are still fit for purpose. For many filter applications, a time-based strategy is sufficient. For strategically important assets, such as fueling machines, there are benefits to be gained from the development of predictive maintenance strategies. In this paper, we propose a predictive condition-based strategy using differential pressure data as a proxy for filter health. The key objective in this work was the creation of a model that could predict a filter asset RUL. The differential pressure for 7 to 14 days is predicted by a heuristic-based regression model of the history of each filter. This approach has been demonstrated using a civil nuclear generation application but could be applied to wider applications. While this model is still undergoing on-site evaluation, it has been estimated that there will be an operationally significant lifetime cost reduction. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

AbstractRemaining useful life (RUL) prediction is an essential tool for enhancing the reliability and resilience of systems. Most existing RUL prediction methods consider degradation-induced failures, and assume there exists a fixed failure threshold for degradation signals. In many real applications, however, it is difficult or even impossible to find such failure thresholds, making the RUL prediction a challenging task. This study addresses the challenge by exploiting the method of forward intensity, a novel tool introduced in econometrics. In particular, the historical degradation signals are treated as time-varying covariates for the forward intensity. The dynamics of unobserved future degradation signals are captured by a time-varying regression parameter in the forward intensity function, which are usually estimated using the maximum pseudolikelihood method in existing studies. To improve prediction accuracy, this study proposes a new estimation method based on smoothing splines. The proposed method not only allows RUL prediction in the absence of a fixed failure threshold, but also achieves satisfactory prediction accuracy with reasonable interpretability of covariate effects. Prediction intervals for the RUL are also developed. The effectiveness of the proposed method is validated through Monte Carlo simulations and three real-data examples. The results show that the proposed method outperforms existing methods in terms of prediction accuracy. [ABSTRACT FROM AUTHOR]

Due to the complex and diverse operating conditions of rolling bearings, it is difficult to accurately predict remaining useful life (RUL) of rolling bearings via traditional prediction models. Besides, when a rolling bearing malfunctions, only single channel or single-domain degradation information is considered to bear RUL prediction, and the prediction effect of existing RUL prediction methods is greatly limited. Therefore, in order to address the above issue, a novel method abbreviated as CNN-GRU-MSA with multi-channel feature fusion is proposed for RUL prediction of rolling bearings. Firstly, the statistical features related to the time series are calculated, and the similarity features are constructed based on the obtained statistical features. Then, the sensitive features are selected and fused through specific indicators. Finally, the dual-channel feature fusion is performed to construct a health indicator (HI), which is input into the proposed CNN-GRU-MSA model for training and achieving RUL prediction of rolling bearings. The effectiveness of the proposed method is validated using two benchmark datasets (i.e. IEEE PHM 2012 challenge datasets and XJTU-SY datasets). Experimental results demonstrate the superiority and effectiveness of the proposed method over other similar prediction methods in bearing RUL prediction. [ABSTRACT FROM AUTHOR]

Remaining Useful Life (RUL) prediction of rolling bearings is one of the intricate and important issues for equipment intelligent maintenance and health management. Various machine learning models and methods have been applied to rolling bearing RUL prediction. However, a single model cannot effectively extract state information and obtain accurate prediction results, and its generalisation is not stable under the condition of small sample data. Therefore this paper proposes an intelligent hybrid deep learning model for achieving accurate RUL prediction of rolling bearings. Firstly, the one-dimensional vibration signal is transformed into the corresponding two-dimensional time-frequency diagram via Continuous Wavelet Transform (CWT). Secondly, the diagram is input into a Multilayer Perceptron (MLP) consisting of a basic three-layer feed-forward network to obtain a one-dimensional feature vector. And lastly, the obtained feature vector is input into an integrated model based on Deep Autoregressive and Transformer to produce the probability distribution and obtain the prediction results of rolling bearing RUL. Extensive experiments on two rolling bearing datasets show that the proposed model outperforms six other comparative models in extracting bearing fault features and predicting bearing RUL, which demonstrates that the proposed model can effectively extract bearing fault features and accurately predict bearing remaining useful life. [ABSTRACT FROM AUTHOR]

Proton exchange membrane fuel cell (PEMFC) is considered as one of the most promising green energy devices. Although fruitful results can be available for the remaining useful life (RUL) prediction of PEMFC, stochastic uncertainties have never been considered. To tackle this problem, a hybrid method is proposed in this paper. Wiener process with temporal uncertainty and individual uncertainty is adopted to model the degradation of the state of health (SOH), which is then estimated from monitoring voltage with measurement noise using the unscented Kalman filter (UKF), where unknown filtering and model parameters are jointly identified by expectation-maximization (EM) algorithm and Rauch-Tung-Striebel (RTS) smoother. Finally, gated recurrent unit (GRU) network is employed to realize the RUL prediction with the prediction uncertainty quantified by the Bayesian variational inference technology. The proposed method is verified on the experimental data. Results indicate that smaller mean absolute percentage error (MAPE), root mean square error (RMSE), and mean absolute error (MAE) values can be obtained compared with other methods. When 60% data are used for prediction, the proposed method can achieve a RUL prediction accuracy with 1.63% and 2.17% relative errors under static and dynamic conditions, respectively, which illustrates the feasibility and superiority of the proposed method. [ABSTRACT FROM AUTHOR]

In this paper, statistical inference of an inverted exponentiated Rayleigh model is studied when the failure times are obtained under a modified progressive hybrid censoring. The maximum likelihood estimators of the model parameters together with associated existence and uniqueness are established, and approximate confidence intervals are constructed based on asymptotic theory. Alternatively, generalized point and interval estimates for unknown parameters are also constructed based on the proposed pivotal quantities for comparison. In addition, predictive intervals of remaining useful life from the inverted exponentiated Rayleigh distribution are also constructed under classical and generalized inferential approaches, respectively. Finally, extensive simulation studies are carried out to compare the performance of the proposed methods, and two real-life examples are analyzed for illustration. The numerical results indicate that both traditional likelihood and generalized inferential methods work satisfactorily, and that our proposed generalized approach appears much more appealing and are superior to classical results. [ABSTRACT FROM AUTHOR]

Silk is highly susceptible to fade, often resulting in colour loss to the fabric even when displayed in controlled museum environments. This study applies the engineering-inspired Prognostics and Health Management (PHM) approach to assess the remaining useful life (RUL) of silk fabric in a museum environment, focussing on predicting colour fade as an indicator of degradation. A novel mathematical model is developed to forecast cumulative colour fade of silk upholstery exhibited at the Great Gallery in The Wallace Collection, London. Unlike traditional accelerated aging methods, this model utilises naturally aged samples to estimate the rate of colour change over time. The main contribution of this work lies in the methodology and computational framework for model development using environmental data and conditions of silk in the museum environment. The proposed PHM methodology allows for continuous modifications of the colour fade model to improve accuracy by deploying new data from different silk collections and environments. The article demonstrates a model-based approach for informed decision making in museums regarding display and storage of silk upholstery. [ABSTRACT FROM AUTHOR]

AbstractMost prognostic methods require a decent amount of data for model training. In reality, however, the amount of historical data owned by a single organization might be small or not large enough to train a reliable prognostic model. To address this challenge, this article proposes a federated prognostic model that allows multiple users to jointly construct a failure time prediction model using their multi-stream, high-dimensional, and incomplete data while keeping each user’s data local and confidential. The prognostic model first employs multivariate functional principal component analysis to fuse the multi-stream degradation signals. Then, the fused features coupled with the times-to-failure are utilized to build a (log)-location-scale regression model for failure prediction. To estimate parameters using distributed datasets and keep the data privacy of all participants, we propose a new federated algorithm for feature extraction. Numerical studies indicate that the performance of the proposed model is the same as that of classic non-federated prognostic models and is better than that of the models constructed by each user itself. [ABSTRACT FROM AUTHOR]

Remaining useful life (RUL) prediction is an important issue in prognostics and health management (PHM). Numerous studies have been conducted to construct degradation models for RUL prediction. However, their models fail to handle the scenarios where multiple failure modes exist, especially when the failure modes are unknown (unlabeled) beforehand and need to be recognized. This paper develops a multimodal recognition and prognostic method based on features extracted via multisensor degradation modeling. Specifically, we assume the failure mode of a unit follows a multinomial distribution. Given the failure mode distribution, we characterize the degradation status of the unit via degradation models based on each sensor signal and a constructed health index (HI). Our innovative idea is to extract features as the derivatives of the degradation status to comprehensively utilize information from multiple sensors for more effective failure mode recognition and RUL prediction. We develop a fusion coefficient-integrated expectation-maximization (FCIEM) algorithm to estimate model parameters by using data from historical units. Finally, we recognize the failure mode and predict the RUL of in-service units based on their extracted features and degradation status. Numerical experiments and a case study of aircraft engines were conducted to evaluate the performance of our proposed method. [ABSTRACT FROM AUTHOR]

In metal cutting processes, tool condition monitoring has a great importance to prevent surface damage and maintaining the quality of surface finishing. With the development of digitalisation and connection of industrial machines, it has become possible to collect real-time data from various types of sensors (e.g. vibration, acoustic or emission) during the process execution. However, information fusion from multiple sensor signals and tool health prediction still present a big challenge. The aim of this paper is to present a data-driven framework to estimate the tool wear status and predict its remaining useful life by using machine learning techniques. The first part of the framework is dedicated to sensor data preprocessing and feature engineering, while the second part deals with the development of prediction models. Different types of machine learning algorithms are used and compared to find the best result. A case study in a milling process is presented to illustrate the potentialities of the proposed framework for tool condition monitoring. [ABSTRACT FROM AUTHOR]

For products whose performance characteristic (PC) gradually degrades with time, one usually observes its degradation levels repeatedly to predict its remaining useful life (RUL). Due to the limited storage space of the server and the low resolution of a measurement instrument, we seldom record the low-magnitude degradation values at the early degradation stage in applications. Such observation setting introduces left-truncated degradation data, in which the data collection starts later than the unit's installation. This brings sampling biases and complicates the degradation data analysis. Moreover, due to the uncontrollable factors in applications, the degradation drift and the degradation diffusion may differ among various units. Motivated by an application of high-speed train bearings, we propose a Wiener process model for the left-truncated degradation data and jointly consider the drift-diffusion random effects. Closed-form formulas are available in the expectation-maximization (EM) algorithm for estimating the model parameters. We derive the RUL distribution in closed form. We also extend the proposed model to the multivariate degradation process. The parameters are estimated with the help of the Monte Carlo EM (MCEM) algorithm. An additional laser application illustrates the performance of the proposed model in RUL prediction, which may help to design a predictive maintenance strategy [ABSTRACT FROM AUTHOR]

In prognostics and health management, the system's degradation condition assessment and corresponding remaining useful life prediction are the most important tasks. Both of these processes are heavily dependent on information gathered by multiple sensors, which eventually causes data fusion-related complex problems. Typically, sensor information contains the speed, pressure, temperature, and similar other types of various system data. These systems' data obtained through sensors can be utilized as a part of the evidence in the evidence-based estimation method. In this work, an artificial intelligence-based novel framework for estimating the remaining useful life using data fusion has been presented. The Dempster–Shafer extended theory is adopted for sensor information modeling and data fusion. Besides, two different scenarios are introduced to determine the similarity between the studied system and the available evidence. As a case study, the turbofan dataset is demonstrated to assess the proposed method. Based on the results, our integrated proposed method performs very competitively compared with the existing methods based on standard scores and performance criteria. [ABSTRACT FROM AUTHOR]

Proton exchange membrane fuel cell (PEMFC) is a new type of clean energy with great development potential. However, as working time increase, the output power of the PEMFC will then be reduced. By predicting the PEMFC degradation trend, faults can be detected in advance to ensure continuous and efficient working of the FC. In this paper, convolutional neural network (CNN) and bidirectional recurrent neural network (BiRNN) are integrated into a new network (CNN-BiRNN) model for voltage degradation and remaining useful life (RUL) prediction of PEMFC. The model is validated by the aging test data of two real FCs. The results indicate that the combination with CNN can significantly enhance the prediction accuracy and calculation speed of the BiRNN model. The CNN-BiRNN model has smaller mean absolute percentage error (MAPE) and mean square root error (RMSE) for voltage degradation prediction than existing models. The mean and standard deviation of the relative error (RE) of the RUL prediction of the FC for five different fault thresholds are smaller. The proposed model is more accurate in predicting the voltage degradation and RUL of PMEFC. [ABSTRACT FROM AUTHOR]

Particle Filtering (PF) has been widely used for predicting Remaining Useful Life (RUL) of industrial products, especially for those with nonlinear degradation behavior and non-Gaussian noise. Traditional PF is a recursive Bayesian filtering framework that updates the posterior probability density function of RULs when new observation data become available. In engineering practice, due to the limited accuracy of monitoring/inspection techniques, the observation data available for PF are inevitably imprecise and often need to be treated as interval data. In this article, a novel Interval Particle Filtering (IPF) approach is proposed to effectively leverage such interval-valued observations for RUL prediction. The IPF is built on three pillars: (i) an interval contractor that mitigates the error explosion problem when the epistemic uncertainty in the interval-valued observation data is propagated; (ii) an interval intersection method for constructing the likelihood function based on the interval observation data; and (iii) an interval kernel smoothing algorithm for estimating the unknown parameters in the IPF. The developed methods are applied on the interval-valued capacity data of batteries and fatigue crack growth data of railroad tracks. The results demonstrate that the developed methods could improve the performance of RUL predictions based on interval observation data. [ABSTRACT FROM AUTHOR]

Sediment deposition is an inherent phenomenon of any reservoir which causes considerable storage loss thereby disturbing the economy of the community for which the reservoir is intended to serve. Failure to take adequate remedial measures to control sedimentation would result in huge loss in storage capacity. Present paper provides the analysis of the field studies using the hydrographic surveys which were conducted on the Wyra Project, a medium irrigation reservoir built across Wyra, a tributary of river Krishna. The surveys were conducted during the period when the reservoir receives good rains. The principal objectives of the study are to assess sedimentation status, annual sedimentation rate in the reservoir and to estimate the trap efficiency (Te) of the reservoir. The 'Te' is useful for predicting the remaining useful life span of the reservoir and the pattern of sediment deposition in the reservoir. Te is also useful in regulating the irrigation water, generation of hydroelectric power and management of sediment treatment plans. Analysis of the results showed that there is a loss of about 27.66 Mm3 (39.47%) in the storage capacity of the reservoir. The sedimentation rate was about 6.86 ha.m/100 km2/year, which is higher than what was considered at the planning stage. [ABSTRACT FROM AUTHOR]

Remaining useful life (RUL) predictions are a key enabler for predictive maintenance. Data-driven approaches, typically based on deep neural networks (DNNs), have shown success in RUL prediction. However, DNNs are usually handcrafted via a labor-intensive design process. To overcome this issue, we propose a neural architecture search (NAS) technique based on a surrogate-assisted genetic algorithm that automatically discovers the optimal architectures of Transformers. To our knowledge, this is the first work to optimize the architecture of Transformers for RUL predictions using evolutionary computation. We evaluate the performance of the proposed method (in terms of RMSE and s -score) on the well-known CMAPSS benchmark dataset. Compared with the state-of-the-art, the Transformers obtained by our NAS method outperform other recent handcrafted DNNs in terms of RMSE and are comparable regarding the s -score. Our results demonstrate that the proposed method provides better prediction accuracy with less human effort compared to other data-driven approaches. [ABSTRACT FROM AUTHOR]

Complex equipment has the characteristics of diverse feature types, complex internal structures, and timing information coupling. This paper realizes a complex gated recurrent unit (GRU) network that contains monotonicity-Las Vegas wrapper based feature selection and accelerated GRU based RUL prediction. By eliminating useless data and noise data, the input data volume of the prediction model is reduced, and the efficiency and accuracy of the RUL prediction for complex equipment are effectively improved. The experimental results show our method can predict the RUL of complex equipment more efficiently and increase the prediction accuracy of GRU by 18.3%. [ABSTRACT FROM AUTHOR]

Accurate prediction of Remaining Useful Life (RUL) plays a critical role in optimizing condition-based maintenance decisions. In this article, a novel joint prognostic modeling framework that simultaneously combines both time-to-event data and multi-sensor degradation signals is proposed. With the increasing use of IoT devices, unprecedented amounts of diverse signals associated with the underlying health condition of in-situ units have become easily accessible. To take full advantage of the modern IoT-enabled engineering systems, we propose a specialized framework for RUL prediction at the level of individual units. Specifically, a Bayesian linear regression model is developed for the multi-sensor degradation signals and a functional neural network is proposed to allow the proportional hazard model to characterize the complex nonlinearity between the hazard function and degradation signals. Based on the proposed model, an online model updating procedure is established to accurately predict RUL in real time. The advantageous features of the proposed method are demonstrated through simulation studies and the application to a high-fidelity gas turbine engine dataset. [ABSTRACT FROM AUTHOR]

Electrical cables provide essential functions, such as delivery of power or instrumentation signals for monitoring systems. Most cables installed in industrial applications are constructed with organic polymer insulations that can become brittle, crack, or degrade over time from exposure to harsh environmental conditions, such as elevated temperatures, moisture, vibration, mechanical shock, and radiation. This paper describes an overall strategy for assessing the health and managing the aging of cables during the operating life of an industrial facility. This strategy involves performing condition assessments and monitoring of electrical cables using both in situ and laboratory testing techniques. It includes in situ testing to identify anomalies in the circuits, such as degraded terminations, splices, connections, and degraded sections of cable insulation, as well as as-found evaluations to determine the current condition of installed cables. These cable condition evaluations provide important information about the current state of the cable circuits. Moreover, the test results can be used to trend/monitor age-related degradation and estimate the remaining useful life of installed cables. [ABSTRACT FROM AUTHOR]

Proton-exchange membrane fuel cells (PEMFCs), as potential energy converters with broad application prospects, have low durability owing to several factors that make it difficult to quantify the degradation of PEMFC components. The accurate prediction of the remaining useful life (RUL) can help users understand the degradation status of PEMFCs and adopt reasonable maintenance strategies to improve durability. This paper proposes an RUL prediction framework based on a temporal convolutional network (TCN). First, an equivalent circuit model of the PEMFC is established, and complex nonlinear least squares regression is used to fit the model to estimate the polarization resistance. Then, the prediction framework and joint degradation indicator of the TCN are constructed to predict the RUL. The TCN is compared with four models: linear regression, Holt–Winters, seasonal autoregressive integrated moving average, and Prophet. The results show that the TCN performs significantly better in terms of all the predictive metrics, including the root-mean-squared error which is at least 13.43% lower than those of the four models. The RUL prediction accuracy of the TCN is at least 7.76% higher than that of the four models. Except at 800 h, the average RUL accuracy of TCN is 92.20%. This confirms that the TCN (double variables) can accurately predict the RUL of PEMFCs. [ABSTRACT FROM AUTHOR]

This paper concerns Remaining Useful Life (RUL) estimation of discrete event systems. For that purpose, physics-based models with partially observed stochastic Petri nets are used to represent the system and its sensors. The advantage of the proposed modelling approach is to provide a realistic representation of the system, including the interaction between the normal behaviours and the failure processes. From the proposed modelling and collected measurements, timed trajectories, which are consistent with the observations, are obtained. Based on the event dates, our approach consists in evaluating the probabilities of the consistent behaviours using probabilistic models. State estimation is obtained as a consequence. The most probable future degradations, from the current state, are then considered and a method for fault prognosis is presented. Finally, the prognosis result is used to estimate the RUL as a time interval. A case study is proposed to show the applicability of the proposed method. [ABSTRACT FROM AUTHOR]

Reverse logistics has emerged as a promising strategy for enhancing environmental sustainability through remanufacturing, reusing, or recycling used components. It is crucial to pursue quality-driven decision-making for component recovery because quality is a dominant factor for component salvage value and its recoverability. To maximise the profit from component recovery, a quality-driven decision model was proposed in this study. Remaining useful life (RUL) was utilised as a measure of quality in the proposed model, where conditional RUL distribution was predicted by utilising both the failure data and condition monitoring data based on a proportional hazard model. Under RUL uncertainty, an interval decision-making approach was developed to suggest recovery strategies for the decision-makers to identify a satisfactory solution according to their risk preferences. Compared to the existing approaches for quality-driven recovery decision-making based on RUL prediction, this work provides a more accurate and powerful approach to managing and mitigating decision risk. Numerical experiments demonstrated the effectiveness and superiority of the proposed model. [ABSTRACT FROM PUBLISHER]

This article introduces a Bayesian multiple change point model for a collection of degradation signals in order to predict remaining useful life of rotational bearings. The model is designed for longitudinal data, where each trajectory is a time series segmented into multiple states of degradation using a product partition structure. An efficient Markov chain Monte Carlo algorithm is designed to implement the model. The model is run on in situ data, where vibration measurements are taken to indicate bearing degradation. The results suggest that bearing degradation exhibit an auto-correlation structure that we incorporate into the product partition model and often experience more than one degradation phase. [ABSTRACT FROM AUTHOR]

The Journal of the Institute of Conservation has made changes to increase access to articles for underrepresented geographical areas by publishing titles and abstracts in Arabic and Portuguese in addition to Spanish and Mandarin. The second issue of 2024 includes articles on topics such as predicting the color fade of silk upholstery, the dialogue between science and conservation, predicting changes in insect demographics in the UK, the devaluation of cultural heritage in southern Ethiopia, and activating archives of neo-avant-garde art. These articles highlight the diverse perspectives and scales of understanding within the field of conservation. [Extracted from the article]

The large tonnage mines use railway transportation as a system for mineral transportation. The rolling stock health condition study and improvement not only reduce the lifecycle cost of the assets but also ensures safe, reliable, punctual, and efficient transportation. The remaining useful life estimation is an efficient approach to condition-based maintenance, prognostics, and health management. This paper aims to predict the remaining life of a mining rolling stocks in the presence of operational environmental effects. In this study, the operation and failure data were obtained from Malmbana, LKAB, Sweden, a Swedish Railway Company, considering the effective operational factors. The failure behaviour of the railcar was evaluated and then the proportional hazard model was used to estimate the conditional reliability functions and accordingly the remaining useful life at the various initial survival time. Finally, the reliability-based time interval is applied to plan the maintenance operations. Results of this study show that the operator's skill level and the maintenance quality had a significant influence on the reliability performance. By considering the proposed PM plan according to the desired reliability level, the remaining lifetime of the rolling stock will be improved by 78.10%, on average. [ABSTRACT FROM AUTHOR]

We present a nonparametric prognostic framework for individualized event prediction based on joint modeling of both time series and time-to-event data. Our approach exploits a multivariate Gaussian convolution process (MGCP) to model the evolution of time series signals and a Cox model to map time-to-event data with time series data modeled through the MGCP. Taking advantage of the unique structure imposed by convolved processes, we provide a variational inference framework to simultaneously estimate parameters in the joint MGCP-Cox model. This significantly reduces computational complexity and safeguards against model overfitting. Experiments on synthetic and real world data show that the proposed framework outperforms state-of-the art approaches built on two-stage inference and strong parametric assumptions. Technical details are available in the . [ABSTRACT FROM AUTHOR]

The increasing use of stainless steel in industrial structures can be attributed to its excellent mechanical properties at elevated temperatures. Martensitic grade stainless-steel is used, for example, to manufacture steam turbine blades in power plants. The failure of these turbine blades can result in equipment damage contributing to expensive plant failures and safety concerns. Degradation and structural failure of these blades is largely attributed to material fatigue, at the microstructure level. Hence, it is important to evaluate the level of fatigue prior to the initiation of macro defects to ensure the viability of these components. Conventional nondestructive evaluation (NDE) techniques such as ultrasonic testing and eddy current testing are suitable in detection of macro defects such as cracks, but not very effective in evaluating degradation of the material at a microstructure scale. This article investigates the feasibility of the nonlinear eddy current (NLEC) technique to detect fatigue in martensitic grade stainless-steel samples along with a methodology to classify the samples. K-medoids clustering algorithm and genetic algorithm are used to classify the samples according to the severity of fatigue. Initial results indicate that stainless-steel samples, in different stages of fatigue, can be classified into broad categories of low, mid, and high levels of fatigue. [ABSTRACT FROM AUTHOR]

When we schedule a system to perform a task, a factor that should be taken into account is the remaining useful life prognostics of the system. This prognostics of the system may depend not only on the health state of the system, but also on the characteristics of the task to be performed. Assuming such prognostics is available at the time of system scheduling, the problem is to find a method to schedule the system, which can improve the expected profit rate. Two system life models were proposed for the case considered in this paper. Due to the dynamic nature of the problem, a global optimal policy is hard to find, we proposed an approach based on the approximated expected profit rate to schedule the systems. The approach is validated through simulations compared with a number of other task scheduling rules to show the advantage of the proposed approach. We also find the optimal global stationary result by exhaustive search of small scheduling problems of few systems and tasks to compare with the proposed approximate one. Further numerical analyses are presented to demonstrate the process of determining a decision variable and the sensitivity analysis in terms of a cost parameter. [ABSTRACT FROM PUBLISHER]

This document is an editorial for a special issue on Reliability Engineering in the journal Quality Engineering. The editorial introduces the concept of reliability as "quality over time" and discusses the challenges faced by reliability engineers in dealing with complex data and system complexity. The special issue includes fourteen papers that cover a wide range of topics, including Bayesian data analysis, reliability modeling, system assessment and optimization, and effective system management and maintenance. The guest editors express their enjoyment in reviewing the insightful and innovative research and applications in reliability engineering and hope that readers will find the special issue helpful and enlightening. [Extracted from the article]

The emerging behavior in complex systems is more complicated than the sum of the behaviors of their constituent parts. This behavior involves the propagation of faults between the parts and requires information about how the parts are related. Therefore, the prognostic function at the system-level becomes a very tough task. Conventional approaches focus on identifying faults and their probabilities of occurrence. In complex systems, this can create statistical limitations for prognostic function where component fault relies on the connected components in the system and their state of degradations. In this paper, a new Holonic agent-based approach is proposed for system-level remaining useful life (S-RUL) estimation with different dependencies. As the proposed approach can capture fault/failure mode propagation and interactions that occur in the system all the way up through the component and eventually system level, it can work as an automatic testing-tool in reliability tasks. Through a numerical example, the implementation is done in Java Agent Development Environment with and without consideration of stochastic dependence. Results show that the indirect effect of influencing components has a massive impact on the S-RUL, and the impact of stochastic dependencies should not be ignored, especially in the early stages of the system design. [ABSTRACT FROM AUTHOR]

Winding fault diagnosis and failure prognosis technique has been developed based on d-q model of brushless synchronous generator (BLSG) considering actual winding insulation degradation curve of machine in inter-turn fault, damper bar and field currents for various severities of inter-turn winding faults have been estimated using extended Kalman filter. For validation of damper bar currents, 2 D transient electromagnetic analyses using finite element method have been done, and 2nd harmonic component of damper bar currents for various severities of inter-turn fault in stator windings have been computed by Fourier transformation. The winding insulation degradation curve of machine has been determined by accelerated life test, and used for estimation of remaining useful life of machine under inter-turn fault, assuming a pre-defined failure threshold. Actual and predicted life of the BLSG has been compared. Wireless sensors using rotor telemetry system have been mounted on the rotor of BLSG for experimental validation of field currents under winding faults. The 2nd harmonic of damper bar currents increase with increase in severities of winding faults and do not get affected by diode failures in rotating rectifier, hence this can be used as a robust fault indicator for diagnosis and prognosis of inter-turn winding fault in BLSG. [ABSTRACT FROM AUTHOR]

The implementation of prognostics and health management solutions is becoming increasingly important. Many industrials are interested in this maintenance process, especially Predix by General Electric and EngineWise by Pratt & Whitney. Predix allows to create innovative industrial internet applications that transform operational data in real-time into actionable information in several domains (aviation, healthcare, ...). EngineWise is a world leader in the design, manufacture and service of aircraft engines and auxiliary power units. The prognostic process is a main step to predict failures before they occur by determining remaining useful life (RUL) of equipment. However, it also poses challenges such as reliability, availability, infrastructure and physics servers. To address these challenges, this paper investigates a cloud-based prognostic system that defines an approach 'Prognostic as a Service.' This approach will provide an efficient prognostic solution in the cloud computing. In this paper, three data-driven algorithms, Artificial Neural Network, Neuro-Fuzzy System and Bayesian Network, are discussed and implemented to estimate the RUL. They are tested for aircraft engines fleet. Furthermore, and in order to test the efficiency of our solution, we have studied the performance of the prognostic system according to the accuracy, precision and mean squared error. [ABSTRACT FROM AUTHOR]

Maintenance cost effectiveness, usability, reliability, safety and the remaining life of engineering assets are key factors for asset management decision-making. Management of an individual or groups of structures requires a systematic approach such that reliability and condition could be maintained within both budget and resource availability. This means maintenance and inspection activities should be planned optimally to ensure operation of structures is safe and economical. Hence, methodologies surrounding the modelling and analysis of data representing the time until the occurrence of an event become crucial to asset managers. This study uses the Explicit Hazard Model (EHM) to demonstrate the modelling of hazard, reliability and Remaining Useful Life (RUL) prediction of naval structures using a quasi-experiment. Amongst the existing covariate-based hazard models, EHM is selected as this model jointly utilises three available asset health data including failure event data, condition data and operating environment data in the modelling effort which provides effective outcomes. The hazard and reliability estimate of these structures using EHM are compared to the traditional Weibull model. Results show that the individual's hazard and reliability closely follow the population's hazard and reliability. The predicted RUL of these structures using EHM is compared to the actual RUL. Results validate the performance and accuracy of this model in reliability and RUL calculation of engineering assets. [ABSTRACT FROM AUTHOR]

Degradation modeling traditionally relies on monitoring degradation signals to model the underlying degradation process. In this context, failure is typically defined as the point where the degradation signal reaches a pre-specified threshold level. Many models assume that degradation signals are completely observed beyond the failure threshold, whereas the issue of truncated degradation signals still remains a challenge. Moreover, based on the physics of a degradation process, the degradation signal should be inherently monotonic. However, it is almost inevitable that most of the sensor-based degradation signals are subject to noise, which can lead to misleading prediction results. In this article, a non-parametric approach to modeling and prognosis of degradation signals using B-splines in a mixed effects setting is proposed. In order to deal with the issue of truncated historical degradation signals, our approach is based on augmenting B-spline basis functions with functions of infinite support. Moreover, to model the degradation signal more accurately and robustly in a noisy setting, necessary and sufficient conditions to ensure monotonic evolution of the modeled signals are derived. Appropriate procedures for online updating of random coefficients of mixed effects model considering derived monotonicity constraints based on degradation data collected from an in-service unit are also presented. The performance of the proposed framework is investigated and benchmarked through analysis based on numerical studies and a case study using real-world data from automotive lead-acid batteries. [ABSTRACT FROM AUTHOR]

Despite considerable advances over the last two decades in sensing instrumentation and information technology infrastructure, monitoring and diagnostics technology has not yet found its place in health management of mainstream machinery and equipment. This is in spite of numerous studies reporting that the expected savings from widespread deployment of condition-based maintenance (CBM) technology would be in the tens of billions of dollars in many industrial sectors as well as in governmental agencies. It turns out that a prerequisite to widespread deployment of CBM technology and practice in industry is cost efficient and effective diagnostics and prognostics. This paper presents a novel method for employing hidden Markov models (HMMs) for carrying out both diagnostic as well as prognostic activities for metal cutting tools. The methods employ HMMs for modelling sensor signals emanating from the machine (or features thereof), and in turn, identify the health state of the cutting tool as well as facilitate estimation of remaining useful life. This paper also investigates some of the underlying issues of proper HMM design and training for the express purpose of effective diagnostics and prognostics. The proposed methods were validated on a physical test-bed, a vertical drilling machine. Experimental results are very promising. [ABSTRACT FROM AUTHOR]

The purpose of this special issue of I IISE Transactions on Data Science, Quality and Reliability i is to create a repository of cutting-edge industrial engineering research work illustrating the novel capabilities of Internet of Things (IoT)-enabled systems. The first category includes three papers on system monitoring and anomaly detection by using high-dimensional IoT data (Ye I et al i ., Wang, I et al i ., and Wu I et al i .). [Extracted from the article]

Condition monitoring (CM) signals play a critical role in assessing the remaining useful life of in-service components. In this article, an alternative view on modeling CM signals is proposed. This view draws its roots from multitask learning and is based on treating each CM signal as an individual task. Each task is then expressed as a convolution of a latent function drawn from a Gaussian process (GP), and the transfer of knowledge is achieved through sharing these latent functions between historical and in-service CM signals. Aside from being nonparametric, the flexible and individualistic approach in our model can account for heterogeneity in the data and automatically infer the commonalities between the new testing observations and CM signals in the historical dataset. The robustness and advantageous features of the proposed method are demonstrated through numerical studies and a case study with real-world data in the application to find the remaining useful life prediction of automotive lead-acid batteries. Technical details and additional numerical results are available in the supplementary materials. [ABSTRACT FROM AUTHOR]

A novel RUL prediction approach for lithium-ion batteries using quantum particle swarm optimization (QPSO)-based particle filter (PF) is proposed. Compared to particle swarm optimization (PSO)-based PF, QPSO-based PF is proved to have a better performance in global searching and has fewer parameters to control, which makes QPSO-PF easier for applications. Moreover, fewer particles are required by QPSO-PF to accurately track the battery's health status, leading to a reduction of computation complexity. RUL prediction results using real data provided by NASA and compared with benchmark approaches demonstrates the superiority of the proposed approach. [ABSTRACT FROM AUTHOR]

The ability to estimate the expected remaining useful life (RUL) is critical to reduce maintenance costs, operational downtime and safety hazards. In most industries, reliability analysis is based on the reliability-centred maintenance and lifetime distribution models. In these models, the lifetime of an asset is estimated using failure time data; however, statistically sufficient failure time data are often difficult to attain in practice due to the fixed time-based replacement and the small population of identical assets. When condition indicator data are available in addition to failure time data, one of the alternate approaches to the traditional reliability models is the condition-based maintenance (CBM). The covariate-based hazard modelling is one of CBM approaches. There are a number of covariate-based hazard models; however, little study has been conducted to evaluate the performance of these models in asset life prediction using various condition indicators and data availability. This paper reviews two covariate-based hazard models, proportional hazard model (PHM) and proportional covariate model (PCM). To assess these models’ performance, the expected RUL is compared to the actual RUL. Outcomes demonstrate that both models achieve convincingly good results in RUL prediction; however, PCM has smaller absolute prediction error. In addition, PHM shows over-smoothing tendency compared to PCM in sudden changes of condition data. Moreover, the case studies show PCM is not being biased in the case of small sample size. [ABSTRACT FROM AUTHOR]

Prognosis of the Remaining Useful Life (RUL) of a unit or system plays an important role in system reliability analysis and maintenance decision making. One key aspect of the RUL prognosis is the construction of the best prediction interval for failure occurrence. The interval should have a reasonable length and yield the best prediction power. In current practice, the center-based interval and traditional confidence interval are widely used. Although both are easy to construct, they do not provide the best prediction performance. In this article, we propose a new scheme, the Maximum Power Interval (MPI), for estimating the interval with maximum prediction power. The MPI guarantees the best prediction power under a given interval length. Some technical challenges involved in the MPI method were resolved using the maximum entropy principle and truncation method. A numerical simulation study confirmed that the MPI has better prediction power than other prediction intervals. A case study using a real industry data set was conducted to illustrate the capability of the MPI method. [ABSTRACT FROM PUBLISHER]

Condition monitoring is an important prognostic tool to determine the current operation status of a system/device and to estimate the distribution of the remaining useful life. This article proposes a two-phase model to characterize the degradation process of rotational bearings. A Bayesian framework is used to integrate historical data with up-to-datein situobservations of new working units to improve the degradation modeling and prediction. A new approach is developed to compute the distribution of the remaining useful life based on the degradation signals, which is more accurate compared with methods reported in the literature. Finally, extensive numerical results demonstrate that the proposed framework is effective and efficient. [ABSTRACT FROM PUBLISHER]