Abstract Remaining useful life (RUL) prediction is crucial for the predictive maintenance and health management of mechanical transmission systems. Although data-driven RUL prediction methods have advanced significantly, three key challenges remain: (i) constructing a physically interpretable HI that is invariant to operating conditions yet sensitive to incipient degradation; (ii) achieving adaptive time to start prediction (TSP) detection that accommodates non-stationarity and controls false and missed alarms; (iii) accurate and generalizable RUL prediction under cross-domain scenarios. To address these issues, a method combining unsupervised anomaly detection and deep feature transfer for TSP determination and RUL prediction is proposed. A residual health indicator is constructed from an expected trajectory learned by Gaussian process regression (GPR) on the healthy segment and a Mahalanobis distance (MD) deviation measure. For the first time extreme value theory is used to create dynamic thresholds for performance degradation analysis and TSP determination. During the RUL prediction phase, transfer component analysis mitigates feature distribution discrepancies between source and target domains. A dual long short-term memory (dual-LSTM) network with L2 regularization is then employed for RUL prediction across two transfer tasks. Experimental validation on a public benchmark dataset and a laboratory run-to-failure bearing dataset demonstrates the superior predictive accuracy and generalization capability of the proposed approach compared to existing methods.

Abstract The remaining useful life (RUL) estimation is an important metric that helps in condition-based maintenance. Damage data obtained from the diagnostics techniques are often noisy, and the RUL estimated from the data is less reliable. Estimating the probabilistic RUL by quantifying the uncertainty in the predictive model parameters using the noisy data increases confidence in the predicted values. In this work, Bayesian inference is used to inversely quantify the uncertainty in the model parameters of the predictive damage model in adhesively bonded joints, and quantified parameter uncertainty is represented by a probability distribution function (PDF). It is difficult to obtain a closed-form solution for the RUL from the PDF of model parameters due to the nonlinearity of the damage models. Instead, statistical simulations are used to generate the model parameter samples from the PDF, and the RUL is estimated from the samples. In the statistical simulations, the predictive damage model is evaluated for each parameter sample. Using a physics-based model as the predictive model increases computational time, which makes the statistical techniques to be computationally expensive. It is essential to reduce the computational time to estimate the RUL in a feasible time. In this work, real-time probabilistic RUL estimation is demonstrated in adhesively bonded joints using the Sequential Monte Carlo (SMC) sampling method and cloud-based computations. The SMC sampling method is an alternative to traditional Markov Chain Monte Carlo (MCMC) methods, which enables generating statistical parameter samples in parallel. The parallel computational capabilities of the SMC methods are exploited by running the SMC simulation on multiple cloud calls. This approach is demonstrated by estimating fatigue RUL in the adhesively bonded joint. The accuracy of probabilistic RUL estimated by SMC is validated by comparing it with RUL estimated by the MCMC and the experimental values. The SMC simulation is run on the cloud and the computational speedup of the SMC is demonstrated.

Abstract Frequency response functions (FRFs) can be calculated from a composite function of other FRFs composition and decomposition problems. Considering that an experimentally measured FRF has an uncertainty in its magnitude and phase, what would be the uncertainty of the magnitude and phase of an FRF calculated from a composite function of experimentally measured FRFs? This work derives analytical expressions for the uncertainty of magnitude and phase of FRFs calculated from functions composed of the basic arithmetic operations involving measured FRFs and their inherent uncertainties. The derivation of the uncertainty values comes from the application of multivariable error analysis to the basic arithmetic operations considering the real and the imaginary parts of the FRFs involved. The resultant uncertainty of the composite FRF is obtained by applying the methodology to every operation in the composite function. Hence, an analytical method is proposed for applying to both composition and decomposition problems. An example of a decomposition problem is presented, and the calculated uncertainty of the magnitude and the phase of the composite FRF showed good agreement with results obtained from Monte Carlo simulation. In addition, it is shown that the blind application of the root-mean-square rule to the composite function written in terms of magnitude is not an appropriate procedure. The proposed methodology is accurate in predicting the uncertainty of composite FRFs.

Abstract Environmental noise energy can be effectively captured by an energy harvester (EH) and then converted into usable electricity for low-powered monitoring sensors in aerospace vehicles. It is important to investigate the influence of potential well parameters on the energy harvesting performance under random excitation. Therefore, this paper theoretically derives the marginal probability density function (PDF), the joint PDF, and the averaging output power of the decoupled bistable energy harvester driven by the Gaussian white noise. First, the bistable energy harvester is linearized using the statistical linearization method, which is advantageous in obtaining coarse mean square values of outputs for further analysis. Second, the dimension of Fokker–Planck–Kolmogorov (FPK) equations is reduced by the state-space-split (SSS) method. Then, the approximate marginal and joint PDF can be obtained. Third, the influence of potential well width and height on PDFs and the averaging output power are, respectively, analyzed and discussed, respectively. Finally, the theoretical derivation is successfully validated by Monte Carlo simulations. Results show that the large potential well width can improve the averaging output power of the bistable EH under random excitation.

Engineering systems are becoming increasingly complex.They need to meet advanced requirements, especially in mission-critical fields with a low failure tolerance.As unexpected failures during the designed lifespan of a system may lead to catastrophic consequences, their reliability modeling and assessment are of utmost importance.The reliability

Abstract Pressure systems contain hazardous fluids within industrial processes. Inspection plays a vital role in managing the reliability of these safety-critical systems. It allows engineers to identify, characterize, and manage degradation of pressure vessels, piping, and associated equipment to prevent failure and the associated consequences on people and the environment. Mixed uncertainty can affect decision-making in at least three distinct aspects of inspection practice: inspection planning, inspection data analysis, and integrity assessment. Despite this, the inspection engineering discipline lacks methodologies for handling both aleatory and epistemic uncertainties within analyses, which could be expensively misleading. This paper demonstrates the benefits of applying mixed uncertainty quantification and analysis techniques to pressure vessel inspection and integrity assessment through a worked example, which shows how the epistemic and aleatory uncertainty in inspection data can be represented using an imprecise probability approach. The limitations of empirical data are shown to pose challenges to implementing these techniques in practice, and so practical requirements for a framework for implementing uncertainty analysis methods in inspection are proposed. These include, for example, the ability to generate meaningful yet conservative results from even a limited amount of poor-quality data, while allowing results to be bounded more narrowly as more data is collected, findings from better data are pooled, or engineering judgment and assumptions are applied.

The Reviewers of the Year Award is given to reviewers who have made an outstanding contribution to the journal in terms of the quantity, quality, and turnaround time of reviews completed during the past 12 months. The prize includes a Wall Plaque, 50 free downloads from the ASME Digital Collection, and a Digital Badge of Recognition.L. AdolphusJ. ArghavaniA. AriffinE. AuerG. BanyayA. BeckJ. BehrensdorfM. BroccardoY. ChengC. DangG. DattaL. DingH. Estrada LugoV. FragkoulisY. GuoH. Haddad KhodaparastX. HuangJ. LeiL. LiK. LyathakulaY. MaG. MalaraS. MarelliY. MarykovskiyI. MavromatisC. MoraisG. MuscolinoP. NathP. PalarE. PapatheouA. PirrottaL. PodofilliniM. PourgolG. QianH. QianM. RamanchaR. RocchettaJ. ShangY. ShiC. SilvaE. SmithR. TeloliM. TroffaesG. TsialiamanisM. ValdebenitoK. VlachasD. WangZ. WangH. WuZ. WuY. XuD. YangL. YangZ. YangT. YuJ. ZengX. ZhangZ. ZhaoF. Zhu

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

Abstract Assessing vehicle safety is a challenging, yet fundamental task. In the early phase of development, car manufacturers need to ensure the compliance with strict safety requirements. An interesting task to automate these early-stage operations is to harness information from already developed products. Established designs are largely accessible, with abundant data; novel designs' data are scarce. While established and novel designs are (by definition) different, it is expected nonetheless that there is a degree of correlation between them. Thus, the established design could be regarded as a low-fidelity (LF) model of the novel design, in the sense that it may provide an approximation of the behavior of the novel design. In turn, the novel design could be regarded as a high-fidelity (HF) model, as it represents the true product being designed. This bifidelity character of the problem stands at the basis of this paper. This work explores the application of control variates (CV) to a crashworthiness analysis scenario. Control variates is a variance reduction technique that exploits the low-fidelity information to improve the accuracy of the response statistics of the high-fidelity model. Such an approach could be most useful for industrial applications. Therefore, we apply control variates to a crash box example and compare its performance to its plain Monte Carlo (MC) counterpart. The results of this paper show the benefits of this bifidelity approach, resulting in control variates being a powerful technique to extract valuable information from limited data sets. Indeed, control variates can serve as an innovative solution to support car manufacturers in the early phase of vehicle development and thus improve the performance in crashworthiness scenarios.

Abstract Complex structural systems deployed for aerospace, civil, or mechanical applications must operate reliably under varying operational conditions. Structural health monitoring (SHM) systems help ensure the reliability of these systems by providing continuous monitoring of the state of the structure. SHM relies on synthesizing measured data with a predictive model to make informed decisions about structural states. However, these models—which may be thought of as a form of a digital twin—need to be updated continuously as structural changes (e.g., due to damage) arise. We propose an uncertainty-aware machine learning model that enforces distance preservation of the original input state space and then encodes a distance-aware mechanism via a Gaussian process (GP) kernel. The proposed approach leverages the spectral-normalized neural GP algorithm to combine the flexibility of neural networks with the advantages of GP, subjected to structure-preserving constraints, to produce an uncertainty-aware model. This model is used to detect domain shift due to structural changes that cannot be observed directly because they may be spatially isolated (e.g., inside a joint or localized damage). This work leverages detection theory to detect domain shift systematically given statistical features of the prediction variance produced by the model. The proposed approach is demonstrated on a nonlinear structure being subjected to damage conditions. It is shown that the proposed approach is able to rely on distances of the transformed input state space to predict increased variance in shifted domains while being robust to normative changes.