With the rapid advancement of sensing technology, some critical components within engineering systems are equipped with sensors to collect condition monitoring (CM) signals. Such systems are referred to as partially monitored systems because only selected components are monitored. However, the method to integrate real-time component-level CM signals into reliability assessments of these systems remains unexplored. This study introduces a novel reliability assessment method designed to address the challenges of evaluating the reliability of partially monitored systems, particularly considering the highly nonstationary nature of CM signals and their dependence on the component states. A multistate degradation hidden Markov model with time-varying parameters (DHMM-TVP) is developed to better handle the nonstationary and nonlinear nature of CM signals. The expectation-maximization (EM) algorithm is adapted to estimate the unknown parameters within the DHMM-TVP framework. Furthermore, leveraging DHMM-TVP in combination with a functional kernel regression model, a generalized reliability assessment method is proposed, specifically tailored for cases where the system reliability structure is unknown or only partially known. A numerical simulation study and two case studies were conducted to validate the proposed reliability assessment approach. The component-level validation was performed using an experimental bearing accelerated degradation testing dataset, while the system-level verification employed aircraft turbofan engine datasets from the NASA prognostics data repository, collectively demonstrating the effectiveness of the proposed method.

Meta-learning has effectively addressed the limit of deep learning fault diagnosis models that demands a large number of samples. However, existing meta-learning models lack the capacity of feature reuse and task adaptability. To address the cross-domain fault diagnosis tasks with small samples, the feature reuse capability and task adaptability of existing meta-learning models need further improvements. To achieve this goal, this paper introduces a new approach built upon the task-supervised Almost No Inner Loop (ANIL). The proposed approach adopts a residual network to optimize the backbone structure of the inner loop, enhancing the feature reuse capability of the meta-learning in the unknown domain. An auxiliary term is introduced to define a supervised task-adaptive loss function, further updating the weight parameters of the inner loop meta-learner by monitoring the states of all meta-diagnostic tasks. The proposed method is used to analyze vibration signals from various bearings. The results demonstrate its superiority over traditional meta-learning methods in multiple sets of cross-domain fault diagnosis tasks with small samples.

Currently, various state-of-the-art Transformer variants have gained widespread attention in the field of fault diagnosis. However, these Transformers often adopt a global sequence modelling strategy to extract fault features, which is susceptible to the interference of redundant information and strong noise, due to the local and sparse nature of vibration signals. Therefore, a new feature enhancement and end-to-end fault diagnosis model named PSparseFormer is proposed in this paper. Firstly, a parallel sparse self-attention module is designed to efficiently extract the local and sparse features at different locations of complex vibration signals to reduce the over-sensitivity to irrelevant information. Secondly, the multiscale broadcast feed-forward block is developed to simultaneously facilitate global and local spatial feature information transmission and adjust the contribution of features at different levels, enhancing the robustness of local feature extraction against noise. Experimental analysis using datasets from two planetary gearboxes illustrates the effectiveness of the proposed method in addressing challenges related to feature extraction and enhancement, particularly in the presence of strong noise interference. Comparative evaluations against various state-of-the-art Transformers reveal that the proposed method exhibits superior diagnostic performance.

Traditional device fault diagnostic methods in Industrial Internet of Things (IIoT) require nodes to upload local data to the cloud, which, however, may lead to privacy leakage issues. Although Federated learning (FL) methods can protect the privacy of data, many challenges still need to be addressed. For example, the nonindependently and identically distributed (non-IID) issue in FL prevents the convergence of global model. Moreover, FL lacks detection mechanism to resist poisoning attacks from malicious nodes, and it requires incentive mechanism to encourage nodes to share their resources. To address these challenges, this article proposes a secure and privacy-preserving FL system that leverages blockchain and edge computing technology. Specifically, a feature-contrastive loss function is constructed to train an unbiased global model under the non-IID condition. Additionally, a Byzantine-tolerance scoring mechanism is designed to resist poisoning attacks, and a reputation-based incentive algorithm is developed to estimate the rewards or penalties owed to nodes. The proposed method is applied to two case studies: 1) chiller fault diagnosis for heating, ventilation and air conditioning systems and 2) gearbox fault diagnosis for wind turbines in IIoT. Experimental results show the superior performance of the proposed method.

The wheels are among the most critical components which largely influence the safe operation of high-speed trains. The existing research in reliability modeling typically assumes the wheel degradation to be a one-dimensional degradation process. This could incur a deficiency in practice, as the wheel degradation is in fact the superposition of multiple complex degradation processes, involving wheel tread wear and wheel polygonal wear. Random shocks also contribute to the wheel degradation. Moreover, these processes are correlated with each other. To fully consider these factors, this article proposes a multistate model for multidimensional degradations. The piecewise-deterministic Markov process (PDMP) model is applied to describe the mutual dependencies between random shocks and multiple degradations. Conventionally, the parameters of PDMP are set by experts’ experience. This article investigates maximum likelihood estimation to estimate the model parameters. Finally, the Monte Carlo simulation algorithm is proposed to evaluate the high-speed train wheel's reliability. Numerical experiments were conducted to validate the proposed method on high-speed train wheels subject to tread wear, polygonal wear, and wheel-rail impacts, which show that dependencies among multidimensional degradation processes and random shocks will largely affect the reliability of the wheels. The application to high-speed train wheels shows the effectiveness of the proposed model.

Although the existing generative adversarial networks (GAN) have the potential for data augmentation and intelligent fault diagnosis of planetary gearbox, it remains difficult to deal with extremely limited training samples and effectively fuse the representative and diverse information. To tackle the abovementioned challenges, an improved local fusion generative adversarial network is proposed. Time-domain waveforms are first transformed into the time–frequency diagrams to highlight the fault characteristics. Subsequently, a local fusion module is used to fully utilize extremely limited samples and fuse the local features. Finally, a new generator embedded with multi-head attention modules is constructed to effectively improve the accuracy and flexibility of the feature fusion process. The proposed method is applied to the analysis of planetary gearbox vibration signals. The results show that the proposed method can generate a large number of samples with higher similarity and better diversity compared with the existing mainstream GANs using six training samples in each type. The generated samples are used to augment the limited dataset, prominently improving the accuracy of the fault diagnosis task.

Dust deposition on the surface of photovoltaic (PV) modules is a nonnegligible factor that reduces a PV system’s efficiency and reliability. Cleaning can remove dust, and the effect of cleaning on PV performance resembles that of maintenance. In this article, we propose a hybrid cleaning scheduling policy with periodic planning and dynamic adjustment for refining the operations and maintenance of PV systems. Specifically, the periodic planning stage aims for medium-term scheduling while the dynamic adjustment stage is tailed for short-term fine-tuning. In the former stage, we show that when the number of cleaning actions is fixed, a periodic cleaning strategy is optimal. Moreover, we derive the optimality condition under which the optimal cleaning interval can be determined. In the latter stage, based on the determined cleaning interval, we dynamically adjust the cleaning schedule with the forecast of meteorological parameters, PV power generation, and dust deposition in order to further minimize economic losses. In addition, we take the forecasting uncertainty into account and propose a new custom parameter called risk-taking tendency (RTT), which is able to quantify the risk preference of decision makers and analyze its influence on the scheduling policy. A case study is provided to illustrate the proposed strategy.

This paper proposes a condition-based maintenance (CBM) policy for a deteriorating system whose state is monitored by a degraded sensor. In the literature of CBM, it is commonly assumed that inspection of system state is perfect or subject to measurement error. The health condition of the sensor, which is dedicated to inspect the system state, is completely ignored during system operation. However, due to the varying operation environment and aging effect, the sensor itself will suffer a degradation process and its performance deteriorates with time. In the presence of sensor degradation, the Kalman filter is employed in this paper to progressively estimate the system and the sensor state. Since the estimation of system state is subject to uncertainty, maintenance solely based on the estimated state will lead to a suboptimal solution. Instead, predictive reliability is used as a criterion for maintenance decision-making, which is able to incorporate the effect of estimation uncertainty. Preventive replacement is implemented when the estimated system reliability at inspection hits a specific threshold, which is obtained by minimizing the long-run maintenance cost rate. An example of wastewater treatment plant is used to illustrate the effectiveness of the proposed maintenance policy. It can be concluded through our research that: 1) disregarding the sensor degradation while it exists will significantly increase the maintenance cost and 2) the negative impact of sensor degradation can be diminished via proper inspection and filtering methods.Note to Practitioners—This paper was motivated by the observation of sensor degradation in wastewater treatment plants but the developed approach also applies to other systems such as manufacturing systems, chemical plants, and pharmaceutical factories, where sensors are dedicated to a long-time operation in a harsh environment. This paper investigates the impact of sensor degradation on CBM and suggests that the effect of sensor degradation should be carefully addressed while making maintenance decisions. Otherwise, it will lead to a suboptimal maintenance decision and increase the operating cost. An optimal maintenance decision, which contains the optimal inspection interval and reliability threshold, is achieved via minimizing the long-run cost rate. In the presence of measurement noise and intrinsic uncertainty from degradation, a stochastic filtering approach is employed to estimate the system and sensor state. Based on the estimated states and the calculated reliability, a dynamic maintenance decision is obtained at each inspection. This paper can be further extended considering non-Gaussian noise and alternative degradation processes.

This paper presents a reliability modeling and analysis framework for load-sharing systems with identical components subject to continuous degradation. It is assumed that the components in the system suffer from degradation through an additive impact under increased workload caused by consecutive failures. A log-linear link function is used to describe the relationship between the degradation rate and load stress levels. By assuming that the component degradation is well modeled by a step-wise drifted Wiener process, we construct maximum likelihood estimates (MLEs) for unknown parameters and related reliability characteristics by combining analytical and numerical methods. Approximate initial guesses are proposed to lessen the computational burden in numerical estimation. The estimated distribution of MLE is given in the form of multivariate normal distribution with the aid of Fisher information. Alternative confidence intervals are provided by bootstrapping methods. A simulation study with various sample sizes and inspection intervals is presented to analyze the estimation accuracy. Finally, the proposed approach is illustrated by track degradation data from an application example.

Accelerated degradation tests (ADT) have been widely used to assess the reliability of products with long lifetime. For many products, environmental stress not only accelerates their degradation rate but also elevates the probability of traumatic shocks. When random traumatic shocks occur during an ADT, it is possible that the degradation measurements cannot be taken afterward, which brings challenges to reliability assessment. In this paper, we propose an ADT optimization approach for products suffering from both degradation failures and random shock failures. The degradation path is modeled by a Wiener process. Under various stress levels, the arrival process of random shocks is assumed to follow a nonhomogeneous Poisson process. Parameters of acceleration models for both failure modes need to be estimated from the ADT. Three common optimality criteria based on the Fisher information are considered and compared to optimize the ADT plan under a given number of test units and a predetermined test duration. Optimal two- and three-level optimal ADT plans are obtained by numerical methods. We use the general equivalence theorems to verify the global optimality of ADT plans. A numerical example is presented to illustrate the proposed methods. The result shows that the optimal ADT plans in the presence of random shocks differ significantly from the traditional ADT plans. Sensitivity analysis is carried out to study the robustness of optimal ADT plans with respect to the changes in planning input.

This paper develops a maintenance policy for a multicomponent system subject to hidden failures. Components of the system are assumed to suffer from hidden failures, which can only be detected at inspection. The objective of the maintenance policy is to determine the inspection intervals for each component such that the long-run cost rate is minimized. Due to the dependence among components, an exact optimal solution is difficult to obtain. Concerned with the intractability of the problem, a heuristic method named “base interval approach” is adopted to reduce the computational complexity. Performance of the base interval approach is analyzed, and the result shows that the proposed policy can approximate the optimal policy within a small factor. Two numerical examples are presented to illustrate the effectiveness of the policy.