End-to-end intelligent diagnosis of rotating machinery under speed fluctuation and limited samples is challenging in industrial practice. The existing limited samples methods usually focus on the data distribution or learning strategy with particularity. Generative adversarial network (GAN) provides a data generation solution with portability in fault diagnosis with limited samples. However, GAN has problems with gradient vanishing, weak extraction of global features, and redundant training. This article proposes a dual-threshold attention-guided GAN (DTAGAN) to generate high-quality infrared thermal (IRT) images to assist fault diagnosis. First, Wasserstein distance and gradient penalty are combined to design loss function to avoid gradient vanishing. Second, attention-guided GAN is constructed to extract global thermal-correlation features of IRT images. Finally, dual-threshold training mechanism is developed to improve the generation quality and training efficiency. The comparative experiments show that DTAGAN is superior to comparison methods in fault diagnosis of rotor-bearing system under speed fluctuation and limited samples.

Transient fault (TF) and intermittent fault (IF) of complex electronic systems are difficult to diagnose. As the performance of electronic products degrades over time, the results of fault diagnosis could be different at different times for the given identical fault symptoms. A dynamic Bayesian network (DBN)-based fault diagnosis methodology in the presence of TF and IF for electronic systems is proposed. DBNs are used to model the dynamic degradation process of electronic products, and Markov chains are used to model the transition relationships of four states, i.e., no fault, TF, IF, and permanent fault. Our fault diagnosis methodology can identify the faulty components and distinguish the fault types. Four fault diagnosis cases of the Genius modular redundancy control system are investigated to demonstrate the application of this methodology.

The Bayesian network (BN) is a powerful model for probabilistic knowledge representation and inference and is increasingly used in the field of reliability evaluation. This paper presents a bibliographic review of BNs that have been proposed for reliability evaluation in the last decades. Studies are classified from the perspective of the objects of reliability evaluation, i.e., hardware, structures, software, and humans. For each classification, the construction and validation of a BN-based reliability model are emphasized. The general procedural steps for BN-based reliability evaluation, including BN structure modeling, BN parameter modeling, BN inference, and model verification and validation, are investigated. Current gaps and challenges in reliability evaluation with BNs are explored, and a few upcoming research directions that are of interest to reliability researchers are identified.

In dynamic complex environments, the degradation of structure systems is generally caused not by a single factor but by multiple ones, and the process is subject to a high level of uncertainty. This paper contributes a hybrid physics-model-based and data-driven remaining useful life (RUL) estimation methodology of structure systems considering the influence of multiple causes by using dynamic Bayesian networks (DBNs). The structure model and parameter model of DBNs for the degradation process caused by a single factor are established on the basis of theoretical or empirical physical models, thereby solving the problem of insufficient data. An RUL estimation model is subsequently established by integrating these degradation process models. The RUL value is obtained from the time difference between the detection point and predicted failure point, which is determined using the failure threshold of performance. The sensor data and expert knowledge can be input into the estimation model to update the RUL value whenever necessary. Subsea pipelines in offshore oil and gas subsea production systems are adopted to demonstrate the proposed methodology. The degradation processes with fatigue, corrosion, sand erosion, and internal waves are modeled using DBNs, and the RUL is estimated using DBN-based RUL methodology.

The application of convolutional neural network (CNN) has greatly promoted the scope and scenario of intelligent fault diagnosis and brought about a significant improvement of intelligent model performance. Solving the feature extraction and fault diagnosis of machinery with heavy noise is beneficial for stable industrial production. However, the local properties of CNN prevent it from obtaining global features to collect sufficient fault information, leading to the degradation of fault diagnosis performance of CNN under heavy noise. In this article, a novel framework named Convformer-NSE is developed to extract robust features that integrate both global and local information, aiming at improving the end-to-end fault diagnostic performance of gearbox under heavy noise. First, Convformer is constructed to improve the nonlinear representation of the feature map, in which the sparse modified multi self-attention is used to model the long-range dependency of the feature map while keeping attention on local features. Then, the extracted spatial features at various scales are fused and fed in the designed novel Senet (NSE) for channel adaptivity learning. The Convformer-NSE is used for the analysis of raw vibration data of different gearbox systems. The experimental signal analyses demonstrate that our developed framework is superior to others.

The existing fault diagnosis methods of rotating machinery constructed with both shallow learning and deep learning models are mostly based on vibration analysis under steady rotating speed. However, the rotating speed frequently changes to meet practical engineering needs. The shallow learning models largely depend on domain experience of feature extraction, and training a deep learning model requires large samples and a long time. In addition, vibration monitoring has the shortcomings of contact measurement, small coverage, and noise interference. To address these problems, this article proposes a new fault diagnosis method with the least square interactive support matrix machine (LSISMM) and infrared thermal images. In this method, a novel matrix-form classifier called LSISMM is constructed under the concept of nonparallel interactive hyperplanes to fully leverage the structure information of infrared thermal images. To improve the computation efficiency, a new least square loss constraint is designed for LSISMM. Besides, we derive an effective solution framework based on the alternating direction method of the multiplier (ADMM) framework. The constructed LSISMM is directly used to analyze the collected thermal images of rotating machinery under time-varying speeds. Experiment results demonstrate that the proposed method is superior to state-of-the-art methods in terms of diagnosis accuracy and efficiency, especially under small thermal image samples.