The core objective of graph neural network (GNN)-based remaining useful life (RUL) prediction methods for equipment with multi-source sensors is to learn effective graph representations, and graph pooling is an efficient approach to achieve it. However, existing graph pooling techniques are limited in modeling hierarchical structures and have limitations in embedding space representation. To overcome these limitations, a dynamic curvature pooling graph convolutional network (DCPGCN) is proposed for RUL prediction of equipment with multi-source sensors. DCPGCN develops a hyperbolic hierarchical graph pooling framework. By leveraging the geometric advantages of hyperbolic space for hierarchical representation, the proposed framework more effectively captures multi-level structural information in graphs, significantly improving the overall structural fidelity of the graph representation. Moreover, a curvature predictor driven by pooling path deviation is proposed. By quantifying the geometric distortion along leaf-to-root paths in hyperbolic space, the predictor dynamically adjusts the curvature parameter, improving the embedding space’s adaptability and expressiveness for the graph’s hierarchical structure. Finally, experiments on the CMAPSS dataset demonstrate that the proposed method outperforms multiple state-of-the-art approaches in prediction accuracy, while experiments on real-world wind turbine RUL prediction further confirm its superiority and potential in engineering applications.

The distribution discrepancy metrics are the core foundation of achieving domain confusion. Therefore, they mainly determine the performance of deep transfer diagnosis models. However, their effectiveness relies on the stability of data local distributions, making them unsuitable for cross-domain machine diagnosis tasks under continuous time-varying conditions. Hence, a new integrated-dispersion manifold distance (IDMD) is proposed to enhance the discrepancy representation capability in dynamic data structures. The maximum entropy-based local distribution (MELD) selection mechanism is designed to represent the global distribution information of time-varying monitoring signals adaptively. Furthermore, the ensemble Grassmann manifold geodesic (EGMG) measurement is constructed to characterize the intrinsic distribution discrepancy information due to complex nonlinear structures of high-dimensional data. The proposed IDMD distribution discrepancy metric is validated against two fault transfer diagnosis experiments under time-varying conditions, including laboratory planetary gearboxes and actual wind turbine bearings. The experimental results demonstrate its effectiveness and advantage over the existing advanced methods.

Metric-based meta-learning has gained extensive attention in recent years due to its rapid adaptability and strong generalization capability. However, most of the existing metric-based meta-learning methods overlook the intrinsic structures of data, and the similarity evaluation methods for the few-shot scenarios are scarce, which also need to be improved. Therefore, this article proposes a novel metric-based meta-learning method, named retrospective prototype network, for few-shot fault diagnosis across both machines and operating conditions. In this method, the retrospective prototype is developed, which utilizes the interclass variability and multidimensional correlation for accurately reflecting the complex class distributions while reducing the prototype oscillation. Moreover, considering the discrepancy between data intrinsic structures, a center difference measure is designed based on the difference between the central matrix of query sample and the prototype, thus it is more suitable for few-shot scenarios, where the high-dimensional covariance matrices are not exact and full-rank. This proposed method is successfully applied to cross-bearing few-shot fault diagnosis, and the comparative results demonstrate its superiority over the typical and advanced fault diagnosis methods.

Intelligent rolling bearing fault diagnosis methods under variable-speed conditions have made significant progress, yet they still suffer from limited physical interpretability of extracted features and high sensitivity to speed fluctuations. To overcome these issues, a physics-guided dynamic tensor projection network (DTPNet) for variable-speed fault diagnosis is proposed. First, the adaptive wavelet feature extractor is specially constructed using a learnable wavelet transform and an attention mechanism to extract physically meaningful fault features across varying rotational speeds. Second, the condition-invariant dynamic subspace projection (CDSP) module is designed to dynamically generate a learnable projection matrix, mapping features into a condition-invariant and fault-relevant subspace. Third, a novel dynamic decoupling projection loss is proposed as a global constraint to guide the training of DTPNet. The synergistic interaction of these modules enables DTPNet to achieve reliable fault diagnosis under complex variable operating conditions. Experimental results on two case studies indicate that DTPNet significantly outperforms other state-of-the-art methods in terms of diagnosis accuracy, robustness, and interpretability.

Concept Bottleneck Models (CBMs) enhance interpretability by explaining predictions through human-understandable concepts but typically assume that training and test data share the same distribution. This assumption often fails under domain shifts, leading to degraded performance and poor generalization. To address these limitations and improve the robustness of CBMs, we propose the Concept-based Unsupervised Domain Adaptation (CUDA) framework. CUDA is designed to: (1) align concept representations across domains using adversarial training, (2) introduce a relaxation threshold to allow minor domain-specific differences in concept distributions, thereby preventing performance drop due to over-constraints of these distributions, (3) infer concepts directly in the target domain without requiring labeled concept data, enabling CBMs to adapt to diverse domains, and (4) integrate concept learning into conventional domain adaptation (DA) with theoretical guarantees, improving interpretability and establishing new benchmarks for DA. Experiments demonstrate that our approach significantly outperforms the state-of-the-art CBM and DA methods on real-world datasets.

There are two problems when the Shapley value is employed to interpret deep neural networks. The first issue is that the computational complexity increases exponentially with the number of players. The other issue is that the contribution evaluation index cannot effectively reflect the nonlinearity of the classification function (i.e., SoftMax), which is often neglected in previous studies. To address these challenges, a method for fast estimating the Shapley value based on the stratified sampling and the Mann–Whitney test (SSMW-Shap) is proposed in this work. In SSMW-Shap, a new contribution index is designed to accurately measure the contribution of each player by leveraging the distance between the outputs of two specific neurons, accounting for the nonlinearity of SoftMax and the efficiency of the Shapley value. Based on the proposed index, a simplified two-player coalition evaluation method is built to select important affiliates for each player, significantly reducing the computational complexity of the Shapley value. Then, the Shapley value is fast estimated by combining the stratified sampling and the Mann–Whitney test. In this process, the Mann–Whitney test is employed to estimate the difference between the samples and the population, and sample expansion is executed for the failed test, improving the estimation accuracy. Finally, a simple but reasonable method based on the proposed index is designed to quantitatively evaluate the explanation accuracy of each method. The proposed method is verified using two classic classification networks trained on two bearing datasets.

Current Internet of Things (IoT)-based equipment management methods often struggle with the diversity of data types and dynamic operating conditions, as fixed neural network structures and parameters lack the flexibility needed for adaptive feature extraction and fine-tuning, leading to suboptimal remaining useful life (RUL) predictions (PRs). To address the gap in current approaches, an innovative dynamic self-learning neural network (DSLNN) is proposed. Inspired by the human eye’s ability to adjust focus, the network introduces an adaptive scaling convolution (ASC) that dynamically adjusts the receptive field by stretching or shrinking, allowing for flexible feature extraction. Building on ASC, a spatiotemporal feature extraction module is developed to capture comprehensive equipment degradation features across both time and space dimensions. Additionally, a regression self-regulating mechanism is incorporated to facilitate flexible RUL inference, with a novel unbalanced tanh function that aligns with practical engineering needs. These innovations are integrated into DSLNN, which through experimental validation on the C-MAPSS, gear, and wind turbine gearbox bearing datasets, achieves state-of-the-art performance in RUL PR and enhances equipment reliability in IoT applications.

Transfer learning generally addresses to reduce the distribution distance between source-domain and target-domain. However, it is unreasonable to use a distribution to represent the life-cycle signals as they are always time-varying, and the improper assumption affects the efficacy of transfer remaining useful life (RUL) prediction. To fill this gap, this research proposes a micro transfer learning mechanism for multiple differentiated distributions, and a transfer RUL prediction model is constructed. First, a multi-cellular long short-term memory (MCLSTM) neural network is applied to obtain multiple differentiated distributions of the monitoring data at some point. Then the domain adversarial mechanism is used to achieve the knowledge transfer of multiple differentiated distributions at the cell level. Furthermore, an active screen mechanism is designed for weighting the domain discrimination losses of multiple differentiated distributions. Through the transfer RUL prediction experiments on aero-engines and actual wind turbine gearboxes, the superiority of this model over the advanced transfer prediction models is verified.Note to Practitioners—The work is motivated by the accuracy reduction problem caused by the time-varying characteristics of life-cycle data in the cross domain equipment RUL prediction scenario, where a fixed single distribution is difficult to cover the full life-cycle data. This article proposes a micro transfer learning mechanism containing multiple differentiated distributions, and a novel transfer RUL prediction model based on the mechanism is constructed for solving the problem caused by the time-varying characteristics of life-cycle data. There are four steps for implementing this method in practice: 1) collecting the full-life cycle signals of historical equipment; 2) modeling the degradation curves of equipment by MCLSTM; 3) solving the cross domain RUL prediction by narrowing the distributions of degradation curves by the micro transfer learning mechanism; and 4) making prognostics for new equipment. The novelty is that the proposed mechanism can self-adaptively align multiple differentiated subspaces of the source domain and the target domain, that is, it can adaptively extract the domain invariant features over time. As a result, the proposed method has two main advantages: 1) capable of characterizing the degradation processes of different equipment; and 2) superior prognostic results on cross domain RUL prediction.

Many transfer learning methods have been proposed to implement fault transfer diagnosis, and their loss functions are usually composed of task-related losses, distribution distance losses, and correlation regularization losses. The intrinsic parameters and trade-off parameters between losses, however, need to be tuned according to the specific diagnosis tasks; thus, the generalization abilities of these methods in multiple tasks are limited. Besides, the alignment goal of most domain adaptation (DA) mechanisms dynamically changes during the training process, which will result in loss oscillation, slow convergence and poor robustness. To overcome the above-mentioned issues, a novel and simple transfer learning diagnosis method named adaptive intermediate class-wise distribution alignment (AICDA) model is proposed, and it is established via the proposed AICDA mechanism, dynamic intermediate alignment (DIA) adaptive layer and AdaSoftmax loss. The AICDA mechanism develops an adaptive intermediate distribution as the alignment goal of multiple source domains and target domains, and it can simultaneously align the global and class-wise distributions of these domains. The DIA layer is designed to adaptively achieve domain confusion without the distribution distance loss and the correlation regularization loss. Meanwhile, to ensure the classification performance of the AICDA mechanism, AdaSoftmax loss is proposed for boosting the separability of Softmax loss. Finally, in order to evaluate the effectiveness and universality of the AICDA diagnosis model to the most degree, various multisource mixed fault transfer diagnosis tasks of wind turbine planetary gearboxes, including DA and domain generalization (DG), are implemented, and the experimental results indicate that our proposed AICDA model has a higher diagnosis accuracy and a stronger generalization ability than other state-of-the-art transfer learning methods.

The rotating machinery is continuously monitored in practical application. However, the historical life-cycle data cannot be always preserved due to the limited storage resource; meanwhile, the on-site computing platform cannot process a large number of monitoring samples. It brings a great challenge for the remaining useful life (RUL) prediction. Thus, continuous learning (CL) is introduced into RUL prediction model for achieving its knowledge accumulation and dynamic update. To improve the performance of continuous RUL prediction, this article presents a new RUL prediction methodology with a multistage attention convolutional neural network (MSACNN) and knowledge weight constraint (KWC). First, an improved multihead full-channel sight self-attention (MFCSSA) mechanism is proposed to capture the global degradation information across all channels. MSACNN is then constructed by embedding MFCSSA, squeeze-and-excitation (SE) mechanism, and convolutional block attention module (CBAM) into different stages of feature extraction, which enables it to capture the global degradation information and refine the feature representations progressively. The KWC mechanism based on the importance of weight parameters and gradient information is proposed and integrated into MSACNN to achieve the continuous RUL prediction task. The proposed KWC can effectively alleviate catastrophic forgetting in CL. Finally, the experimental results on the life-cycle bearing and gear datasets demonstrate that MSACNN has a higher accuracy than the existing prediction methods. Moreover, the KWC mechanism performs better than typical CL methods in retaining the previously learned knowledge while acquiring the new task knowledge. Therefore, the proposed methodology can be better applied to the continuous RUL prediction tasks than the advanced methods of the same kind.

Methods based on transfer learning have achieved rich research results in the field of intelligent diagnosis of mechanical devices. However, current transfer learning methods typically require the source and target domains to be known in advance, heavily relying on historical data, which fails to meet the requirements of practical applications. Therefore, this study proposes a multisource online transfer learning with joint adaptive distribution selection (MSOTL-JADS) algorithm for real-time diagnosis of online samples. First, during the offline phase, a metric function is designed to extract sub-domain feature information in the multisource domain scenario, facilitating accurate knowledge transfer. Second, the multisource weight distribution parameters obtained based on the distribution distance are dynamically selected for the multisource domains to achieve differentiated transfer in the domain. Third, in the online phase, the pretrained offline model is integrated using online input target samples to construct an online diagnostic model and fine-tuning the weight parameters to match the model accuracy. Finally, several online transfer diagnostic tasks were constructed using two public datasets and one self-constructed dataset. The experimental results demonstrate that the proposed MSOTL-JADS outperforms the comparison methods in terms of performance.

Aiming at the large differences between tasks in continuous remaining useful life (RUL) prediction and the limited information capturing capability of the existing continuous learning (CL) methods, this article develops a novel multibranch horizontal augmentation network (MBHAN). First, a hierarchical self-attention (HSA) mechanism is proposed to capture the local degradation features and dependencies at different scales and enhance the representation capacity of RUL prediction model. Based on HSA and temporal convolutional network (TCN), a time-frequency fusion TCN (TFFTCN) is designed to mine the hidden degradation information from the time-domain and frequency-domain data. Then, a memory weight constraint (MWC) regularization term is built to control the update of important parameters for pervious tasks during the learning of new task. A horizontal network augmentation rule based on the task similarity and MWC is proposed, including the augmentation of a task branch network for small task difference and the augmentation of a feature extraction backbone network for large task difference. On this basis, the MBHAN is proposed to continuously predict RUL of machinery. Finally, the experimental results on the life-cycle bearing and gear datasets demonstrate that TFFTCN achieve an average accuracy of 93% across both datasets, surpassing the existing prediction methods.

The simulation signals generated by the bearing dynamics model have a big gap with the actual signals, which limits their efficacy in bearing fault diagnosis. Therefore, it is valuable to build an accurate digital twin model of faulty rolling bearing . Firstly, a multi-degree-of-freedom bearing fault dynamics model is constructed in the virtual space for generating the vibration responses of bearing parts. Then considering that the frequency spectrum contains more characteristic information than the time-domain signal, a frequency-domain bi-directional long short-term memory (Bi-LSTM) cycle generative adversarial network (CycleGAN) named FBC-GAN is proposed to construct the frequency-domain coupling mapping relationship between the multipart vibration responses and the measured signals. In the proposed network, Bi-LSTM is used for enhancing the feature extraction ability. Meantime, a new spectrum-constraint loss is proposed to ensure the frequency-domain mapping. Next, the simulated fault bearing signals close to the actual signals are generated by FBC-GAN and Fourier transform . Finally, the results of two experiments show the superiority of the proposed method over other advanced data augmentation methods in bearing fault diagnosis with the imbalanced samples.

The performance of neural networks is directly affected by the features obtained from the backbones of fault diagnosis neural networks. To obtain clear features and improve the performance of diagnosis networks, this paper constructs a new block based on a linear transformation. Firstly, the feature vector is divided into a decisive component and an invalid component. Then, it is worth noting that the orthogonality of these two components is beneficial to model learning. According to this, the two components are extracted using two spaces that are constructed based on the relationships between the four fundamental sub-spaces of a matrix. In the four sub-spaces, the row space and the null space are employed to extract the decisive component and useless component, respectively. Both spaces are implemented by two linear layers and are designed as an encoder-decoder structure to ensure the existence of the null space. To ensure the orthogonality of the two spaces, a constraint term is proposed to modify their weights. Lastly, the cosine similarity between the input feature and the invalid component is designed to extract the invalid component entirely. When incorporating the proposed block into some classic classifying neural networks, they can achieve improved diagnosis accuracy. Moreover, when comparing it to two conventional spatial attention mechanisms, the proposed module demonstrates superior overall performance, including diagnosis accuracy, antinoise ability, and generalization ability.

To accurately predict the remaining useful life (RUL) of rotating machinery while continuously providing the task data, a novel continuous RUL prediction methodology was proposed. The methodology comprises a self-guided attention convolutional neural network (SGACNN) and memory consciousness adjustment (MCA) mechanism. First, a multihead focal channel-wise self-attention (MFCWSA) mechanism was implemented to effectively capture the degradation information across all the channels and achieve the attentional focus. Next, the SGACNN was constructed using the MFCWSA, squeeze-and-excitation mechanism, and convolutional block attention module. A new network gradient direction was synthesized by leveraging the gradients from both the previous task and the current task. Further, a weight constraint loss term based on the gradient magnitude was designed to constrain the learning process of important parameters. With the new network gradient direction and weight constraint loss, a novel MCA mechanism was proposed and integrated into the SGACNN for implementing the continuous RUL prediction tasks. Finally, various RUL prediction experiments on the life-cycle bearing and gear data sets were carried out, and its outcomes were compared to those of the advanced methods of the same kind. The comparative results validated the superiority of the proposed methodology.

Operating condition monitoring of wind turbine (WT) key components is of significant importance to preventative maintenance and the improvement of WT reliability. To realize this industrial target, health indicator (HI) construction is a crucial and indispensable step. While most of the recently reported HIs are emphasized effective in stationary cases, they are insufficiently applicable to variable speed conditions. To address this issue, a novel HI through operating speed slicing and discrepancy compensation is proposed in this article for WT generator bearing condition monitoring. First, signal probability distributions of the collected degradation data are appropriately characterized by an optimized multiparameter regression method. Then, benchmark distributions established at the normal state are identified through operating speed slicing, and the discrepancies induced by the time-varying operating condition are subsequently calibrated with a compensation strategy. On this basis, a globally comparable metric, by quantitatively evaluating the degree to which the currently established distribution deviates from the corresponding slice-related benchmark, is accordingly constructed. Experimental tests demonstrate that the proposed HI can make a more effective health state assessment for WT generator bearing under variable speed conditions when compared with the conventional indicators.

Various federated transfer learning (FTL) methods have been proposed to address domain shift and safeguard data privacy in the field of fault diagnosis. However, the effectiveness of these methods entirely relies on the presumption that the source clients must be homogenous with the target client. Meanwhile, these methods also require that the testing target-domain data are available during the communication process. Considering that target-domain data are typically unseen and heterogenous with source clients, the traditional FTL-based diagnosis methods cannot meet the demand of high data utilization rate and real-time diagnosis in real engineering. To overcome the above-mentioned issues, a novel heterogeneous federated domain generalization network (HFDGN) is proposed to fill the gap in the heterogeneous multisource federated diagnosis. In the HFDGN, the heterogeneous FTL framework is first proposed to achieve the generalized fault diagnosis of a target client by obtaining the common representation mappings from heterogeneous source clients. Additionally, the disentangled domain adaptation (DDA) base model is designed to remove the negative effect caused by noise. This model can enhance the ability of domain confusion and extract the inherent fault-relevant features. The asynchronous unbalanced update paradigm is utilized to optimize the DDA base model. Experimental results on two heterogeneous federated transfer cases prove that HFDGN outperforms other well-known and advanced diagnosis methods. The related code can be downloaded fromhttps://qinyi-team.github.io/2024/05/Heterogeneous-federated-domain-generalization-network.

Various domain adaptation (DA) methods have been proposed to address distribution discrepancy and knowledge transfer between the source and target domains. However, many DA models focus on matching the marginal distributions of two domains and cannot satisfy fault-diagnosed-task requirements. To enhance the ability of DA, a new DA mechanism, called deep joint distribution alignment (DJDA), is proposed to simultaneously reduce the discrepancy in marginal and conditional distributions between two domains. A new statistical metric that can align the means and covariances of two domains is designed to match the marginal distributions of the source and target domains. To align the class conditional distributions, a Gaussian mixture model is used to obtain the distribution of each category in the target domain. Then, the conditional distributions of the source domain are computed via maximum-likelihood estimation, and information entropy and Wasserstein distance are employed to reduce class conditional distribution discrepancy between the two domains. With joint distribution alignment, DJDA can achieve domain confusion to the highest degree. DJDA is applied to the fault transfer diagnosis of a wind turbine gearbox and cross-bearing with unlabeled target-domain samples. Experimental results verify that DJDA outperforms other typical DA models.

Many domain adaptation (DA) models have been explored for fault transfer diagnosis. However, their successes completely rely on the availability of target-domain samples during the training process. As target domain is usually unseen, the domain-adaptation-based diagnostic models cannot meet the requirement of real-time diagnosis in actual engineering. To achieve the domain confusion in the actual diagnosis scenario, a novel relationship transfer (RT) diagnosis framework is first proposed, which can indirectly measure and reduce the distribution discrepancy between the source domain and unseen target domain. Based on the proposed RT framework, a new domain generalization transfer method, called relationship transfer domain generalization network (RTDGN) is constructed. RTDGN is divided into two phases including task-irrelevant domain adaptation (TIDA) and task-relevant domain generalization (TRDG). In the TIDA phase, a DA adversarial network with several domain discriminators is built to enhance the domain confusion of RT framework. Furthermore, to bring the adversarial network a more general domain confusion ability, a new inverse entropy loss is designed. In the TRDG phase, a residual fusion classifier is constructed to improve the generalization ability of fault classifier. Finally, the experimental results on the wind turbine planetary gearbox dataset and bearing dataset verify the effectiveness and superiority of the proposedRTDGN.

Remaining useful life (RUL) prediction can provide a foundation for the operation and maintenance of industrial equipment. In order to improve the predictive ability for the complex degradation trajectory, a new dual-thread gated recurrent unit (DTGRU) is explored. It uses a dual-thread learning strategy to mine the stationary and nonstationary information from the input data and the difference of hidden states at two adjacent time steps. Then the state transition updating formulas of DTGRU are derived. Using the collected gear vibration signals and degradation-trend-constrained variational autoencoder, the gear health indicator (HI) is constructed. Based on the constructed HI and DTGRU, a novel RUL prediction method is developed. Via multiple gear life-cycle datasets, the effectiveness of the DTGRU-based RUL prediction approach is verified. Furthermore, compared with the existing typical prediction methods, the experimental results show that DTGRU has higher predictive ability in terms of HI fitting precision and RUL prediction performance.

Facing the gap in the unsupervised construction of health indicator (HI) with a uniform failure threshold, a new unsupervised HI construction approach is developed. First, the distribution of the raw vibration signal is estimated by the Gaussian mixture model, then a distribution contact ratio metric (DCRM) is designed to compute the distance between two arbitrary distributions. With DCRM, a distribution contact ratio metric health indicator (DCRHI) is innovatively constructed for well representing the degradation process and obtaining a uniform failure threshold. Next, aiming at the challenge of prediction under limited samples, a novel consolidated memory gated recurrent unit (CMGRU) is proposed by making full use of the historical state information, and it can effectively slow down the forgetting speed of important trend information. Combing the proposed DCRHI and CMGRU, a novel remaining useful life (RUL) prediction methodology is put forward for enhancing the predictive performance. Via two public bearing datasets, several contrast experiments are implemented, and the comparative results show that DCRHI can better describe the degradation process of bearing than other typical unsupervised HIs, and CMGRU has a stronger prediction ability than other classical time series processing networks. Thus, the proposed methodology has great application value in the RUL prediction.

Domain adaptation has been widely used for knowledge transfer. However, the aligning targets of the existing domain adaptation mechanisms dynamically vary during the training, which leads to the loss oscillation, slow convergence, and poor robustness. To overcome this main problem, a novel domain adaptation mechanism named intermediate distribution alignment (IDA) is proposed. For implementing the end-to-end diagnostic tasks, a feature extractor based on deep convolutional neural network with wide first-layer kernel is first built to fit the posterior distributions of source and target domains. Then through the KL divergence, IDA maps the learned features from the source and target domains into a specific intermediate distribution. It is proved theoretically that IDA can align the prior distributions of two domains. The proposed IDA mechanism is successfully applied to the fault transfer diagnosis of planetary gearboxes without labeled target-domain samples. The comparative results show that the proposed IDA mechanism has higher diagnostic performance than the typical domain adaptation mechanisms.

The digital twin of a life-cycle rolling bearing is significant for its degradation performance analysis and health management. This article proposes a digital twin model of life-cycle rolling bearing driven by the data-model combination. With the measured signals and the bearing fault dynamic model, the time-varying defect size is estimated, and the evolution law of bearing defect during the life cycle is revealed by a back propagation neural network. Then, the excitations of evolutionary defects are introduced into the bearing dynamic model, so as to form a life-cycle bearing dynamic model in the virtual space. Finally, the simulation data in the virtual space is mapped into the corresponding data in the physical space via an improved CycleGAN neural network with the smooth cycle consistency loss. By comparing the obtained digital twin result with the measured signal in the time-domain and frequency-domain, the effectiveness of the proposed model is verified.

In this article, facing the gaps that the traditional long short-term memory (LSTM) and convolution neural network (CNN) cannot differentially deal with the input data based on the corresponding trend and stage information in remaining useful life (RUL) prediction, a more accurate and robust RUL prediction model is constructed. First, a temporally multidifferential LSTM (TMLSTM) with the multitrend division unit and multicellular unit is proposed, and a spatially multidifferential CNN (SMCNN) with the multistage division unit and differentiated convolutions is designed. Then, by combining TMLSTM and SMCNN, a spatiotemporally multidifferential deep neural network is developed for predicting the equipment RUL, which enhances the ability of feature extraction from the spatiotemporal perspective by using the multitrend and multistage information. Via several evaluation indexes, the commercial modular aero propulsion system simulation dataset and the wind turbine gearbox bearing dataset are used to validate the superiority of the proposed method over several existing prediction methods.

In the mechatronic system, rolling bearing is a frequently used mechanical part, and its failure may result in serious accident and major economic loss. Therefore, the remaining useful life (RUL) prediction of rolling bearing is greatly indispensable. To accurately predict the RUL of the rolling bearing, a new kind of gated recurrent unit neural network with dual attention gates, namely, gated dual attention unit (GDAU), is proposed. With the acquired life-cycle vibration data of a rolling bearing, a series of root mean squares at different time instants are calculated as the health indicator (HI) vector. Next, the to-be HI sequence is predicted by GDAU according to the existing HI vector, and then the RUL of the rolling bearing is estimated. The experimental results show that the proposed GDAU can effectively predict the RULs of rolling bearings, and it has higher prediction accuracy and convergence speed than the conventional prediction methods.

Domain adaption models are widely applied to fault transfer diagnosis. However, the traditional domain adaption models can output only one high-dimensional transfer feature (TF); thus, it is difficult to capture domain-invariant information. Besides, using only one fully connected top classifier probably causes overfitting. Considering these two problems, in this article, we propose a multiscale transfer voting mechanism (MSTVM) to improve the classical domain adaption models and it can be universally applicable to any one of most domain adaption models. MSTVM consists of two substrategies: multiscale transfer mechanism (MSTM) and multiple transfer voting mechanisms (MTVM). The MSTM block includes several branches with multiscale convolutional and pooling operations, and it can output several multiscale TFs to strengthen the domain confusion. The MTVM block consists of multiple top classifiers and a plurality voting operation; thus, MTVM can effectively avoid overfitting and improve generalization ability. MSTVM has the advantages of MSTM and MTVM. Via two transfer diagnosis experiments, the advantage of MSTVM for improving various domain adaption models is verified.

To detect the incipient faults of rotating parts used in electromechanical systems widely, a novel transient feature extraction method based on the improved orthogonal matching pursuit (OMP) and one-dimensional K-SVD algorithm is explored in this paper. First, the stopping criterion of adaptive spark is developed, and then the corresponding OMP algorithm is used to remove the modulated and harmonic signals adaptively. Second, the residual signal is reformulated as a signal matrix by period segmentation and circulating shift, and the initial transient dictionary is constructed via the time-domain average technique. Subsequently, a novel K-SVD algorithm is proposed to get the optimized transient dictionary for the one-dimensional signal. Finally, the repetitive transient signal is recovered by the optimized dictionary. The simulated and experimental results show that the proposed method can not only much faster extract the fault characteristics than the traditional K-SVD method, but also more accurately detect the repetitive transients than the infogram method and the traditional K-SVD method.

Diagnosis of a civil aircraft engine, which is operating under speed variation conditions, is a representative problem encountered in aeronautic industry. It is still very challenging to estimate the instantaneous angular speed (IAS) through the aircraft engine vibration signal when no encoder or tachometer is available due to cost or technological reasons. However, for the currently available tacholess order tracking algorithms, many vital parameters must be initialized manually in advance, which lead to user-friendliness, even false diagnosis. To address this issue, a novel method is proposed and the merits of nonlinear mode decomposition are inherited, so the IAS can be estimated adaptively without prior knowledge. The vibration signal collected from a civil aircraft engine is used for validation; the experimental results exhibit that the proposed method is more accurate and flexible when compared with the conventional methods.