The effective fault diagnosis of the motor bearings not only can ensure the smooth and efficient operation of equipment but also can detect and eliminate the running fault in time to prevent major accidents. Based on deep learning algorithm, this article constructs a stacked auto-encoder network. The input data are compressed and reduced by introducing sparsity constraint, so that the network can accurately extract the fault characteristics of the input data, and the fault recognition ability of the network can be improved by introducing random noise. The simulation result shows that the stacked auto-encoder network can not only overcome the shortcomings of traditional fault diagnosis method that requires to distinguish fault samples manually and needs a large number of prior knowledge but also realize the self-learning of fault signal feature. The accuracy rate of fault identification reaches 98%, 94%, 96%, and 95.5% in four different working conditions. What’s more, the network can exhibit strong robustness under different working conditions. Finally, the new research ideas of fault diagnosis in thermal power plant are put forward by copying the idea of fault diagnosis of motor bearing.

Pipelines play a vital role in material transportation within industrial settings. This review synthesizes detection technologies for early-stage small gas leaks from pipelines in the industrial sector, with a focus on acoustic-based methods, optical gas imaging (OGI), and multimodal fusion approaches. It encompasses detection principles, inherent challenges, mitigation strategies, and the state of the art (SOTA). Small leaks refer to low flow leakage originating from defects with apertures at millimeter or submillimeter scales, posing significant detection difficulties. Acoustic detection leverages the acoustic wave signals generated by gas leaks for non-contact monitoring, offering advantages such as rapid response and broad coverage. However, its susceptibility to environmental noise interference often triggers false alarms. This limitation can be mitigated through time-frequency analysis, multi-sensor fusion, and deep-learning algorithms—effectively enhancing leak signals, suppressing background noise, and thereby improving the system’s detection robustness and accuracy. OGI utilizes infrared imaging technology to visualize leakage gas and is applicable to the detection of various polar gases. Its primary limitations include low image resolution, low contrast, and interference from complex backgrounds. Mitigation techniques involve background subtraction, optical flow estimation, fully convolutional neural networks (FCNNs), and vision transformers (ViTs), which enhance image contrast and extract multi-scale features to boost detection precision. Multimodal fusion technology integrates data from diverse sensors, such as acoustic and optical devices. Key challenges lie in achieving spatiotemporal synchronization across multiple sensors and effectively fusing heterogeneous data streams. Current methodologies primarily utilize decision-level fusion and feature-level fusion techniques. Decision-level fusion offers high flexibility and ease of implementation but lacks inter-feature interaction; it is less effective than feature-level fusion when correlations exist between heterogeneous features. Feature-level fusion amalgamates data from different modalities during the feature extraction phase, generating a unified cross-modal representation that effectively resolves inter-modal heterogeneity. In conclusion, we posit that multimodal fusion holds significant potential for further enhancing detection accuracy beyond the capabilities of existing single-modality technologies and is poised to become a major focus of future research in this domain.

Fault Diagnosis for the rolling bearing is an important field that has received increasing attention in recent years. The main challenge for this task is the lack of labeled data. Existing works circumvent this problem with pseudo labels generated from labeled data. However, these pseudo labels are noisy even with consistency check or confidence-based filtering due to the minimal amount of training data. To solve this problem, a novel Label-level Anti-noise Fault Diagnosis Network (LAFD-Net) is proposed in this paper. Specifically, we propose an Online Asymptotic Label Updating (OALU) strategy which contains two updating stages: self-correction stage and cross-correction stage. The proposed OALU can stably and reliably generate new corrected pseudo labels, gradually replacing the old noisy ones. The LAFD-Net adopts a Student-Teacher architecture. For such a Student-Teacher model, we propose a Consistency Enhancement (CE) loss to strengthen the feature consistency between student and teacher networks, aiming to achieve more efficient use of plentiful unlabeled data via feature regularization. Finally, a series of experiments were conducted using the University of Cincinnati Intelligent Maintenance System (IMS) Center dataset and the Case Western Reserve University (CWRU) bearing dataset. The experimental results demonstrate that the proposed semi-supervised learning schemes outperformed existing state-of-the-art methods with the same percentage of labeled data samples.

Effectively learning and extracting the feature representations of 3D point clouds is an important yet challenging task. Most of existing works achieve reasonable performance in 3D vision tasks by modeling the relationships among points appropriately. However, the feature representations are only learned with a specific transform through these methods, which are easy to overlap and thus limit the representation ability of the model. To address these issues, we propose a novel Multi-Transform Learning framework for point clouds (PointMTL), which can extract diverse features from multiple mapping transform to obtain richer representations. Specifically, we build a module named Multi-Transform Encoder (MTE), which encodes and aggregates local features from multiple non-linear transforms. To further explore global context representations, a module named Global Spatial Fusion (GSF) is proposed to capture global information and selectively fuse with local representations. Moreover, to guarantee the richness and diversity of learned representations, we further propose a Spatial Independence Criterion (SIC) strategy to enlarge the differences between the transforms and reduce information redundancies. In contrast to previous works, our approach fully exploits representations from multiple transforms, thus having strong expressiveness and good robustness for point clouds related tasks. The experiments on three typical tasks (i.e., semantic segmentation on S3DIS and ScanNet, part segmentation on ShapeNet and shape classification on ModelNet40) demonstrates the effectiveness of our method.

In order to improve the reliability and maintainability of rod control power cabinets in nuclear power plants, this paper uses insulated gate bipolar transistors (IGBTs), the key power device of rod control power cabinets, as the object of research on cross-working-condition fault prediction. An improved transfer learning (TL) model based on a temporal convolutional network (TCN) is proposed to solve the problem of low fault prediction accuracy across operating conditions. First, the peak emitter voltage of an IGBT aging dataset is selected as the source domain failure characteristic, and the TCN model is trained after the removal of outliers and noise reduction. Then, the time–frequency features are extracted according to the characteristics of the target domain data, and the target domain representation data are obtained using kernel principal component analysis (KPCA) for dimensionality reduction. Finally, the TCN model trained on the source domain is transferred; the model is fine-tuned according to the target domain data, and the learning rate, the number of hidden layer nodes, and the number of training times in the network model are optimized using the dung beetle optimization (DBO) algorithm to obtain the optimal network, making it more suitable for target sample fault prediction. The prediction results of this TCN model, the long short-term memory (LSTM) model, the gated recurrent unit (GRU) model, and the recursive neural network (RNN) model are compared and analyzed by selecting prediction performance evaluation indexes. The results show that the TCN model has a better predictive effect. Comparing the prediction results of the TCN-based optimized transfer learning model with those of the directly trained TCN model, the mean square error, root mean square error, and mean absolute error are reduced by a factor of two to three, which provides an effective solution for fault prediction across operating conditions.