Search Results (152)

Predictive maintenance (PdM) represents a significant evolution in maintenance strategies. However, challenges such as system integration complexity, data quality, and data availability are intricately intertwined, collectively impacting the successful deployment of PdM systems. Recently, large model-based agents, or agentic artificial intelligence (AI), have evolved from simple task automation to active problem-solving and strategic decision-making. As such, we propose an AI agent-enabled PdM method that leverages an agentic AI development platform to streamline the development of a multimodal data-based fault detection agent, a RAG (retrieval-augmented generation)-based fault classification agent, a large model-based fault diagnosis agent, and a digital twin-based fault handling simulation agent. This approach breaks through the limitations of traditional PdM, which relies heavily on single models. This combination of “AI workflow + large reasoning models + operational knowledge base + digital twin” integrates the concepts of BaaS (backend as a service) and LLMOps (large language model operations), constructing an end-to-end intelligent closed loop from data perception to decision execution. Furthermore, a tentative prototype is demonstrated to show the technology stack and the system integration methods of the agentic AI-based PdM. Full article

The ship waterjet propulsion system is a crucial power unit for high-performance vessels, and the operational state of its core component, the waterjet pump, is directly related to navigation safety and mission reliability. To enhance the intelligence and accuracy of pump fault diagnosis, this paper proposes a novel diagnostic framework that integrates a supervised autoencoder (SAE) with a large language model (LLM). This framework first employs an SAE to perform task-oriented feature learning on raw vibration signals collected from the pump’s guide vane casing. By jointly optimizing reconstruction and classification losses, the SAE extracts deep features that both represent the original signal information and exhibit high discriminability for different fault classes. Subsequently, the extracted feature vectors are converted into text sequences and fed into an LLM. Leveraging the powerful sequential information processing and generalization capabilities of LLM, end-to-end fault classification is achieved through parameter-efficient fine-tuning. This approach aims to avoid the traditional dependence on manually extracted time-domain and frequency-domain features, instead guiding the feature extraction process via supervised learning to make it more task-specific. To validate the effectiveness of the proposed method, we compare it with a baseline approach that uses manually extracted features. In two experimental scenarios, direct diagnosis with full data and transfer diagnosis under limited-data, cross-condition settings, the proposed method significantly outperforms the baseline in diagnostic accuracy. It demonstrates excellent performance in automated feature extraction, diagnostic precision, and small-sample data adaptability, offering new insights for the application of large-model techniques in critical equipment health management. Full article

The complex topology of shipboard DC microgrids and the strong coupling between positive and negative poles during faults pose significant challenges for faulted-pole identification, especially under high-resistance conditions. To address these issues, this paper proposes a novel faulted-pole identification method based on S-Transformation and convolutional neural networks (CNNs). Single-ended voltage and current measurements from the generator side are used to generate time–frequency spectrograms via S-Transformation, which are then processed by a CNN trained to classify the faulted pole. This approach avoids reliance on complex threshold settings. Simulation results on a representative shipboard DC microgrid demonstrate that the proposed method achieves high accuracy, fast response, and strong robustness, even under high-resistance fault scenarios. The method significantly enhances the selectivity and reliability of fault protection, offering a promising solution for advanced marine DC power systems. Compared to conventional fault-diagnosis techniques, the proposed model achieves notable improvements in classification accuracy and computational efficiency for line-fault detection. Full article

With advancements in computational resources, artificial intelligence has gained significant attention in motor health monitoring. These sophisticated deep learning algorithms have been widely used for induction motor health monitoring due to their autonomous feature extraction abilities and end-to-end learning capabilities. However, in real-world scenarios, challenges such as limited labeled data and diverse operating conditions have led to the application of transfer learning for motor health monitoring. Transfer learning utilizes pretrained models to address new tasks with limited labeled data. Recent advancements in this domain have significantly improved fault diagnosis, condition monitoring, and the predictive maintenance of induction motors. This study reviews state-of-the-art transfer learning techniques, including domain adaptation, fine-tuning, and feature-based transfer for induction motor health monitoring. The key methodologies are analyzed, highlighting their contributions to improving fault detection, diagnosis, and prognosis in industrial applications. Additionally, emerging trends and future research directions are discussed to guide further advancements in this rapidly evolving field. Full article

To address the issues of high model complexity and weak noise resistance in convolutional neural networks for bearing fault diagnosis, this paper proposes a novel lightweight multi-angle feature fusion convolutional neural network (LMAFCNN). First, the original signal was preprocessed using a wide-kernel convolutional layer to achieve data dimensionality reduction and feature channel expansion. Second, a lightweight multi-angle feature fusion module was designed as the core feature extraction unit. The main branch fused multidimensional features through pointwise convolution and large-kernel channel-wise expansion convolution, whereas the auxiliary branch introduced an efficient channel attention (ECA) mechanism to achieve channel-adaptive weighting. Feature enhancement was achieved through the addition of branches. Finally, global average pooling and fully connected layers were used to complete end-to-end fault diagnosis. The experimental results showed that the proposed method achieved an accuracy of 99.5% on the Paderborn University (PU) artificial damage dataset, with a computational complexity of only 14.8 million floating-point operations (MFLOPs) and 55.2 K parameters. Compared with existing mainstream methods, the proposed method significantly reduces model complexity while maintaining high accuracy, demonstrating excellent diagnostic performance and application potential. Full article

This paper introduces a novel end-to-end fault diagnosis framework that integrates Bidirectional Long Short-Term Memory (BiLSTM) networks with Time-Domain Reflectometry (TDR) for the detection, characterization, and localization of wiring faults. The method is designed to operate directly on TDR signals, requiring no manual feature extraction or preprocessing. A forward model is used to simulate TDR responses across various fault scenarios and topologies, serving as the basis for supervised learning. The proposed BiLSTM-based model is trained and validated on common wiring network topologies, demonstrating high diagnostic performance. Experimental results show a diagnostic accuracy of 98.97% and a macro-average sensitivity exceeding 98%, outperforming conventional machine learning techniques. In addition to technical performance, the proposed approach supports sustainable and predictive maintenance strategies by reducing manual inspection efforts and enabling real-time automated diagnostics. Full article

The stability of gearbox bearings is crucial to the operational efficiency and safety of industrial equipment, as their faults can lead to downtime, economic losses, and safety risks. Traditional models face difficulties in handling complex industrial time-series data due to insufficient feature extraction capabilities and poor training stability. Although transformers show advantages in fault diagnosis, their ability to model local dependencies is limited. To improve feature extraction from time-series data and enhance model robustness, this paper proposes an innovative method based on the ViT. Time-series data were converted into two-dimensional images using polar coordinate transformation and Gramian matrices to enhance classification stability. A lightweight front-end encoder and depthwise feature extractor, combined with multi-scale depthwise separable convolution modules, were designed to enhance fine-grained features, while two-dimensional rotary position encoding preserved temporal information and captured temporal dependencies. The constructed RoPE-DWTrans model implemented a unified feature extraction process, significantly improving cross-dataset adaptability and model performance. Experimental results demonstrated that the RoPE-DWTrans model achieved excellent classification performance on the combined MCC5 and HUST gearbox datasets. In the fault category diagnosis task, classification accuracy reached 0.953, with precision at 0.959, recall at 0.973, and an F1 score of 0.961; in the fault category and severity diagnosis task, classification accuracy reached 0.923, with precision at 0.932, recall at 0.928, and an F1 score of 0.928. Compared with existing methods, the proposed model showed significant advantages in robustness and generalization ability, validating its effectiveness and application potential in industrial fault diagnosis. Full article

In recent years, Academia and industry have conducted extensive and in-depth research on bearing-fault-diagnosis technology. However, the current modeling of time–space coupling characteristics in rolling bearing fault diagnosis remains inadequate, and the integration of multi-modal correlations requires further improvement. To address these challenges, this paper proposes a joint diagnosis framework integrating graph convolutional networks (GCNs) with attention-enhanced bidirectional gated recurrent units (BiGRUs). The proposed framework first constructs an improved K-nearest neighbor-based spatio-temporal graph to enhance multidimensional spatial–temporal feature modeling through GCN-based spatial feature extraction. Subsequently, we design an end-to-end spatio-temporal joint learning architecture by implementing a global attention-enhanced BiGRU temporal modeling module. This architecture achieves the deep fusion of spatio-temporal features through the graph-structural transformation of vibration signals and a feature cascading strategy, thereby improving overall model performance. The experiment demonstrated a classification accuracy of 97.08% on three public datasets including CWRU, verifying that this method decouples bearing signals through dynamic spatial topological modeling, effectively combines multi-scale spatiotemporal features for representation, and accurately captures the impact characteristics of bearing faults. Full article

To address the challenge of incomplete fault feature extraction in rolling bearing fault diagnosis under small-sample conditions, this paper proposes a Temporal-Graph Convolutional Fusion Network (T-GCFN). The method enhances diagnostic robustness through collaborative extraction and dynamic fusion of features from time-domain and frequency-domain branches. First, Variational Mode Decomposition (VMD) was employed to extract time-domain Intrinsic Mode Functions (IMFs). These were then input into a Temporal Convolutional Network (TCN) to capture multi-scale temporal dependencies. Simultaneously, frequency-domain features obtained via Fast Fourier Transform (FFT) were used to construct a K-Nearest Neighbors (KNN) graph, which was processed by a Graph Convolutional Network (GCN) to identify spatial correlations. Subsequently, a channel attention fusion layer was designed. This layer utilized global max pooling and average pooling to compress spatio-temporal features. A shared Multi-Layer Perceptron (MLP) then established inter-channel dependencies to generate attention weights, enhancing critical features for more complete fault information extraction. Finally, a SoftMax classifier performed end-to-end fault recognition. Experiments demonstrated that the proposed method significantly improved fault recognition accuracy under small-sample scenarios. These results validate the strong adaptability of the T-GCFN mechanism. Full article

Winding interturn short-circuit (ISCF) fault is a common problem which occurs in distribution transformers due to multiple internal and external factors. Unfortunately, the variations in electric parameters under a slight fault are tiny and hardly used as effective characteristics for the detection and protection system. To address this issue, a low-cost robust detection method of ISCF based on the port voltage–current (ΔU-I) locus characteristic is presented in this paper. The mathematical model of the three-phase distribution transformer with ISCF is first established. Then, the ΔU-I locus function and relevant characteristic parameters are analyzed, respectively, which can reflect the healthy and faulty conditions. The axis length ratio between the major axis length and the minor axis length in the ΔU-I ellipse curve is defined as the fault indicator for the sensitivity and robustness of fault diagnosis. Moreover, this method can reduce the number of sensors and has strong robustness against load fluctuations. In the end, the theoretical analysis and simulation results verify the effectiveness of the ΔU-I locus characteristic. Full article

With the deep integration of distributed network technology and intelligent medical care, how to achieve efficient collaboration under the premise of safeguarding data security and system efficiency has become an important challenge for intelligent medical diagnosis systems. The traditional practical Byzantine fault tolerance (PBFT) algorithm has difficulty meeting the demands of large-scale distributed medical scenarios due to high communication overhead and poor scalability. In addition, the existing improvement schemes are still deficient in dynamic node management and complex attack defence. To this end, this paper proposes the VS-PBFT consensus algorithm, which fuses a verifiable random function (VRF) and reputation mechanism, and designs a distributed intelligent medical diagnosis collaboration system based on this algorithm. Firstly, we introduce the VRF technique to achieve random and unpredictable selection of master nodes, which reduces the risk of fixed verification nodes being attacked. Secondly, we construct a dynamic reputation evaluation model to quantitatively score the nodes’ historical behaviors and then adjust their participation priority in the consensus process, thus reducing malicious node interference and redundant communication overhead. In the application of an intelligent medical diagnosis collaboration system, the VS-PBFT algorithm effectively improves the security and efficiency of diagnostic data sharing while safeguarding patient privacy. The experimental results show that in a 40-node network environment, the transaction throughput of VS-PBFT is 21.05% higher than that of PBFT, the delay is reduced by 33.62%, the communication overhead is reduced by 8.63%, and the average number of message copies is reduced by about 7.90%, which demonstrates stronger consensus efficiency and anti-attack capability, providing the smart medical diagnosis collaboration system with the first VS-PBFT algorithm-based technical support. Full article

Distributed Acoustic Sensing (DAS) systems face increasing challenges in massive data processing and real-time fault diagnosis due to the growing complexity of industrial environments and data volume. To address these issues, an end-to-end diagnostic framework is developed, integrating Mel-Frequency Cepstral Coefficients (MFCCs) for high-efficiency signal compression and Liquid Neural Networks (LNNs) for lightweight, real-time classification. The MFCC algorithm, originally used in speech processing, is adapted to extract key features from DAS vibration signals, achieving compression ratios of 60–100× without significant information loss. LNNs’ dynamic topology and sparse activation enable high accuracy with extremely low latency and minimal computational cost, making it highly suitable for edge deployment. The proposed framework was validated both in simulated environments and on a real-world conveyor belt system at Qinhuangdao Port, where it achieved 100% accuracy across four vibration modes over 14 weeks of operation. Comparative experiments show that LNNs outperform traditional models such as 1D-CNN and LSTMs in terms of accuracy, inference speed, and model size. The proposed MFCC-LNN pipeline also demonstrates strong cross-domain generalization capabilities in pipeline monitoring, seismic detection, and speech signal processing. Full article

This paper proposes a novel fault diagnosis framework that integrates the Osprey–Cauchy–Sparrow Search Algorithm (OCSSA) optimized Variational Mode Decomposition (VMD) with a Bidirectional Temporal Convolutional Network-Attention mechanism (BiTCN-Attention). To address the limitations of empirical parameter selection in VMD, OCSSA adaptively optimizes the decomposition parameters (penalty factor $\alpha$ and mode number K) through a hybrid strategy that combines chaotic initialization, Osprey-inspired global search, and Cauchy mutation. Subsequently, the BiTCN captures bidirectional temporal dependencies from vibration signals, while the attention mechanism dynamically filters critical fault features, constructing an end-to-end diagnostic model. Experiments on the CWRU dataset demonstrate that the proposed method achieves an average accuracy of 99.44% across 10 fault categories, outperforming state-of-the-art models (e.g., VMD-TCN: 97.5%, CNN-BiLSTM: 84.72%). Full article

CNC machine and cutting tools are an indispensable part of the cutting process. Their life default diagnosis is related to the efficiency of the entire production process, which ultimately impacts economic performance. Many methods provided by deep learning articles have been verified for use on large cutting datasets and can help in diagnosing tools’ lifetime well; however, on small samples, the challenge of learning difficulties still emerges. The rise in large language models (LLMs) has brought changes to tool life diagnosis. This study proposes a fault diagnosis algorithm based on GLM-4, and the experimental validation on the PHM 2010 dataset and a proprietary milling cutter dataset demonstrates the superiority of the proposed model, achieving diagnostic accuracies of 93.8% and 93.3%, respectively, outperforming traditional models (SVM, CNN, RNN) and baseline LLMs (ChatGLM2-6B variants). Further robustness and noise-resistance analyses confirm its stability under varying SNR levels (10 dB to −10 dB) and limited training samples. This work highlights the potential of integrating domain-specific feature engineering with LLMs to advance intelligent manufacturing diagnostics. Full article

To address the challenge of low diagnostic accuracy in rolling bearing fault diagnosis under varying operating conditions, this paper proposes a novel method integrating the synchronized wavelet transform (SWT) with an enhanced Vision Transformer architecture, referred to as ResCAA-ViT. The SWT is first applied to process raw vibration signals, generating high-resolution time–frequency maps as input for the network model. By compressing and reordering wavelet transform coefficients in the frequency domain, the SWT enhances time–frequency resolution, enabling the clear capture of instantaneous changes and local features in the signals. Transfer learning further leverages pre-trained ResNet50 parameters to initialize the convolutional and residual layers of the ResCAA-ViT model, facilitating efficient feature extraction. The extracted features are processed by a dual-branch architecture: the left branch employs a residual network module with a CAA attention mechanism, improving sensitivity to critical fault characteristics through strip convolution and adaptive channel weighting. The right branch utilizes a Vision Transformer to capture global features via the self-attention mechanism. The outputs of both branches are fused through addition, and the diagnostic results are obtained using a Softmax classifier. This hybrid architecture combines the strengths of convolutional neural networks and Transformers while leveraging the CAA attention mechanism to enhance feature representation, resulting in robust fault diagnosis. To further enhance generalization, the model combines cross-entropy and mean squared error loss functions. The experimental results show that the proposed method achieves average accuracy rates of 99.96% and 96.51% under constant and varying load conditions, respectively, on the Case Western Reserve University bearing fault dataset, outperforming other methods. Additionally, it achieves an average diagnostic accuracy of 99.25% on a real-world dataset of generator non-drive end bearings in wind turbines, surpassing competing approaches. These findings highlight the effectiveness of the SWT and ResCAA-ViT-based approach in addressing complex variations in operating conditions, demonstrating its significant practical applicability. Full article