Search Results (126)

Fault diagnosis in modern power systems increasingly depends on unstructured operation and maintenance (O&M) logs, yet real-world logs are often small in scale and highly imbalanced across fault types, which degrades the generalizability of standard neural models. This paper proposes a graph-augmented diagnostic framework that integrates imbalance-aware knowledge extraction with interpretable reasoning. The framework consists of three stages: (1) domain adaptation of a BERT–BiLSTM–CRF NER model and a BERT–MLP RE model using an imbalance-aware training recipe that combines Low-Rank Adaptation (LoRA), a mixed focal–range loss, and undersampling; (2) construction of a power-system knowledge graph that organizes extracted entities and relations (e.g., fault devices, abnormal phenomena, causes, and handling measures); and (3) a graph-augmented assistant agent that reuses the NER model as a graph-aware retriever within a retrieval-augmented generation (RAG) architecture to support contextualized and interpretable diagnostic reasoning. Experiments on 3921 real-world fault-processing logs show consistent gains: NER reaches 92.0% accuracy and 71.3% Macro-F1 (vs. 80.3% and 63.2%), and RE achieves 88.0% accuracy and 70.1% F1 (vs. 82.1% and 60.4%), while reducing average training time per epoch by about 18%. These results demonstrate an efficient and practical path toward robust log-based fault diagnosis under scarce and imbalanced data. Full article

To address the challenges commonly encountered in civil aircraft operating under multi-mode, strongly coupled closed-loop control—namely scarce fault samples, pronounced distribution shift, and root-cause explanations that are easily confounded by covariates—this paper proposes a root-cause analysis method that integrates ensemble learning with constraint-guided reasoning by large language models (LLMs). First, for Full Authority Digital Engine Control (FADEC) monitoring sequences, a feature system comprising environment-normalized ratios, mechanism-informed mixing indices, and multi-scale temporal statistics is constructed, thereby improving cross-mode comparability and enhancing engineering-semantic expressiveness. Second, in the anomaly detection stage, a cost-sensitive LightGBM model is adopted and a validation-set-based adaptive thresholding strategy is introduced to achieve robust identification under highly imbalanced fault conditions. Furthermore, for Root Cause Analysis (RCA), a “computation–reasoning decoupling” framework is developed: Shapley Additive exPlanations (SHAP) are used to generate segment-level contribution evidence, while causal chains, engineering prohibitions, and structured output templates are injected into prompts to constrain the LLM, enabling it to infer root-cause candidates and produce structured explanations under mechanism-consistency constraints. Experiments on real flight data demonstrate that our method yields an anomaly detection F1-score of 0.9577 and improves overall RCA accuracy to 97.1% (versus 62.3% for a pure SHAP baseline). Practically, by translating complex high-dimensional data into actionable natural language diagnostic reports, the proposed method provides reliable and interpretable decision support for rapid RCA. Full article

The blast furnace ironmaking process (BFIP) is a highly complex and dynamic industrial system where strong spatiotemporal coupling and severe data imbalance pose substantial challenges for fault diagnosis. To address these issues, this study proposes a Transformer–BiLSTM Double Deep Q-Network (TBDDQN) framework for intelligent fault diagnosis. The framework employs a dual-branch architecture that integrates a Transformer-based spatial encoder with a BiLSTM-attention temporal extractor to capture global dependencies and dynamic patterns from multivariate time-series data. To mitigate class imbalance and asymmetric fault costs, a cost-sensitive reinforcement learning scheme based on Double DQN is incorporated, featuring prioritized experience replay and adaptive misclassification penalties. Experiments on real blast furnace datasets show that TBDDQN achieves a macro-averaged precision of 0.970 and a macro-averaged F1-score of 0.929, outperforming conventional CNN, LSTM, and DQN-based baselines. These results demonstrate that TBDDQN offers a robust and interpretable solution for imbalanced industrial fault diagnosis in the BFIP. Full article

Network fault diagnosis has evolved in response to the needs of modern networks, transitioning from traditional methods, such as passive and active monitoring, to advanced learning techniques. While conventional methods often introduce invasive traffic and control overhead, newer approaches face challenges such as increased internal processes and the need for extensive knowledge of network behavior. Learning-based methods offer an advantage by not requiring a complete network model, allowing the use of statistical and Machine Learning techniques to process historical data. However, existing learning methods face limitations, such as the need for extensive data samples and extended retraining periods, which can leave systems vulnerable to failures, particularly in dynamic environments. This work addresses these issues by proposing an incremental learning approach for continuous fault diagnosis in IP-based networks. The approach utilizes online learning to process symptoms in real-time, adapting to network changes while managing data imbalance through drift detection and rebalancing strategies, such as ADWIN and SMOTE. We evaluated the performance of this method using 25 incremental algorithms on the SOFI dataset. The results, assessed using metrics such as recall, G-mean, kappa, and MCC, demonstrated high performance over time, indicating the potential for resilient, adaptive fault detection processes in dynamic network environments. Additionally, a non-invasive process can be ensured through peripheral observation of failure symptoms, provided that data collection does not increase network traffic, overhead control, or internal network processes. Full article

Severe diagnostic errors are often caused by the significant imbalance between normal and fault data in bearing datasets. To solve this challenge, a graph attention convolutional neural network based on sensitivity analysis and correlation analysis (SCGAT) is proposed to achieve bearing fault diagnosis under imbalanced-dataset conditions. Firstly, a graph attention convolutional neural network is constructed to effectively extract fault-related features from multi-sensor data. Then, a sensor sensitivity analysis module is built to filter and select effective sensor information. A sensor correlation analysis module is introduced to distinguish the correlation between different sensors, and strongly correlated sensors are merged. Finally, the merged features are input into a classifier for fault diagnosis. The effectiveness of the proposed method is verified on a power transmission simulation experiment platform. The experimental results show that the proposed SCGAT can effectively achieve fault diagnosis under imbalanced data conditions, and exhibits higher diagnostic accuracy and stability compared to other models. Full article

Coalbed methane, an abundant clean energy resource in China, is gaining significant attention. Electric submersible progressive cavity pumps, ideal for downhole extraction with high solids content, are vital in coalbed methane operations. Current fault diagnosis research for these pumps mainly relies on machine learning algorithms to identify fault features, but complex working conditions and imbalanced sample distributions challenge these models’ ability to perceive multi-scale and multi-dimensional features. To enhance the model’s perception of deep abnormal data in complex multi-case industrial datasets, this study proposes a deep learning model based on a multi-scale extraction and residual module convolutional neural network. Innovatively, a cross-attention module using global autocorrelation and local cross-correlation is introduced to constrain the multi-scale feature extraction process, making the model better suited to specific and differentiated data environments. Post feature extraction, the model employs Borderline-SMOTE to augment minority class samples and uses Tomek Links for noise removal. These enhancements improve the comprehensive perception of fault types with significant differences in period, amplitude, and dimension, as well as the learning capability for rare faults. Based on field-collected fault data and using enhanced and cleaned features for classifier training, tests on a real industrial dataset show the proposed model achieves an F1 Measure of 90.7%—an improvement of 13.38% over the unimproved model and 9.15–31.64% over other common fault diagnosis models. Experimental results confirm the method’s effectiveness in adapting to extremely imbalanced sample distributions and complex, variable field data characteristics. Full article

Industrial pumps are critical components in manufacturing and process plants, where early acoustic anomaly detection is essential for preventing unplanned downtime and reducing maintenance costs. In practice, however, strong background noise, severe class imbalance between rare faults and abundant normal data, and the limited computing resources of edge devices make reliable deployment challenging. In this work, a lightweight Audio Spectrogram Transformer (Tiny-AST) is proposed for robust pump anomaly detection under imbalanced supervision. Building on the Audio Spectrogram Transformer, the internal Transformer encoder is redesigned by jointly reducing the embedding dimension, depth, and number of attention heads, and combined with a class frequency-based balanced sampling strategy and time–frequency masking augmentation. Experiments on the pump subset of the MIMII dataset across three SNR levels (−6 dB, 0 dB, 6 dB) demonstrate that Tiny-AST achieves an effective trade-off between computational efficiency and noise robustness. With 1.01 M parameters and 1.68 GFLOPs, it maintains superior performance under heavy noise (−6 dB) compared to ultra-lightweight CNNs (MobileNetV3) and offers significantly lower computational cost than standard compact baselines (ResNet18, EfficientNet-B0). Furthermore, comparisons highlight the performance gains of this lightweight supervised approach over traditional unsupervised benchmarks (e.g., autoencoders, GANs) by effectively leveraging scarce fault samples. These results indicate that a carefully designed lightweight Transformer, together with appropriate sampling and augmentation, can provide competitive acoustic anomaly detection performance while remaining suitable for deployment on resource-constrained industrial edge devices. Full article

Fatigue-related ‘rotor crack’ can cause catastrophic failure if neglected. Thus, IoT-enabled AI-based predictive maintenance for fault detection and diagnosis is explored. Training and testing AI models under similar conditions improves their prediction performance. On variable speed machines, loss of performance occurs when the testing speed differs from the training speed. This research addresses significant performance loss issues using convolutional neural network (CNN)-based transfer learning models. The main causes of performance loss are domain shift, overfitting, data class imbalance, low fault data availability, and biassed prediction. All the above difficult issues make CNN-based fault prediction systems function badly under varying operating conditions. The proposed methodology addresses all domain adaptation challenges. The proposed methodology was tested by collecting vibration data from an experimental rotor system under varied operating conditions. The proposed methodology outperforms classical machine learning (ML) and deep learning (DL) models, overcoming the overfitting issue with optimised hyperparameters, achieving a prediction accuracy of 99.5%. Under varying operating conditions, it outperforms with a prediction accuracy of 93.2%, and in the ‘data class imbalanced’ scenario, the maximal transfer learning capability achieved was 84.4% with the highest F1-Score. Thus, CNN-based transfer learning enables industrial variable speed machines diagnose rotor crack flaws better than ML and DL models. Full article

Detecting active failures is important for the Industrial Internet of Things (IIoT). The IIoT aims to connect devices and machinery across industries. The devices connect via the Internet and provide large amounts of data which, when processed, can generate information and even make automated decisions on the administration of industries. However, traditional active fault management techniques face significant challenges, including highly imbalanced datasets, a limited availability of failure data, and poor generalization to real-world conditions. These issues hinder the effectiveness of prompt and accurate fault detection in real IIoT environments. To overcome these challenges, this work proposes a data augmentation mechanism which integrates generative adversarial networks (GANs) and the synthetic minority oversampling technique (SMOTE). The integrated GAN-SMOTE method increases minority class data by generating failure patterns that closely resemble industrial conditions, increasing model robustness and mitigating data imbalances. Consequently, the dataset is well balanced and suitable for the robust training and validation of learning models. Then, the data are used to train and evaluate a variety of models, including deep learning architectures, such as convolutional neural networks (CNNs) and long short-term memory networks (LSTMs), and conventional machine learning models, such as support vector machines (SVMs), K-nearest neighbors (KNN), and decision trees. The proposed mechanism provides an end-to-end framework that is validated on both generated and real-world industrial datasets. In particular, the evaluation is performed using the AI4I, Secom and APS datasets, which enable comprehensive testing in different fault scenarios. The proposed scheme improves the usability of the model and supports its deployment in a real IIoT environment. The improved detection performance of the integrated GAN-SMOTE framework effectively addresses fault classification challenges. This newly proposed mechanism enhances the classification accuracy up to 0.99. The proposed GAN-SMOTE framework effectively overcomes the major limitations of traditional fault detection approaches and proposes a robust, scalable and practical solution for intelligent maintenance systems in the IIoT environment. Full article

This paper presents Hy-LIFT (Hybrid LLM-Integrated Fault Diagnosis Toolkit), a multi-stage framework for interpretable and data-efficient fault diagnosis in 5G/6G networks that integrates a high-precision interpretable rule-based engine (IRBE) for known patterns, a semi-supervised classifier (SSC) that leverages scarce labels and abundant unlabeled logs via consistency regularization and pseudo-labeling, and an LLM Augmentation Engine (LAE) that generates operator-ready, context-aware explanations and zero-shot hypotheses for novel faults. Evaluations on a five-class, imbalanced Dataset-A and a simulated production setting with noise and label scarcity show that Hy-LIFT consistently attains higher macro-F1 than rule-only and standalone ML baselines while maintaining strong per-class precision/recall (≈0.85–0.93), including minority classes, indicating robust generalization under class imbalance. IRBE supplies auditable, high-confidence seeds; SSC expands coverage beyond explicit rules without sacrificing precision; and LAE improves operational interpretability and surfaces potential “unknown/novel” faults without altering classifier labels. The paper’s contributions are as follows: (i) a reproducible, interpretable baseline that doubles as a high-quality pseudo-label source; (ii) a principled semi-supervised learning objective tailored to network logs; (iii) an LLM-driven explanation layer with zero-shot capability; and (iv) an open, end-to-end toolkit with scripts to regenerate all figures and tables. Overall, Hy-LIFT narrows the gap between brittle rules and opaque black-box models by combining accuracy, data efficiency, and auditability, offering a practical path toward trustworthy AIOps in next-generation mobile networks. Full article

To improve/enhance the intelligence and accuracy of fault diagnosis in high-voltage direct current (HVDC) systems, this paper proposes a fault diagnosis model for HVDC systems based on the multimodal sensor feature-light gradient boosting machine (MSF-LightGBM) algorithm. First, a sample set encompassing four typical types of faults, namely alternating current (AC) faults, direct current (DC) faults, inverter commutation failures, and converter valve faults, was constructed based on the actual HVDC transmission data from China. Second, considering the issues of imbalanced sample classes and a relatively small sample size in the original dataset, a data augmentation method incorporating multiple types of noise is introduced to improve the diversity and practical representativeness of the samples. Then, time-series features in the time domain, frequency domain, and wavelet domain, along with Pearson correlation features among 15 sensors, are extracted to form a comprehensive feature vector. On this basis, automatic feature selection is performed using recursive feature elimination (RFE) to screen out the key features. Finally, the paper builds an optimized LightGBM classification model is built using the key features. Through comparative experiments with five machine learning methods, the results indicate that the accuracy of the proposed method on the test set reaches 0.9583, significantly outperforming the other comparison models. The receiver operating characteristic (ROC) curve analysis reveals that the average area under the curve (AUC) for all four types of faults is 0.975, validating the stability and accuracy of the proposed model in multi-class fault identification. Full article

As an important part of the ship’s power system, the bearing operation status of the propulsion motor is directly related to the reliability and safety of the whole system. However, in the field of marine propulsion motor bearing fault diagnosis, the data imbalance problem seriously affects the performance of the fault detection model. Due to the scarcity of fault data relative to normal operation data, traditional diagnostic methods are ineffective in dealing with unbalanced data. To solve this problem, a dynamic class weighting solution is proposed. The dynamic class weighting method introduces the weight coefficient λ on the basis of the traditional class weighting, which can adjust the class weight value in real time according to the training situation, and comprehensively considers the data distribution and the training situation to ensure that the model can learn better even in the case of insufficient data. Testing on the imbalanced distribution of bearing natural-failure data shows that the proposed method achieves a 5.25% improvement in diagnostic accuracy compared to direct training. Compared with traditional class-weighted approaches, diagnostic accuracy is enhanced by 3.56%, effectively mitigating the impact of scarce and unevenly distributed failure data on model training. Full article

In real-world industrial settings, obtaining class-balanced fault data is often difficult. Imbalanced data across categories can degrade diagnostic accuracy. Time-series Generative Adversarial Network (TimeGAN) is an effective tool for addressing one-dimensional data imbalance; however, when dealing with multiple fault categories, it faces issues such as unstable training processes and uncontrollable generation states. To address this issue, from the perspective of data augmentation and classification, a gradient-penalized Conditional Time-series Generative Adversarial Network with a Multi-Scale Importance-aware Network (CTGAN-MSIN) is proposed in this paper. Firstly, a gradient-penalized Conditional Time-Series Generative Adversarial Network (CTGAN) is designed to alleviate data imbalance by controllably generating high-quality fault samples. Secondly, a Multi-scale Importance-aware Network (MSIN) is constructed for fault classification. The MSIN consists of the Multi-scale Depthwise Separable Residual (MDSR) and Scale Enhanced Local Attention (SELA): the MDSR network can efficiently extract multi-scale features, while the SELA network is capable of screening out the most discriminative scale features from them. Finally, the proposed method is validated using the HUST bearing dataset and the axial piston pump dataset. The results show that under the data imbalance ratio of 15:1, the CTGAN-MSIN achieves diagnostic accuracies of 98.75% and 96.50%, respectively, on the two datasets and outperforms the comparison methods under different imbalance ratios. Full article

Rolling bearings are critical components in mechanical systems, and their health directly affects operational reliability and safety. However, their exposure to harsh conditions makes accurate fault diagnosis essential. Conventional methods relying on expert knowledge and handcrafted features are inefficient, while deep learning still suffers from data imbalance, which limits generalization. To address this challenge, an Attention-Enhanced Conditional Wasserstein GAN (ACWGAN) is proposed, in which the attention mechanism is incorporated into both the generator and discriminator to capture global dependencies and enhance feature diversity. By combining attention guidance with the Wasserstein distance, the framework achieves more stable training, alleviates mode collapse, and generates high-fidelity fault samples to balance imbalanced datasets. Compared with existing GAN-based methods, this method, combined with wavelet-based ResNet, significantly improves the accuracy of diagnosis, achieving 100% accuracy in the generated dataset. Full article

As a critical component of rail travel, the train communication network (TCN) is an integrated central platform that is used to realize the train control, condition monitoring, and data transmission, whose failure will disrupt the symmetry of TCN topology and endanger the security of rail trains. To enhance the reliability of TCN, an intelligent fault diagnosis method is proposed based on active learning (AL) and a stacked consistent autoencoder (SCAE), which is capable of building a competitive classifier with a limited amount of labeled training samples. SCAE can learn better feature presentations from electrical multifunction vehicle bus (MVB) signals by reconstructing the same raw input data layer by layer in the unsupervised feature learning phase. In the supervised fine-tuning phase, a deep AL-based fault diagnosis framework is proposed, and a dynamic fusion AL method is presented. The most valuable unlabeled samples are selected for labeling and training by considering uncertainty and similarity simultaneously, and the fusion weight is dynamically adjusted at the different training stages. A TCN experimental platform is constructed, and experimental results show that the proposed method achieves better performance under three different metrics with fewer labeled samples compared to the state-of-the-art methods; it is also symmetrically valid in class-imbalanced data. Full article