Jul 2026· Sound & Vibration· 0 citations· 35 references
TL;DR
The proposed method forms a failure probability–evolutionary entropy dual-index evaluation system and a hierarchical early warning mechanism with strong physical interpretability, providing reliable technical support for reliability evaluation and predictive maintenance of complex mechanical systems.
Abstract
To address the problems of one-sided modal information, unclear fault evolution, and insufficient support for early fault diagnosis warning of complex systems, a method for evaluating system vibration characteristics and fault evolution based on multimodal data fusion is proposed. With multimodal data fusion, factor space mapping, fault evolution network modeling, and probabilistic evaluation as the core, the unified characterization of heterogeneous data to fault-influencing factors is realized through feature extraction and hierarchical mapping of multi-source data, including vibration, acoustic emission, and oil analysis. Based on the Space Fault Network (SFN), the topological relationship and probability transfer model of fault events are constructed. Combined with evolutionary entropy analysis, an evaluation system of failure probability-evolutionary entropy and a hierarchical early warning mechanism are formed. Taking the axle box bearing as an example, with thresholds determined by full-life cycle fault data fitting and engineering experience, the system fault is identified as the attention state at 80 hours and the high-risk state at 100 hours, which is consistent with the law of gradual fault evolution and engineering practicability. The proposed method forms a failure probability–evolutionary entropy dual-index evaluation system and a hierarchical early warning mechanism with strong physical interpretability, providing reliable technical support for reliability evaluation and predictive maintenance of complex mechanical systems.
To tackle the intractable problems including weak fault feature extraction and evolution uncertainty quantification for complex systems in strong noise environments, a novel method for weak fault diagnosis and evolution analysis is proposed. This method integrates the fuzzy structured element (FSE), cloud model (CM), and Space Fault Network (SFN). The method centers on adaptive wavelet denoising, fault feature cloudification, and SFN probability propagation. The fault signal under strong noise is reconstructed by optimizing the wavelet threshold with the FSE. The uncertainty encapsulation of the peak factor of fault features is realized based on the CM to establish the feature CM. The fault event topology is constructed relying on the SFN. The quantitative transfer of uncertainty in the fault evolution is achieved combined with cloud algebra. Verified by the inner ring pitting fault of axle box bearings, the results demonstrate that the proposed method can extract the fault characteristic frequency of 250.5 Hz. The derived fault probability CM (0.680, 0.059, 0.023) accurately quantifies the system risk level. This result is consistent with the actual fault evolution law in engineering practice. This method provides technical support for early fault warning and maintenance of complex industrial system. Furthermore, comparative experiments confirm its superiority over traditional methods in noise suppression and feature retention. Parameter analysis is also discussed to improve engineering generalization.
The recoil suppression device is a key component of modern artillery systems. Its dynamic performance directly affects the stability and control accuracy of the machinery operation, and subsequently influences work efficiency and operational safety. However, traditional fault diagnosis methods are unable to handle the ambiguity issues arising from multi-source faults, resulting in low accuracy of the diagnosis results. Therefore, this paper proposes a fault diagnosis method based on knowledge-data fuzzy fusion (KDFF). Firstly, the expert experience knowledge(EEK) is introduced into the operating data of the recoil suppression device under different operating conditions, and the fault features are extracted through knowledge and data fusion-driven processing. Then, these knowledge are refined into membership function(MF) and confidence function(CF), and the fuzzy theory(FT) is used to improve the neural network. Finally, comparative experiments under three fault modes are conducted to verify the effectiveness of the algorithm. The verification results show that the KDFF can control the diagnostic error within 3%, effectively improving the fault diagnosis accuracy, and laying the foundation for predictive maintenance of such devices.
Kuikui Feng, Yunhe Zhang, Guangxiong Hu et al.· International Conference on...· 0 citations
Bearing fault diagnosis is a key strategy to ensure the stability of mechanical systems, optimize maintenance plans and improve operational reliability. Vibration signals are complex time series with unique properties. Most of the current methods only consider the spatial characteristics of the signal, but do not take into account its temporal characteristics. In fact, vibration signals contain both spatial and temporal information, offering not only rich temporal dynamic details but also spatial structural insights that reflect fault characteristics. Therefore, in order to fully mine and integrate the spatiotemporal feature information in vibration signals to enhance the accuracy and robustness of intelligent diagnosis, we propose a bearing fault diagnosis method based on the fusion of spatial and temporal features. Firstly, an improved wide kernel deep convolutional neural network method was proposed. By using an adaptive channel module, the model was enabled to focus on the key features of the vibration signal and suppress the interference of irrelevant information. At the same time, the superimposed bidirectional long short-term memory layer and the gated recurrent unit effectively capture the long-term dependencies of the time series in the dataset, covering both past and future signal features. This method can effectively utilize temporal information and combine it with spatial features, significantly improving the accuracy and robustness of bearing diagnosis. To verify the proposed method, ablation and comparative experiments were conducted on two publicly available bearing datasets: the Case Western Reserve University dataset and the Guangdong University of Petrochemical Technology dataset. The experimental results show that the average accuracy rates of fault diagnosis of the WBLG network on the two sets of datasets have reached 99.7% and 96.5% respectively. Compared with the existing models, the maximum improvement rates are 3.73% and 12.4% respectively. It demonstrates its superior classification performance and generalization applicable to bearing fault diagnosis.
Qi Wang, Rui Huang, Yongda Cai et al.· Measurement science and tech...· 0 citations
Accurate diagnosis of rolling bearing faults is critical to the reliability of industrial equipment. However, rolling bearings often operate under complex operating conditions, and with data imbalances and noise interference, fault diagnosis of them remains extremely challenging. To address these issues, a novel mode entropy knowledge machine (MEKM) framework for robust bearing fault diagnosis is proposed in this study. For MEKM, the mode entropy space is firstly constructed to decompose the vibration signal into intrinsic mode components, and the noise-resistant feature extraction and dimensionality reduction are realized by principal component analysis. Secondly, a fast classifier based on extreme learning machines is introduced, and its parameters are automatically adjusted through a particle swarm optimization to establish an adaptive extreme learning machine diagnosis model, ensuring optimal generalization under different load and speed levels. Then, a collaborative optimization paradigm is developed to coordinate mode entropy features and classifier parameters through fully automated learning, in which entropy-driven feature characterization guides the iterative refinement of decision boundaries, while classifier feedback dynamically improves the selectivity of entropy features. Finally, validation is performed on bearings with multiple operating conditions, and the results indicated that the MEKM outperformed conventional deep learning methods in terms of diagnostic accuracy and generalization ability. The work provides a theoretical basis and an industrially feasible solution for health monitoring of mechanical equipment.
Hongchuang Tan, Yiheng Su, Jiang Ding et al.· Journal of Dynamics Monitori...· 0 citations
Existing intelligent fault diagnosis methods based on multimodal fusion face the problem of significant differences in the representation capabilities of different modal data for machine faults, making it difficult to achieve optimal cross-modal data fusion and accurate fault identification. This study proposes a prior-enhanced cross-modal vibration and acoustic data fusion network based on directed attention mechanisms to address the aforementioned issue.First, through preliminary experiments in fault diagnosis, the differences in fault sensitivity between vibration and acoustic data are measured to determine the prior dominant data modality. Then, based on the directed cross-attention mechanism, a prior-dominant modality-weighted fusion of vibration and acoustic data features is realized. This process allows for unidirectional feature information transfer from the dominant data modality to the weaker one, avoiding reverse information contamination. Thus, cross-modal fusion features that are more sensitive to machine faults can be extracted. Finally, the extracted cross-modal fusion features are used to achieve fault diagnosis. The results of two machine fault experiments demonstrate that, compared with the state-of-the-art methods, the proposed method can achieve a significant leading advantage in the same diagnostic tasks, with a identification accuracy rate of bearing faults reaching 0.9898 under noisy conditions.
Qi-Bo Wang, Tianci Zhang· Measurement science and tech...· 0 citations
Large-scale integration of high-proportion new energy sources and continuous expansion of network scale complicate the transient characteristics of distribution networks. Conventional fault diagnosis methods suffer from insufficient feature extraction and weak capture of topological correlation, which degrade diagnosis accuracy. To tackle this issue, this paper proposes a complex fault diagnosis strategy for distribution networks based on analysis of the dynamic variation law of zero-sequence current. First, multivariate variational mode decomposition (MVMD) is adopted to process zero-sequence current signals, which effectively fuses multi-dimensional zero-sequence current data and fully excavates fault features. Moreover, the zebra optimization algorithm is utilized to optimize the parameters of MVMD for further improving feature extraction performance. Subsequently, a graph convolutional neural network is employed to extract temporal features from the processed waveforms, enhancing the model’s recognition capability under high-resistance faults and typical disturbance conditions. Finally, multiple IEEE test systems are used for verification, which demonstrates the effectiveness and feasibility of the proposed method.
Ruihao Zhou, Penghui Liu, Wenxiang Li et al.· Processes· 0 citations