Attention-Based Multi-Scale Temporal Fusion Network for Uncertain-Mode Fault Diagnosis in Multimode Processes

Fault diagnosis in multimode processes plays a critical role in ensuring the safe operation of industrial systems across multiple modes. It faces a great challenge yet to be addressed - that is, the significant distributional differences among monitoring data from multiple modes make it difficult for the models to extract shared feature representations related to system health conditions. In response to this problem, this paper introduces a novel method called attention-based multi-scale temporal fusion network. The multi-scale depthwise convolution and gated recurrent unit are employed to extract multi-scale contextual local features and long-short-term features. A temporal attention mechanism is designed to focus on critical time points with higher cross-mode shared information, thereby enhancing the accuracy of fault diagnosis. The proposed model is applied to Tennessee Eastman process dataset and three-phase flow facility dataset. The experiments demonstrate that the proposed model achieves superior diagnostic performance and maintains a small model size.

Double Gradient Reversal Network for Single-Source Domain Generalization in Multi-mode Fault Diagnosis

Domain generalization achieves fault diagnosis on unseen modes. In process industrial systems, fault samples are limited, and only single-mode fault data can be obtained. Extracting domain-invariant fault features from single-mode data for unseen mode fault diagnosis poses challenges. Existing methods utilize a generator module to simulate samples of unseen modes. However, multi-mode samples contain complex spatiotemporal information, which brings significant difficulties to accurate sample generation. Therefore, double gradient reversal network (DGRN) is proposed. First, the model is pre-trained to acquire fault knowledge from the single seen mode. Then, pseudo-fault feature generation strategy is designed by Adaptive instance normalization, to simulate fault features of unseen mode. The dual adversarial training strategy is created to enhance the diversity of pseudo-fault features, which models unseen modes with significant distribution differences. Subsequently, domain-invariant feature extraction strategy is constructed by contrastive learning and adversarial learning. This strategy extracts common features of faults and helps multi-mode fault diagnosis. Finally, the experiments were conducted on Tennessee Eastman process and continuous stirred-tank reactor. The experiments demonstrate that DGRN achieves high classification accuracy on unseen modes while maintaining a small model size.

Remaining useful life prediction of rolling bearings based on refined composite multi-scale attention entropy and dispersion entropy

Remaining useful life (RUL) prediction based on vibration signals is crucial for ensuring the safe operation and effective health management of rotating machinery. Existing studies often extract health indicators (HI) from time domain and frequency domain features to analyze complex vibration signals, but these features may not accurately capture the degradation process. In this study, we propose a degradation feature extraction method called Fusion of Multi-Modal Multi-Scale Entropy (FMME), which utilizes multi-modal Refined Composite Multi-scale Attention Entropy (RCMATE) and Fluctuation Dispersion Entropy (RCMFDE), to solve the problem that the existing degradation features cannot accurately reflect the degradation process. Firstly, the Empirical Mode Decomposition (EMD) is employed to decompose the dual-channel vibration signals of bearings into multiple modals. The main modals are then selected for further analysis. The subsequent step involves the extraction of RCMATE and RCMFDE from each modal, followed by wavelet denoising. Next, a novel metric is proposed to evaluate the quality of degradation features. The attention entropy and dispersion entropy of the optimal scales under different modals are fused using Laplacian Eigenmap (LE) to obtain the health indicators. Finally, RUL prediction is performed through the similarity of health indicators between fault samples and bearings to be predicted. Experimental results demonstrate that the proposed method yields favorable outcomes across diverse operating conditions.