Sequential ISAR Images Classification Using CNN-Bi-LSTM Method

Ni, Peishuang; Sheng, Jialian; Jiang, Lizhong; Xu, Gang

doi:10.1109/ciss57580.2022.9971386

Cited by 2 publications

(1 citation statement)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Guo et al [29] used dimensionality reduction and visualization techniques to examine the feature distribution of each layer in the model and attempt to understand the internal mechanism of feature extraction in each layer of the network. Zheng et al [30] applied attention mechanisms and bidirectional long short-term memory (Bi-LSTM) to achieve fault diagnosis in rotating machinery, while Ni et al [31] further employed attention mechanisms and bidirectional LSTM for time-varying state monitoring tasks. Additionally, using simpler models like decision trees [32] to replace parts of deep networks is also a method for constructing interpretable models.…”

Section: Introductionmentioning

confidence: 99%

Knowledge features enhanced intelligent fault detection with progressive adaptive sparse attention learning for high-power diesel engine

Liu

Kong

et al. 2023

Meas. Sci. Technol.

View full text Add to dashboard Cite

High-power diesel engines are core power equipment in some key fields, and fault diagnosis is of great significance for improving their long-term operational reliability and safety. The lack of sufficient fault samples, known as few-shot conditions, has resulted in the performance degradation of most current intelligent diagnostic methods under complex and variable working conditions. Moreover, the end-to-end deep learning diagnostic models based on implicit layer features do not have clear physical meanings, making it difficult for intelligent diagnostic models to be recognized by equipment managers in key fields. Mechanism-based fusion methods can effectively alleviate the above problems by incorporating fault-sensitive features with clear physical meanings. However, the lack of sufficient knowledge-related features that can characterize fault information is a challenge facing current mechanism fusion methods. In this work, we propose a progressive adaptive sparse attention mechanism-guided knowledge feature incremental mining method. Fault-sensitive segments are obtained based on attention-supervised learning with an improved activation function. Both knowledge-related features and hidden layer features from these segments are incorporated into the feature library. A differential constraint is designed between the distribution of knowledge features and hidden layer features, encouraging the model to focus on learning new knowledge-related features in the subsequent iteration process. Finally, a feature set containing a large amount of knowledge features is constructed to enhance fault diagnosis. Testing on a V12 diesel engine test bench under the conditions of rich and few-shot data sets, shows that the proposed method significantly enhances the fault recognition performance of diesel engines under complex variable working conditions and few-shot data set conditions.

show abstract