变压器
人工神经网络
同轴
复合数
计算机科学
模式识别(心理学)
工程类
电气工程
人工智能
电压
算法
作者
Xiaotian Bai,Jiafeng Zhu,Huaitao Shi,Chengying Zhao,R Zou
摘要
Abstract In order to address the limitations of condition monitoring of multi-part coaxial structure equipment, which are due to the placement of sensors and the inability to accurately identify weak faults, a fault diagnosis method based on a convolutional neural network (CNN) and a transformer neural network is proposed. Firstly, a neural network based on a Transformer encoder is constructed. The original signal is then processed by a signal preprocessing method, after which the original signal and the processed signal are fused to form the input. Finally, the rich and complementary fault features are effectively extracted by re-splicing the data shape. The sliding window is utilized to stitch the one-dimensional timing signal for the initial time and input the model. Subsequently, the data is stitched for a second time and input into the one-dimensional convolutional neural network (CNN) layer and embedded layer. Subsequently, a multi-layer transformer encoder is introduced to capture global information. The experimental results demonstrate that the proposed method exhibits an accuracy rate of 97.2%, accompanied by a discernible clustering effect. This approach effectively addresses the challenge of accurately extracting weak fault features from composite faults, offering a promising avenue for practical applications.
科研通智能强力驱动
Strongly Powered by AbleSci AI