Mao Meijiao, Jiang Zhiwen, Tan Zhifei, Xiao Wenqiang, Du Guangchao
School of Mechanical Engineering and Mechanics, Xiangtan University, Xiangtan 411105, China.
Engineering Research Center of Complex Trajectory Machining Process and Equipment, Ministry of Education, Xiangtan University, Xiangtan 411105, China.
Sensors (Basel). 2025 Feb 2;25(3):904. doi: 10.3390/s25030904.
Tilting pad thrust bearings are widely utilized in large rotating machinery such as steam turbines and hydraulic turbines. Defects in their shaft tiles directly impact lubrication characteristics, thereby influencing the overall safety performance of the entire unit. To address this issue, this paper presents a fault diagnosis method for tilting pad thrust bearings using a modified multi-feature fused convolutional neural network (MMFCNN). Initially, an experimental bench for diagnosing faults in tilting pad thrust bearings was developed to collect multi-channel acoustic emission (AE) signals from both normal and faulty pads. Subsequently, the squeeze-and-excitation (SE) module was employed to reallocate the weights of each channel and fuse the features of multi-channel signals. Learning was then conducted on the signal fused with multiple features using the inverse-add module and spanning convolution. Next, a comparative analysis was carried out among the CNN1D, ResNet, and DFCNN models, and the MMFCNN model proposed in this study. The results show that under consistent operating conditions, the MMFCNN model achieves an average fault diagnosis accuracy of 99.58% when utilizing AE signal data from tilting pad thrust bearings in four states as inputs. Furthermore, when different operational conditions are introduced, the MMFCNN model also outperforms other models in terms of accuracy.
可倾瓦推力轴承广泛应用于汽轮机和水轮机等大型旋转机械中。其轴瓦缺陷直接影响润滑特性,进而影响整个机组的整体安全性能。为解决这一问题,本文提出一种基于改进的多特征融合卷积神经网络(MMFCNN)的可倾瓦推力轴承故障诊断方法。首先,搭建了可倾瓦推力轴承故障诊断实验台,用于采集正常和故障轴瓦的多通道声发射(AE)信号。随后,采用挤压激励(SE)模块对各通道权重进行重新分配,并融合多通道信号特征。然后利用逆加法模块和跨度卷积对融合了多个特征的信号进行学习。接下来,对一维卷积神经网络(CNN1D)、残差网络(ResNet)、深度可分离卷积神经网络(DFCNN)模型以及本文提出的MMFCNN模型进行了对比分析。结果表明,在相同运行条件下,以可倾瓦推力轴承四种状态的AE信号数据作为输入时,MMFCNN模型的平均故障诊断准确率达到99.58%。此外,在引入不同运行条件时,MMFCNN模型在准确率方面也优于其他模型。