Shock detection of rotating machinery based on activated time-domain images and deep learning: An application to railway wheel flat detection. (1st March 2023)

• Record Type: Journal Article
• Authors: Ye, Yunguang; Huang, Caihong; Zeng, Jing; Zhou, Yichang; Li, Fansong
• Is Part Of: Mechanical systems and signal processing. Volume 186(2023)
• Publication Date: 2023-03-01
• Subjects: Shock detection -- Rotating machinery -- Activated time-domain image -- Adaptive activation function -- Deep learning -- Railway wheel flat; Structural dynamics -- Periodicals; Vibration -- Periodicals; Constructions -- Dynamique -- Périodiques; Vibration -- Périodiques; Structural dynamics; Vibration; Periodicals; 621
• DOI: 10.1016/j.ymssp.2022.109856
• Languages: English
• ISSNs: 0888-3270

Abstract

Abstract: Failures of rotating mechanical components (e.g., turbine, gear, wheelset) often cause serious shocks to the mechanical system, and real-time detection of these shocks is of importance in maintenance decision-making for the equipment. The service conditions (e.g., rotating speed, load) of rotating machinery are often complex, and therefore the self-adaptability and generalizability of shock detection methods under variable operating conditions is an issue worthy of in-depth study. In this paper, a novel hybrid method combining a threshold-based method for feature extraction and a machine-learning-based method for pattern recognition is developed. This method consists of two steps. First, an adaptive feature called activated time-domain image (ATDI) is proposed, where two adaptive activation functions are proposed to activate the time-domain vibration signals after being preprocessed. The resulting ATDI feature image is highly adaptive and changes adaptively depending on the operating conditions. Then, a hybrid method combining ATDI and deep neural network (ATDI-DNN) is developed, where a circshift-based data augmentation method is introduced for enriching the ATDI feature images. Finally, the proposed ATDI-DNN method is used for wheel flat detection of a railway vehicle under variable operating conditions. Experiments demonstrate that the ATDI-DNN model trained with samples from one speed level can be directly applied to other speed levels, and its superiority is demonstrated by comparative methods. The proposed method can be extended to shock detection of other similar rotating machinery.