Blade Crack Diagnosis Based on Blade Tip Timing and Convolution Neural Networks

The diagnosis of blade crack faults is critical to ensuring the safety turbomachinery. Blade tip timing (BTT) a non-contact vibration displacement measurement technique, which has been extensively studied for condition monitoring recently. fault methods based on deep learning can be summarized as studying internal logical relationship data, automatically mining features, and intelligently identifying faults. This research proposes diagnostic method BTT data convolutional neural networks (CNNs) detection blades. There are two main aspects: numerical analysis rotating experimental in diagnosis. results show that outperforms many other traditional machine models both tests diagnosing depth location cracks. findings this study contribute real-time online