Case Study Analysis of Rotating Machinery Fault Diagnosis for Course on Vibration Testing and Signal Analysis Techniques

With the development of modern educational technology, the teaching of vibration testing and signal analysis techniques faces new challenges. To enhance teaching effectiveness and improve students' understanding of complex theories, this paper proposes a teaching case for bearing fault diagnosis based on continuous wavelet transform and CNN-BiLSTM. First, by utilizing wavelet transform for time-frequency analysis of vibration signals, students can gain a deeper understanding of the core principles of signal processing. Second, the introduction of the CNN-BiLSTM model in deep learning enables students to not only grasp the fundamental concepts of deep learning but also enhance their problem-solving abilities in practical engineering scenarios. Experimental results indicate that this approach can effectively improve students' mastery of signal analysis and fault diagnosis techniques, showing significant advantages in fostering innovative thinking and practical skills. This study provides new ideas and practical cases for the reform of teaching vibration testing and signal analysis techniques.