written in front
A stage of study is over, and I used my spare time to make a series of excellent course resources about the basics of bearing fault diagnosis. Explaining the theory from a perspective suitable for Xiaobai combined with specific code cases will also inspire students to think and explore innovation points. The content of each section is selected from the content that can be used in this field, which is more suitable for graduate students Xiaobai.
1. The first part
1.1 Overview of bearing fault diagnosis
1.2 Mechanism of bearing fault diagnosis
1.3 Sharing of classic introductory references
1.4 Calculation skills of eigenfrequency
1.5 Calculation and batch processing of time domain indicators
1.6 ☆How should I learn
2. The second part
2.1 Common Spectral Analysis Algorithms [Combined Code]
2.2 Fast Fourier Transform (FFT)
2.3 Hilbert-Huang Transform
2.4 Power Spectral Density
3. The third part
3.1 Preprocessing Noise Reduction Optimization
3.2 Empirical mode decomposition
3.3 Improved Empirical Mode Decomposition (EEMD)
3.4 Variational mode decomposition
3.5 Calculation of time-frequency domain indicators
3.6 Signal Decomposition and Reconstruction
3.7 Comparative analysis of preprocessing
3.8 Optimization of Particle Swarm Optimization
4. The fourth part
4.1 Code Interpretation of Spectral Kurtosis Algorithm
4.2 What is resonance demodulation?
4.3 Why use spectral kurtosis?
4.4 What is Envelope Demodulation?
4.5 Code frame of spectral kurtosis algorithm?
4.6 How to quickly use it?
4.7 Interpretation of the details of each piece of code combined with the source code?
4.8 How to set the optimal parameters?
4.9 Ideas and direction of algorithm optimization
4.10 Reminders for some details
5. Part Five
5.1 Explanation of the deconvolution algorithm [combined code]
5.2 Maximum correlation kurtosis deconvolution (MCKD)
5.3 Minimum Entropy Deconvolution (MED)
5.4 Multipoint Optimal Minimum Entropy Deconvolution Adjustment (MOMEDA)
6. Part VI
6.1 Wavelet analysis [combined code]
6.2 One-dimensional wavelet decomposition
6.3 Wavelet Packet Decomposition (Energy Ratio)
6.4 Optimization of wavelet analysis
7. Part VII
7.1 Resonant Sparse Decomposition Algorithm
7.2 Parameters of resonance sparse decomposition
7.3 Various particle swarm optimization algorithms to optimize the parameters of resonance sparse decomposition
8. Part 8
8.1 Batch processing and interface design [combined code]
8.2 Batch processing feature index (Example)
8.3 GUI interface design (Example)
Always remember, there will be reverberations
Summarize
The author has studied fault diagnosis for many years, has been engaged in academics, and has also done enterprise research and development. I can understand the difficulties of Xiaobai, and I am committed to helping everyone better get started in this field from the perspective of newcomers and unique ideas. The content of the deep learning chapter will continue to be updated, please stay tuned.My micro is: ForwardTszs.