README.md

 

AI Based Predictive Maintaenance

🚧 🚀 Data Engineering and Time + Frequency Domain Feature Extraction from IMS Dataset. 🚧

---

About   |   Features   |   Technologies   |   Requirements   |   Starting   |   Contributing   |   License   |   Author

🎯 About

Predictive maintenance (PdM), is an idea incorporated for early detection of faults in machines. For the purpose, there needs to be essential collection of data, and converting it into a desired format, getting essential time and frequency domain features and performing desired analysis based on visualizations and results. The main objective of this research is to focus on different aspects of faults in vibratory machine following predictive maintenance, getting the desired features, and providing effective visualization for the same.

✨ Features

Time Domain

✔️ Mean;
✔️ Absolute Mean;
✔️ Standard Deviation;
✔️ Variance;
✔️ Max Amplitude;
✔️ Min Amplitude;
✔️ Root Mean Square;
✔️ Peak to Peak;
✔️ Square Mean Root;
✔️ Standard Moment;
✔️ Skewness;
✔️ Skewness Factor;'
✔️ Kurtosis;
✔️ Kurtosis Factor;
✔️ Clearance Factor;
✔️ Shape Factor;
✔️ Impulse Factor;
✔️ Crest Factor;
✔️ Sum;
✔️ Log;
✔️ Entropy Factor;

Frequency Domain

✔️ Analytic Signal;
✔️ Fast Fourier Transform;
✔️ Max Power Spectrum;
✔️ Max Envelope;
✔️ Frequency Center;
✔️ Root Mean Square Frequency;
✔️ Variance Frequency;
✔️ Root Variance Frequency;
✔️ Median Frequency;
✔️ Bearing Frequencies;

🚀 Technologies

The following tools were used in this project:

• Python
• Numpy
• Scipy
• PyFFTW
• json
• mongodb

✅ Requirements

Before starting 🏁, you need to have Git, Python 3.8, and PyFFTW installed.

🏁 Starting

# Clone this project
$ git clone https://github.com/anshulg954/pdm

# Access
$ cd pdm

# Run the project
$ python main.py 

👨‍💼 Contributing

For major changes, please open an issue first to discuss what you would like to change.

📝 License

This project is under license from MIT. For more details, see the LICENSE file.

Made with ❤️ by Anshul Gupta

 

Back to top