Predictive maintenance has become a hot topic in the last few years. There are various reasons for it. I am creating a four part series to give a gentle introduction about predictive maintenance using machine learning. The four part series are fault detection, supervised fault classification, unsupervised fault classification and time to failure prediction. This series is aimed to help other researchers in similar fields. If you have any comments or requests create a issue ticket.
If you are using this as a part of your research, kindly cite the following papers. You can also use this for your reference and extend your research upon these papers.
[1] Amruthnath, Nagdev, and Tarun Gupta. "A research study on unsupervised machine learning algorithms for early fault detection in predictive maintenance." In 2018 5th International Conference on Industrial Engineering and Applications (ICIEA), pp. 355-361. IEEE, 2018.
[2] Amruthnath, Nagdev, and Tarun Gupta. "Fault class prediction in unsupervised learning using model-based clustering approach." In Information and Computer Technologies (ICICT), 2018 International Conference on, pp. 5-12. IEEE, 2018.
[3] Amruthnath, N., & Gupta, T. (2019, March). Fault Diagnosis using Clustering. What Statistical Test to use for Hypothesis Testing?, Journal reference: Machine Learning and Applications: An International Journal (MLAIJ), Vol 6 Issue 1 (pp. 17-33)
[4] Amruthnath N, Gupta T (2019) Factor Analysis in Fault Diagnostics Using Random Forest. Ind Eng Manage 8: 278.
This is a tutorial for performing fault detection using machine learning. You this code at your own risk. I do not gurantee that this would work as shown below. If you have any suggestions please branch this project.