Search This Blog

Broken Rotor Bar Fault Detection and Severity Analysis using Machine Learning Techniques

This blog has been created for the purpose of our EE461 Project on Broken Rotor Bar Faults. The group members are: Shahil Kumar & Nafiz Buksh

Demo Video

Get link
Facebook
X
Pinterest
Email
Other Apps

- December 14, 2022

This is our project demo video

Get link
Facebook
X
Pinterest
Email
Other Apps

Comments

What are Broken Rotor bar Faults?!

- November 15, 2022

Induction machines are one of the crucial elements of many industrial processes nowadays (IM). These machines are prone to rotor, stator, or bearing failure due to diverse operating circumstances. All of these IM flaws have the potential to impair output, harm neighboring equipment, or, in the worst case, lead to the system’s complete failure[1]–[3]. Induction machines have been in use since the early 1800s. The operators or the equipment close to the working zones may be at danger from this motor’s strong starting torque and high operating speeds. Broken rotor bar defects are one of the frequent causes of motor failure, which may also be brought on by an unfavorable operating environment or artificial mis-operation during the manufacturing process. The rotor bar will first fracture locally, and the surrounding area will experience increased stress. As the defect worsens, the rotor bar entirely breaks, along with any adjacent bars, and finally the whole motor collapses. The early detec...

Using the Classification Learner App for The First Time - Current Signals Directly

- November 16, 2022

Since we had visualized the data and had also seen the class separability using PCA and ICA, it was time to move on to training the models. We directly fed in the three phase currents into the classification learner app. Three Phase Currents The group used the classification learner app to train the model, however very bad results were seen. The percentage accuracies were averaging at around 20 to 50%. This isn't what we required!! We did get an accuracy of 100%! But this was due to applying the ICA data. Obviously, ICA data will give us an accuracy of 100% because it already has the classes separated . This is wrong!! Now we need to move on to calculate something known as "The 15 statistical time features."