This document compares the performance of random forest, artificial neural networks, and support vector machines for intelligent fault diagnosis of rotating machinery. It presents a framework to compare the classification accuracy, stability, and robustness of random forest, extreme learning machine, probabilistic neural network, and support vector machine. The study finds that random forest outperforms the other methods, especially with small training sets, and is less influenced by environmental noise. Random forest also has more user-friendly parameters, making it a promising pattern recognition method for intelligent fault diagnosis of rotating machinery.

Comparison of Random Forest, Artificial Neural Networks and Support Vector Machine For Intelligent Diagnosis of Rotating Machinery PDF PDF

The list of books you might like