Application of EMD ANN and DNN for Self-Aligning Bearing Fault Diagnosis

Self-aligning roller bearings are an integral part of the industrial machinery. The proper analysis and prediction various faults that may happen to bearing beforehand contributes increase in working life bearing. This study aims at developing a novel method for self-aligning as well automatic classification using artificial neural network (ANN) deep (DNN). vibration data is collected six different faults healthy Empirical mode decomposition (EMD) followed by Hilbert Huang transform used extract instantaneous frequency peaks which fault analysis. Time domain time-frequency features then extracted implement networks through pattern recognition tool MATLAB. A comparative outputs from two also performed. From confusion matrix, efficiency ANN has been found be 95.7% DNN 100%.