Enhanced motor fault detection system based on a dual-signature image classification method using CNN

Abstract This paper proposes a new Motor Image Classification (MIC) approach based on multi-signal conversion technique using Convolutional Neural Network (CNN). In this regard, two one-dimensional (1D) signals are combined and converted into (2D) color image with motor information pixels. Initially, the vibration signal is frequency domain. Each point of firstly assigned according to its amplitude then placed successively specific column obtain pixilated image. An outline added representing internal temperature. Therefore, vibratory thermal situation engine clearly represented in Dual-Signature (DSI). Our system proves efficiency compared grayscale images. It ensures fast effective prevention, which results long service lifetime maximum availability. The diagnostic success rate our 99.93%.