LAUSR

This paper presents a method of classifying impact noises obtained from a washer machine by obtaining the time frequency image of the sound signals and applying an artificial neural network for classification. Classifying the impact noises is critical for fault detection and diagnosis of the machines, especially by distinguishing actual fault impact noises from background noises. Audio recordings are taken from a washing machine manufacturing assembly line where faults that commonly occur were measured. A short-time Fourier Transform is applied to obtain a time-frequency-image that is employed as the input signal to an artificial neural network (ANN) classifier. The ANN classifier distinguishes the different impact noises with 100% accuracy on the test data.