摘要：This paper presents the effect of data preprocessing methods and hyperparameters in deep learning on the accuracy of ball bearing fault detection. In this study, artificial defects in the ball bearing were created to obtain the machine learning data for ball bearing fault detection. Vibration data were acquired by an accelerometer mounted in the bearing housing at three different rotation speeds. The obtained one-dimensional acceleration-based vibration data were changed into five different data forms: one-dimensional fast Fourier transform data, two-dimensional spectrogram image data, etc. One-dimensional numerical data were used as training data in the multi-layer perceptron and two-dimensional image data in the convolutional neural network classifier. After training, the accuracy and effectiveness of the validation test and the training data formats and deep learning models are discussed in this paper. 1D time- and frequency-domain numerical data showed 100% accuracy within the same rotation speed, but the accuracy was down to less than 50% in the mixed rotation speeds. On the other hand, 2D frequency-domain image data presented more than 99% accuracy for the mixed rotation speeds. Among 2D image data, FFT-image data is less sensitive to hyperparameters such as kernel and convolution layer and shows high test accuracy of 99% at least. Consequently, 2D image data format with the convolutional neural network more accurately worked in a complicated situation.
关键词：Bearing fault detection;deep learning;training data format;convolutional neural network;multi-layer perceptron
