A novel approach for tool condition monitoring based on transfer learning of deep neural networks using time-frequency images

Traditional tool condition monitoring methods developed in an ideal environment are not universal in multiple working conditions considering different signal sources and recognition methods. This paper presents a novel tool condition monitoring approach that packages deep learning networks for accurate condition recognition with a cocktail solver library. First, the multisource signals from the machining process are collected and sequenced as the input of the cocktail solver library. The machining signals are transformed into a series of two-dimensional images by a continuous wavelet transform. In addition, ten pretrained networks with transfer learning are rapidly transferred with a finetuning operation, which contributes to a set of monitor networks. Three major processes are integrated by the cocktail solver library, which is the choosing dataset process for multi-signals, the training option process for network training parameters, and the network package process for the basic monitoring model. A Bayesian optimization method is employed to handle a tradeoff for these three processes to improve the prediction accuracy and reduce the recognition time. In the testing experiment, the milling datasets are used to train the model, and the results show that the accuracy of the model proposed in this paper can exceed 90%. The proposed method was also compared with other traditional methods to verify its effectiveness.