In-Process Chatter Detection Using Signal Analysis in Frequency and Time-Frequency Domain

All machining processes involve vibrations generated by structural sources such as a machine’s moving parts or by the interaction between cutting tools and work-pieces. Relative vibrations between the work-pieces and the cutting tool are the most relevant from the point of view of the regenerative chatter phenomenon. In fact, these vibrations can lead to a chip yregeneration effect, which results in unwanted consequences, rapidly degenerating towards a very poor quality of surface finishing or, in case of severe chatter conditions, to machine-tool or work-piece damage. In the past decades, two different approaches for chatter avoidance were proposed by the scientific community, and they are commonly referred to as Out-of-Process (OuP) and in-Process (iP) solutions. The OuP solutions are off-line approaches, which allow to properly set the working parameters before machining starts. Ip solutions are on-line techniques, which allow to dynamically change the working parameters during machining by using single or multiple sensors. By monitoring the machining process, iP algorithms try to keep the machining process in stable working conditions while keeping high productivity levels. This study dealt with a novel iP chatter-detection strategy based on the Power Spectral Density (PSD) analysis and on the Wavelet Packet Decomposition (WPD) of different sensor signals. The preliminary results demonstrate the stability and feasibility of proposed indicators for chatter detection in industrial application.

Nonlinear Chen-Lee Chaotic System Based Deep Convolutional Generative Adversarial Nets for Chatter Diagnosis

Chatter has a direct effect on the precision and life of machine tools and its detection is a crucial issue in all metal machining processes. Traditional methods focus on how to extract discriminative features to help identify chatter. Nowadays, deep learning models have shown an extraordinary ability to extract data features which are their necessary fuel. In this study deep learning models have been substituted for more traditional methods. Chatter data are rare and valuable because the collecting process is extremely difficult. To solve this practical problem an innovative training strategy has been proposed that is combined with a modified convolutional neural network and deep convolutional generative adversarial nets. This improves chatter detection and classification. Convolutional neural networks can be effective chatter classifiers, and adversarial networks can act as generators that produce more data. The convolutional neural networks were trained using original data as well as by forged data produced by the generator. Original training data were collected and preprocessed by the Chen-Lee chaotic system. The adversarial training process used these data to create the generator and the generator could produce enough data to compensate for the lack of training data. The experimental results were compared with without a data generator and data augmentation. The proposed method had an accuracy of 95.3% on leave-one-out cross-validation over ten runs and surpassed other methods and models. The forged data were also compared with original training data as well as data produced by augmentation. The distribution shows that forged data had similar quality and characteristics to the original data. The proposed training strategy provides a high-quality deep learning chatter detection model.