Milling chatter detection by multi-feature fusion and Adaboost-SVM.

• Supervised learning is used for chatter detection to avoid the threshold selection. • Combination of features by manually selected and extracted by SDAE are utilized. • Adaboost algorithm is utilized to obtain a strong classifier by a series of SVM weak classifiers. • Adaboost-SVM is improved to mitigate negative effects of wrong labels on classification accuracy. Unstable chatter vibration in the milling process significantly affect the machining quality and efficiency. In order to suppress or avoid the chatter vibration in the cutting operation, detection of chatter onset is highly needed. Until now, most of the existing chatter detection methods designed chatter indicators by extracting signal features, and the threshold of designed chatter indicator is usually needed, which is difficult to determine and might not be applicable in different cutting conditions. In fact, chatter detection is essentially a typical classification problem, hence milling chatter detection based on machine learning method is presented in this paper. In order to obtain the needed data set, milling experiments under different cutting conditions were performed. Multi-features are utilized for the chatter detection, including the dimensionless features in time domain and frequency domain, and the automatic features extracted by stacked-denoising autoencoder (SDAE). In order to improve the accuracy of chatter classification and avoid the negative effects of possible samples with wrong labels, adaptive boosting (Adaboost) algorithm that consists of a series of weak classifiers by support vector machine (SVM) is utilized and further improved. Experimental verification and performance analysis are also performed, and the results show that the presented method can detect the chatter with a high accuracy and is applicable in different milling conditions. [ABSTRACT FROM AUTHOR]