Sparse representation and its applications in micro-milling condition monitoring: noise separation and tool condition monitoring

This paper presents a new approach for cutting force denoising in micro-milling condition monitoring. In micro-milling, the comparatively small cutting force signal is contaminated by heavy noise, and as a result it is necessary to denoise the force signal before further processing it. The traditional denoising methods, based on Gaussian noise assumption, are not effective in this situation because the noise is found to contain high non-Gaussian component. Based on the force and noise’s sparse structures in the time-frequency domain, this approach employs a sparse decomposition approach and solves denoising as a convex optimization problem. It is shown that the proposed approach can separate the heavy non-Gaussian noise and recover useful information for condition monitoring.     «

This paper presents a new approach for cutting force denoising in micro-milling condition monitoring. In micro-milling, the comparatively small cutting force signal is contaminated by heavy noise, and as a result it is necessary to denoise the force signal before further processing it. The traditional denoising methods, based on Gaussian noise assumption, are not effective in this situation because the noise is found to contain high non-Gaussian component. Based on the force and noise’s sparse...     »