Compressive sensing and sparse decomposition in precision machining process monitoring: From theory to applications.

Precision machining has been claimed to be the backbone to modern industry. It has been widely applied to the key parts’ production in the aerospace, medical and automotive industries. One of the main problems related to precision machining productivity and safety is the machining condition. By utilizing the acquired information from sensory measurements to direct the further actions, the signal processing bridges the gap between human instruction and full automation. Traditional signal acquisition and processing methods are mainly based on Shannon’s Sampling theory, Fourier methods or wavelet analysis. While these techniques meet challenges in precision machining environment, such as machining at high speed, low signal to noise ratio, and high sampling rate. These factors limit their applications especially the online monitoring implementation. The newly developed compressive sensing theory and sparse decomposition techniques provide a possible solution to these problems, while limited studies have been investigated. This paper serves as an introduction to the theory and shows the theory’s potentials in machining condition monitoring by reviewing related literatures and demonstrating case studies from real experiments. [ABSTRACT FROM AUTHOR]