Hardware design of features extraction using wavelet packet method for intelligent diagnostic system

This paper aims to develop a hardware architecture of features extraction using wavelet packet method for an intelligent diagnostic system. Verilog-based features extraction architecture is proposed and implemented. Test results verify the design architecture of features extraction using wavelet packet method. A CNC spindle motor commonly featured in intelligent diagnosis of manufacturing systems is chosen to verify this architecture. Under the normal and eccentric spindle states, system modeling is built up for a high speed (10,000RPM), medium speed (5,000RPM) and low speed (1,000RPM) The test results of samples of different rotating speeds under the normal and eccentric spindle states show the effect of the hardware of features extraction and verify the feasibility of hardware design.