Energy Efficiency State Identification Based on Continuous Wavelet Transform—Fast Independent Component Analysis

Abstract

In metal cutting operations, energy efficiency can have significant consequences for the environment and for sustainable development (such as ever-increasing demand for cost saving and quality improvements), particularly when the processes are practiced on a very large scale. The energy efficiency state is a cutting process condition that coexists with other conditions such as cutter state, workpiece quality state, or machine tool state. It must be monitored by operators to avoid system failure of low energy efficiency state, on-line energy efficiency state monitoring is becoming more and more important in intelligent manufacturing and green manufacturing. The idea of energy efficiency state identification is proposed and the monitoring strategy of energy efficiency state is established for this subject. A combined application method of continuous wavelet transform (CWT) and fast independent component analysis (FICA) is proposed for feature extraction of low or high energy efficiency state. The feature of energy efficiency state is extracted by CWT on the premise of determining the state of high and low energy efficiency based on modeling of energy efficiency state and experiment data. The feature signal is reconstructed by FICA and the reconstruction signal is verified by short time Fourier transform (STFT). The feature tracing of cutting system is carried out. It is illustrated that the feature of energy efficiency state can be extracted and the different energy efficiency states also can be identified for milling processes. The proposed method will be helpful for energy efficiency state monitoring.