The property of high frequency in micro-EDM (electrical discharge machining) causes the discharge states to vary much faster than in conventional EDM, and discharge states of micro-EDM have the characteristics of nonstationarity, nonlinearity, and internal coupling, all of this makes it very difficult to carry out stable control. Thus empirical mode decomposition is adopted to conduct the prediction of the discharge states obtained through multisensor data fusion and fuzzy logic in micro-EDM. Combined with the autoregressive (AR) model identification and linear prediction, the mathematical model for EDM discharge state prediction using empirical mode decomposition is established and the corresponding prediction method is presented. Experiments demonstrate that the new prediction method with short identification data is highly accurate and operates quickly. Even using short model identification data, the accuracy of empirical mode decomposition prediction can stably reach a correlation of 74%, which satisfies statistical expectations. Additionally, the new process can also effectively eliminate the lag of conventional prediction methods to improve the efficiency of micro-EDM, and it provides a good basis to enhance the stability of the control system.
Support Vector Regression Model Based on Empirical Mode Decomposition and Auto Regression for Electric Load Forecasting
