Study On The Piezoelectric Self-adaptive Micro Electrical Discharge Machining Process

As an important micro machining method, micro electrical discharge machining (micro-EDM) is widely used in machining micro parts because of its a series of advantages, including simple equipment, easy control, free of machining force and good adaptability. Therefore, micro-EDM has been paid intense attention to by scholars both at home and abroad. However, the machining scale of micro-EDM is very small, causing difficult removal of discharge debris, low working efficiency and unstable machining state. All these problems restrict the development of micro-EDM. In order to overcome these shortcomings of micro-EDM, a new piezoelectric self-adaptive micro electrical discharge machining (PSMEDM) technology was developed in this paper.This PSMEDM method based on inverse piezoelectric effect of piezoceramics references the advantage of traditional RC circuit EDM, which hasn't maintaining voltage, having the ability of causing micro discharge energy. Piezoceramics actuator is integrated into discharge circuit, used to driving electrode. Tool electrode driven by piezoelectric actuator makes concertina movement each pulse discharge, achieving micro-feeding. This new technology can achieve the self-tuning regulation of discharge gap depending on discharge conditions, reduce the occurrence of arcing and short circuit, and can realize the self-elimination of short circuits, thus the machining efficiency and stability of the working process can be improved greatly.Based on PSMEDM micro-holes machining experiments, this paper systematic studied the effects of each electrical parameter on material removal rate (MRR), electrode wear ratio (EWR) and surface roughness (SR). Experimental results indicate that:open-circuit voltage and capacitance have greater effect on MRR, EWR and SR, and all the three performances increase with the increase of open-circuit voltage and capacitance. The effects of current-limiting resistance on MRR, EWR and SR are light.According to the analysis mentioned above, appropriate electrical parameters were determined to design orthogonal experiment project. Signal to noise ratio (SNR) method was used to analyze the three levels and four factors orthogonal experiment results, and the factors affecting the machining performances and their primary and secondary relations were obtained. Single objective optimization was finished adopting grey relational analysis method based on SNR. Then the optimization of multi-objective was transformed into the maximization of single grey relational grade, realizing the optimization of multiple performance objectives. Verification experiments were conducted, and the results indicate that:this optimal parameters combinatory can obtain optimal processing effect based on an overall consideration of various factors.Choosing PSMEDM micro-holes machining experiment results as the learning sample, the multiple performance objectives predictive model of PSMEDM micro-holes was proposed, with the BP algorithm of artificial neural network based on MATLAB software platform. The proposed model can relatively accurately predict process time, EWR and SR of setting process parameters.The research results of this paper can be used as the selection of optimal parameters and forecast of performances of PSMEDM, and have significance to promoting the practicability of PSMEDM technology.