On-line Estimation of Workpiece Height by Using Neural Networks and Hierarchical Adaptive Control of WEDM

Wire breakage and unstable machining drastically reduce the machining efficiency and accuracy in wire electrical discharge machining (WEDM). When a stair-shaped workpiece is machined, poor electrolyte flow around the steps leads to wire rupture or unstable machining. This paper presents a WEDM adaptive control system that maintains optimal machining and improves the stability of machining at the stair section where workpiece thickness changes. A three-layer back propagation neural network is used to estimate the thickness of a workpiece. The developed adaptive control system is executed in the hierarchical structure of three control loops, using fuzzy control strategy. In the first control loop, the total sparking frequency is controlled within a safe level for wire rupture suppression. In the second control loop, the proportion of abnormal sparks is maintained at a pre-determined level for process control purposes. Based on the estimated thickness of a workpiece, adaptive parameter optimisation is carried out to determine the optimal machining settings and to provide the reference targets for the other two control loops. Experimental results demonstrate that the workpiece height can be estimated by using a feed-forward neural network. The developed adaptive control system results in faster machining and better machining stability than does the commonly used gap voltage control system.