Integrated ANN-LWPA for cutting parameter optimization in WEDM

摘要: In this paper, we present a new approach to determinate cutting parameters in wire electrical discharge machining (WEDM), integrated artificial neuron network (ANN), and wolf pack algorithm based on the strategy of leader (LWPA). The considered paper are pulse-on, current, water pressure, feed rate. Models effects four time (Tp), cost (Cp), surface roughness (Ra) mathematically constructed. An ANN-LWPA integration system with multiple fitness functions is proposed solve modelling problem. By using approach, study demonstrates that Tp, Cp, Ra can be estimated at 164.1852 min, 239.5442 RMB, 1.0223 μm single objective optimization, respectively. For example, as for Ra, has optimized value by reduction 0.1337 (11.6 %), 0.3377 (24.8 0.105 (10.3 %) compared experimental data, regression model, ANN Consequently, boasts some advantages over decreasing comparison conventional LWPA result. Moreover, also utilized obtain solutions uniform design-based exploration. Therefore, order complex optimization problems, an intelligent process scheme could into numeric control WEDM.