Wire electrical discharge machining (WEDM) process used in a wide spectrum of industrial applications. AISI 1045 is medium carbon steel, because of its excellent physical and chemical properties, it is used in many applications. However, the review of the state of the art literature reveals that literature is lacking research to optimize WEDM process for machining AISI 1045 steel. The objectives of this research are building ANN model to predict metal removal rate (MRR) and surface roughness (Ra) values for machining AISI 1045 steel, identifying the significance of the pulse on-time (T_ON), pulse off time (T_OFF) and servo feed (S_F) for the MRR and Ra, and selecting optimal machining parameters that give maximum MRR value and that give the minimum Ra value. Taguchi method (Design of Experiments), artificial neural network (ANN), and analysis of variances (ANOVA) used in this research as a methodology to fulfill research objectives. This research reveals that the architecture (3-5-1) of ANN models is the best architecture to predict the Ra and MRR with about 98.136% and 97.3% accuracy respectively. It can be realized that T_ON is the most significant cutting parameter affecting Ra by P % value 42.922% followed by T_OFF with a P % value of 24.860%. S_F was not a significant parameter for Ra because of Fα > F. For MRR, the most significant parameter is T_ON with a P % value of (71.733%), i.e. about three times the T_OFFP % value (21.796%) and the S_F parameter has a small influence with P % value 3.02%. The analysis confirmed that the optimal cutting parameters for maximum MRR were: T_ON at the third level (25 µs), T_OFF at the first level (20 µs), and S_F at the third level (700 mm/min). On the other hand, the optimal cutting parameters for minimum Ra were: T_ON at the first level (10 µs), T_OFF at the third level (40 µs), and S_F at the first level (500 mm/min). Future work may focus on optimizing the WEDM process for machining other types of materials or other sets of parameters and performance measures.

线切割加工（WEDM）工艺广泛用于工业应用中。AISI 1045是中碳钢，由于其出色的物理和化学性能，因此在许多应用中使用。然而，对现有技术文献的回顾表明，缺乏文献来优化用于加工AISI 1045钢的WEDM工艺。这项研究的目的是建立ANN模型，以预测用于加工AISI 1045钢的金属去除率（MRR）和表面粗糙度（Ra）值，确定脉冲开启时间（T _ON），脉冲关闭时间（T _OFF）的重要性）和伺服进给（S _F）中的MRR和Ra，然后选择最佳的加工参数，以给出最大MRR值和最小Ra值。Taguchi方法（实验设计），人工神经网络（ANN）和方差分析（ANOVA）在本研究中用作实现研究目标的方法。该研究表明，ANN模型的架构（3-5-1）是预测Ra和MRR的最佳架构，其准确度分别约为98.136％和97.3％。可以认识到，T _ON是影响Ra的最重要切削参数，其P％值为42.922％，其次是T _OFF，其P％值为24.860％。小号_˚F由于Fα> F，对Ra而言不是一个重要参数。对于MRR，最重要的参数是T _ON，其P％值为（71.733％），即约为T _OFF P％值（21.796％）的三倍。 S _F参数的影响很小，P％值为3.02％。分析证实，获得最大MRR的最佳切削参数为：第三级的T _ON（25 µs），第一级的T _OFF（20 µs）和第三级的S _F（700 mm / min）。另一方面，最小Ra的最佳切削参数为：第一电平的T _ON（10 µs），T _OFF在第三级（40 µs）处，S _F在第一级（500 mm / min）。未来的工作可能集中在优化WEDM工艺以加工其他类型的材料或其他参数和性能指标集。