This paper proposes an intelligent model-based optimization methodology for optimizing the production cost and material removal rate subjected to surface quality constraint in turning operation of hardened AISI D2. Unlike traditional approaches, this paper deals with finding optimum cutting parameters considering the real condition of the cutting tool. Tool flank wear is predicted by the model obtained using genetic programming. On the basis of the predicted flank wear value, the surface roughness of work piece is estimated by neural networks. Applying the particle swarm optimization algorithm, the optimum machining parameters are determined. The simulation and experimental results show that machining with proposed intelligent optimization methodology has higher efficiency than conventional techniques with constant optimized cutting parameters.

中文翻译：

---

基于模型的智能切削参数优化用于淬硬 AISI D2 的高质量车削

本文提出了一种基于智能模型的优化方法，用于优化淬火 AISI D2 车削加工中受表面质量约束的生产成本和材料去除率。与传统方法不同，本文处理的是根据刀具的实际情况寻找最佳切削参数。通过使用遗传编程获得的模型预测刀具后刀面磨损。在预测的后刀面磨损值的基础上，通过神经网络估计工件的表面粗糙度。应用粒子群优化算法，确定最佳加工参数。仿真和实验结果表明，采用所提出的智能优化方法进行加工比具有恒定优化切削参数的传统技术具有更高的效率。