Multi-Objective Optimization of Processing Parameters for Disc-Mill Cutter Machining Blisk-Tunnel Based on GRA-RBF-FA Method

基于GRA-RBF-FA的整体叶盘通道盘铣加工多目标参数优化

¹ The Key Laboratory of Contemporary Design and Integrated Manufacturing Technology, Ministry of Education, Northwestern Polytechnical University, Xi’an 710072, China
² School of Mechanical Engineering, Inner Mongolia University of Technology, Hohhot 010051, China

Received: 5 March 2018

Abstract

The process of disc-mill cutter machining blisk-tunnel is a typical multi-input and multi-output system, therefore multi-objective optimization is applied to improve the process. In this paper, an integrated approach that Grey Relational Analysis(GRA)couples with Radial Basis Function (RBF) neural network and Firefly algorithm (FA) is used to solve the optimization problem. The aim is to satisfy the minimum cutting force and maximum material removal rate simultaneously by optimizing the cutting speed, feed rate per tooth and cutting height. The results for verifying experiment indicated that GRA-RBF-FA method can be applied to optimize the processing parameters of disc-mill cutter machining TC17 blisk-tunnel and the optimization results are superior to the GRA's.

摘要

整体叶盘通道盘铣加工是典型的多输入输出系统，改善该加工过程需要多目标优化。应用集灰色关联分析（grey relations analysis，GRA）、径向基神经网络（radial basis function neural network，RBF）和萤火虫智能算法（firefly algorithm，FA）于一体的多目标优化方法。通过优化加工参数：切削速度、每齿进给率和切削高度，同时满足最小切削力和最大材料去除率的目标。验证试验结果表明，灰色关联分析-径向基神经网络-萤火虫算法（GRA-RBF-FA）可用于盘铣TC17整体叶盘通道的加工参数优化；该方法优于灰色关联度分析。