基於均勻設計法之CNC銑床的穩健最佳加工參數研究

• Main Authors: Chun-kai Cheng, 鄭駿凱
• Other Authors: Jyh-horng Chou
• Format: Others
• Language: zh-TW
• Published: 2016
• Online Access: http://ndltd.ncl.edu.tw/handle/30952493874826432555

碩士 === 國立高雄第一科技大學 === 電機工程研究所碩士班 === 104 === Recently, computerized numerical control (CNC) drilling plays an important role in aerospace component manufacturing processes. However, the machining parameters are usually selected prior to machining according to standards or user’s experience. In addition, the useful life of a cutting tool largely controls the economics of the machining operations. Hence, estimation of the tool wear of drilling tools can help decide about possible optimization of the process parameters or replacing the worn out tool with a fresh tool. The objective of this study is to optimize the process parameters of CNC vertical drilling such as spindle speed, and feed rate on minimizing cycle time and tool wear. The machining efficiency and cost saving rate are strongly affected by cycle time and the tool wear. In order to achieve the optimization, it is necessary to construct relationships between the output responses and process parameters of interest. Uniform design (UD) is used to construct a small set of drilling experiments by using uniformity measure, such that the experiments are uniformly scattered. That is, the experiment number is significantly decreased and it is especially suitable for cost-effective experiments with many experimental variables. Regression analysis (RA), back propagation artificial neural network (BP) and particle swarm optimization-based back propagation artificial neural network (PSO-BP) are used to evaluate the relationships between inputs and outputs, and optimize the process parameters of aerospace component for CNC vertical drilling. Experimental results confirm the excellent performance of PSO-BP by comparing with those obtained by RA and BP in modeling and optimizing the CNC vertical drilling.