Article Preview
TopIntroduction
Drilling is one of the basic, most frequently performed materials removing process in manufacturing industry. It has been reported that one-third of material removal process performed in industry is drilling operation. In spite of significant increase in the demand of producing holes economically, drill manufacturing is still considered as an esoteric art. The drilling operation is frequently used as a preliminary step for many operations like boring, reaming and tapping. This complex cutting operation holds a substantial portion for all metal cutting operations and the largest amount of money spent on any class of cutting tool. Drilling is crucial from the viewpoint of cost, productivity and manufacturing. Effective drilling also reduces the down time of the manufacturing processes. One way to overcome this challenge is by constantly monitoring the cutting process and thus determines the right time for the tool change. The other way is to optimize the cutting variables of the drilling process in order to improve the tool life and apparently increase the cutting length in the period of improved tool life.
Li and Wu (1998) have introduced a new approach for online monitoring of drill wears by using a fuzzy c-means algorithm. Experimental and simulation results have shown that wear conditions can be represented by fuzzy grade. Dutta, Kiran, Paul, and Chattopadhyay (2000) have proposed machining features in tool condition monitoring during the drilling process, in which process parameter coupled with machining responses and experimental observations provide a basis for monitoring the tool wear. Yao, Li, and Yuan (1999) have proposed tool wear detection by fuzzy classification and wavelet fuzzy network. El-Wardany, Gao, and Elbestawi (1996) have proposed vibration analysis for drilling process monitoring. Drilling wear monitoring based on current signals was proposed by Li and Tso (1999). Thangaraj and Wright (1998) used change rate of thrust force for drilling failure monitoring. Liu and Wu (1990) incorporated sensor fusion methods for monitoring drill wear. Singh, Panda, Pal, and Chakraborty (2006) used an artificial neural network to predict drill wear. The performance of the network to predict the wear has been tested against the experimental data and found to be satisfactory. Ghaiebi and Solimanpur (2007) have proposed the use of an ant algorithm to optimize drill making operation using tool airtime and tool switch time as the objective function.
On the other hand, Lee, Liu, and Tarng (1998) used the abductive network for modeling and optimization of drilling process. Once the process parameters such as drill diameter, cutting speed and feed are given, the drilling performance such as tool life, removal rate and thrust force can be predicted by this proposed network. Other optimization methods that have been published in literatures and applied to the related machining processes are deterministic optimization approach (Wang, Kuriyagawa, Wei, & Guo, 2002; Armarego, Smith, & Wang, 1993) applied to turning and peripheral milling processes; polynomial geometric programming (Gopalakrishnak & Al-Khayyal, 1991) for turning process; fuzzy optimization (Fang & Jawahir, 1994) for turning; particle swarm (Tandon, El-Mounary, & Kishawy, 2002; Lee, Ting, Lin, & Htay, 2006) for end milling and grinding, and genetic algorithm (Gopal & Rao, 2003) for grinding.
The rest of the paper is organized as follows. First, we discuss the experiment used to collect the data for the modeling process in the section afterwards. Consequently, the formulation of the drilling problem with respect to some equality and inequality constraints is given after that. The general overview of the Particle Swarm Optimization is then presented. The objective function with respect to coding employed is detailed in the following. This is followed by results and conclusions respectively.