A fuzzy expert system for optimizing parameters and predicting performance measures in hard-milling process

https://doi.org/10.1016/j.eswa.2006.02.003Get rights and content

Abstract

The main focus of research in hard-milling domain has been the enhancement of tool life and the improvement in workpiece surface quality. This paper deals with the application of expert system technology in order to use the experimental data for optimization of milling parameters so as to achieve targets of enhancing tool life and improving workpiece surface finish. Hard-milling experiments were conducted to study the effects of workpiece material hardness, cutter’s helix angle, milling orientation and coolant upon tool life, workpiece surface roughness, and cutting forces. The experimental data were converted to useful information using ANOVA and numeric optimization, and this information was used to develop the knowledge-base in form of IF–THEN rules. Expert system utilized fuzzy logic for its reasoning mechanism, while, fuzzy data sets and crisp sets were freely mixed in antecedents and consequents of the rules. Effectiveness of the expert system was based upon two modules, namely optimization module and prediction module, with each of them operating upon different set of rules. Optimization module provides the optimal selection and combination of aforementioned milling parameters according to the desired objective, while the prediction module provides the prediction of performance measures for the combination of parameters finalized by the optimization module.

Introduction

High-speed milling (HSM) is the technology that utilizes higher cutting speeds and feed rates – 5–9 times as compared to conventional milling process – for the metal cutting requirements, so as to achieve the benefits of smaller cutting forces, reduced lead times, better surface finish, improved dimensional accuracy and much more (Schulz, 2004). Hard-milling is the name given to HSM process applied to machining of steels in their hardened state (40–70 HRc). The benefits specific to hard-milling process include compressive residual stresses, minimal micro-hardness and micro-structural alterations, and improved fatigue life of the machined workpiece (Axinte & Dewes, 2001). The only major demerit of HSM (or hard-milling) process is the unacceptably shortened tool life (Schulz, 2004). Enormous amount of research has been carried out in order to seek the ways to improve the tool life in HSM process. Besides tool life, the objective of reducing the workpiece surface roughness has also been addressed in lot of research papers.

This paper deals with the application of expert system for optimization of milling parameters (e.g. workpiece material hardness, tool’s helix angle, milling orientation, and coolant) for maximization of tool life and/or minimization of workpiece surface roughness; and also with the prediction of performance measures (e.g. cutting forces, tool life, and surface roughness) in a hard-milling process. Not much work has been done related to utilization of expert system technique for optimization and prediction purposes in relation to the machining domain. Papers (Arezoo et al., 2000, Cakir et al., 2005, Chen et al., 1995, Fang, 1995, Hashmi et al., 1998, Wong and Hamouda, 2002, Wong and Hamouda, 2003) can be studied in this regard. Most of these papers focus upon cutter selection procedures, cutting condition monitoring, and conversion of machining handbook data especially related to the turning process.

Section snippets

The experimental work

In this research work the optimization of hard-milling process with respect to four milling parameters (workpiece material hardness, tool’s helix angle, milling orientation, and coolant) is sought. In order to have pertinent data, series of experiments were conducted so as to quantify the effects of aforementioned parameters upon the performance measures like tool life, workpiece surface roughness, and cutting forces.

A 24−1 (4 factors, 2 levels, 8 test) fractional factorial design was used for

The expert system

Expert systems are computer programs embodying knowledge about a narrow domain for solving problems related to that domain (Pham & Pham, 2001). Knowledge-base is considered as the heart of any expert system and for the current research work, the knowledge from the experimental data, numeric optimization, and ANOVA results was used for its development. The functionality of this expert system is two-folded: first it seeks the optimal selection and combination of the four predictor variables in

Example

Consider the application of the presented fuzzy expert system for optimization of parameters and prediction of performance measures in hard-milling process. Suppose it is required to find optimal values of cutter’s helix angle and milling orientation in order to attain best possible surface finish, when AISI D2 workpiece, hardened to 59 HRc, is to be end milled under MQL environment. It is also desired to have prediction of tool life, surface roughness, and cutting forces for the recommended

Conclusions

In this paper, an innovative effort was described regarding application of AI to the domain of high-speed machining. An expert system, incorporating fuzzy reasoning mechanism, was presented for purpose of optimizing parameters and predicting performance measures in high-speed milling of hardened AISI D2. This expert system can optimize the parameters in accordance with the objectives of ‘maximizing tool life’, ‘minimizing surface roughness’, and also the attainment of both of these

References (14)

There are more references available in the full text version of this article.

Cited by (0)

View full text