Surface Roughness Prediction in Deep Drilling by Fuzzy Expert System

Sivarao, Subramonian and Tajul Ariffin, Abdullah (2009) Surface Roughness Prediction in Deep Drilling by Fuzzy Expert System. International Journal of Mechanical and Mechatronics Engineering, 9 (9). pp. 331-335. ISSN 2077-124X

[img] PDF
Restricted to Registered users only

Download (121kB) | Request a copy


Numerous operations in manufacturing industries require a length-to-diameter ratio greater than 5 times tool diameter. These types of operations, known as deep drilling, normally need the use of special tools and devices. The deep drilling is a process of high complexity due to its special difficulties such as cutting in a closed and limited space, high cutting temperature and the difficulty of chip formation and removal. Such conditions involve the chip formation and the flow difficulty, the tool overhang length, the surface quality and the hole geometric and form tolerances. This work presents an experimental and an analysis of the performance of carbide drill geometry in drilling of GG25 gray cast iron. The experiments have been carried out in line of production and laboratory, using tungsten carbide drills with straight flutes and internal cutting fluid. The aim of this experimental and analytical research is to identify the parameters which enable the prediction of surface roughness in drilling by integrating expert system. Fuzzy expert system were used to analyze the best fit model in predicting the quality of the deep drilled holes. With the results obtained in this work it was possible to acquire a major knowledge on the deep drilling process of gray cast iron, which allow improvements in the production of pieces in industrial scale.

Item Type: Article
Subjects: T Technology > TJ Mechanical engineering and machinery
Divisions: Faculty of Manufacturing Engineering > Department of Manufacturing Process
Depositing User: Assoc. Pror. Ir. Dr. Sivarao Subramonian
Date Deposited: 13 Aug 2013 15:28
Last Modified: 28 May 2015 04:02
Statistic Details: View Download Statistic

Actions (login required)

View Item View Item