Response Surface Methodology and Artificial Neural Network To Evaluate Tool Wear in MQL - Turning
Cutting fluids play major role in chip removal, protection against oxidation and corrosion, improvement in tool life and the quality of the product. However, mineral-based cutting fluids are environment unfriendly and poisonous. These cutting fluids create numerous environmental evils. The worker may suffer from different life threatening disease. Cutting fluids also incur a main part of the total manufacturing cost. It is necessary to reduce the use of the cutting fluids without affecting the product quality. Minimum quantity lubrication with vegetable-based cutting fluids will be a feasible option to the conventional machining. The main emphasis of this research study is to evaluate the performance of vegetable oils in terms of tool wear. The performance of different vegetable oils such as soyabean oil, sunflower oil, groundnut oil and coconut oil is compared with mineral-based cutting fluid blasocut-4000 during turning of AISI 4130 steel. A mathematical model for tool wear is developed to show the relation between significant parameters such as cutting speed, depth of cut and feed rate using response surface methodology. Analysis of variance (ANOVA) test is carried out to verify the capability of the developed model. The result shows that the developed models are accurate and adequate. Response surface methodology (RSM) results are compared with artificial neural network (ANN) results to validate the model. Reduction in tool wear has been observed for soyabean oil. Moreover, use of soyabean oil as cutting fluid is economical, environmentally friendly and provides healthy working conditions for an operator.
ISSN : 2180-3811 E-ISSN : 2289-814X
Best viewed using Mozilla Firefox, Google Chrome and Internet Explorer with the resolution of 1280 x 800