Estimation of Surface Roughness in Turning by Considering the Cutting Tool Vibration, Cutting Force and Tool Wear

Abstract

Surfacequality along with the low production cost, play significant role in today’s manufacturing market. Quality of a product can be described by various parameters. One of the most important parameters affecting the product quality is surface roughness of the machined parts. Good surface finish not only assures quality, but also reduces the product cost. Before starting any machining process, surface finish is predictable using cutting parameters and estimation methods. Establishing a surface prediction system on a machine tool, avoids the need for secondary operation and leads to overall cost reduction. On the other hand, creating a surface estimation system in a machining plant, plays an important role in computer integrated manufacturing systems (CIMS). In this study, the effect of cutting parameters, cutting tool vibration, tool wear and cutting forces on surface roughness are analyzed by conducting experiments using different machining parameters, vibration and dynamometers sensors to register the amount of tool vibration amplitude and cutting force during the machining process. For this, a number of 63 tests are conducted using of different cutting parameters. To predict the surface quality for different parameters and sensor variables, an ANN model is designed and verified using the test results. The results confirm the model accuracy in which the R2 value of the tests was obtained as 0.99 comparing with each other.

Keywords

• artificial neural networks
• cutting forces
• surface roughness
• vibration