Manufacturing Technology Today

A. Mallikarjuna Rao ¹, G. Dilli Babu ¹, B. S. K. Sundara Siva Rao ²

Affiliations
1 Dept. of Mechanical Engg., V R Siddhartha Engg. College, Vijayawada, IN
2 Dept. of Mechanical Engg., A U College of Engg., Visakhapatnam, IN

Abstract

In this work, a 2 link planar robot arm is studied for the inter relation between the inclinations of links and the end-effector position. Due to the deflection of the link under loading, the end-effector needs specific corrections to keep it at a desired location in space. The values are theoretically calculated for specific number of examples with varied loading and link inclinations. C-programme is composed to calculate the theoretical deflections and those results are cross checked with the results from ANSYS 10.0 analysis. These values are assigned as inputs to train a BPNN suitably. The characteristics of BPNN are varied to find the accuracy of the network in predicting the location corrections of end-effector. The network is trained with 30 sets of sample i.e. the network is adjusted for the function and weights according to the input and output values. After the formation of the function, the network is tested for different input values.

Full Text

     

G. Dilli Babu ¹, P. B. Dhanish ², P. Prabhakara Rao ¹

Affiliations
1 Dept. of Mech. Engg., V R Siddhartha Engg. College, Vijayawada, IN
2 Dept. of Mech. Engg., National Institute of Technology, Calicut, IN

Abstract

In this work, a machine vision system has been utilized to determine the surface roughness of the milled surfaces. For checking the effectiveness of the machine vision based results, a wide range of surface roughness were generated on CNC milling centre using DoE technique. Stylus-based parameters R_a and R_sm were acquired and compared with vision-based parameters (cofvar, G_a, R2, contrast etc). Also, experiments are conducted for three different work piece materials to see the effect of work piece material colour change. Model equations have been developed, in terms ofthe machining parameters, image parameters and machining and image parameters using response surface methodology on the basis of experimental results. The experimental result indicates that the surface roughness of milled surfaces could be estimated/predicted with a reasonable accuracy using machine vision.

Full Text