China
Africa
Explore chapters and articles related to this topic
Applications in Automobile Industries
Published in S. S. Nandhini, M. Karthiga, S. B. Goyal, Computational Intelligence in Robotics and Automation, 2023
G. Sathish Kumar, D. Prabha Devi, R. Ramya, P. Rajesh Kanna
Industries involved in manufacturing agricultural and construction-related machines make use of these paint robots. Such machines face substantial operation in their environment. Prevention from rust and extension of machine’s life cycle can be done through multiple numbers of coatings. This task is not that much easy to do manually. An industrial paint robot provides the durable coating for this robust equipment involved in agriculture and construction. In addition to the above-said areas, the industrial paint robots are further used in the manufacturing of cookware, cosmetics, defence, aluminium panels, etc.
A comparative analysis of surface roughness in robot spray painting using nano paint by Taguchi – fuzzy logic-neural network methods
Published in Australian Journal of Mechanical Engineering, 2023
Prabhu sethuramalingam, J. R. V. Sai Kiran, M Uma, T Thushar
The focus on the present experimental analysis is to improving the surface finish, maximizing the time for CRCA steel surface by the addition of CNT infused nano paint using a robot process furthermore, advancing all the procedure factors. Taguchi’s Technique has been utilized to direct the analyses by changing the procedure parameters. The Fuzzy logic investigation used to predict and compared with neural network and the results are summarized below:The expected models do effectively connected towards evaluating the estimations about surface scratch beneath the different test circumstances. The maximum test errors for nano painting 1.51% for the given dimensions. The optimised level of robot painting parameters using the factor effect diagram of Taguchi analysis is A2B1C1, i.e., Distance 245 mm, pressure 3 bar and speed 80 mm/sec will give the minimal of thickness variation. The factor reaction graph portrayed that the pressure giving more influence to improve the surface roughness.The conclusion of ANOVA indicates that the pressure criterion has a significant increase in the surface roughness of nano paint with a percentage contribution of 76.19%, of pressure followed by a Distance of 14.29%. In view of P-values, the overall significance (0.059) of the factor impact on the relative closeness coefficient can be distinguished for nano paint.The moderate test flaw for the regression model employing nano paint-coated surface roughness is 14.63% when correlated to normal painting is 19.1%. This strategy is appropriate for evaluating nano paint robot painting in acceptable error ranges. Sensitivity analysis shows that the speed of the Robot is positively influenced and the pressure is negatively influenced by a wide range of sensitivity occurs.The fuzzy rationale analyses are contrasted and test esteems by utilising CNT mixed nano paint utilising a robot. The R2 estimation of the fuzzy model for with CNT is 0.892. The high R2 expresses the best model fits the information, certainly utilising CNT injected painting.Surface topology researched through the SEM investigation delineates a particular improvement in the surface finish and Globules of debris and craters and pits are extensively reduced in the Nano painted plates and the reason is to adhesion property of CNT.The greatest test errors for thickness variety utilising the ANN model are 3.5% for nano painting. This Technique is best appropriate for evaluating thickness variety, which has a worthy flaw range. ANN creates the exact connection among painting parameters and thickness variety. Consequently, ANN can be utilised to anticipate thickness variety even before the painting stage, which will be particularly near qualities and has acquired after painting.