An investigation on dimensional accuracy of fused deposition modeling (FDM) processed parts using fuzzy logic

Sahu, Ranjeet Kumar (2011) An investigation on dimensional accuracy of fused deposition modeling (FDM) processed parts using fuzzy logic. MTech thesis.



on dimensional accuracy of FDM processed ABSP 400 (Acrylonitrile-butadine-styrene) part which can be expressed as change in length, width and thickness. This study presents experimental data and fuzzy decision making logic in integration with the Taguchi method for improving the dimensional accuracy of FDM built parts. It is observed that length and width decreases but thickness shows positive deviation from desired value of the built part. Optimum parameters setting to minimize change in length, width and thickness of standard test specimen
have been found out using Taguchi’s parameter design. Experimental results indicate that optimal factor settings for each response are different. Therefore, all the three responses are expressed in a single response index through fuzzy logic approach. The process parameters are optimized with consideration of all the performance characteristics simultaneously. An inference engine is developed to perform the inference operations on the rules for fuzzy logic based on Mamdani method. This study also presents two prediction models- one based on Taguchi approach and the other on ANN approach for assessment of dimensional accuracy of FDM built parts subjected to different operating conditions. The predicted values obtained from Taguchi’s additive model and ANN model are in good agreement with the values from the experimental
data with mean absolute percentage error of 3.16 and 0.15 respectively. It was found that ANN model is able to predict overall performance characteristic at all operating condition to a higher degree of accuracy. Finally, experimental results are provided to confirm the effectiveness of the proposed fuzzy approach.

Item Type:Thesis (MTech)
Uncontrolled Keywords:Fused deposition modeling (FDM); Fuzzy logic; membership functions; multiresponse performance index; artificial neural network;
Subjects:Engineering and Technology > Mechanical Engineering > Production Engineering
Divisions: Engineering and Technology > Department of Mechanical Engineering
ID Code:2818
Deposited By:Sahu Ranjeet Kumar
Deposited On:06 Jun 2011 17:36
Last Modified:06 Jun 2011 17:36
Supervisor(s):Mahapatra, S S

Repository Staff Only: item control page