Quality improvement of machine vision-based non-contact inspection of surface roughness in turning through adaptive neuro-fuzzy interference system

Author(s):  
D. Shome ◽  
P.K. Ray ◽  
B. Mahanty
Author(s):  
IV Manoj ◽  
S Narendranath

Hastelloy-X a nickel-based alloy used in nozzles, flame holders, turbine blades, turbocharges, jet engine tailpipes, afterburner components etc. having complex tapering profiles. Wire electric discharge machining proves to be the most beneficial machining technique as it provides required accuracy for the components. In the present research, a slant type taper fixture is employed for achieving taper angles as convention tapering have many hindrances like wire bend, angular inaccuracy, guide wear, insufficient flushing and wire breakage etc. and machining a simple circular profile on Hastelloy-X. The behaviour of different output parameters like profiling speed, surface roughness, profile areas, microhardness and recast layer were investigated for various input parameters for machined taper components at 0°, 15° and 30°. The cutting speed override parameter influenced most on the profiling speed and surface roughness. The wire offset parameter was found to be the most significant factor in the case of circular profile areas that were machined. The variation of different output parameters to profiling/cutting speed and taper angle was also highlighted. It is found the recast layer decreased which indicated lesser thermal degradation at higher taper angles at different profiling parameters. This is also validated by the microhardness where the machined surface hardness of taper angular profiles was found to be greater than the 0° profiles. The artificial neural networks and adaptive neuro-fuzzy interference system were used for the prediction of profiling speed. The adaptive neuro-fuzzy interference system was found better in prediction as the percentage error varies between 0–5 per cent. In conclusion, the profiling speed influences both on the accuracy and surface of machined taper circular profiles.


2019 ◽  
Vol 21 (4) ◽  
pp. 523-540 ◽  
Author(s):  
Mohammad Aamir ◽  
Zulfequar Ahmad

Abstract An analysis of laboratory experimental data pertaining to local scour downstream of a rigid apron developed under wall jets is presented. The existing equations for the prediction of the maximum scour depth under wall jets are applied to the available data to evaluate their performance and bring forth their limitations. A comparison of measured scour depth with that computed by the existing equations shows that most of the existing empirical equations perform poorly. Artificial neural network (ANN)- and adaptive neuro-fuzzy interference system (ANFIS)-based models are developed using the available data, which provide simple and accurate tools for the estimation of the maximum scour depth. The key parameters that affect the maximum scour depth are densimetric Froude number, apron length, tailwater level, and median sediment size. Results obtained from ANN and ANFIS models are compared with those of empirical and regression equations by means of statistical parameters. The performance of ANN (RMSE = 0.052) and ANFIS (RMSE = 0.066) models is more satisfactory than that of empirical and regression equations.


Sign in / Sign up

Export Citation Format

Share Document