Neural Predictor for Surface Roughness of Turned Parts

2018 ◽  
Vol 29 (3) ◽  
pp. 360-370 ◽  
Author(s):  
Demerval Mizuyama ◽  
Carlos Elias da Silva ◽  
Alessandro Goedtel ◽  
Clayton L. Graciola ◽  
Rodrigo H. C. Palácios
Author(s):  
R. Kamguem ◽  
A. S. Tahan ◽  
V. Songmene

The surface roughness is very significant information required for product quality on the field of mechanical engineering and manufacturing, especially in aeronautic. Its measurement must therefore be conducted with care. In this work, a measuring method of the surface roughness based on machine vision was studied. The authors' use algorithms to evaluate new discriminatory features thereby than the statistical characteristics using the coefficients of the wavelet transform and used to estimate the roughness parameters. This vision system allows measuring simultaneously several parameters of the roughness at the same time, order to meet for the desired surface function used. The results were validated on three different families of materials: aluminum, cast iron and brass. The impact of material on the quality of the results was analyzed, leading to the development of multi-materials. The study had shown that several roughness parameters can be estimated using only features extracted from the image and a neural network without a priori knowledge of the machining parameters.


2011 ◽  
Vol 383-390 ◽  
pp. 4576-4584 ◽  
Author(s):  
M.N. Islam ◽  
N. H. Rafai ◽  
B. C. Heng

This paper presents the experimental and analytical results of different cutting fluid supply strategies—dry, minimum quantity lubrication (MQL) and flood turning in terms of the surface finish of turned parts. Subsequently, the influence of independent input parameters on surface finish is investigated in order to optimize their effects. Three techniques—traditional analysis, Pareto ANOVA analysis, and the Taguchi method—are employed. Initially mild steel AISI 1030 has been selected as the work material. The results indicate that the cutting fluid supply strategy has insignificant influence on the surface finish of turned parts. However, the amount of cutting fluid in MQL showed some influence. Further research on two additional materials, aluminum 6061 and alloy steel AISI 4340, reveals that the surface roughness for different work materials is influenced differently by the cutting fluid supply strategies and there is a scope for optimizing the cutting fluid supply strategy in terms of both method and the amount of cutting fluid. This will reduce the amount of cutting fluids used and consequently, their negative impact on the environment, by avoiding unnecessary applications.


2012 ◽  
Vol 498 ◽  
pp. 213-218
Author(s):  
P. Morala-Argüello ◽  
J. Barreiro ◽  
E. Alegre ◽  
M. García-Ordás ◽  
O. García-Olalla ◽  
...  

Current trends in machining processes are focused in three goals: to increase the productivity and the reliability and to minimize costs. In this context, the development of signal monitoring systems is of vital importance for surface roughness inspection. One of the research lines associated to this context is oriented to predict surface roughness using indirect signal analysis, such as cutting forces or vibrations in the machining process. This paper analyzes the results obtained when comparing different nature signals combined with cutting parameters. The final goal is to quantify the deviations obtained with different monitoring signals for establishing the best ones to use as roughness evaluators. The best predictions were obtained when force and cutting conditions were combined together. The absolute error values remains always below 1.28 and 1.11 µm when using the median and root mean square (RMS) as descriptors, respectively.


Author(s):  
I. H. Musselman ◽  
R.-T. Chen ◽  
P. E. Russell

Scanning tunneling microscopy (STM) has been used to characterize the surface roughness of nonlinear optical (NLO) polymers. A review of STM of polymer surfaces is included in this volume. The NLO polymers are instrumental in the development of electrooptical waveguide devices, the most fundamental of which is the modulator. The most common modulator design is the Mach Zehnder interferometer, in which the input light is split into two legs and then recombined into a common output within the two dimensional waveguide. A π phase retardation, resulting in total light extinction at the output of the interferometer, can be achieved by changing the refractive index of one leg with respect to the other using the electrooptic effect. For best device performance, it is essential that the NLO polymer exhibit minimal surface roughness in order to reduce light scattering. Scanning tunneling microscopy, with its high lateral and vertical resolution, is capable of quantifying the NLO polymer surface roughness induced by processing. Results are presented below in which STM was used to measure the surface roughness of films produced by spin-coating NLO-active polymers onto silicon substrates.


Author(s):  
H. Kinney ◽  
M.L. Occelli ◽  
S.A.C. Gould

For this study we have used a contact mode atomic force microscope (AFM) to study to topography of fluidized cracking catalysts (FCC), before and after contamination with 5% vanadium. We selected the AFM because of its ability to well characterize the surface roughness of materials down to the atomic level. It is believed that the cracking in the FCCs occurs mainly on the catalysts top 10-15 μm suggesting that the surface corrugation could play a key role in the FCCs microactivity properties. To test this hypothesis, we chose vanadium as a contaminate because this metal is capable of irreversibly destroying the FCC crystallinity as well as it microporous structure. In addition, we wanted to examine the extent to which steaming affects the vanadium contaminated FCC. Using the AFM, we measured the surface roughness of FCCs, before and after contamination and after steaming.We obtained our FCC (GRZ-1) from Davison. The FCC is generated so that it contains and estimated 35% rare earth exchaged zeolite Y, 50% kaolin and 15% binder.


Author(s):  
Amritpal Singh ◽  
Rakesh Kumar

In the present study, Experimental investigation of the effects of various cutting parameters on the response parameters in the hard turning of EN36 steel under the dry cutting condition is done. The input control parameters selected for the present work was the cutting speed, feed and depth of cut. The objective of the present work is to minimize the surface roughness to obtain better surface finish and maximization of material removal rate for better productivity. The design of experiments was done with the help of Taguchi L9 orthogonal array. Analysis of variance (ANOVA) was used to find out the significance of the input parameters on the response parameters. Percentage contribution for each control parameter was calculated using ANOVA with 95 % confidence value. From results, it was observed that feed is the most significant factor for surface roughness and the depth of cut is the most significant control parameter for Material removal rate.


Sign in / Sign up

Export Citation Format

Share Document