Intelligent Vision Based Technique Using ANN for Surface Finish Assessment of Machined Components

2007 ◽  
Vol 364-366 ◽  
pp. 1251-1256
Author(s):  
M.Rajaram Narayanan ◽  
S. Gowri

In this work, an FPGA hardware based image processing algorithm for preprocessing the images and enhance the image quality has been developed. The captured images were processed using a FPGA chip to remove the noise and then using a neural network, the surface roughness of machined parts produced by the grinding process was estimated. To ensure the effectiveness of this approach the roughness values quantified using these image vision techniques were then compared with widely accepted standard mechanical stylus instrument values. Quantification of digital images for surface roughness was performed by extracting key image features using Fourier transform and the standard deviation of gray level intensity values. A VLSI chip belonging to the Xilinx family Spartan-IIE FPGA board was used for the hardware based filter implementation. The coding was done using the popular VHDL language with the algorithms developed so as to exploit the implicit parallel processing capability of the chip. Thus, in this work an exhaustive analysis was done with comparison studies wherever required to make sure that the present approach of estimating surface finish based on the computer vision processing of image is more accurate and could be implemented in real time on a chip.

Author(s):  
Mandeep Singh ◽  
Ashwani Kumar

To judge the success of a machining operation, surface finish of the machined parts is one of the important criteria. The value of optimum machining parameters (for better surface finish) can be either decided on the basis of a large number of experimental trails or design of experiments (DoE) can be used to predict the same with significantly lesser number of experimental trails. The aim of this work was to reveal the application of Taguchi method to study the effect of the machining/cutting parameters for surface finish during turning of AISI 1020 steel under different cutting environments. The results revealed that spindle speed was the most influential factor which affected surface roughness in dry turning as well as wet turning. However, depth of cut was second influential factor in dry turning but feed rate was more influential than depth of cut during wet turning Machining, Turning, Steel, Surface finish, Taguchi, Minitab, Anova


2010 ◽  
Vol 447-448 ◽  
pp. 51-54
Author(s):  
Mohd Fazuri Abdullah ◽  
Muhammad Ilman Hakimi Chua Abdullah ◽  
Abu Bakar Sulong ◽  
Jaharah A. Ghani

The effects of different cutting parameters, insert nose radius, cutting speed and feed rates on the surface quality of the stainless steel to be use in medical application. Stainless steel AISI 316 had been machined with three different nose radiuses (0.4 mm 0.8 mm, and 1.2mm), three different cutting speeds (100, 130, 170 m/min) and feed rates (0.1, 0.125, 0.16 mm/rev) while depth of cut keep constant at (0.4 mm). It is seen that the insert nose radius, feed rates, and cutting speed have different effect on the surface roughness. The minimum average surface roughness (0.225µm) has been measured using the nose radius insert (1.2 mm) at lowest feed rate (0.1 mm/rev). The highest surface roughness (1.838µm) has been measured with nose radius insert (0.4 mm) at highest feed rate (0.16 mm/rev). The analysis of ANOVA showed the cutting speed is not dominant in processing for the fine surface finish compared with feed rate and nose radius. Conclusion, surface roughness is decreasing with decreasing of the feed rate. High nose radius produce better surface finish than small nose radius because of the maximum uncut chip thickness decreases with increase of nose radius.


2014 ◽  
Vol 989-994 ◽  
pp. 3331-3334
Author(s):  
Tao Zhang ◽  
Guo He Li ◽  
L. Han

High speed milling is a newly developed advanced manufacturing technology. Surface integrity is an important object of machined parts. Surface roughness is mostly used to evaluate to the surface integrity. A theoretical surface roughness model for high face milling was established. The influence of cutting parameters on the surface roughness is analyzed. The surface roughness decreases when the cutter radius increases, total number of tooth and rotation angular speed, while it increases with the feeding velocity. The high speed face milling can get a smooth surface and it can replace the grinding with higher efficiency.


2017 ◽  
Vol 749 ◽  
pp. 9-14 ◽  
Author(s):  
Masato Okada ◽  
Yuki Miyagoshi ◽  
Masaaki Otsu

This paper proposes a roller burnishing method that controls the sliding direction of the burnishing tool on the surface of cylindrical workpiece. In this study, the sliding direction was set by inclining the axis of the burnishing tool with respect to the axis of the workpiece and by actively rotating the roller of the burnishing tool. The workpiece was a cylindrical aluminum alloy bar, which was rotated in a bench lathe. The burnished surfaces at several sliding angles between 15º and 90º were evaluated. The sliding direction, which is set according to a theoretical equation, was experimentally obtained for every sliding angle in the range of 15-90º with respect to the circumferential direction of the workpiece. The sectional profile was flattened and surface roughness was decreased with increasing sliding angle. As a result, the burnished surfaces obtained in this work were superior to those obtained in an earlier study by the authors, in which the burnishing tool was not actively rotated.


2012 ◽  
Vol 576 ◽  
pp. 41-45
Author(s):  
A.K.M. Nurul Amin ◽  
M.A. Mahmud ◽  
M.D. Arif

The majority of semiconductor devices are made up of silicon wafers. Manufacturing of high-quality silicon wafers includes numerous machining processes, including end milling. In order to end mill silicon to a nano-meteric surface finish, it is crucial to determine the effect of machining parameters, which influence the machining transition from brittle to ductile mode. Thus, this paper presents a novel experimental technique to study the effects of machining parameters in high speed end milling of silicon. The application of compressed air, in order to blow away the chips formed, is also investigated. The machining parameters’ ranges which facilitate the transition from brittle to ductile mode cutting as well as enable the attainment of high quality surface finish and integrity are identified. Mathematical model of the response parameter, the average surface roughness (Ra) is subsequently developed using RSM in terms of the machining parameters. The model was determined, by Analysis of Variance (ANOVA), to have a confidence level of 95%. The experimental results show that the developed mathematical model can effectively describe the performance indicators within the controlled limits of the factors that are being considered.


Author(s):  
Prof. Hemant k. Baitule ◽  
Satish Rahangdale ◽  
Vaibhav Kamane ◽  
Saurabh Yende

In any type of machining process the surface roughness plays an important role. In these the product is judge on the basis of their (surface roughness) surface finish. In machining process there are four main cutting parameter i.e. cutting speed, feed rate, depth of cut, spindle speed. For obtaining good surface finish, we can use the hot turning process. In hot turning process we heat the workpiece material and perform turning process multiple time and obtain the reading. The taguchi method is design to perform an experiment and L18 experiment were performed. The result is analyzed by using the analysis of variance (ANOVA) method. The result Obtain by this method may be useful for many other researchers.


2018 ◽  
Vol 53 (20) ◽  
pp. 2909-2924 ◽  
Author(s):  
Ajit Dhanawade ◽  
Shailendra Kumar

Traditional machining of carbon epoxy composite material is difficult due to excessive tool wear, excessive stresses and heat generation, delamination, high surface waviness, etc. In the present paper, research work involved in the experimental study of abrasive water jet machining of carbon epoxy composite material is described. The aim of present work is to improve surface finish and studying defects in machined samples. Taguchi's orthogonal array approach is used to design experiments. Process parameters namely hydraulic pressure, traverse rate, stand-off distance and abrasive mass flow rate are considered for this study. Analysis of machined surfaces and kerf quality is carried out using scanning electron microscope to evaluate microscopic features. Further, the effect of machining parameters on surface roughness is investigated using analysis of variance approach. It is found that traverse rate and pressure are most significant parameters to control surface roughness. Optimization of process parameters is performed using grey relational analysis. Thereafter, confirmation tests are carried out to verify the improvement in the surface quality with optimum set of process parameters. It is found that surface finish of machined samples is improved by 10.75% with optimum levels of process parameters. Defects like delamination, fiber pull-out and abrasive embedment are also studied using SEM. It is observed that delamination and fiber pull-out are prominent in samples machined at low pressure and high traverse rate.


2014 ◽  
Vol 902 ◽  
pp. 95-100 ◽  
Author(s):  
Heraldo J. Amorim ◽  
Augusto O. Kunrath Neto

The aim of this work is to analyze the tool wear effects on surface finish of machined components. Long-term machinability tests were performed for ASTM 1040 and 1045 carbon steels with carbide tools, in which tool wear and surface roughness were periodically evaluated. Surface finish was analyzed as a function of processed material and cutting speed with new machining tool, and a significant influence was found for cutting speed at a confidence interval of 10%. When evaluated as a function of time and tool wear, surface roughness showed an exponential relationship with both variables. However, a high dispersion occurs close to the end of tool life, especially for AISI 1040 steel. Weak influence of cutting speed (for the range of speeds tested) was observed on the relationship between tool wear and surface finish, indicating that a single equation can describe its behavior for all studied conditions. The relationship between the surface roughness and the cutting time was found to be stronger for the ABNT 1040 steel.


2019 ◽  
Vol 26 (3) ◽  
pp. 473-483
Author(s):  
Muhammad Omar Shaikh ◽  
Ching-Chia Chen ◽  
Hua-Cheng Chiang ◽  
Ji-Rong Chen ◽  
Yi-Chin Chou ◽  
...  

Purpose Using wire as feedstock has several advantages for additive manufacturing (AM) of metal components, which include high deposition rates, efficient material use and low material costs. While the feasibility of wire-feed AM has been demonstrated, the accuracy and surface finish of the produced parts is generally lower than those obtained using powder-bed/-feed AM. The purpose of this study was to develop and investigate the feasibility of a fine wire-based laser metal deposition (FW-LMD) process for producing high-precision metal components with improved resolution, dimensional accuracy and surface finish. Design/methodology/approach The proposed FW-LMD AM process uses a fine stainless steel wire with a diameter of 100 µm as the additive material and a pulsed Nd:YAG laser as the heat source. The pulsed laser beam generates a melt pool on the substrate into which the fine wire is fed, and upon moving the X–Y stage, a single-pass weld bead is created during solidification that can be laterally and vertically stacked to create a 3D metal component. Process parameters including laser power, pulse duration and stage speed were optimized for the single-pass weld bead. The effect of lateral overlap was studied to ensure low surface roughness of the first layer onto which subsequent layers can be deposited. Multi-layer deposition was also performed and the resulting cross-sectional morphology, microhardness, phase formation, grain growth and tensile strength have been investigated. Findings An optimized lateral overlap of about 60-70% results in an average surface roughness of 8-16 µm along all printed directions of the X–Y stage. The single-layer thickness and dimensional accuracy of the proposed FW-LMD process was about 40-80 µm and ±30 µm, respectively. A dense cross-sectional morphology was observed for the multilayer stacking without any visible voids, pores or defects present between the layers. X-ray diffraction confirmed a majority austenite phase with small ferrite phase formation that occurs at the junction of the vertically stacked beads, as confirmed by the electron backscatter diffraction (EBSD) analysis. Tensile tests were performed and an ultimate tensile strength of about 700-750 MPa was observed for all samples. Furthermore, multilayer printing of different shapes with improved surface finish and thin-walled and inclined metal structures with a minimum achievable resolution of about 500 µm was presented. Originality/value To the best of the authors’ knowledge, this is the first study to report a directed energy deposition process using a fine metal wire with a diameter of 100 µm and can be a possible solution to improving surface finish and reducing the “stair-stepping” effect that is generally observed for wires with a larger diameter. The AM process proposed in this study can be an attractive alternative for 3D printing of high-precision metal components and can find application for rapid prototyping in a range of industries such as medical and automotive, among others.


Author(s):  
Vishal Gandhi

This study investigate the machining operation perform by the combination of EDM and ECM process. Since in case of EDM the surface finish obtain is not as good as required so next machining operation is done by ECM. As we have, in EDM metal is removed from the workpiece through spark erosion and in ECM metal removed by anodic dissolution in the electrolyte. Both the process is done simultaneously in single machine changing the potential on anode and cathode and the medium. The EDM surface of 1μ mm Ra is improved to 0.2μ mm Ra by applying ECM. The surface roughness of a machined hole is improved to 0.07 mm Ra by applying 2 min of ECM lapping. Both the process is done simultaneously.


Sign in / Sign up

Export Citation Format

Share Document