Modeling and Analysis of Surface Roughness with Statistical and Soft Computing Approach

2021 ◽  
Vol 106 ◽  
pp. 109-115
Author(s):  
L.B. Abhang ◽  
M. Hameedullah
Keyword(s):  
Surface Roughness ◽  
Fuzzy Logic ◽  
Soft Computing ◽  
Prediction Models ◽  
Tool Geometry ◽  
Modeling And Analysis ◽  
Empirical Prediction ◽  
Lathe Machine ◽  
Carbide Inserts ◽  
Computing Approach

The objective of this study focuses on developing empirical prediction models using response regression analysis and fuzzy-logic. These models latter can be used to predict surface roughness according to technological variables. The values of surface roughness produced by these models are compared with experimental results. Experimental investigation has been carried out by using scientific composite factorial design on precision lathe machine with tungsten carbide inserts. Surface roughness measured at end of each experimental trial (three times), to get the effect of machining conditions and tool geometry on the surface finish values. Research showed that soft computing fuzzy logic model developed produces smaller error and has satisfactory results as compared to response regression model during machining.

scholarly journals A Soft Computing Approach to Crack Detection and Impact Source Identification with Field-Programmable Gate Array Implementation

2013 ◽  
Vol 2013 ◽  
pp. 1-12 ◽  
Author(s):  
Arati M. Dixit ◽  
Harpreet Singh
Keyword(s):  
Fuzzy Logic ◽  
Soft Computing ◽  
Fuzzy Inference System ◽  
Source Identification ◽  
Field Programmable Gate Array ◽  
Crack Detection ◽  
Fuzzy Inference ◽  
Inference System ◽  
Field Programmable ◽  
Computing Approach

The real-time nondestructive testing (NDT) for crack detection and impact source identification (CDISI) has attracted the researchers from diverse areas. This is apparent from the current work in the literature. CDISI has usually been performed by visual assessment of waveforms generated by a standard data acquisition system. In this paper we suggest an automation of CDISI for metal armor plates using a soft computing approach by developing a fuzzy inference system to effectively deal with this problem. It is also advantageous to develop a chip that can contribute towards real time CDISI. The objective of this paper is to report on efforts to develop an automated CDISI procedure and to formulate a technique such that the proposed method can be easily implemented on a chip. The CDISI fuzzy inference system is developed using MATLAB’s fuzzy logic toolbox. A VLSI circuit for CDISI is developed on basis of fuzzy logic model using Verilog, a hardware description language (HDL). The Xilinx ISE WebPACK9.1i is used for design, synthesis, implementation, and verification. The CDISI field-programmable gate array (FPGA) implementation is done using Xilinx’s Spartan 3 FPGA. SynaptiCAD’s Verilog Simulators—VeriLogger PRO and ModelSim—are used as the software simulation and debug environment.

scholarly journals Modeling of Cutting Parameters and Tool Geometry for Multi-Criteria Optimization of Surface Roughness and Vibration via Response Surface Methodology in Turning of AISI 5140 Steel

Materials ◽  
2020 ◽  
Vol 13 (19) ◽  
pp. 4242 ◽  
Author(s):  
Mustafa Kuntoğlu ◽  
Abdullah Aslan ◽  
Danil Yurievich Pimenov ◽  
Khaled Giasin ◽  
Tadeusz Mikolajczyk ◽  
...  
Keyword(s):  
Surface Roughness ◽  
Response Surface Methodology ◽  
Response Surface ◽  
Prediction Models ◽  
High Reliability ◽  
Cutting Speed ◽  
Cutting Parameters ◽  
Cutting Edge ◽  
Tool Geometry ◽  
Machining Processes

AISI 5140 is a steel alloy used for manufacturing parts of medium speed and medium load such as gears and shafts mainly used in automotive applications. Parts made from AISI 5140 steel require machining processes such as turning and milling to achieve the final part shape. Limited research has been reported on the machining vibration and surface roughness during turning of AISI 5140 in the open literature. Therefore, the main aim of this paper is to conduct a systematic study to determine the optimum cutting conditions, analysis of vibration and surface roughness under different cutting speeds, feed rates and cutting edge angles using response surface methodology (RSM). Prediction models were developed and optimum turning parameters were obtained for averaged surface roughness (Ra) and three components of vibration (axial, radial and tangential) using RSM. The results demonstrated that the feed rate was the most affecting parameter in increasing the surface roughness (69.4%) and axial vibration (65.8%) while cutting edge angle and cutting speed were dominant on radial vibration (75.5%) and tangential vibration (64.7%), respectively. In order to obtain minimum vibration for all components and surface roughness, the optimum parameters were determined as Vc = 190 m/min, f = 0.06 mm/rev, κ = 60° with high reliability (composite desirability = 90.5%). A good agreement between predicted and measured values was obtained with the developed model to predict surface roughness and vibration during turning of AISI 5140 within a 10% error range.

Prediction of workpiece surface roughness using soft computing

2008 ◽  
Vol 222 (10) ◽  
pp. 1221-1232 ◽  
Author(s):  
B Samanta ◽  
W Erevelles ◽  
Y Omurtag
Keyword(s):  
Surface Roughness ◽  
Soft Computing ◽  
Prediction Models ◽  
End Milling ◽  
Depth Of Cut ◽  
Model Parameters ◽  
Machining Parameters ◽  
Validation Data ◽  
Inference System ◽  
Workpiece Surface

A study is presented to model surface roughness in end-milling using soft computing (SC) or computational intelligence (CI) techniques. The techniques include the artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS). ANFIS combines the learning capability of ANN and the effective handling of imprecise information in fuzzy logic. Prediction models based on multivariate regression analysis (MRA) are also presented for comparison. The machining parameters, namely, the spindle speed, feed rate, and depth of cut, were used as inputs to model the workpiece surface roughness. The model parameters were tuned using the training data maximizing the modelling accuracy. The trained models were tested using the set of validation data. The effects of different machining parameters, number, and type of model parameters on the prediction accuracy were studied. The procedure is illustrated using the experimental data of end-milling 6061 aluminium alloy. Although statistically all three models predicted roughness with satisfactory goodness of fit, the test performance of ANFIS was better than ANN and MRA. In comparison with MRA, the performance of ANN was better in training but similar in test. The results show the effectiveness of CI techniques in modelling surface roughness.

SOFT COMPUTING APPROACH TO DETECT FAULT IN INDUCTION MOTOR

2018 ◽  
Vol 12 (2) ◽  
pp. 6
Author(s):  
SEKHAR PUHAN PRATAP ◽  
BEHERA SUDARSAN ◽  
◽  
Keyword(s):  
Induction Motor ◽  
Soft Computing ◽  
Computing Approach
Sign in / Sign up

Export Citation Format

Share Document