Surface roughness accuracy prediction in turning of Al7075 by adaptive neuro-fuzzy inference system

2020 ◽  
Author(s):  
B. Veluchamy ◽  
N. Karthikeyan ◽  
B. Radha Krishnan ◽  
C. Mathalai Sundaram
Keyword(s):  
Surface Roughness ◽  
Fuzzy Inference System ◽  
Fuzzy Inference ◽  
Inference System ◽  
Neuro Fuzzy

Adaptive Neuro-Fuzzy Inference System Modelling of Surface Roughness in High Speed Turning of AISI P 20 Tool Steel

2011 ◽  
Vol 314-316 ◽  
pp. 341-345
Author(s):  
Bo Di Cui
Keyword(s):  
Experimental Data ◽  
Surface Roughness ◽  
Tool Steel ◽  
Fuzzy Inference System ◽  
High Speed ◽  
Fuzzy Inference ◽  
System Modelling ◽  
Inference System ◽  
High Speed Turning ◽  
Neuro Fuzzy

Accurate predictive modelling is an essential prerequisite for optimization and control of production in modern manufacturing environments. In this paper, an adaptive neuro-fuzzy inference system (ANFIS) model was developed to predict the surface roughness in high speed turning of AISI P 20 tool steel. Experiments were designed and performed to collect the training and testing data for the proposed model based on orthogonal array. For decreasing the complexity of the ANFIS structure, principal component analysis (PCA) was used to deal with the experimental data. The comparison between predictions and experimental data showed that the proposed method was both effective and efficient for modelling surface roughness.

Surface Roughness Prediction in High Speed End Milling Using Adaptive Neuro-Fuzzy Inference System

2015 ◽  
Vol 1115 ◽  
pp. 122-125
Author(s):  
Muataz Hazza F. Al Hazza ◽  
Amin M.F. Seder ◽  
Erry Y.T. Adesta ◽  
Muhammad Taufik ◽  
Abdul Hadi bin Idris
Keyword(s):  
Surface Roughness ◽  
Fuzzy Inference System ◽  
High Speed ◽  
Fuzzy Inference ◽  
End Milling ◽  
Machining Process ◽  
Inference System ◽  
Neuro Fuzzy ◽  
Roughness Prediction ◽  
Coated Carbide

One of the significant characteristics in machining process is final quality of surface. The best measurement for this quality is the surface roughness. Therefore, estimating the surface roughness before the machining is a serious matter. The aim of this research is to estimate and simulate the average surface roughness (Ra) in high speed end milling. An experimental work was conducted to measure the surface roughness. A set of experimental runs based on box behnken design was conducted to machine carbon steel using coated carbide inserts. Moreover, the Adaptive Neuro-Fuzzy Inference System (ANFIS) has been used as one of the unconventional methods to develop a model that can predict the surface roughness. The adaptive-network-based fuzzy inference system (ANFIS) was found to be capable of high accuracy predictions for surface roughness within the range of the research boundaries.

Computer vision measurement and optimization of surface roughness using soft computing approaches

2020 ◽  
Vol 42 (13) ◽  
pp. 2475-2481 ◽  
Author(s):  
Radha Krishnan Beemaraj ◽  
Mathalai Sundaram Chandra Sekar ◽  
Venkatraman Vijayan
Keyword(s):  
Genetic Algorithm ◽  
Surface Roughness ◽  
Soft Computing ◽  
Fuzzy Inference System ◽  
Fuzzy Inference ◽  
Optimization Technique ◽  
Inference System ◽  
Random Forest Classification ◽  
Vision Measurement ◽  
Neuro Fuzzy

This paper proposes an efficient methodology for predicting surface roughness using different soft computing approaches. The soft computing approaches are artificial neural network, adaptive neuro-fuzzy inference system and genetic algorithm. The proposed surface roughness prediction procedure has the following stages as feature extraction from the materials, classifications using random forests, adaptive neuro-fuzzy inference system (ANFIS). In this paper, the statistical features are extracted from material images as skewness, kurtosis, mean, variance, contrast, and energy.The surface roughness accuracy value varied between ANFIS and random forest classification in every measurement sequence. This limitation can be overcome by the genetic algorithm to optimize the best results. The optimization technique can produce more accurate surface roughness results for more than 98% and reduce the error rate up to 0.5%.

Sign in / Sign up

Export Citation Format

Share Document