Accurate estimation of surface roughness from texture features of the surface image using an adaptive neuro-fuzzy inference system

Lee, Kuang Chyi; Ho, Shinn‐Ying

doi:10.1016/j.precisioneng.2004.05.002

Cited by 67 publications

(31 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Later, the parameters were optimized using MINITAB 15 software and regression equations were compared, with and without SWCNTs. Kuang-Chyi Lee et al [6] proposed a method using ANFIS to establish the relationship between actual surface roughness and texture features of the surface image. The input parameters of the training model were spatial frequency, arithmetic mean value and standard deviation of gray levels from the surface image, without involving cutting parameters.…”

Section: Previous Workmentioning

confidence: 99%

Adaptive Neuro-Fuzzy Interference System Modelling of EDM Process Using CNT Infused Copper Electrode

Sethuramalingam¹,

Sundararaj²

2017

IJIES

View full text Add to dashboard Cite

This study deals with the experimental investigation of the machining characteristics of AISI D2 Tool Steel on the EDM process by using Carbon Nanotube (CNT) infused nano copper electrode, and checking the improvement in machinability characteristics like Material Removal Rate (MRR), Electrode wear rate (EWR) and Surface finish (SR). The work material is spark machined with pure copper and CNT-infused copper electrodes by varying parameters on an EDM. Experiment work is conducted based on Taguchi L9 orthogonal array. The various results of the machining characteristics of with and without CNT are compared and analyzed by means of Adaptive Neuro-Fuzzy Inference System (ANFIS) approach; Analysis of variance (ANOVA) and F-test are used to check the validity of regression model and determine the significant parameter affecting the surface roughness. The output values are found to be close to predicted values with an error of less than 5%.

show abstract

Section: Previous Workmentioning

confidence: 99%

Adaptive Neuro-Fuzzy Interference System Modelling of EDM Process Using CNT Infused Copper Electrode

Sethuramalingam¹,

Sundararaj²

2017

IJIES

View full text Add to dashboard Cite

show abstract

“…According to Lee et al [29], ANFIS is a fuzzy inference system introduced in the work structure of an adaptive neuro-fuzzy network. Using a hybrid learning procedure, the ANFIS system is able to build an input-output map based on human knowledge and on input/output data pairs.…”

Section: Adaptive Neuro-fuzzy Inference System (Anfis)mentioning

confidence: 99%

Digital Signal Processing for Acoustic Emission

Aguiar¹,

Martins²,

Marchi³

et al. 2012

Data Acquisition Applications

View full text Add to dashboard Cite

“…These methods assess surface roughness using texture features of image data collected from the test specimen. Lee et al [15] has proposed a method for such measurements and have demonstrated the validity of their proposed method to achieve accurate Ra readings; however the effects of light variation and material changes on their results have not been discussed.…”

Section: Vision Basedmentioning

confidence: 99%

Pneumatic non-contact roughness assessment of moving surfaces

2009

View full text Add to dashboard Cite

All machined surfaces inherently have roughness. The level of control of this surface is dependeat on the specifications outlined for its intended use. In strictly controlled situatiom, the monitoring and characterization of these surfaces becomes increasingly important to ensure that each component conforms to specifications. For this reason, the need f,)r in-situ monitoring systems has increased in order to optimize manufacturing time and minimize generated scrap for companies to remain competitive in industry. Current in-situ roughness monitoring systems, such as optical methods, are limited by the harsl: environments in which these systems are required to operate and the requirement for highly reflective materials. Accordingly, the need to develop a more robust system is required. The objective of this work was to develop and test a noncontact surface roughness characterization system which can be implemented into a machining center in order to provide in-situ measurements where currently available methods are rendered inappropriate.

show abstract

Accurate estimation of surface roughness from texture features of the surface image using an adaptive neuro-fuzzy inference system

Cited by 67 publications

References 12 publications

Adaptive Neuro-Fuzzy Interference System Modelling of EDM Process Using CNT Infused Copper Electrode

Adaptive Neuro-Fuzzy Interference System Modelling of EDM Process Using CNT Infused Copper Electrode

Digital Signal Processing for Acoustic Emission

Pneumatic non-contact roughness assessment of moving surfaces

Contact Info

Product

Resources

About