Application of compressed air in the online monitoring of surface roughness and grinding wheel wear when grinding Ti-6Al-4V titanium alloy

This work aimed to improve the surface quality and precision in machining process and speed up intelligent production. Hence, this work proposed a grinding process from a control perspective which provides a cognitive decision-making process. From this viewpoint, a new approach to measure the amount...

Full description

Saved in:
Bibliographic Details
Published in:International journal of advanced manufacturing technology 2019-04, Vol.101 (5-8), p.1315-1331
Main Authors: Yin, Shaohui, Nguyen, DuyTrinh, Chen, FengJun, Tang, Qingchun, Duc, Le Anh
Format: Article
Language:English
Subjects:
Abrasive wear
Air monitoring
Algorithms
Artificial neural networks
CAE) and Design
Ceramics industry
Compressed air
Computer-Aided Engineering (CAD
Confidence intervals
Decision making
Empirical analysis
Engineering
Fuzzy logic
Grinding wheels
Industrial and Production Engineering
Machining
Mechanical Engineering
Media Management
Neural networks
Original Article
Rapid prototyping
Regression analysis
Statistical analysis
Surface properties
Surface roughness
Titanium alloys
Titanium base alloys
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This work aimed to improve the surface quality and precision in machining process and speed up intelligent production. Hence, this work proposed a grinding process from a control perspective which provides a cognitive decision-making process. From this viewpoint, a new approach to measure the amount of grinding wheel wear and predict the surface roughness was designed by the authors on the basis of the compressed air measuring head and hybrid algorithms between fuzzy neural networks (i.e., ANFIS)—Gaussian regression function (i.e., GPR) and Taguchi empirical analysis. A series of experiments was conducted under different processing conditions. Results showed that the proposed method can measure the abrasive wear and predict the surface roughness accurately during Ti-6Al-4V titanium alloy grinding. The proposed model can predict surface roughness values with an error rate of 0.31% and a confidence interval of 98%. This study laid the foundation for monitoring the grinding wheel wear and the surface roughness in real-life industrial environments.
ISSN:0268-3768
1433-3015
DOI:10.1007/s00170-018-2909-6