Study on Fuzzy Data Fusion for Real-Time Intelligent Recognition of Tool Wear State

Bang Yan Ye; Jian Ping Liu; Rui Tao Peng; Yong Tang; Xue Zhi Zhao

doi:10.4028/www.scientific.net/KEM.375-376.626

Paper Titles

Numerical Analysis on the Process of Laser Continuous Peen Forming of Metal Plate
p.603

Automatic Testing Equipment and Experiments Based on the Quantitative Shadow Method for Measuring Sub-Nanometer Deformations on Aspheric Surface
p.608

Study on Balance Precision of Ultra-High Speed CBN Grinding Wheel System
p.614

Analysis of the Effects of Multi-Clamps Fixture on Workpiece Location Errors
p.619

Study on Fuzzy Data Fusion for Real-Time Intelligent Recognition of Tool Wear State
p.626

Static and Dynamic Analysis of Carbon Nanotube Cantilever Based on Molecular Dynamics Simulation
p.631

Clamping Behaviour of Modern Jaw-Chuck with Centrifugal Force Compensation during High Speed Turning
p.636

Design and Simulation of Spring-Driven Lock-Unlock Mechanism for Spaceborne Flexible Appendages
p.643

On the Dynamics of Piezoelectric-Driven Stick-Slip Actuator
p.648

HomeKey Engineering MaterialsKey Engineering Materials Vols. 375-376Study on Fuzzy Data Fusion for Real-Time...

Study on Fuzzy Data Fusion for Real-Time Intelligent Recognition of Tool Wear State

Abstract:

For detecting gradual tool wear state on line, the methods of Wavelet Fuzzy Neural Network, Regression Neural Network and Sample Classification Fuzzy Neural Network by detecting cutting force, motor power of machine tool and AE signal respectively are presented. Although these methods are not difficult to come true and processed accurately and rapidly, it is difficult to obtain comprehensive information of machining and exact value of tool wear when using single method of intelligent modeling and single signal detecting. For this purpose, fuzzy inference technique is adopted to fuse the recognized data. Emulation experiment is carried out by using Matlab software platform and this method is verified to be feasible. Experimental result indicates that by applying fuzzy data fusion, we can get an exact tool wear forecast rapidly.