A neuro-fuzzy system is used to predict the condition of the tool in a milling process. Specifically the relationship between the sensor readings and tool wear state is first captured via a neural network and is subsequently reflected in linguistic form in terms of a fuzzy logic based diagnostic algorithm. In this approach, the neural network serves as an interpolative mechanism for the generation of data that is consistent with the behavior of the process, whereas fuzzy logic provides a transparent view of the relationship between the measured variables and the tool wear state. The methodology used in this paper incorporates an error-based, density-driven adaptation scheme in conjunction with a neural network based reference model to adapt the fuzzy membership functions associated with the tool condition monitoring algorithm to ensure that the rule set reflects the true nature of the inter-relationship between the sensor readings and the tool condition. Experimental results show that the proposed fuzzy mechanism correctly predicts the condition of the tool in 97 percent of the cases where it is applied.

Issue Section:
Technical Papers
Keywords:
machine tools, cutting, neural nets, fuzzy systems, wear, machining, fuzzy logic, monitoring
Topics:
Artificial neural networks, Cutting, Fuzzy logic, Fuzzy neural nets, Sensors, Wear, Condition monitoring, Algorithms, Machining, Density
1.
Chryssolouris, G., and Domroese, M., 1988, “Sensor Integration for Tool Wear Estimating in Machining,” Winter Annual Meeting of the ASME, pp. 115–123.
2.
Li, S., Elbestawi, M. A., and Du, R. X., 1992, “Fuzzy Logic Approach for Multi-Sensor Process Monitoring in Machining,” Winter Annual Meeting of the American Society of Mechanical Engineers, 55, pp. 1–16.
3.
Ko
,
T. J.
, and
Cho
,
D. W.
,
1994
, “
Tool Wear Monitoring in Diamond Turning by Fuzzy Pattern Recognition
,”
ASME J. Eng. Ind.
,
116
, No.
2
, pp.
225
–
232
.
4.
Fang
,
X. D.
,
1995
, “
Expert System-Supported Fuzzy Diagnosis of Finish-Turning Process States
,”
Int. J. Mach. Tools Manuf.
,
35
, No.
6
, pp.
913
–
924
.
5.
Rangwala
,
S.
, and
Dornfeld
,
D.
,
1990
, “
Sensor Integration Using Neural Networks for Intelligent Tool Condition Monitoring
,”
ASME J. Eng. Ind.
,
112
, pp.
219
–
228
.
6.
Masory, O., 1991, “Monitoring Machining Processes Using Multi-Sensor Readings Fused by Artificial Neural Networks,” 7th International Conference on Computer-Aided Production Engineering, 28, No. 1–2, pp. 231–240.
7.
Emel, E., 1991, “Tool Wear Detection By Neural Network Based Acoustic Emission Sensing,” Control of Manufacturing Processes, ASME, pp. 79–85.
8.
Wang, Z., and Dornfeld, D., 1992, “In-Process Tool Wear Monitoring Using Neural Networks,” Proceedings of the 1992 Japan-USA Symposium on Flexible Automation, pp. 263–270.
9.
Elanayar, S., and Shin, Y., 1992, “Robust Tool Wear Estimation via Radial Basis Function Neural Networks,” Winter Annual Meeting of the American Society of Mechanical Engineers, 57, pp. 37–51.
10.
Weis, Wolfgang, 1994, “Processing of Optical Sensor Data for Tool Condition Monitoring Wit Neural Networks,” WESCON Conference Proceedings, Los Angeles, CA, pp. 351–355.
11.
Rahman
,
M.
,
Zhou
,
Q.
, and
Hong
,
G. S.
,
1995
, “
On-Line Cutting State Recognition Using a Neural Network
,”
International Journal of Advanced Manufacturing Technology
,
0
, No.
2
, pp.
87
–
92
.
12.
Choudhury
,
S. K.
,
Jain
,
V. K.
, and
Ramo Rao
,
Ch. V. V.
,
1999
, “
On-Line Monitoring of Tool Wear in Turning Using a Neural Network
,”
Int. J. Mach. Tools Manuf.
,
39
, No.
3
, pp.
489
–
504
.
13.
Niu
,
Y. M.
,
Wong
,
Y. S.
,
Hong
,
G. S.
, and
Liu
,
T. I.
,
1998
, “
Multi-Category Classification of Tool Conditions Using Wavelets Packets and ART2 Networks
,”
ASME J. Manuf. Sci. Eng.
,
120
, No.
4
, pp.
807
–
816
.
14.
Matsumura
,
T.
,
Obikawa
,
T.
,
Shirkashi
,
T.
, and
Usui
,
E.
,
1992
, “
On the Development of Expert System for Selecting the Optimum Cutting Condition
,”
Journal of the Japan Society of Precision Engineering
,
58
, No.
10
, pp.
1691
–
1696
.
15.
Teshima
,
T.
,
Shibasaka
,
T.
,
Takuma
,
M.
,
Yamamoto
,
A.
, and
Iwata
,
K.
,
1993
, “
Estimation of Cutting Tool Life by Processing Tool Image Data with Neural Network
,”
CIRP Ann.
,
42
, No.
1
, pp.
59
–
62
.
16.
Burke
,
L.
,
1992
, “
Competitive Learning Based Approaches to Tool Wear Identification
,”
IEEE Trans. Syst. Man Cybern.
,
22
, No.
3
, pp.
559
–
563
.
17.
Burke
,
L.
, and
Rangwala
,
S.
,
1991
, “
Tool Condition Monitoring in Metal Cutting: A Neural Network Approach
,”
Journal of Intelligent Manufacturing
,
2
, Issue
5
, pp.
269
–
280
.
18.
Tansel
,
I. N.
,
1994
, “
Identification of the Pre-failure Phase in Microdrilling Operations with Multiple Sensors
,”
Int. J. Mach. Tools Manuf.
,
34
, No.
3
, pp.
351
–
364
.
19.
Langari, R., and Tomizuka, M., 1990, “Self Organizing Fuzzy Linguistic Control with Application to Arc Welding,” Proceedings of the 1990 IEEE Workshop on Intelligent Systems & Robots-IROS.
Copyright © 2001
 by ASME
You do not currently have access to this content.