Manufacturing Technology Today

Open Access Open Access  Restricted Access Subscription Access
Open Access Open Access Open Access  Restricted Access Restricted Access Subscription Access

Tool Wear Monitoring and Control


Affiliations
1 Department of Industrial and Production Engg., K.L. College of Engineering, Vaddeswaram, Guntur (Dist.), India
2 Department of the Mechanical Engineering, Chaitanya Engineering College, Visakhapatnam, India
     

   Subscribe/Renew Journal


This paper presents, a control methodology based on experimental data of the tool wear as a function of cutting variables. In automatic machine tools, there is strong need to control the tool wear by adjustment of the cutting parameters. In this connection, a control system, which can adjust the cutting parameters for a desired wear rate, is necessary. A regression relation is also established between the flank-wear, and the cutting parameters. An inversely trained neural network model, which supplies the modified values of the cutting parameters, is used as a controller. The results are shown in the form of tables and graphs.
User
Subscription Login to verify subscription
Notifications
Font Size

Abstract Views: 204

PDF Views: 0




  • Tool Wear Monitoring and Control

Abstract Views: 204  |  PDF Views: 0

Authors

K. Rama Kotaiah
Department of Industrial and Production Engg., K.L. College of Engineering, Vaddeswaram, Guntur (Dist.), India
J. Srinivas
Department of the Mechanical Engineering, Chaitanya Engineering College, Visakhapatnam, India
K. Jayanendra Babu
Department of Industrial and Production Engg., K.L. College of Engineering, Vaddeswaram, Guntur (Dist.), India

Abstract


This paper presents, a control methodology based on experimental data of the tool wear as a function of cutting variables. In automatic machine tools, there is strong need to control the tool wear by adjustment of the cutting parameters. In this connection, a control system, which can adjust the cutting parameters for a desired wear rate, is necessary. A regression relation is also established between the flank-wear, and the cutting parameters. An inversely trained neural network model, which supplies the modified values of the cutting parameters, is used as a controller. The results are shown in the form of tables and graphs.