Tool Wear Monitoring using NNge Algorithm
Journal: International Journal of Mechanical and Production Engineering Research and Development (IJMPERD ) (Vol.9, No. 5)Publication Date: 2019-10-31
Authors : J. Saran M. Elangovan; V. Sugumara;
Page : 53-62
Keywords : Machine Learning; NNge; Tool Condition Monitoring & Vibration Signals;
Abstract
Cutting tools are required to do the necessary machining operations in the manufacturing Industry. Continuous machining operation causes the tool to degrade. The machining operation done using a worn-out tool will have a poor surface finish. The poor surface finish undermines the accuracy of the component. This can be solved by using online system condition monitoring tools which helps in reducing the tool maintenance cost all the while increasing the productivity. This paper presents the classification performance of the Nearest-neighbour-like algorithm using non-nested generalized exemplar (NNge). A set of statistical data extracted from vibration signals for both good and faulty conditions form the input to the algorithm. In the present study, the NNge algorithm is able to achieve 100% classification accuracy.
Other Latest Articles
- Effect of Permanent Magnetic Pole Orientation on Field Strength in Viscoelastic Magnetic Abrasive Finishing Process
- Execution of Cryogenically Treated Brisk Steel Enters in Exhausting of Austenitic Solidified Steels
- Design and Analysis of Solid Propellant Rocket Nozzle and its Applications to RCS
- Experimental Evaluation of Closed Loop Pulsating Heat Pipe with Water based Working Fluids
- An Energy Production Evaluation from PV Arrays with Different Inter-Row Distances
Last modified: 2019-11-13 13:21:09