ANN Based Tool Condition Monitoring System for CNC Milling Machines

Abstract

Sistema basado en redes neuronales artificiales para el monitoreo de la herramienta en fresadoras CNC AbstractMost of the companies have as objective to manufacture high-quality products, then by optimizing costs, reducing and controlling the variations in its production processes it is possible. Within manufacturing industries a very important issue is the tool condition monitoring, since the tool state will determine the quality of products. Besides, a good monitoring system will protect the machinery from severe damages. For determining the state of the cutt ing tools in a milling machine, there is a great variety of models in the industrial market, however these systems are not available to all companies because of their high costs and the requirements of modifying the machining tool in order to att ach the system sensors. This paper presents an intelligent classifi cation system which determines the status of cutt ers in a Computer Numerical Control (CNC) milling machine. This tool state is mainly detected through the analysis of the cutt ing forces drawn from the spindle motors currents. This monitoring system does not need sensors so it is no necessary to modify the machine. The correct classifi cation is made by advanced digital signal processing techniques. Just after acquiring a signal, a FIR digital fi lter is applied to the data to eliminate the undesired noisy components and to extract the embedded force components. A Wavelet Transformation is applied to the fi ltered signal in order to compress the data amount and to optimize the classifi er structure. Then a multilayer perceptron-type neural network is responsible for carrying out the classifi cation of the signal. Achieving a reliability of 95%, the system is capable of detecting breakage and a worn cutt er.

Scoring Models for Process Montioring in Industry a Mechatronic Application

“…They are the use of multiple sensors [11], the integration of control signals from the machine controller into the monitoring system [12] and finally the use of wireless and telecommunication based systems to facilitate dissemination of information [13][14]. Among these techniques, artificial neural network ANNs and its combination with other methods have been the most predominant to date [15][16][17][18]. ANNs techniques are characterized as black box approaches which model the relation between different variables to a desired response without giving any information about what happens inside the process.…”