Effective tool wear estimation through multisensory information fusion using Artificial Neural Network
On-line tool wear monitoring plays a significant role in industrial automation for higher productivity and product quality. In addition, an intelligent system is required to make a timely decision for tool change in machining systems in order to avoid the subsequent consequences on the dimensional accuracy and surface finish of the product. The present study deals with developing an intelligent system using Artificial Neural Network (ANN) to monitor and estimate the tool wear in face milling operation using Acoustic Emission (AE) and cutting force sensor signals. This Paper also highlights the significance of multi sensory information fusion for effective tool wear estimation by using ANN. Further, it provides a sequential approach to minimize the error in tool wear estimation by illustrating the influence of ANN parameters, stopping criterion, modes of training the network, adaptation of learning rate parameter using fuzzy logic and population size on wear estimation.
Keywords: Monitoring, Tool Wear, Face Milling, Cutting Force, Acoustic Emission, Sensor Fusion, Artificial Neural Networks.