Growing Cell Structures (GCS) - A Constructive Learning Neural Network for Tool Wear Estimation Application

Tool wear is one of the major factors that affect the automation of machining operations. There is a need to reliably detect the condition of the tool because it affects the product quality, increases machine downtime and sometimes affect the machine tool and the personnel. Tool condition monitoring (TCM) is important in the successful automation of manufacturing processes. In this paper, a new constructive learning algorithm proposed by Fritzke, namely Growing Cell Structures (GCS) is being used for tool wear estimation in face milling operation, thereby monitoring the condition of the tool. GCS generates compact network architecture in less training time and performs well on new untrained data, establishing its feasibility in tool wear estimation applications. The performance of this network has been compared with that of another constructive learning algorithm based neural network namely the Resource Allocation Network (RAN). GCS has been found to be effective and efficient for tool wear estimation.