Tool Condition Monitoring in Composite Materials Machining through Neural Network Processing of Acoustic Emission

By their nature, composite materials are non-homogeneous, anisotropic, and reinforced with abrasive components. Because of their structure and component properties, composite materials are much more difficult to machine than metal alloys and fall under the category of difficult-to-machine-materials. The composite material workpiece can easily suffer intolerable damage during cutting and the tool wear rate can turn out to be unacceptably high. As the available knowledge on the machining of ductile metals is not suitable for composite materials, the need is felt for getting a deeper understanding of the mechanisms governing chip formation and tool wear development in these new materials. In this paper, tool condition monitoring during machining of the most common composite types, i.e. glass and carbon fibre reinforced polymer matrix composites, is carried out through acoustic emission based sensor monitoring, advanced sensor signal processing and neural network data analysis