Tool health monitoring for wood milling process using airborne acoustic emission

Tool condition monitoring is gaining importance in area of the intelligent manufacturing. It not only reduces the time loss due to breakdown maintenance therefore reduces the production cost. The paper provides an approach to monitor tool health for a wood milling process using airborne acoustic emission. A total of six experiments are conducted for two types of woods; hard wood (Indian rosewood) and soft wood (Kair wood) with different tool health conditions. Acoustic signals of a milling process are recorded through a low-cost microphone and four features have been used for classification. Back-propagation neural network has been used to classify the tool health. Average accuracy of tool condition classification for hard wood is found to be 97.0%, while for the soft wood, it is found to be 78.4%. Experiments shows promising results for tool health monitoring for a wood milling process using airborne acoustic emission.