• Proceedings of the Korean Society of Tribologists and Lubrication Engineers Conference
• /
• 2000.06a
• /
• pp.68-75
• /
• 2000

The development of flexible automation in the manufacturing industry is concerned with production activities performed by unmanned machining system. A major topic relevant to metal-cutting operations is monitoring tool wear, which affects process efficiency and product quality, and implementing automatic tool replacements. In this paper, the measurement of the cutting force components has been found to provide a method for an in-process detection of tool wear. Cutting force components are divided into static and dynamic components in this paper, and the static components of cutting force have been used to detect flank wear. To eliminate the influence of variations in cutting conditions, tools, and workpiece materials, the force modeling is performed for various cutting conditions. The normalized force disparities are defined in this paper, and the relationships between normalized disparity and flank wear are established. Finally, Artificial neural network is used to learn these relationships and detect tool wear. According to the proposed method, the static force components could provide the effective means to detect flank wear for varying cutting conditions in turning operation.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.10 no.1
• /
• pp.1-9
• /
• 2001

The development of flexible automation in the manufacturing industry is concerned with production activities performed by unmanned machining system A major topic relevant to metal-cutting operations is monitoring toll wear, which affects process efficiency and product quality, and implementing automatic toll replacements. In this paper, the measurement of the cutting force components has been found to provide a method for an in-process detection of tool wear. The static com-ponents of cutting force have been used to detect flank wear. To eliminate the influence of variations in cutting conditions, tools, and workpiece materials, the force modeling is performed for various cutting conditions. The normalized force dis-parities are defined in this paper, and the relationships between normalized disparity and flank were are established. Final-ly, artificial neural network is used to learn these relationships and detect tool wear. According to proposed method, the static force components could provide the effective means to detect flank wear for varying cutting conditions in turning operation.