Real-time estimation of machine cutting tool wear. (17th February 2022)

• Record Type: Journal Article
• Authors: Shen, Zhi-An; Cheng, Jiangfeng; Tang, Chieh-Tse; Lin, Chun-Liang; Juang, Chia-Feng
• Is Part Of: Journal of the Chinese Institute of Engineers. Volume 45:Number 2(2022)
• Page Start: 117
• Page End: 130
• Publication Date: 2022-02-17
• Subjects: Tool condition monitoring -- indirect measurement -- tool wear -- neural network; Technology -- Periodicals; Engineering -- Periodicals; 620.005
• DOI: 10.1080/02533839.2021.2012526
• Languages: English
• ISSNs: 0253-3839

Abstract

ABSTRACT: Status of the cutting tool has a great impact on the quality of the final product during the machining processes. However, the cutting tool condition monitoring (TCM) system mostly stays at the stage of research and development in the literature. In this research task, a combination of multiple sensors including three-axis accelerometer and acoustic emission (AE) sensor and driver current detector of the spindle, is used to collect respective data of the milling cutter during machining process of the CNC machines. The information is used indirectly to justify the tool wear level. During the machining process, two types of the cutter with different materials are considered with cutting paths classified into three categories: straight cutting path, square cutting path, and circle cutting path. We also propose a signal feature extraction method combined with an ANN for the TCM system. It can be used to perceive the difference between tool materials and wear level in three standard types of cutting path. Finally, online analysis supported by the TCM system is developed to show the identification accuracy of tool wear.