Tool wear condition monitoring based on a two-layer angle kernel extreme learning machine using sound sensor for milling
- PDF / 1,631,348 Bytes
- 12 Pages / 595.276 x 790.866 pts Page_size
- 39 Downloads / 198 Views
Tool wear condition monitoring based on a two-layer angle kernel extreme learning machine using sound sensor for milling process Yuqing Zhou1
· Bintao Sun1 · Weifang Sun1
· Zhi Lei1
Received: 18 November 2019 / Accepted: 5 September 2020 © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract Tool condition monitoring (TCM) in numerical control machines plays an essential role in ensuring high manufacturing quality. The TCM process is conducted according to the data obtained from one or more of a variety of sensors, among which acoustic sensors offer numerous practical advantages. However, acoustic sensor data suffer from strong noise, which can severely limit the accuracy of predictions regarding tool condition. The present work addresses this issue by proposing a novel TCM method that employs only a few appropriate feature parameters of acoustic sensor signals in conjunction with a two-layer angle kernel extreme learning machine. The two-layer network structure is applied to enhance the learning of features associated with complex nonlinear data, and two angle kernel functions without hyperparameters are employed to avoid the complications associated with the use of preset hyperparameters in conventional kernel functions. The proposed TCM method is experimentally demonstrated to achieve superior TCM performance relative to other state-of-the-art methods based on sound sensor data. Keywords Tool wear monitoring · Milling process · Sound sensor · Kernel extreme learning
Introduction Milling is a common and efficient machining operation employed in modern industrial manufacturing for fabricating various mechanical parts. Among all the components of milling machines, the cutting tool is subject to the most wear by far during the machining process, and the conditions of cutting tools vary widely over their effective lifetimes (Javed et al. 2018). Moreover, studies have demonstrated that cutting tools are typically used for only 50–80% of their effective lifetimes owing to excessive tool wear and breakage (Konstantinos and Athanasios 2014; Karandikar et al. 2015). These tool faults are major causes of unscheduled downtime in milling processes and typically account for 7–20% of the total downtime (Vetrichelvan et al. 2014). In addition, costs associated with tools and tool changes account for 3–12% of the total processing cost in milling activities (Liu
B
Weifang Sun [email protected] Yuqing Zhou [email protected]
1
College of Mechanical and Electrical Engineering, Wenzhou University, Wenzhou, China
et al. 2015). As such, deteriorating tool conditions and tool faults have seriously negative effects on milling performance. Therefore, the development of effective and timely tool condition monitoring (TCM) methods is essential for increasing machining efficiency, reducing processing cost, and ensuring good workpiece quality (Aliustaoglu et al. 2009; Gao et al. 2015). The development of TCM methods in milling processes has been a subject of great interest for over 30 years, and two primary
Data Loading...