Indirect tool monitoring in drilling based on gap sensor signal and multilayer perceptron feed forward neural network
- PDF / 3,826,099 Bytes
- 15 Pages / 595.276 x 790.866 pts Page_size
- 97 Downloads / 170 Views
Indirect tool monitoring in drilling based on gap sensor signal and multilayer perceptron feed forward neural network Siti Nurfadilah Binti Jaini1 · Deug‑Woo Lee2 · Seung‑Jun Lee1 · Mi‑Ru Kim3 · Gil‑Ho Son4 Received: 13 April 2020 / Accepted: 25 July 2020 © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract In this study, an indirect tool monitoring was developed based on the installation of a gap sensor in measuring the signal related to the tool behavior during the drilling process. Eleven types of twist drills with different tool conditions were utilized to differentiate the sensorial signals based on the tool states. A statistical analysis was conducted in the signal processing, by extracting the gap sensor signal associates from each tool condition, using the skewness and kurtosis features. Multi-class classification was conducted using the multilayer perceptron (MLP) feed forward neural network (FF-NN) model to classify and predict the tool condition based on the skewness and kurtosis data. The architectures of the MLP FF-NN models were varied to optimize the classification accuracy. This study found that the tool condition was correlated to the displacement of the drill machine spindle because the runout occurred when the sensor signal displayed fluctuation and irregularity trends. The peak intensity of the gap sensor signals increased with increasing wear severity of the twist drill. An ideal MLP FF-NN structure was achieved when the classification performance was optimized to be consistent with the learning curve. Keywords Indirect tool monitoring · Drilling · Supervised learning · Multilayer perceptron feed forward neural network · Statistical analysis
Introduction The drilling process is among the oldest machining method that is still vastly used in the recent manufacturing industry. The modern machining industry has been making an effort in developing automated machines that are capable of precisely detecting tool defects to prevent machining * Deug‑Woo Lee [email protected] 1
Department of Nano Fusion Technology, Pusan National University, 2 Busandaehak‑ro, 63beon‑gil, Geumjeonggu 46241, Republic of Korea
2
Department of Nano Mechatronics Engineering, Pusan National University, 2 Busandaehak‑ro, 63beon‑gil, Geumjeonggu 46241, Republic of Korea
3
Precision Mechanical Process and Control R&D Group, Dongnam Division, Korea Institute of Industrial Technology (KITECH), 25, Yeonkkot‑ ro, 165beon‑gil, Jeongchon‑myeon, Jinju‑si, Gyeongsangnam‑do 52845, Republic of Korea
4
Doosan Machine Tools, 40, Jeongdong‑ro 162beon‑gil, Seongsan‑gu, Changwon‑si, Gyeongsangnam‑do 51537, Republic of Korea
processes from continuously running with defected tools. Conducting machining processes using defected tools not only negatively impacts the quality of the machined products, but also affects the machine condition. Statistics have shown that tool defects contribute to 20% of machine downtime and production and economic losses. Moreover, the probability of defects in tools i
Data Loading...
