MaxEnt feature-based reliability model method for real-time detection of early chatter in high-speed milling

Real-time detection of early chatter is a vital strategy to improve machining quality and material removal rate in the high-speed milling processes. This paper proposes maximum entropy (MaxEnt) feature-based reliability model method for real-time based on multiple sampling per revolution (MSPR) technique second-order (SORM). To enhance reliability, MSPR used acquire sets once-per-revolution sampled data (i.e., data) overcome shortcoming sampling. The proposed MaxEnt solves issue while ensuring its reliability. failure hazard function (FHF) estimated as indicator by using SORM with feature. consists five steps. First, set prior parameters. Then collect technique. Next, calculate standard deviation collected feature estimate FHF applying Finally, implement threshold FHF0. applied process. Two examples prove that can detect two kinds chatter: early-stage severe slightly intolerable chatter.