Evaluation of automated stability testing in machining through closed-loop control and Bayesian machine learning. (1st December 2022)

• Record Type: Journal Article
• Authors: Karandikar, Jaydeep; Saleeby, Kyle; Feldhausen, Thomas; Kurfess, Thomas; Schmitz, Tony; Smith, Scott
• Is Part Of: Mechanical systems and signal processing. Volume 181(2022)
• Publication Date: 2022-12-01
• Subjects: Machining -- Chatter -- Control -- Machine learning; Structural dynamics -- Periodicals; Vibration -- Periodicals; Constructions -- Dynamique -- Périodiques; Vibration -- Périodiques; Structural dynamics; Vibration; Periodicals; 621
• DOI: 10.1016/j.ymssp.2022.109531
• Languages: English
• ISSNs: 0888-3270

Abstract

Highlights: A system for automated identification of the optimal stable cutting parameters in milling through Bayesian machine learning and closed-loop control is described. Experimental results demonstrate that the system can identify the optimal stable parameters without information about the cutting force model or the structural dynamics in an automated way. Multiple strategies for test parameter selection are described and evaluated. Methods for implementing closed-loop control in different commercial machine tool controllers are described. The system provides a low-cost method for optimal stable parameter identification in an industrial environment. Abstract: This paper describes a system for automated identification of the optimal stable cutting parameters in milling through Bayesian machine learning and closed-loop control. The closed-loop control system consists of a process monitoring architecture, an analysis framework, and a feedback mechanism. The analysis framework consists of a Bayesian machine learning algorithm that learns a stability map given test results. The learned stability map is used to select parameters for stability testing using an expected improvement in the material removal rate criterion. The test parameters are communicated to the machine controller to complete the test cut through a feedback mechanism. The test cuts were monitored using an audio signal; the stability of the test cut was determined by analyzing the frequency content of the audio signal. The test result was fed back to the Bayesian learning algorithm to complete the loop. Experimental results demonstrate that the system can identify the optimal stable parameters without information about the cutting force model or the structural dynamics. The system provides a low-cost method for optimal stable parameter identification in an industrial environment.