It is well-established that unbalance in tool assembly causes excessive loads on spindle bearings and tool wear and increased vibration levels. However, in the days where high-speed machining (HSM) has become a common practice in the manufacturing industry, methodologies to measure tool assembly unbalance are not developed. In HSM the effects are worse, as the unbalance force is directly proportional to square of the spindle speed. Common practice in industry is to balance the tool assembly either with in-house balancing machines or use third-party balancing services after every batch cycle.
This paper describes a data-driven methodology that detects the presence of unbalance in a tool assembly relative to the tools with known balance levels. The unbalance detection prognostic application developed as part of the Smart Machine Platform Initiative (SMPI) checks for the threshold unbalance level in the tool assembly for the given machining requirements before the start of any run. This approach uses statistical tools and a supervised learning algorithm based on the Watchdog Agent® toolbox developed by the Center for Intelligent Maintenance Systems. The proposed research finds high applicability in high-precision manufacturing operations involving high-volume production.
Reference: Smart Machine Health and Maintenance: Tool Assembly Prognostics, The International Manufacturing Science and Engineering Conference, Evanston, IL, October 2008
Authors: Edzel Lapira, Amit Deshpande, Dr. Jay Lee and Dr. John Snyder
No comments:
Post a Comment