Usage
  • 155 views
  • 222 downloads

Redefining the tool condition monitoring: A framework for machining quality prediction and tool life management

  • Author / Creator
    Mamledesai, Harshavardhan
  • Tool wear morphology is one of the established topics in the field of manufacturing. Wear morphology monitoring offers significant information about the machining process such as, the condition of the tool and the quality of the machined component, but the information has not been utilized to its full potential in the automation of the machining processes. The objective of the thesis is to proposes different systems that utilize this tool wear morphology information for tool condition monitoring (TCM), machining quality improvement, and machining parameter optimization. The proposed study has four objectives. First, the development of a new definition for TCM considering the barriers between present TCM systems and their deployment in machine shops around the world. Second, the development of a TCM system that achieves the proposed new definition of TCM. Third, the development of a fuzzy controller that helps in machining parameters optimization decision making with the objective of tool life improvement utilizing the wear morphology information as feedback. Lastly, a TCM methodology for monitoring form tools that develop wear on different tool surfaces is proposed. Monitoring the wear morphologies also helps the developed systems to work with different, workpiece materials, tool geometries and tool grades; this allows a faster transition of the proposed systems to industrial setups. The proposed systems use advanced artificial intelligence technologies life Convolution Neural Network, Transfer Learning, and Fuzzy logic to achieve the objectives.

  • Subjects / Keywords
  • Graduation date
    Spring 2021
  • Type of Item
    Thesis
  • Degree
    Master of Science
  • DOI
    https://doi.org/10.7939/r3-z91b-dz60
  • License
    This thesis is made available by the University of Alberta Libraries with permission of the copyright owner solely for non-commercial purposes. This thesis, or any portion thereof, may not otherwise be copied or reproduced without the written consent of the copyright owner, except to the extent permitted by Canadian copyright law.