Towards Early and Reliable Detection of Thermal Degradation in High-Precision Machine Tools via Hybrid Condition Monitoring
##plugins.themes.bootstrap3.article.main##
##plugins.themes.bootstrap3.article.sidebar##
Abstract
Thermal Condition Monitoring (TCM) provides a means to monitor the operation of precision machine tools on a continuous
basis to maintain micron level accuracy and allow for the identification of the early stages of component degradation.
Gradual changes in the mechanical aspects of friction, lubrication, pre-load and wear all contribute to variations in both
heat generated and transferred which directly affect the location of the tool center point (TCP). While conventional TCP
correction models are highly effective at compensating for instantaneous positioning errors in real time, their residuals are
heavily influenced by reversible operational and environmental factors. Consequently, these residuals alone do not allow
reliable differentiation between reversible variations and irreversible, slow-evolving degradation processes. This research
will propose an innovative hybrid model combining physical based thermal modeling for increased interpretability, with
data driven methods to improve the sensitivity of progressive changes. Data-driven components will analyze the machine’s
full operational history to identify how the system evolves over time and the normal patterns and relationships between
variables. Key innovations include (i) the systematic determination of residuals, and (ii) a dual-time scale methodology
that isolates fast transient thermal responses from slower degradation processes. In this manner, the framework utilizes
TCP correction models as baseline diagnostics to extract physically meaningful degradation parameters that can
be monitored along with residuals. Preliminary modeling results demonstrate the effectiveness of the hybrid model separating the reversible and irreversible effects.
How to Cite
##plugins.themes.bootstrap3.article.details##
thermal condition monitoring, TCP correction, thermal anomaly detection, hybrid physics-data driven, degradation prognostics, machine tool health monitoring, uncertainty-aware residuals
learning for predictive maintenance in industry 4.0. IEEE access, 11, 12887–12910.
Brecher, C., Ihlenfeldt, S., Neus, S., Steinert, A., & Galant, A. (2019). Thermal condition monitoring of a motorized
milling spindle. Production Engineering, 13(5), 539–546.
Clough, D., Fletcher, S., Longstaff, A. P., & Willoughby, P. (2012). Thermal analysis for condition monitoring of
machine tool spindles. In Journal of physics: Conference series (Vol. 364, p. 012088).
Drowatzky, L., M¨alzer, M., Wejlupek, K. A., Wiemer, H., & Ihlenfeldt, S. (2024). Digitization workflow for data mining in production technology applied to a feed axis of a cnc milling machine. Procedia Computer Science, 232, 169–182.
Gupta, S., Kumar, A., & Maiti, J. (2024). A critical review on system architecture, techniques, trends and challenges
in intelligent predictive maintenance. Safety Science, 177, 106590.
Thiem, X., Kauschinger, B., & Ihlenfeldt, S. (2019). Online correction of thermal errors based on a structure model. International Journal of Mechatronics and Manufacturing Systems, 12(1), 49–62.
Veldman, J., Wortmann, H., & Klingenberg, W. (2011). Typology of condition based maintenance. Journal Article. Wiemer, H., Drowatzky, L., & Ihlenfeldt, S. (2019). Data mining methodology for engineering applications (dmme)—a holistic extension to the crisp-dm model. Applied Sciences, 9(12), 2407.
This work is licensed under a Creative Commons Attribution 3.0 Unported License.
The Prognostic and Health Management Society advocates open-access to scientific data and uses a Creative Commons license for publishing and distributing any papers. A Creative Commons license does not relinquish the author’s copyright; rather it allows them to share some of their rights with any member of the public under certain conditions whilst enjoying full legal protection. By submitting an article to the International Conference of the Prognostics and Health Management Society, the authors agree to be bound by the associated terms and conditions including the following:
As the author, you retain the copyright to your Work. By submitting your Work, you are granting anybody the right to copy, distribute and transmit your Work and to adapt your Work with proper attribution under the terms of the Creative Commons Attribution 3.0 United States license. You assign rights to the Prognostics and Health Management Society to publish and disseminate your Work through electronic and print media if it is accepted for publication. A license note citing the Creative Commons Attribution 3.0 United States License as shown below needs to be placed in the footnote on the first page of the article.
First Author et al. This is an open-access article distributed under the terms of the Creative Commons Attribution 3.0 United States License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.