---
_id: '66541'
abstract:
- lang: eng
  text: Expulsion in resistance spot welding (RSW) causes weld quality fluctuations
    and increases quality-control effort in high-volume manufacturing. Existing data-driven
    studies have mainly addressed post-occurrence expulsion detection, process-end
    classification, or the identification of influencing factors, whereas online monitoring
    requires short-term risk estimation before the event occurs. In this study, expulsion
    prediction is formulated as a sliding-window-based pre-expulsion risk estimation
    task for the currently welded spot. A physics-guided hybrid GRU-XGBoost ensemble
    is developed to combine temporal learning from dynamic resistance and electrode-force
    signals with process-physics-related scalar features describing heat input, resistance
    state, and force response. The framework was evaluated on 2730 valid welds, including
    588 expulsion and 2142 non-expulsion welds, using weld-grouped five-fold cross-validation
    with fold-level working-point selection. The ensemble achieved an area under the
    ROC curve of 0.945 ± 0.004 and a weld-level recall of 90.6 ± 3.7% at an average
    false alarm rate of 9.8 ± 0.2%, outperforming both individual branches. For the
    533 correctly warned expulsion welds, the median early-warning lead time was 56
    ms. These results indicate that online, physically interpretable pre-expulsion
    risk prediction is feasible under low-false-alarm constraints within the investigated
    RSW configuration and provide a basis for future adaptive monitoring and control
    studies.
article_type: original
author:
- first_name: Keke
  full_name: Yang, Keke
  id: '65085'
  last_name: Yang
  orcid: 0000-0001-9201-9304
- first_name: Chong
  full_name: Li, Chong
  last_name: Li
- first_name: Robert
  full_name: Beck, Robert
  id: '38279'
  last_name: Beck
  orcid: 0000-0001-9056-4528
- first_name: David
  full_name: Hein, David
  id: '7728'
  last_name: Hein
- first_name: Gerson
  full_name: Meschut, Gerson
  id: '32056'
  last_name: Meschut
  orcid: 0000-0002-2763-1246
citation:
  ama: Yang K, Li C, Beck R, Hein D, Meschut G. A physics-guided hybrid framework
    for online pre-expulsion prediction in resistance spot welding. <i>Journal of
    Manufacturing Processes</i>. 2026;174:135-153. doi:<a href="https://doi.org/10.1016/j.jmapro.2026.07.042">10.1016/j.jmapro.2026.07.042</a>
  apa: Yang, K., Li, C., Beck, R., Hein, D., &#38; Meschut, G. (2026). A physics-guided
    hybrid framework for online pre-expulsion prediction in resistance spot welding.
    <i>Journal of Manufacturing Processes</i>, <i>174</i>, 135–153. <a href="https://doi.org/10.1016/j.jmapro.2026.07.042">https://doi.org/10.1016/j.jmapro.2026.07.042</a>
  bibtex: '@article{Yang_Li_Beck_Hein_Meschut_2026, title={A physics-guided hybrid
    framework for online pre-expulsion prediction in resistance spot welding}, volume={174},
    DOI={<a href="https://doi.org/10.1016/j.jmapro.2026.07.042">10.1016/j.jmapro.2026.07.042</a>},
    journal={Journal of Manufacturing Processes}, publisher={Elsevier BV}, author={Yang,
    Keke and Li, Chong and Beck, Robert and Hein, David and Meschut, Gerson}, year={2026},
    pages={135–153} }'
  chicago: 'Yang, Keke, Chong Li, Robert Beck, David Hein, and Gerson Meschut. “A
    Physics-Guided Hybrid Framework for Online Pre-Expulsion Prediction in Resistance
    Spot Welding.” <i>Journal of Manufacturing Processes</i> 174 (2026): 135–53. <a
    href="https://doi.org/10.1016/j.jmapro.2026.07.042">https://doi.org/10.1016/j.jmapro.2026.07.042</a>.'
  ieee: 'K. Yang, C. Li, R. Beck, D. Hein, and G. Meschut, “A physics-guided hybrid
    framework for online pre-expulsion prediction in resistance spot welding,” <i>Journal
    of Manufacturing Processes</i>, vol. 174, pp. 135–153, 2026, doi: <a href="https://doi.org/10.1016/j.jmapro.2026.07.042">10.1016/j.jmapro.2026.07.042</a>.'
  mla: Yang, Keke, et al. “A Physics-Guided Hybrid Framework for Online Pre-Expulsion
    Prediction in Resistance Spot Welding.” <i>Journal of Manufacturing Processes</i>,
    vol. 174, Elsevier BV, 2026, pp. 135–53, doi:<a href="https://doi.org/10.1016/j.jmapro.2026.07.042">10.1016/j.jmapro.2026.07.042</a>.
  short: K. Yang, C. Li, R. Beck, D. Hein, G. Meschut, Journal of Manufacturing Processes
    174 (2026) 135–153.
date_created: 2026-07-18T12:03:15Z
date_updated: 2026-07-18T12:07:50Z
ddc:
- '600'
department:
- _id: '157'
doi: 10.1016/j.jmapro.2026.07.042
file:
- access_level: closed
  content_type: application/pdf
  creator: kekeyang
  date_created: 2026-07-18T12:04:02Z
  date_updated: 2026-07-18T12:04:02Z
  file_id: '66542'
  file_name: 1-s2.0-S1526612526007012-main.pdf
  file_size: 10864983
  relation: main_file
  success: 1
file_date_updated: 2026-07-18T12:04:02Z
has_accepted_license: '1'
intvolume: '       174'
keyword:
- Resistance spot welding
- Expulsion prediction
- Physics-guided machine learning
- Hybrid ensemble modelling
- Process monitoring
language:
- iso: eng
main_file_link:
- open_access: '1'
oa: '1'
page: 135-153
publication: Journal of Manufacturing Processes
publication_identifier:
  issn:
  - 1526-6125
publication_status: published
publisher: Elsevier BV
quality_controlled: '1'
status: public
title: A physics-guided hybrid framework for online pre-expulsion prediction in resistance
  spot welding
type: journal_article
user_id: '65085'
volume: 174
year: '2026'
...
---
_id: '33356'
abstract:
- lang: eng
  text: By monitoring the recoating process within polymer laser sintering production,
    it was shown that multiple powder-spread-flaws can be detected. Those groove-like
    flaws are expected to be the result of agglomerates jamming between the recoater
    and the last powder layer. This work is analyzing the interaction between powder-spread-flaws
    and part properties, showing the influence of the recoating process on the performance
    of laser sintering parts. Therefore, artificial powder-spread-flaws are applied
    to the build jobs of tensile test specimens which are measured and analyzed regarding
    the elongation at break, strength and fracture position. For the characteristics
    of the flaws, the artificial grooves are varied in depth and width. Furthermore,
    the position of the flaw is changed form mid part to close to surface areas. It
    was shown, that several flaws are visible at the part surface, resulting in stress
    concentration and reduced performance. But there are as well parts with flaw-layers,
    which are not visible after the build process on the part. Those parts can have
    significantly reduced mechanical properties as well.
author:
- first_name: Sven Helge
  full_name: Klippstein, Sven Helge
  id: '71545'
  last_name: Klippstein
- first_name: Hans-Joachim
  full_name: Schmid, Hans-Joachim
  id: '464'
  last_name: Schmid
  orcid: 000-0001-8590-1921
citation:
  ama: 'Klippstein SH, Schmid H-J. Powder Spread Flaws in Polymer Laser Sintering
    and its Influences on Mechanical Performance. In: <i>Proceedings of the 33nd Annual
    International Solid Freeform Fabrication Symposium</i>. ; 2022.'
  apa: Klippstein, S. H., &#38; Schmid, H.-J. (2022). Powder Spread Flaws in Polymer
    Laser Sintering and its Influences on Mechanical Performance. <i>Proceedings of
    the 33nd Annual International Solid Freeform Fabrication Symposium</i>.
  bibtex: '@inproceedings{Klippstein_Schmid_2022, place={Austin, TX, USA}, title={Powder
    Spread Flaws in Polymer Laser Sintering and its Influences on Mechanical Performance},
    booktitle={Proceedings of the 33nd Annual International Solid Freeform Fabrication
    Symposium}, author={Klippstein, Sven Helge and Schmid, Hans-Joachim}, year={2022}
    }'
  chicago: Klippstein, Sven Helge, and Hans-Joachim Schmid. “Powder Spread Flaws in
    Polymer Laser Sintering and Its Influences on Mechanical Performance.” In <i>Proceedings
    of the 33nd Annual International Solid Freeform Fabrication Symposium</i>. Austin,
    TX, USA, 2022.
  ieee: S. H. Klippstein and H.-J. Schmid, “Powder Spread Flaws in Polymer Laser Sintering
    and its Influences on Mechanical Performance,” 2022.
  mla: Klippstein, Sven Helge, and Hans-Joachim Schmid. “Powder Spread Flaws in Polymer
    Laser Sintering and Its Influences on Mechanical Performance.” <i>Proceedings
    of the 33nd Annual International Solid Freeform Fabrication Symposium</i>, 2022.
  short: 'S.H. Klippstein, H.-J. Schmid, in: Proceedings of the 33nd Annual International
    Solid Freeform Fabrication Symposium, Austin, TX, USA, 2022.'
date_created: 2022-09-13T16:42:10Z
date_updated: 2023-05-04T08:31:49Z
department:
- _id: '150'
- _id: '624'
- _id: '219'
keyword:
- Selective Sasersintering
- Process Monitoring
- Powder Spread
language:
- iso: eng
main_file_link:
- open_access: '1'
  url: https://utw10945.utweb.utexas.edu/sites/default/files/2022/Powder%20Spread%20Flaws%20in%20Polymer%20Laser%20Sintering%20and.pdf
oa: '1'
place: Austin, TX, USA
publication: Proceedings of the 33nd Annual International Solid Freeform Fabrication
  Symposium
quality_controlled: '1'
status: public
title: Powder Spread Flaws in Polymer Laser Sintering and its Influences on Mechanical
  Performance
type: conference
user_id: '464'
year: '2022'
...
---
_id: '9783'
abstract:
- lang: eng
  text: To optimize the ultrasound irradiation for cavitation based ultrasound applications
    like sonochemistry or ultrasound cleaning, the correlation between cavitation
    intensity and the resulting effect on the process is of interest. Furthermore,
    changing conditions like temperature and pressure result in varying acoustic properties
    of the liquid. That might necessitate an adaption of the ultrasound irradiation.
    To detect such changes during operation, process monitoring is desired. Labor
    intensive processes, that might be carried out for several hours, also require
    process monitoring to increase their reliability by detection of changes or malfunctions
    during operation. In some applications cavitation detection and monitoring can
    be achieved by the application of sensors in the sound field. Though the application
    of sensors is possible, this necessitates modifications on the system and the
    sensor might disturb the sound field. In other applications harsh, process conditions
    prohibit the application of sensors in the sound field. Therefore alternative
    techniques for cavitation detection and monitoring are desired. The applicability
    of an external microphone and a self-sensing ultrasound transducer for cavitation
    detection were experimentally investigated. Both methods were found to be suitable
    and easily applicable.
author:
- first_name: Peter
  full_name: Bornmann, Peter
  last_name: Bornmann
- first_name: Tobias
  full_name: Hemsel, Tobias
  id: '210'
  last_name: Hemsel
- first_name: Walter
  full_name: Sextro, Walter
  id: '21220'
  last_name: Sextro
- first_name: Takafumi
  full_name: Maeda, Takafumi
  last_name: Maeda
- first_name: Takeshi
  full_name: Morita, Takeshi
  last_name: Morita
citation:
  ama: 'Bornmann P, Hemsel T, Sextro W, Maeda T, Morita T. Non-perturbing cavitation
    detection / monitoring in sonochemical reactors. In: <i>Ultrasonics Symposium
    (IUS), 2012 IEEE International</i>. ; 2012:1141-1144. doi:<a href="https://doi.org/10.1109/ULTSYM.2012.0284">10.1109/ULTSYM.2012.0284</a>'
  apa: Bornmann, P., Hemsel, T., Sextro, W., Maeda, T., &#38; Morita, T. (2012). Non-perturbing
    cavitation detection / monitoring in sonochemical reactors. In <i>Ultrasonics
    Symposium (IUS), 2012 IEEE International</i> (pp. 1141–1144). <a href="https://doi.org/10.1109/ULTSYM.2012.0284">https://doi.org/10.1109/ULTSYM.2012.0284</a>
  bibtex: '@inproceedings{Bornmann_Hemsel_Sextro_Maeda_Morita_2012, title={Non-perturbing
    cavitation detection / monitoring in sonochemical reactors}, DOI={<a href="https://doi.org/10.1109/ULTSYM.2012.0284">10.1109/ULTSYM.2012.0284</a>},
    booktitle={Ultrasonics Symposium (IUS), 2012 IEEE International}, author={Bornmann,
    Peter and Hemsel, Tobias and Sextro, Walter and Maeda, Takafumi and Morita, Takeshi},
    year={2012}, pages={1141–1144} }'
  chicago: Bornmann, Peter, Tobias Hemsel, Walter Sextro, Takafumi Maeda, and Takeshi
    Morita. “Non-Perturbing Cavitation Detection / Monitoring in Sonochemical Reactors.”
    In <i>Ultrasonics Symposium (IUS), 2012 IEEE International</i>, 1141–44, 2012.
    <a href="https://doi.org/10.1109/ULTSYM.2012.0284">https://doi.org/10.1109/ULTSYM.2012.0284</a>.
  ieee: P. Bornmann, T. Hemsel, W. Sextro, T. Maeda, and T. Morita, “Non-perturbing
    cavitation detection / monitoring in sonochemical reactors,” in <i>Ultrasonics
    Symposium (IUS), 2012 IEEE International</i>, 2012, pp. 1141–1144.
  mla: Bornmann, Peter, et al. “Non-Perturbing Cavitation Detection / Monitoring in
    Sonochemical Reactors.” <i>Ultrasonics Symposium (IUS), 2012 IEEE International</i>,
    2012, pp. 1141–44, doi:<a href="https://doi.org/10.1109/ULTSYM.2012.0284">10.1109/ULTSYM.2012.0284</a>.
  short: 'P. Bornmann, T. Hemsel, W. Sextro, T. Maeda, T. Morita, in: Ultrasonics
    Symposium (IUS), 2012 IEEE International, 2012, pp. 1141–1144.'
date_created: 2019-05-13T13:18:49Z
date_updated: 2022-01-06T07:04:20Z
department:
- _id: '151'
doi: 10.1109/ULTSYM.2012.0284
keyword:
- cavitation
- chemical reactors
- microphones
- process monitoring
- reliability
- ultrasonic applications
- ultrasonic waves
- acoustic properties
- cavitation based ultrasound applications
- cavitation intensity
- change detection reliability
- external microphone
- malfunction detection reliability
- nonperturbing cavitation detection
- nonperturbing cavitation monitoring
- process monitoring
- self-sensing ultrasound transducer
- sonochemical reactors
- sonochemistry
- ultrasound cleaning
- ultrasound irradiation
- Acoustics
- Liquids
- Monitoring
- Sensors
- Sonar equipment
- Transducers
- Ultrasonic imaging
language:
- iso: eng
page: 1141-1144
publication: Ultrasonics Symposium (IUS), 2012 IEEE International
publication_identifier:
  issn:
  - 1948-5719
quality_controlled: '1'
status: public
title: Non-perturbing cavitation detection / monitoring in sonochemical reactors
type: conference
user_id: '55222'
year: '2012'
...