International Conference on Advanced and Competitive Manufacturing Technologies milling tool wear prediction using unsupervised machine learning
Abstract Degraded or defect machine components and consumables negatively impact manufacturing quality and productivity. Diagnosing and predicting the wear or degradation status of critical machine components or parts are therefore of general interest. To tackle this challenge, data-driven approache...
Ausführliche Beschreibung
Gespeichert in:
| Autor*in: |
Gittler, Thomas [verfasserIn] |
|---|
| Format: |
Artikel |
|---|---|
| Sprache: |
Englisch |
| Erschienen: |
2021 |
|---|
| Schlagwörter: |
|---|
| Anmerkung: |
© The Author(s) 2021 |
|---|
| Übergeordnetes Werk: |
Enthalten in: The international journal of advanced manufacturing technology - Springer London, 1985, 117(2021), 7-8 vom: 24. Mai, Seite 2213-2226 |
|---|---|
| Übergeordnetes Werk: |
volume:117 ; year:2021 ; number:7-8 ; day:24 ; month:05 ; pages:2213-2226 |
| Links: |
|---|
| DOI / URN: |
10.1007/s00170-021-07281-2 |
|---|
| Katalog-ID: |
OLC2077360356 |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | OLC2077360356 | ||
| 003 | DE-627 | ||
| 005 | 20230505144303.0 | ||
| 007 | tu | ||
| 008 | 221220s2021 xx ||||| 00| ||eng c | ||
| 024 | 7 | |a 10.1007/s00170-021-07281-2 |2 doi | |
| 035 | |a (DE-627)OLC2077360356 | ||
| 035 | |a (DE-He213)s00170-021-07281-2-p | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 082 | 0 | 4 | |a 670 |q VZ |
| 100 | 1 | |a Gittler, Thomas |e verfasserin |0 (orcid)0000-0002-1932-2494 |4 aut | |
| 245 | 1 | 0 | |a International Conference on Advanced and Competitive Manufacturing Technologies milling tool wear prediction using unsupervised machine learning |
| 264 | 1 | |c 2021 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a ohne Hilfsmittel zu benutzen |b n |2 rdamedia | ||
| 338 | |a Band |b nc |2 rdacarrier | ||
| 500 | |a © The Author(s) 2021 | ||
| 520 | |a Abstract Degraded or defect machine components and consumables negatively impact manufacturing quality and productivity. Diagnosing and predicting the wear or degradation status of critical machine components or parts are therefore of general interest. To tackle this challenge, data-driven approaches based on supervised machine learning principles have demonstrated promising results. However, supervised learning models capable of degradation identification require large quantities of data. In practice, run-to-failure data in large amounts is usually not available and expensive to obtain. To overcome this issue, this study proposes an unsupervised learning approach for degradation prognostics of machine tool components and consumables. It uses time series of multi-sensor signal data, which are transformed into a feature representation. The features consist of various characterizations of the time series, allowing to make different signal measurements comparable, and cluster them according to their feature values. The herewith obtained density-based clustering model is used to diagnose and predict the degradation states of components and parts in unknown conditions. The novelty in the proposed approach lies within the identification of continuous component and part degradation states based on unsupervised learning principles. The proposal is verified and demonstrated on an exemplary data set containing a small sample of run-to-failure multi-sensor signals of milling inserts and their corresponding wear state. By the application of the proposed procedure on the exemplary data set, we demonstrate that an unsupervised clustering approach is capable of separating wear data such that meaningful and accurate estimations of the part condition are possible. The advantages are its ability to cope with scarce data sets, its limited engineering and hyperparameter tuning effort, and its straightforward implementation to a multitude of degradation and wear diagnostics scenarios. | ||
| 650 | 4 | |a Condition monitoring | |
| 650 | 4 | |a Machine learning | |
| 650 | 4 | |a Prognostics and health monitoring | |
| 650 | 4 | |a Unsupervised learning | |
| 650 | 4 | |a Machine tools | |
| 650 | 4 | |a Manufacturing | |
| 650 | 4 | |a Milling | |
| 650 | 4 | |a Tool wear | |
| 700 | 1 | |a Glasder, Magnus |4 aut | |
| 700 | 1 | |a Öztürk, Elif |4 aut | |
| 700 | 1 | |a Lüthi, Michel |4 aut | |
| 700 | 1 | |a Weiss, Lukas |4 aut | |
| 700 | 1 | |a Wegener, Konrad |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t The international journal of advanced manufacturing technology |d Springer London, 1985 |g 117(2021), 7-8 vom: 24. Mai, Seite 2213-2226 |w (DE-627)129185299 |w (DE-600)52651-4 |w (DE-576)014456192 |x 0268-3768 |7 nnns |
| 773 | 1 | 8 | |g volume:117 |g year:2021 |g number:7-8 |g day:24 |g month:05 |g pages:2213-2226 |
| 856 | 4 | 1 | |u https://doi.org/10.1007/s00170-021-07281-2 |z lizenzpflichtig |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a SYSFLAG_A | ||
| 912 | |a GBV_OLC | ||
| 912 | |a SSG-OLC-TEC | ||
| 912 | |a GBV_ILN_2018 | ||
| 912 | |a GBV_ILN_2333 | ||
| 951 | |a AR | ||
| 952 | |d 117 |j 2021 |e 7-8 |b 24 |c 05 |h 2213-2226 | ||
| author_variant |
t g tg m g mg e ö eö m l ml l w lw k w kw |
|---|---|
| matchkey_str |
article:02683768:2021----::nentoacneecoavneadopttvmnfcuigehooisilntowapeito |
| hierarchy_sort_str |
2021 |
| publishDate |
2021 |
| allfields |
10.1007/s00170-021-07281-2 doi (DE-627)OLC2077360356 (DE-He213)s00170-021-07281-2-p DE-627 ger DE-627 rakwb eng 670 VZ Gittler, Thomas verfasserin (orcid)0000-0002-1932-2494 aut International Conference on Advanced and Competitive Manufacturing Technologies milling tool wear prediction using unsupervised machine learning 2021 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © The Author(s) 2021 Abstract Degraded or defect machine components and consumables negatively impact manufacturing quality and productivity. Diagnosing and predicting the wear or degradation status of critical machine components or parts are therefore of general interest. To tackle this challenge, data-driven approaches based on supervised machine learning principles have demonstrated promising results. However, supervised learning models capable of degradation identification require large quantities of data. In practice, run-to-failure data in large amounts is usually not available and expensive to obtain. To overcome this issue, this study proposes an unsupervised learning approach for degradation prognostics of machine tool components and consumables. It uses time series of multi-sensor signal data, which are transformed into a feature representation. The features consist of various characterizations of the time series, allowing to make different signal measurements comparable, and cluster them according to their feature values. The herewith obtained density-based clustering model is used to diagnose and predict the degradation states of components and parts in unknown conditions. The novelty in the proposed approach lies within the identification of continuous component and part degradation states based on unsupervised learning principles. The proposal is verified and demonstrated on an exemplary data set containing a small sample of run-to-failure multi-sensor signals of milling inserts and their corresponding wear state. By the application of the proposed procedure on the exemplary data set, we demonstrate that an unsupervised clustering approach is capable of separating wear data such that meaningful and accurate estimations of the part condition are possible. The advantages are its ability to cope with scarce data sets, its limited engineering and hyperparameter tuning effort, and its straightforward implementation to a multitude of degradation and wear diagnostics scenarios. Condition monitoring Machine learning Prognostics and health monitoring Unsupervised learning Machine tools Manufacturing Milling Tool wear Glasder, Magnus aut Öztürk, Elif aut Lüthi, Michel aut Weiss, Lukas aut Wegener, Konrad aut Enthalten in The international journal of advanced manufacturing technology Springer London, 1985 117(2021), 7-8 vom: 24. Mai, Seite 2213-2226 (DE-627)129185299 (DE-600)52651-4 (DE-576)014456192 0268-3768 nnns volume:117 year:2021 number:7-8 day:24 month:05 pages:2213-2226 https://doi.org/10.1007/s00170-021-07281-2 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-TEC GBV_ILN_2018 GBV_ILN_2333 AR 117 2021 7-8 24 05 2213-2226 |
| spelling |
10.1007/s00170-021-07281-2 doi (DE-627)OLC2077360356 (DE-He213)s00170-021-07281-2-p DE-627 ger DE-627 rakwb eng 670 VZ Gittler, Thomas verfasserin (orcid)0000-0002-1932-2494 aut International Conference on Advanced and Competitive Manufacturing Technologies milling tool wear prediction using unsupervised machine learning 2021 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © The Author(s) 2021 Abstract Degraded or defect machine components and consumables negatively impact manufacturing quality and productivity. Diagnosing and predicting the wear or degradation status of critical machine components or parts are therefore of general interest. To tackle this challenge, data-driven approaches based on supervised machine learning principles have demonstrated promising results. However, supervised learning models capable of degradation identification require large quantities of data. In practice, run-to-failure data in large amounts is usually not available and expensive to obtain. To overcome this issue, this study proposes an unsupervised learning approach for degradation prognostics of machine tool components and consumables. It uses time series of multi-sensor signal data, which are transformed into a feature representation. The features consist of various characterizations of the time series, allowing to make different signal measurements comparable, and cluster them according to their feature values. The herewith obtained density-based clustering model is used to diagnose and predict the degradation states of components and parts in unknown conditions. The novelty in the proposed approach lies within the identification of continuous component and part degradation states based on unsupervised learning principles. The proposal is verified and demonstrated on an exemplary data set containing a small sample of run-to-failure multi-sensor signals of milling inserts and their corresponding wear state. By the application of the proposed procedure on the exemplary data set, we demonstrate that an unsupervised clustering approach is capable of separating wear data such that meaningful and accurate estimations of the part condition are possible. The advantages are its ability to cope with scarce data sets, its limited engineering and hyperparameter tuning effort, and its straightforward implementation to a multitude of degradation and wear diagnostics scenarios. Condition monitoring Machine learning Prognostics and health monitoring Unsupervised learning Machine tools Manufacturing Milling Tool wear Glasder, Magnus aut Öztürk, Elif aut Lüthi, Michel aut Weiss, Lukas aut Wegener, Konrad aut Enthalten in The international journal of advanced manufacturing technology Springer London, 1985 117(2021), 7-8 vom: 24. Mai, Seite 2213-2226 (DE-627)129185299 (DE-600)52651-4 (DE-576)014456192 0268-3768 nnns volume:117 year:2021 number:7-8 day:24 month:05 pages:2213-2226 https://doi.org/10.1007/s00170-021-07281-2 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-TEC GBV_ILN_2018 GBV_ILN_2333 AR 117 2021 7-8 24 05 2213-2226 |
| allfields_unstemmed |
10.1007/s00170-021-07281-2 doi (DE-627)OLC2077360356 (DE-He213)s00170-021-07281-2-p DE-627 ger DE-627 rakwb eng 670 VZ Gittler, Thomas verfasserin (orcid)0000-0002-1932-2494 aut International Conference on Advanced and Competitive Manufacturing Technologies milling tool wear prediction using unsupervised machine learning 2021 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © The Author(s) 2021 Abstract Degraded or defect machine components and consumables negatively impact manufacturing quality and productivity. Diagnosing and predicting the wear or degradation status of critical machine components or parts are therefore of general interest. To tackle this challenge, data-driven approaches based on supervised machine learning principles have demonstrated promising results. However, supervised learning models capable of degradation identification require large quantities of data. In practice, run-to-failure data in large amounts is usually not available and expensive to obtain. To overcome this issue, this study proposes an unsupervised learning approach for degradation prognostics of machine tool components and consumables. It uses time series of multi-sensor signal data, which are transformed into a feature representation. The features consist of various characterizations of the time series, allowing to make different signal measurements comparable, and cluster them according to their feature values. The herewith obtained density-based clustering model is used to diagnose and predict the degradation states of components and parts in unknown conditions. The novelty in the proposed approach lies within the identification of continuous component and part degradation states based on unsupervised learning principles. The proposal is verified and demonstrated on an exemplary data set containing a small sample of run-to-failure multi-sensor signals of milling inserts and their corresponding wear state. By the application of the proposed procedure on the exemplary data set, we demonstrate that an unsupervised clustering approach is capable of separating wear data such that meaningful and accurate estimations of the part condition are possible. The advantages are its ability to cope with scarce data sets, its limited engineering and hyperparameter tuning effort, and its straightforward implementation to a multitude of degradation and wear diagnostics scenarios. Condition monitoring Machine learning Prognostics and health monitoring Unsupervised learning Machine tools Manufacturing Milling Tool wear Glasder, Magnus aut Öztürk, Elif aut Lüthi, Michel aut Weiss, Lukas aut Wegener, Konrad aut Enthalten in The international journal of advanced manufacturing technology Springer London, 1985 117(2021), 7-8 vom: 24. Mai, Seite 2213-2226 (DE-627)129185299 (DE-600)52651-4 (DE-576)014456192 0268-3768 nnns volume:117 year:2021 number:7-8 day:24 month:05 pages:2213-2226 https://doi.org/10.1007/s00170-021-07281-2 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-TEC GBV_ILN_2018 GBV_ILN_2333 AR 117 2021 7-8 24 05 2213-2226 |
| allfieldsGer |
10.1007/s00170-021-07281-2 doi (DE-627)OLC2077360356 (DE-He213)s00170-021-07281-2-p DE-627 ger DE-627 rakwb eng 670 VZ Gittler, Thomas verfasserin (orcid)0000-0002-1932-2494 aut International Conference on Advanced and Competitive Manufacturing Technologies milling tool wear prediction using unsupervised machine learning 2021 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © The Author(s) 2021 Abstract Degraded or defect machine components and consumables negatively impact manufacturing quality and productivity. Diagnosing and predicting the wear or degradation status of critical machine components or parts are therefore of general interest. To tackle this challenge, data-driven approaches based on supervised machine learning principles have demonstrated promising results. However, supervised learning models capable of degradation identification require large quantities of data. In practice, run-to-failure data in large amounts is usually not available and expensive to obtain. To overcome this issue, this study proposes an unsupervised learning approach for degradation prognostics of machine tool components and consumables. It uses time series of multi-sensor signal data, which are transformed into a feature representation. The features consist of various characterizations of the time series, allowing to make different signal measurements comparable, and cluster them according to their feature values. The herewith obtained density-based clustering model is used to diagnose and predict the degradation states of components and parts in unknown conditions. The novelty in the proposed approach lies within the identification of continuous component and part degradation states based on unsupervised learning principles. The proposal is verified and demonstrated on an exemplary data set containing a small sample of run-to-failure multi-sensor signals of milling inserts and their corresponding wear state. By the application of the proposed procedure on the exemplary data set, we demonstrate that an unsupervised clustering approach is capable of separating wear data such that meaningful and accurate estimations of the part condition are possible. The advantages are its ability to cope with scarce data sets, its limited engineering and hyperparameter tuning effort, and its straightforward implementation to a multitude of degradation and wear diagnostics scenarios. Condition monitoring Machine learning Prognostics and health monitoring Unsupervised learning Machine tools Manufacturing Milling Tool wear Glasder, Magnus aut Öztürk, Elif aut Lüthi, Michel aut Weiss, Lukas aut Wegener, Konrad aut Enthalten in The international journal of advanced manufacturing technology Springer London, 1985 117(2021), 7-8 vom: 24. Mai, Seite 2213-2226 (DE-627)129185299 (DE-600)52651-4 (DE-576)014456192 0268-3768 nnns volume:117 year:2021 number:7-8 day:24 month:05 pages:2213-2226 https://doi.org/10.1007/s00170-021-07281-2 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-TEC GBV_ILN_2018 GBV_ILN_2333 AR 117 2021 7-8 24 05 2213-2226 |
| allfieldsSound |
10.1007/s00170-021-07281-2 doi (DE-627)OLC2077360356 (DE-He213)s00170-021-07281-2-p DE-627 ger DE-627 rakwb eng 670 VZ Gittler, Thomas verfasserin (orcid)0000-0002-1932-2494 aut International Conference on Advanced and Competitive Manufacturing Technologies milling tool wear prediction using unsupervised machine learning 2021 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © The Author(s) 2021 Abstract Degraded or defect machine components and consumables negatively impact manufacturing quality and productivity. Diagnosing and predicting the wear or degradation status of critical machine components or parts are therefore of general interest. To tackle this challenge, data-driven approaches based on supervised machine learning principles have demonstrated promising results. However, supervised learning models capable of degradation identification require large quantities of data. In practice, run-to-failure data in large amounts is usually not available and expensive to obtain. To overcome this issue, this study proposes an unsupervised learning approach for degradation prognostics of machine tool components and consumables. It uses time series of multi-sensor signal data, which are transformed into a feature representation. The features consist of various characterizations of the time series, allowing to make different signal measurements comparable, and cluster them according to their feature values. The herewith obtained density-based clustering model is used to diagnose and predict the degradation states of components and parts in unknown conditions. The novelty in the proposed approach lies within the identification of continuous component and part degradation states based on unsupervised learning principles. The proposal is verified and demonstrated on an exemplary data set containing a small sample of run-to-failure multi-sensor signals of milling inserts and their corresponding wear state. By the application of the proposed procedure on the exemplary data set, we demonstrate that an unsupervised clustering approach is capable of separating wear data such that meaningful and accurate estimations of the part condition are possible. The advantages are its ability to cope with scarce data sets, its limited engineering and hyperparameter tuning effort, and its straightforward implementation to a multitude of degradation and wear diagnostics scenarios. Condition monitoring Machine learning Prognostics and health monitoring Unsupervised learning Machine tools Manufacturing Milling Tool wear Glasder, Magnus aut Öztürk, Elif aut Lüthi, Michel aut Weiss, Lukas aut Wegener, Konrad aut Enthalten in The international journal of advanced manufacturing technology Springer London, 1985 117(2021), 7-8 vom: 24. Mai, Seite 2213-2226 (DE-627)129185299 (DE-600)52651-4 (DE-576)014456192 0268-3768 nnns volume:117 year:2021 number:7-8 day:24 month:05 pages:2213-2226 https://doi.org/10.1007/s00170-021-07281-2 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-TEC GBV_ILN_2018 GBV_ILN_2333 AR 117 2021 7-8 24 05 2213-2226 |
| language |
English |
| source |
Enthalten in The international journal of advanced manufacturing technology 117(2021), 7-8 vom: 24. Mai, Seite 2213-2226 volume:117 year:2021 number:7-8 day:24 month:05 pages:2213-2226 |
| sourceStr |
Enthalten in The international journal of advanced manufacturing technology 117(2021), 7-8 vom: 24. Mai, Seite 2213-2226 volume:117 year:2021 number:7-8 day:24 month:05 pages:2213-2226 |
| format_phy_str_mv |
Article |
| institution |
findex.gbv.de |
| topic_facet |
Condition monitoring Machine learning Prognostics and health monitoring Unsupervised learning Machine tools Manufacturing Milling Tool wear |
| dewey-raw |
670 |
| isfreeaccess_bool |
false |
| container_title |
The international journal of advanced manufacturing technology |
| authorswithroles_txt_mv |
Gittler, Thomas @@aut@@ Glasder, Magnus @@aut@@ Öztürk, Elif @@aut@@ Lüthi, Michel @@aut@@ Weiss, Lukas @@aut@@ Wegener, Konrad @@aut@@ |
| publishDateDaySort_date |
2021-05-24T00:00:00Z |
| hierarchy_top_id |
129185299 |
| dewey-sort |
3670 |
| id |
OLC2077360356 |
| language_de |
englisch |
| fullrecord |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">OLC2077360356</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230505144303.0</controlfield><controlfield tag="007">tu</controlfield><controlfield tag="008">221220s2021 xx ||||| 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1007/s00170-021-07281-2</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)OLC2077360356</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-He213)s00170-021-07281-2-p</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">670</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Gittler, Thomas</subfield><subfield code="e">verfasserin</subfield><subfield code="0">(orcid)0000-0002-1932-2494</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">International Conference on Advanced and Competitive Manufacturing Technologies milling tool wear prediction using unsupervised machine learning</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2021</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">ohne Hilfsmittel zu benutzen</subfield><subfield code="b">n</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Band</subfield><subfield code="b">nc</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="500" ind1=" " ind2=" "><subfield code="a">© The Author(s) 2021</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Abstract Degraded or defect machine components and consumables negatively impact manufacturing quality and productivity. Diagnosing and predicting the wear or degradation status of critical machine components or parts are therefore of general interest. To tackle this challenge, data-driven approaches based on supervised machine learning principles have demonstrated promising results. However, supervised learning models capable of degradation identification require large quantities of data. In practice, run-to-failure data in large amounts is usually not available and expensive to obtain. To overcome this issue, this study proposes an unsupervised learning approach for degradation prognostics of machine tool components and consumables. It uses time series of multi-sensor signal data, which are transformed into a feature representation. The features consist of various characterizations of the time series, allowing to make different signal measurements comparable, and cluster them according to their feature values. The herewith obtained density-based clustering model is used to diagnose and predict the degradation states of components and parts in unknown conditions. The novelty in the proposed approach lies within the identification of continuous component and part degradation states based on unsupervised learning principles. The proposal is verified and demonstrated on an exemplary data set containing a small sample of run-to-failure multi-sensor signals of milling inserts and their corresponding wear state. By the application of the proposed procedure on the exemplary data set, we demonstrate that an unsupervised clustering approach is capable of separating wear data such that meaningful and accurate estimations of the part condition are possible. The advantages are its ability to cope with scarce data sets, its limited engineering and hyperparameter tuning effort, and its straightforward implementation to a multitude of degradation and wear diagnostics scenarios.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Condition monitoring</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Machine learning</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Prognostics and health monitoring</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Unsupervised learning</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Machine tools</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Manufacturing</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Milling</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Tool wear</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Glasder, Magnus</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Öztürk, Elif</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Lüthi, Michel</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Weiss, Lukas</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Wegener, Konrad</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">The international journal of advanced manufacturing technology</subfield><subfield code="d">Springer London, 1985</subfield><subfield code="g">117(2021), 7-8 vom: 24. Mai, Seite 2213-2226</subfield><subfield code="w">(DE-627)129185299</subfield><subfield code="w">(DE-600)52651-4</subfield><subfield code="w">(DE-576)014456192</subfield><subfield code="x">0268-3768</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:117</subfield><subfield code="g">year:2021</subfield><subfield code="g">number:7-8</subfield><subfield code="g">day:24</subfield><subfield code="g">month:05</subfield><subfield code="g">pages:2213-2226</subfield></datafield><datafield tag="856" ind1="4" ind2="1"><subfield code="u">https://doi.org/10.1007/s00170-021-07281-2</subfield><subfield code="z">lizenzpflichtig</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_OLC</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-TEC</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2018</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2333</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">117</subfield><subfield code="j">2021</subfield><subfield code="e">7-8</subfield><subfield code="b">24</subfield><subfield code="c">05</subfield><subfield code="h">2213-2226</subfield></datafield></record></collection>
|
| author |
Gittler, Thomas |
| spellingShingle |
Gittler, Thomas ddc 670 misc Condition monitoring misc Machine learning misc Prognostics and health monitoring misc Unsupervised learning misc Machine tools misc Manufacturing misc Milling misc Tool wear International Conference on Advanced and Competitive Manufacturing Technologies milling tool wear prediction using unsupervised machine learning |
| authorStr |
Gittler, Thomas |
| ppnlink_with_tag_str_mv |
@@773@@(DE-627)129185299 |
| format |
Article |
| dewey-ones |
670 - Manufacturing |
| delete_txt_mv |
keep |
| author_role |
aut aut aut aut aut aut |
| collection |
OLC |
| remote_str |
false |
| illustrated |
Not Illustrated |
| issn |
0268-3768 |
| topic_title |
670 VZ International Conference on Advanced and Competitive Manufacturing Technologies milling tool wear prediction using unsupervised machine learning Condition monitoring Machine learning Prognostics and health monitoring Unsupervised learning Machine tools Manufacturing Milling Tool wear |
| topic |
ddc 670 misc Condition monitoring misc Machine learning misc Prognostics and health monitoring misc Unsupervised learning misc Machine tools misc Manufacturing misc Milling misc Tool wear |
| topic_unstemmed |
ddc 670 misc Condition monitoring misc Machine learning misc Prognostics and health monitoring misc Unsupervised learning misc Machine tools misc Manufacturing misc Milling misc Tool wear |
| topic_browse |
ddc 670 misc Condition monitoring misc Machine learning misc Prognostics and health monitoring misc Unsupervised learning misc Machine tools misc Manufacturing misc Milling misc Tool wear |
| format_facet |
Aufsätze Gedruckte Aufsätze |
| format_main_str_mv |
Text Zeitschrift/Artikel |
| carriertype_str_mv |
nc |
| hierarchy_parent_title |
The international journal of advanced manufacturing technology |
| hierarchy_parent_id |
129185299 |
| dewey-tens |
670 - Manufacturing |
| hierarchy_top_title |
The international journal of advanced manufacturing technology |
| isfreeaccess_txt |
false |
| familylinks_str_mv |
(DE-627)129185299 (DE-600)52651-4 (DE-576)014456192 |
| title |
International Conference on Advanced and Competitive Manufacturing Technologies milling tool wear prediction using unsupervised machine learning |
| ctrlnum |
(DE-627)OLC2077360356 (DE-He213)s00170-021-07281-2-p |
| title_full |
International Conference on Advanced and Competitive Manufacturing Technologies milling tool wear prediction using unsupervised machine learning |
| author_sort |
Gittler, Thomas |
| journal |
The international journal of advanced manufacturing technology |
| journalStr |
The international journal of advanced manufacturing technology |
| lang_code |
eng |
| isOA_bool |
false |
| dewey-hundreds |
600 - Technology |
| recordtype |
marc |
| publishDateSort |
2021 |
| contenttype_str_mv |
txt |
| container_start_page |
2213 |
| author_browse |
Gittler, Thomas Glasder, Magnus Öztürk, Elif Lüthi, Michel Weiss, Lukas Wegener, Konrad |
| container_volume |
117 |
| class |
670 VZ |
| format_se |
Aufsätze |
| author-letter |
Gittler, Thomas |
| doi_str_mv |
10.1007/s00170-021-07281-2 |
| normlink |
(ORCID)0000-0002-1932-2494 |
| normlink_prefix_str_mv |
(orcid)0000-0002-1932-2494 |
| dewey-full |
670 |
| title_sort |
international conference on advanced and competitive manufacturing technologies milling tool wear prediction using unsupervised machine learning |
| title_auth |
International Conference on Advanced and Competitive Manufacturing Technologies milling tool wear prediction using unsupervised machine learning |
| abstract |
Abstract Degraded or defect machine components and consumables negatively impact manufacturing quality and productivity. Diagnosing and predicting the wear or degradation status of critical machine components or parts are therefore of general interest. To tackle this challenge, data-driven approaches based on supervised machine learning principles have demonstrated promising results. However, supervised learning models capable of degradation identification require large quantities of data. In practice, run-to-failure data in large amounts is usually not available and expensive to obtain. To overcome this issue, this study proposes an unsupervised learning approach for degradation prognostics of machine tool components and consumables. It uses time series of multi-sensor signal data, which are transformed into a feature representation. The features consist of various characterizations of the time series, allowing to make different signal measurements comparable, and cluster them according to their feature values. The herewith obtained density-based clustering model is used to diagnose and predict the degradation states of components and parts in unknown conditions. The novelty in the proposed approach lies within the identification of continuous component and part degradation states based on unsupervised learning principles. The proposal is verified and demonstrated on an exemplary data set containing a small sample of run-to-failure multi-sensor signals of milling inserts and their corresponding wear state. By the application of the proposed procedure on the exemplary data set, we demonstrate that an unsupervised clustering approach is capable of separating wear data such that meaningful and accurate estimations of the part condition are possible. The advantages are its ability to cope with scarce data sets, its limited engineering and hyperparameter tuning effort, and its straightforward implementation to a multitude of degradation and wear diagnostics scenarios. © The Author(s) 2021 |
| abstractGer |
Abstract Degraded or defect machine components and consumables negatively impact manufacturing quality and productivity. Diagnosing and predicting the wear or degradation status of critical machine components or parts are therefore of general interest. To tackle this challenge, data-driven approaches based on supervised machine learning principles have demonstrated promising results. However, supervised learning models capable of degradation identification require large quantities of data. In practice, run-to-failure data in large amounts is usually not available and expensive to obtain. To overcome this issue, this study proposes an unsupervised learning approach for degradation prognostics of machine tool components and consumables. It uses time series of multi-sensor signal data, which are transformed into a feature representation. The features consist of various characterizations of the time series, allowing to make different signal measurements comparable, and cluster them according to their feature values. The herewith obtained density-based clustering model is used to diagnose and predict the degradation states of components and parts in unknown conditions. The novelty in the proposed approach lies within the identification of continuous component and part degradation states based on unsupervised learning principles. The proposal is verified and demonstrated on an exemplary data set containing a small sample of run-to-failure multi-sensor signals of milling inserts and their corresponding wear state. By the application of the proposed procedure on the exemplary data set, we demonstrate that an unsupervised clustering approach is capable of separating wear data such that meaningful and accurate estimations of the part condition are possible. The advantages are its ability to cope with scarce data sets, its limited engineering and hyperparameter tuning effort, and its straightforward implementation to a multitude of degradation and wear diagnostics scenarios. © The Author(s) 2021 |
| abstract_unstemmed |
Abstract Degraded or defect machine components and consumables negatively impact manufacturing quality and productivity. Diagnosing and predicting the wear or degradation status of critical machine components or parts are therefore of general interest. To tackle this challenge, data-driven approaches based on supervised machine learning principles have demonstrated promising results. However, supervised learning models capable of degradation identification require large quantities of data. In practice, run-to-failure data in large amounts is usually not available and expensive to obtain. To overcome this issue, this study proposes an unsupervised learning approach for degradation prognostics of machine tool components and consumables. It uses time series of multi-sensor signal data, which are transformed into a feature representation. The features consist of various characterizations of the time series, allowing to make different signal measurements comparable, and cluster them according to their feature values. The herewith obtained density-based clustering model is used to diagnose and predict the degradation states of components and parts in unknown conditions. The novelty in the proposed approach lies within the identification of continuous component and part degradation states based on unsupervised learning principles. The proposal is verified and demonstrated on an exemplary data set containing a small sample of run-to-failure multi-sensor signals of milling inserts and their corresponding wear state. By the application of the proposed procedure on the exemplary data set, we demonstrate that an unsupervised clustering approach is capable of separating wear data such that meaningful and accurate estimations of the part condition are possible. The advantages are its ability to cope with scarce data sets, its limited engineering and hyperparameter tuning effort, and its straightforward implementation to a multitude of degradation and wear diagnostics scenarios. © The Author(s) 2021 |
| collection_details |
GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-TEC GBV_ILN_2018 GBV_ILN_2333 |
| container_issue |
7-8 |
| title_short |
International Conference on Advanced and Competitive Manufacturing Technologies milling tool wear prediction using unsupervised machine learning |
| url |
https://doi.org/10.1007/s00170-021-07281-2 |
| remote_bool |
false |
| author2 |
Glasder, Magnus Öztürk, Elif Lüthi, Michel Weiss, Lukas Wegener, Konrad |
| author2Str |
Glasder, Magnus Öztürk, Elif Lüthi, Michel Weiss, Lukas Wegener, Konrad |
| ppnlink |
129185299 |
| mediatype_str_mv |
n |
| isOA_txt |
false |
| hochschulschrift_bool |
false |
| doi_str |
10.1007/s00170-021-07281-2 |
| up_date |
2024-07-03T15:08:38.035Z |
| _version_ |
1803570976437305344 |
| fullrecord_marcxml |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">OLC2077360356</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230505144303.0</controlfield><controlfield tag="007">tu</controlfield><controlfield tag="008">221220s2021 xx ||||| 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1007/s00170-021-07281-2</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)OLC2077360356</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-He213)s00170-021-07281-2-p</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">670</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Gittler, Thomas</subfield><subfield code="e">verfasserin</subfield><subfield code="0">(orcid)0000-0002-1932-2494</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">International Conference on Advanced and Competitive Manufacturing Technologies milling tool wear prediction using unsupervised machine learning</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2021</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">ohne Hilfsmittel zu benutzen</subfield><subfield code="b">n</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Band</subfield><subfield code="b">nc</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="500" ind1=" " ind2=" "><subfield code="a">© The Author(s) 2021</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Abstract Degraded or defect machine components and consumables negatively impact manufacturing quality and productivity. Diagnosing and predicting the wear or degradation status of critical machine components or parts are therefore of general interest. To tackle this challenge, data-driven approaches based on supervised machine learning principles have demonstrated promising results. However, supervised learning models capable of degradation identification require large quantities of data. In practice, run-to-failure data in large amounts is usually not available and expensive to obtain. To overcome this issue, this study proposes an unsupervised learning approach for degradation prognostics of machine tool components and consumables. It uses time series of multi-sensor signal data, which are transformed into a feature representation. The features consist of various characterizations of the time series, allowing to make different signal measurements comparable, and cluster them according to their feature values. The herewith obtained density-based clustering model is used to diagnose and predict the degradation states of components and parts in unknown conditions. The novelty in the proposed approach lies within the identification of continuous component and part degradation states based on unsupervised learning principles. The proposal is verified and demonstrated on an exemplary data set containing a small sample of run-to-failure multi-sensor signals of milling inserts and their corresponding wear state. By the application of the proposed procedure on the exemplary data set, we demonstrate that an unsupervised clustering approach is capable of separating wear data such that meaningful and accurate estimations of the part condition are possible. The advantages are its ability to cope with scarce data sets, its limited engineering and hyperparameter tuning effort, and its straightforward implementation to a multitude of degradation and wear diagnostics scenarios.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Condition monitoring</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Machine learning</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Prognostics and health monitoring</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Unsupervised learning</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Machine tools</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Manufacturing</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Milling</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Tool wear</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Glasder, Magnus</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Öztürk, Elif</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Lüthi, Michel</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Weiss, Lukas</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Wegener, Konrad</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">The international journal of advanced manufacturing technology</subfield><subfield code="d">Springer London, 1985</subfield><subfield code="g">117(2021), 7-8 vom: 24. Mai, Seite 2213-2226</subfield><subfield code="w">(DE-627)129185299</subfield><subfield code="w">(DE-600)52651-4</subfield><subfield code="w">(DE-576)014456192</subfield><subfield code="x">0268-3768</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:117</subfield><subfield code="g">year:2021</subfield><subfield code="g">number:7-8</subfield><subfield code="g">day:24</subfield><subfield code="g">month:05</subfield><subfield code="g">pages:2213-2226</subfield></datafield><datafield tag="856" ind1="4" ind2="1"><subfield code="u">https://doi.org/10.1007/s00170-021-07281-2</subfield><subfield code="z">lizenzpflichtig</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_OLC</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-TEC</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2018</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2333</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">117</subfield><subfield code="j">2021</subfield><subfield code="e">7-8</subfield><subfield code="b">24</subfield><subfield code="c">05</subfield><subfield code="h">2213-2226</subfield></datafield></record></collection>
|
| score |
7.401326 |