110 http://isa.epfl.ch/imoniteur_ISAP/ itffichecours.txt?path=EPFL.Etu.FicheCours.HeaderFR itffichecours.txt?path=EPFL.Etu.FicheCours.GlobalNav_js fr 2026 942623 6683147 942623 2301874614 2301874614 0 0 Genie civil GC ENAC Faculté de l'environnement naturel, architectural et construit School of Architecture, Civil and Environmental Engineering !itffichecours.htm?ww_i_matiere=3200276537&ww_x_anneeAcad=2301874614&ww_i_section=942623&ww_i_niveau=6683147 1696552884 1696552963 2023-2024 COURSE BOOKLET CIVIL-426 Machine learning for predictive maintenance applications Machine learning for predictive maintenance applications Lecturers Fink Olga Language of teaching English Cursus Civil Engineering(2023-2024, GC - Master 2022)
Civil Engineering(2023-2024, GC - Master 2023)
Data and Internet of Things minor(2023-2024, Data and Internet of Things minor 2023-24)
Robotics(2023-2024, MT_RO - Master 2022)
Robotics(2023-2024, MT_RO - Master 2023)
SemesterMand.OptionFilières
Hx
MA1, MA3xA
MA1, MA3xC D
 Credits 4 Withdrawal Unauthorized It is not allowed to withdraw from this subject after the registration deadline. Session Winter Workload 120h Exam During the semester Number of positions Il n'est pas autorisé de se retirer de cette matière après le délai d'inscription. Semester Fall Weeks 14 Hours 4 weekly
Courses 2 weekly
Exercises 2 weekly
Study planSemesterMand.OptionFilières
Génie civil 2023-24MA1xC D
Génie civil 2023-24MA3xC D
Minor : Data and Internet of Things 2023-24Hx
Robotique 2023-24MA1xA
Robotique 2023-24MA3xA
Cursus Sem. Type
Civil Engineering MA1, MA3 Opt.
Data and Internet of Things minor H Opt.
Robotics MA1, MA3 Opt.
Summary The course aims at developing machine learning algorithms that are able to use condition monitoring data efficiently and detect occurring faults in complex industrial assets, isolate their root cause and ultimately predict the remaining useful lifetime. Content

Early and reliable detection, isolation and prediction of faulty system conditions enables the operators to take recovery actions to prevent critical system failures and ensure a high level of availability and safety. This is particularly crucial for complex systems such as infrastructures, power plants and aircraft engines. Therefore, their system condition is increasingly tightly monitored by a large number of diverse condition monitoring sensors. With the increased availability of data on system condition on the one hand, and the increased complexity of explicit physics-based system models on the other hand, the application of data-driven approaches for predictive maintenance has been recently increasing.
This course provides insights and hands-on experience in selecting, designing, optimizing and evaluating machine learning algorithms to tackle the challenges faced by maintenance systems of complex engineered systems.

Specific topics include:

-Introduction to condition monitoring and predictive maintenance systems

-Feature extraction and selection methodology

-Machine learning algorithms for fault detection and fault diagnostics

-End-to-end learning architectures for fault detection and fault diagnostics

-Unsupervised and semi-supervised learning algorithms for predictive maintenance

-Deep learning algorithms for predicting the remaining useful lifetime

-Performance evaluation of the algorithms

-Predictive maintenance systems at fleet level

-Domain adaptation for fault diagnostics

-Explainable machine learning algorithms for predictive maintenance

-Introduction to decision support systems for maintenance applications

-Benefits and costs of predictive maintenance

 Keywords

machine learning; predictive maintenance, fault detection, fault diagnostics, fault prognostics

 

 Learning Prerequisites Required courses

Mandatory pre-requisite course: Introduction to machine learning for engineers or other machine learning courses

 Recommended courses

 

 

 Learning Outcomes By the end of the course, the student must be able to:
  • Define the learning problem in way that allows its solution based on existing constrains such as lack of fault samples
  • Design data-driven predictive maintenance applications for complex engineered systems from raw condition monitoring data
  • Assess / Evaluate the performance of the applied algorithms
  • Choose machine learning algorithms for fault detection, diagnostics and prognostics
  • Interpret the results of the algorithms
 Teaching methods

Lectures, excercises, final project

 Assessment methods

Performance will be assessed during the semester based on
-4 exercises, requiring the students to perform defined sub-tasks for designing a predictive maintenance system (70% of the final grade in total)
-Final project on a real case study (and real data) of designing a predictive maintenance system based on raw condition monitoring signals of a complex engineered system, requiring a report (including the implementation) and a presentation (30% of the final grade)

 Supervision Office hours Yes Assistant.e.s Yes Forum Yes Resources Moodle Link Génie civil, 2023-2024, Master semestre 1 Civil Engineering, 2023-2024, Master semester 1 Ecole polytechnique fédérale de Lausanne EPFL Ecole polytechnique fédérale de Lausanne EPFL 2023-2024 Master semestre 1 MA1 HIVER Master semester 1 MA1 Génie civil GC Civil Engineering GC
Génie civil GC Civil Engineering GC
C D optionnel optional
2 Cours Courses Heure(s) hebdo x 14 semaines Hour(s) per week x 14 weeks H hebdo H hebdo Fink Olga 349138
Génie civil GC Civil Engineering GC
2 Exercices Exercises Heure(s) hebdo x 14 semaines Hour(s) per week x 14 weeks H hebdo H hebdo Fink Olga 349138
Génie civil GC Civil Engineering GC
3200276537 Machine learning for predictive maintenance applications Machine learning for predictive maintenance applications 4
Pendant le semestre During the semester Crédit Credits 4 Session hiver Session winter HIV HIV
Génie civil, 2023-2024, Master semestre 3 Civil Engineering, 2023-2024, Master semester 3 Ecole polytechnique fédérale de Lausanne EPFL Ecole polytechnique fédérale de Lausanne EPFL 2023-2024 Master semestre 3 MA3 HIVER Master semester 3 MA3 Génie civil GC Civil Engineering GC
Génie civil GC Civil Engineering GC
C D optionnel optional
2 Cours Courses Heure(s) hebdo x 14 semaines Hour(s) per week x 14 weeks H hebdo H hebdo Fink Olga 349138
Génie civil GC Civil Engineering GC
2 Exercices Exercises Heure(s) hebdo x 14 semaines Hour(s) per week x 14 weeks H hebdo H hebdo Fink Olga 349138
Génie civil GC Civil Engineering GC
3200276537 Machine learning for predictive maintenance applications Machine learning for predictive maintenance applications 4
Pendant le semestre During the semester Crédit Credits 4 Session hiver Session winter HIV HIV
Robotique, 2023-2024, Master semestre 1 Robotics, 2023-2024, Master semester 1 Ecole polytechnique fédérale de Lausanne EPFL Ecole polytechnique fédérale de Lausanne EPFL 2023-2024 Master semestre 1 MA1 HIVER Master semester 1 MA1 Robotique MT_RO Robotics MT_RO
Microtechnique MT Microengineering MT
A optionnel optional
2 Cours Courses Heure(s) hebdo x 14 semaines Hour(s) per week x 14 weeks H hebdo H hebdo Fink Olga 349138
Génie civil GC Civil Engineering GC
2 Exercices Exercises Heure(s) hebdo x 14 semaines Hour(s) per week x 14 weeks H hebdo H hebdo Fink Olga 349138
Génie civil GC Civil Engineering GC
3200276537 Machine learning for predictive maintenance applications Machine learning for predictive maintenance applications 4
Pendant le semestre During the semester Crédit Credits 4 Session hiver Session winter HIV HIV
Robotique, 2023-2024, Master semestre 3 Robotics, 2023-2024, Master semester 3 Ecole polytechnique fédérale de Lausanne EPFL Ecole polytechnique fédérale de Lausanne EPFL 2023-2024 Master semestre 3 MA3 HIVER Master semester 3 MA3 Robotique MT_RO Robotics MT_RO
Microtechnique MT Microengineering MT
A optionnel optional
2 Cours Courses Heure(s) hebdo x 14 semaines Hour(s) per week x 14 weeks H hebdo H hebdo Fink Olga 349138
Génie civil GC Civil Engineering GC
2 Exercices Exercises Heure(s) hebdo x 14 semaines Hour(s) per week x 14 weeks H hebdo H hebdo Fink Olga 349138
Génie civil GC Civil Engineering GC
3200276537 Machine learning for predictive maintenance applications Machine learning for predictive maintenance applications 4
Pendant le semestre During the semester Crédit Credits 4 Session hiver Session winter HIV HIV
Data and Internet of Things minor, 2023-2024, Semestre automne Data and Internet of Things minor, 2023-2024, Autumn semester Ecole polytechnique fédérale de Lausanne EPFL Ecole polytechnique fédérale de Lausanne EPFL 2023-2024 Semestre automne H HIVER Autumn semester H Data and Internet of Things minor MIN_IOT Data and Internet of Things minor MIN_IOT
optionnel optional
2 Cours Courses Heure(s) hebdo x 14 semaines Hour(s) per week x 14 weeks H hebdo H hebdo Fink Olga 349138
Génie civil GC Civil Engineering GC
2 Exercices Exercises Heure(s) hebdo x 14 semaines Hour(s) per week x 14 weeks H hebdo H hebdo Fink Olga 349138
Génie civil GC Civil Engineering GC
3200276537 Machine learning for predictive maintenance applications Machine learning for predictive maintenance applications 4
Pendant le semestre During the semester Crédit Credits 4 Session hiver Session winter HIV HIV
BALISES_TEXTES BOOLEAN_Symbol BaliseJS_debut BaliseJS_fin Balise_debut Balise_fin FO_debut FO_fin HTML_debut HTML_fin JS_debut JS_fin BALISE_BOLD BOOLEAN_Symbol BaliseJS_debut \x5bb\x5d BaliseJS_fin \x5b\x2fb\x5d Balise_debut [b] Balise_fin [/b] FO_debut font-weight=bold FO_fin font-weight=normal HTML_debut <b> HTML_fin </b> JS_debut \x3cb\x3e JS_fin \x3c\x2fb\x3e BALISE_ITALIC BOOLEAN_Symbol BaliseJS_debut \x5bi\x5d BaliseJS_fin \x5b\x2fi\x5d Balise_debut [i] Balise_fin [/i] FO_debut font-style=italic FO_fin font-style=normal HTML_debut <i> HTML_fin </i> JS_debut \x3ci\x3e JS_fin \x3c\x2fi\x3e BALISE_RED BOOLEAN_Symbol BaliseJS_debut \x5bred\x5d BaliseJS_fin \x5b\x2fred\x5d Balise_debut [red] Balise_fin [/red] FO_debut color=#990033 FO_fin color=black HTML_debut <span style="color:#990033;"> HTML_fin </span> JS_debut \x3cspan style="color:#990033;"\x3e JS_fin \x3c\x2fspan\x3e BALISE_TAB BOOLEAN_Symbol BaliseJS_debut \x5btab\x5d BaliseJS_fin Balise_debut [tab] Balise_fin FO_debut [inline]=&#160;&#160;&#160;&#160;&#160;&#160;&#160;&#160; FO_fin HTML_debut <img src="/images/gestacplus/base/pixel.gif" width="40" height="1"/> HTML_fin JS_debut \x3cimg src="\x2fimages\x2fgestacplus\x2fbase\x2fpixel.gif" width="40" height="1"\x2f\x3e JS_fin BALISE_LIST BOOLEAN_Symbol BaliseJS_debut \x5bli\x5d BaliseJS_fin Balise_debut [li] Balise_fin FO_debut [inline]=&#x2022;&#160;&#160; FO_fin HTML_debut &#x2022;&#160;&#160; HTML_fin JS_debut \x26#x2022;\x26#160;\x26#160; JS_fin CODE5045487 BOOLEAN_Symbol BaliseJS_debut \x5b\x5d BaliseJS_fin Balise_debut [] Balise_fin FO_debut [inline]=&#160; FO_fin HTML_debut &#160; HTML_fin JS_debut \x26#160; JS_fin BALISE_GREEN BOOLEAN_Symbol BaliseJS_debut \x5bgreen\x5d BaliseJS_fin \x5b\x2fgreen\x5d Balise_debut [green] Balise_fin [/green] FO_debut color=#008000 FO_fin color=black HTML_debut <span style="color:#008000;"> HTML_fin </span> JS_debut \x3cspan style="color:#008000;"\x3e JS_fin \x3c\x2fspan\x3e CODE7508550 BOOLEAN_Symbol BaliseJS_debut \x5bblue\x5d BaliseJS_fin \x5b\x2fblue\x5d Balise_debut [blue] Balise_fin [/blue] FO_debut color=#0080FF FO_fin color=black HTML_debut <span style="color:#0080FF;"> HTML_fin </span> JS_debut \x3cspan style="color:#0080FF;"\x3e JS_fin \x3c\x2fspan\x3e BALISE_COURIER BOOLEAN_Symbol BaliseJS_debut \x5bcourier\x5d BaliseJS_fin \x5b\x2fcourier\x5d Balise_debut [courier] Balise_fin [/courier] FO_debut font-family=Courier FO_fin font-family= HTML_debut <font style="font-family:Courier;"> HTML_fin </font> JS_debut \x3cfont style="font-family:Courier;"\x3e JS_fin \x3c\x2ffont\x3e BALISE_SIZE20 BOOLEAN_Symbol BaliseJS_debut \x5b20\x5d BaliseJS_fin \x5b\x2f20\x5d Balise_debut [20] Balise_fin [/20] FO_debut font-size=20pt FO_fin font-size= HTML_debut <font style="font-size:20pt;"> HTML_fin </font> JS_debut \x3cfont style="font-size:20pt;"\x3e JS_fin \x3c\x2ffont\x3e BALISE_SIZE16 BOOLEAN_Symbol BaliseJS_debut \x5b16\x5d BaliseJS_fin \x5b\x2f16\x5d Balise_debut [16] Balise_fin [/16] FO_debut font-size=16pt FO_fin font-size= HTML_debut <font style="font-size:16pt;"> HTML_fin </font> JS_debut \x3cfont style="font-size:16pt;"\x3e JS_fin \x3c\x2ffont\x3e BALISE_SIZE12 BOOLEAN_Symbol BaliseJS_debut \x5b12\x5d BaliseJS_fin \x5b\x2f12\x5d Balise_debut [12] Balise_fin [/12] FO_debut font-size=12pt FO_fin font-size= HTML_debut <font style="font-size:12pt;"> HTML_fin </font> JS_debut \x3cfont style="font-size:12pt;"\x3e JS_fin \x3c\x2ffont\x3e BALISE_SIZE8 BOOLEAN_Symbol BaliseJS_debut \x5b8\x5d BaliseJS_fin \x5b\x2f8\x5d Balise_debut [8] Balise_fin [/8] FO_debut font-size=8pt FO_fin font-size= HTML_debut <font style="font-size:8pt;"> HTML_fin </font> JS_debut \x3cfont style="font-size:8pt;"\x3e JS_fin \x3c\x2ffont\x3e BALISE_BLACKBACK BOOLEAN_Symbol BaliseJS_debut \x5bblackback\x5d BaliseJS_fin \x5b\x2fblackback\x5d Balise_debut [blackback] Balise_fin [/blackback] FO_debut background-color=black FO_fin background-color=white HTML_debut <span style="background-color:black;"> HTML_fin </span> JS_debut \x3cspan style="background-color:black;"\x3e JS_fin \x3c\x2fspan\x3e BALISE_WHITE BOOLEAN_Symbol BaliseJS_debut \x5bwhite\x5d BaliseJS_fin \x5b\x2fwhite\x5d Balise_debut [white] Balise_fin [/white] FO_debut color=white FO_fin color=black HTML_debut <span style="color:white;"> HTML_fin </span> JS_debut \x3cspan style="color:white;"\x3e JS_fin \x3c\x2fspan\x3e CODE47534071 BOOLEAN_Symbol 1 BaliseJS_debut \x5bbeta\x5d BaliseJS_fin Balise_debut [beta] Balise_fin FO_debut [inline]=&#946; FO_fin HTML_debut &#946; HTML_fin JS_debut \x26#946; JS_fin CODE47534435 BOOLEAN_Symbol 1 BaliseJS_debut \x5balpha\x5d BaliseJS_fin Balise_debut [alpha] Balise_fin FO_debut [inline]=&#945; FO_fin HTML_debut &#945; HTML_fin JS_debut \x26#945; JS_fin CODE47551722 BOOLEAN_Symbol BaliseJS_debut \x5bsub\x5d BaliseJS_fin \x5b\x2fsub\x5d Balise_debut [sub] Balise_fin [/sub] FO_debut vertical-align=sub FO_fin vertical-align=baseline HTML_debut <sub> HTML_fin </sub> JS_debut \x3csub\x3e JS_fin \x3c\x2fsub\x3e CODE48535424 BOOLEAN_Symbol 1 BaliseJS_debut \x5bLAMBDA\x5d BaliseJS_fin Balise_debut [LAMBDA] Balise_fin FO_debut [inline]=&#923; FO_fin HTML_debut &#923; HTML_fin JS_debut \x26#923; JS_fin CODE48535666 BOOLEAN_Symbol 1 BaliseJS_debut \x5blambda\x5d BaliseJS_fin Balise_debut [lambda] Balise_fin FO_debut [inline]=&#955; FO_fin HTML_debut &#955; HTML_fin JS_debut \x26#955; JS_fin CODE47551793 BOOLEAN_Symbol BaliseJS_debut \x5bsup\x5d BaliseJS_fin \x5b\x2fsup\x5d Balise_debut [sup] Balise_fin [/sup] FO_debut vertical-align=super FO_fin vertical-align=baseline HTML_debut <sup> HTML_fin </sup> JS_debut \x3csup\x3e JS_fin \x3c\x2fsup\x3e CODE56031535 BOOLEAN_Symbol 1 BaliseJS_debut \x5bdelta\x5d BaliseJS_fin Balise_debut [delta] Balise_fin FO_debut [inline]=&#948; FO_fin HTML_debut &#948; HTML_fin JS_debut \x26#948; JS_fin CODE56073309 BOOLEAN_Symbol 1 BaliseJS_debut \x5bpi\x5d BaliseJS_fin Balise_debut [pi] Balise_fin FO_debut [inline]=&#960; FO_fin HTML_debut &#960; HTML_fin JS_debut \x26#960; JS_fin CODE56074095 BOOLEAN_Symbol 1 BaliseJS_debut \x5bDELTA\x5d BaliseJS_fin Balise_debut [DELTA] Balise_fin FO_debut [inline]=&#916; FO_fin HTML_debut &#916; HTML_fin JS_debut \x26#916; JS_fin CODE56074172 BOOLEAN_Symbol 1 BaliseJS_debut \x5bMU\x5d BaliseJS_fin Balise_debut [MU] Balise_fin FO_debut [inline]=&#924; FO_fin HTML_debut &#924; HTML_fin JS_debut \x26#924; JS_fin CODE56074264 BOOLEAN_Symbol 1 BaliseJS_debut \x5bPI\x5d BaliseJS_fin Balise_debut [PI] Balise_fin FO_debut [inline]=&#928; FO_fin HTML_debut &#928; HTML_fin JS_debut \x26#928; JS_fin CODE56074328 BOOLEAN_Symbol 1 BaliseJS_debut \x5bSIGMA\x5d BaliseJS_fin Balise_debut [SIGMA] Balise_fin FO_debut [inline]=&#931; FO_fin HTML_debut &#931; HTML_fin JS_debut \x26#931; JS_fin CODE56075056 BOOLEAN_Symbol 1 BaliseJS_debut \x5bALPHA\x5d BaliseJS_fin Balise_debut [ALPHA] Balise_fin FO_debut [inline]=&#913; FO_fin HTML_debut &#913; HTML_fin JS_debut \x26#913; JS_fin CODE56075186 BOOLEAN_Symbol 1 BaliseJS_debut \x5bBETA\x5d BaliseJS_fin Balise_debut [BETA] Balise_fin FO_debut [inline]=&#914; FO_fin HTML_debut &#914; HTML_fin JS_debut \x26#914; JS_fin BALISE_SYMBOL BOOLEAN_Symbol BaliseJS_debut \x5bsymbol\x5d BaliseJS_fin \x5b\x2fsymbol\x5d Balise_debut [symbol] Balise_fin [/symbol] FO_debut font-family=Symbol FO_fin font-family= HTML_debut <font style="font-family:Symbol;"> HTML_fin </font> JS_debut \x3cfont style="font-family:Symbol;"\x3e JS_fin \x3c\x2ffont\x3e CODE56072935 BOOLEAN_Symbol 1 BaliseJS_debut \x5bmu\x5d BaliseJS_fin Balise_debut [mu] Balise_fin FO_debut [inline]=&#956; FO_fin HTML_debut &#956; HTML_fin JS_debut \x26#956; JS_fin CODE56073842 BOOLEAN_Symbol 1 BaliseJS_debut \x5bsigma\x5d BaliseJS_fin Balise_debut [sigma] Balise_fin FO_debut [inline]=&#963; FO_fin HTML_debut &#963; HTML_fin JS_debut \x26#963; JS_fin CODE68199232 BOOLEAN_Symbol 1 BaliseJS_debut \x5bphi\x5d BaliseJS_fin Balise_debut [phi] Balise_fin FO_debut [inline]=&#966; FO_fin HTML_debut &#966; HTML_fin JS_debut \x26#966; JS_fin CODE68199285 BOOLEAN_Symbol 1 BaliseJS_debut \x5bPHI\x5d BaliseJS_fin Balise_debut [PHI] Balise_fin FO_debut [inline]=&#934; FO_fin HTML_debut &#934; HTML_fin JS_debut \x26#934; JS_fin CODE68199991 BOOLEAN_Symbol 1 BaliseJS_debut \x5bgamma\x5d BaliseJS_fin Balise_debut [gamma] Balise_fin FO_debut [inline]=&#947; FO_fin HTML_debut &#947; HTML_fin JS_debut \x26#947; JS_fin CODE68200031 BOOLEAN_Symbol 1 BaliseJS_debut \x5bGAMMA\x5d BaliseJS_fin Balise_debut [GAMMA] Balise_fin FO_debut [inline]=&#915; FO_fin HTML_debut &#915; HTML_fin JS_debut \x26#915; JS_fin CODE68200077 BOOLEAN_Symbol 1 BaliseJS_debut \x5bomega\x5d BaliseJS_fin Balise_debut [omega] Balise_fin FO_debut [inline]=&#969; FO_fin HTML_debut &#969; HTML_fin JS_debut \x26#969; JS_fin CODE68200150 BOOLEAN_Symbol 1 BaliseJS_debut \x5bOMEGA\x5d BaliseJS_fin Balise_debut [OMEGA] Balise_fin FO_debut [inline]=&#937; FO_fin HTML_debut &#937; HTML_fin JS_debut \x26#937; JS_fin CODE72092691 BOOLEAN_Symbol BaliseJS_debut \x5beta\x5d BaliseJS_fin Balise_debut [eta] Balise_fin FO_debut [inline]=&#951; FO_fin HTML_debut &#951; HTML_fin JS_debut \x26#951; JS_fin CODE72092805 BOOLEAN_Symbol BaliseJS_debut \x5bETA\x5d BaliseJS_fin Balise_debut [ETA] Balise_fin FO_debut [inline]=&#919; FO_fin HTML_debut &#919; HTML_fin JS_debut \x26#919; JS_fin BALISE_SOULIGNER BOOLEAN_Symbol BaliseJS_debut \x5bu\x5d BaliseJS_fin \x5b\x2fu\x5d Balise_debut [u] Balise_fin [/u] FO_debut text-decoration=underline FO_fin text-decoration=none HTML_debut <u> HTML_fin </u> JS_debut \x3cu\x3e JS_fin \x3c\x2fu\x3e CODE72092388 BOOLEAN_Symbol BaliseJS_debut \x5bpsi\x5d BaliseJS_fin Balise_debut [psi] Balise_fin FO_debut [inline]=&#968; FO_fin HTML_debut &#968; HTML_fin JS_debut \x26#968; JS_fin CODE72092541 BOOLEAN_Symbol BaliseJS_debut \x5bPSI\x5d BaliseJS_fin Balise_debut [PSI] Balise_fin FO_debut [inline]=&#936; FO_fin HTML_debut &#936; HTML_fin JS_debut \x26#936; JS_fin CODE140502511 BOOLEAN_Symbol 1 BaliseJS_debut \x5brho\x5d BaliseJS_fin Balise_debut [rho] Balise_fin FO_debut [inline]=&#961; FO_fin HTML_debut &#961; HTML_fin JS_debut \x26#961; JS_fin CODE140504636 BOOLEAN_Symbol 1 BaliseJS_debut \x5bRHO\x5d BaliseJS_fin Balise_debut [RHO] Balise_fin FO_debut [inline]=&#929; FO_fin HTML_debut &#929; HTML_fin JS_debut \x26#929; JS_fin CODE148292791 BOOLEAN_Symbol BaliseJS_debut \x5bepsilon\x5d BaliseJS_fin Balise_debut [epsilon] Balise_fin FO_debut [inline]=&#949; FO_fin HTML_debut &#949; HTML_fin JS_debut \x26#949; JS_fin CODE169976220 BOOLEAN_Symbol BaliseJS_debut \x5blig\x5d BaliseJS_fin Balise_debut [lig] Balise_fin FO_debut [inline]=&#x203A;&#160;&#160; FO_fin HTML_debut &#x203A;&#160;&#160; HTML_fin JS_debut \x26#x203A;\x26#160;\x26#160; JS_fin CODE148292899 BOOLEAN_Symbol BaliseJS_debut \x5bEPSILON\x5d BaliseJS_fin Balise_debut [EPSILON] Balise_fin FO_debut [inline]=&#917; FO_fin HTML_debut &#917; HTML_fin JS_debut \x26#917; JS_fin BALISETXT_SAUT BOOLEAN_Symbol BaliseJS_debut \x5bbr\x2f\x5d BaliseJS_fin Balise_debut [br/] Balise_fin FO_debut FO_fin HTML_debut <br/> HTML_fin JS_debut \x3cbr\x2f\x3e JS_fin 3200276537 Machine learning for predictive maintenance applications Machine learning for predictive maintenance applications anglais Fink Olga 349138 942623