Selbstgesteuertes Projekt
Predictive Maintenance: Industrial ML for Fault Detection
Condition-Monitoring Engineer · KI / ML · August 2026
Eine ProoV-Fallstudie · Lernprojekt, kein Arbeitsverhältnis
Built an end-to-end rolling-bearing fault detector on vibration data: plotted and interpreted a faulty snapshot, used kurtosis to capture impulsive behavior, trained a shallow decision tree on training bearings only, and evaluated it on held-out healthy and faulty bearings. The final memo defended a 0.60 alarm threshold with catch-rate, false-alarm, and cost figures, and identified the outer race as the likely fault location.
Bewertet nach
- Feature engineering (signal to honest numbers)25%
- Held-out evaluation (honest measurement)25%
- Cost-based threshold decision + memo25%
- Compact model + embedded-budget justification15%
- Plain-language explanation10%
Bestanden · Bestehensgrenze 60/100
Was herausstach6
- Used a depth-capped decision tree and explicitly stated depth 2 and 7 nodes against an embedded budget
- Reported held-out catch-rate and false-alarm rate rather than evaluating on training data
- Wrote a maintenance memo that ties the threshold to cost trade-offs and explains the fault in plain language
- Leakage-Free Feature Engineering
- Honest Held-Out Evaluation
- Compact Interpretable Modeling
Meine eingereichte Arbeit18 Aufgaben
10 Aufgaben · 6.1k Zeichen · Python · 8 Textantworten · 407 Wörter
- Initial Prediction62 Zeichen
- Load Plot Signal CodePython · 1.9k Zeichen
- Load Plot Signal205 Zeichen
- Example Rms WorkedPython · 697 Zeichen
- Time Features143 Zeichen
- Freq FeaturesPython · 927 Zeichen
- Train Classifier363 Zeichen
- Evaluation Heldout288 Zeichen
- Threshold Decision332 Zeichen
- Decision Memo1.2k Zeichen
- Initial Prediction9 Wörter
- Load Plot Signal Code164 Wörter
- Load Plot Signal15 Wörter
- Example Rms Worked72 Wörter
- Time Features10 Wörter
- Freq Features82 Wörter
- Train Classifier31 Wörter
- Evaluation Heldout24 Wörter
Bewusst zusammengefasst — der eingereichte Code und die Texte bleiben privat, damit diese Seite nicht als Lösungsvorlage dient. Die vollständige Einreichung steht hinter dem verifizierten Zertifikat.