Selbstgesteuertes Projekt
Predictive Maintenance: Industrial ML for Fault Detection
Condition-Monitoring Engineer · KI / ML · September 2026
Eine ProoV-Fallstudie · Lernprojekt, kein Arbeitsverhältnis
Built an end-to-end rolling-bearing fault detector from vibration data: engineered RMS, kurtosis, crest factor, and defect-frequency envelope features; trained a depth-capped decision tree on training bearings only; and validated it on a held-out set with catch-rate and false-alarm metrics. The student also localized the fault to the outer race via BPFO and defended a 0.42 alarm threshold using concrete cost tradeoffs.
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
- Computed envelope-spectrum energy around the supplied defect frequencies and correctly selected BPFO as dominant
- Used kurtosis as the root split in a shallow decision tree and stated depth/node count against the embedded budget
- Reported held-out catch-rate and false-alarm rate rather than evaluating on training data
- Justified the alarm threshold with explicit euro-cost calculations from the student's own results
- Leakage-Free Feature Engineering
- Honest Model Evaluation
Meine eingereichte Arbeit18 Aufgaben
10 Aufgaben · 9.1k Zeichen · Python · 8 Textantworten · 447 Wörter
- Initial Prediction62 Zeichen
- Load Plot Signal CodePython · 1.8k Zeichen
- Example Rms WorkedPython · 697 Zeichen
- Time Features143 Zeichen
- Freq FeaturesPython · 2.8k Zeichen
- Fault Location239 Zeichen
- Train Classifier363 Zeichen
- Evaluation Heldout288 Zeichen
- Threshold Decision335 Zeichen
- Decision Memo2.5k Zeichen
- Initial Prediction9 Wörter
- Load Plot Signal Code163 Wörter
- Example Rms Worked72 Wörter
- Time Features10 Wörter
- Freq Features124 Wörter
- Fault Location14 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.