Industrial Time-Series Anomaly Detection
Detect anomalies in multivariate sensor streams, distinguishing genuine faults from sensor failures and process changes.
Detect anomalies in multivariate sensor streams, distinguishing genuine faults from sensor failures and process changes.
GitHub repo or evidence pack + live demo / report + README + milestone logbook
- Problem & requirements15
Loads, constraints, standards and success criteria are written down before the design starts.
- Calculations & analysis30
Hand calculations or simulation set out step by step with units, assumptions and a check against a second method or code limit.
- Design output20
Drawings, models, schematics or code that match the calculations and could be handed to the next person.
- Validation & files15
Test data, simulation files, calculation sheets or photos attached, with what each one shows.
- Report & judgement20
A clear report that states the result, its limits, cost or risk, and what you would change next.
Pass 60% · Merit 75% · Distinction 90%
Engineering Students
Diploma, B.Tech, B.E., BCA, MCA, or M.Tech students seeking practical experience.
Aspiring Developers
Developers who want to build proof-of-work capstone projects for tech resumes.
Job Seekers
Graduates looking for AI-evaluated code review & verified industry credentials.