Skip to content
SIH Buddyby Ganeev Singh
Dev
All problem statements
SIH26054Proceed with cautionacceptance 2/5

AI-Enabled Real-Time Digital Twin System for Health Monitoring, Fault Prediction and Mission Reliability Enhancement of Aero Piston Engines used in MALE UAVs.

DRDO · Robotics and Drones · Software

The architecture the statement asks for is sound but there is no aero piston engine data anywhere for you to ground it in, so unless you can get real telemetry off some instrumented engine, you will be predicting faults you injected into a simulator you wrote.

What it actually is

Long-endurance surveillance drones run on piston engines, and if one fails mid-flight the mission and often the aircraft are lost. Current monitoring only raises an alarm after something has already gone wrong. The ask is a live virtual copy of the engine that mirrors the real one from its sensor feed, spots degradation early, estimates how much life is left, and lets engineers replay a flight afterwards.

What to build

A digital twin with the six components the statement lays out: a virtual engine model synchronised to live telemetry through a real-time ingestion path over CAN or an engine controller interface; a health monitoring layer computing indices from the parameters the statement names individually including RPM, cylinder head and exhaust gas temperature, oil pressure and temperature, fuel flow, vibration signature, alternator health and injection timing; a predictive diagnostics layer for the eight named fault modes from misfire and injector abnormality through lubrication issues, sensor drift and combustion instability; an AI layer providing anomaly detection, remaining useful life estimation and maintenance recommendations; a simulation and replay capability reproducing engine behaviour under high altitude, endurance, hot weather and rapid throttle transitions; and an operator dashboard carrying health status, alerts, efficiency trends and mission-wise reports.

Smallest thing that wins the room

Replay a mission profile with a developing fault seeded into it and show the twin flagging the divergence between predicted and observed cylinder head temperature well before any threshold alarm would fire, with the remaining useful life curve bending as it does.

How crowded this one gets

A guess, projected from the 2025 statements — the last year where both the submission counts and the winners were published.

Moderate110–250 teams expectedroughly 1 in 91–209 wins it

Quieter than 65% of the 226 · #80 of 226 by expected field

A normal-sized field. Your idea has to be good, not miraculous.

Why: defence, intelligence and space bodies drew small fields.

This is a guess, not a fact

Nobody has published 2026’s numbers yet. This is an analysed estimate from last year’s pattern, so please do not take it as the truth — check the live counter on the SIH portal before you decide anything. The range covers the middle half of likely outcomes, so one statement in two lands outside it. Entry closes at 500 ideas per statement, so no range goes past that — a statement that reaches the cap fills and shuts rather than drawing an unlimited crowd. The model reads only three things a team can see before choosing — software or hardware, the theme, and what kind of body posted it — and those explain about a quarter of the variation in last year’s field sizes (R² 0.25 on held-out statements). Trust the band more than the number, and the ordering more than either. It cannot see how good your idea is, which is the part that actually decides it.

The scores

The number is the shorthand. The line under it is the reason.

What you will be writing

  • physics-informed thermodynamic engine model
  • SocketCAN telemetry ingestion from ECU/FADEC
  • LSTM or transformer remaining useful life estimation
  • residual-based anomaly detection against model prediction
  • SHAP explainable fault attribution
  • React operator dashboard with mission replay
  • Predictive maintenance
  • UAV propulsion
  • Digital twin systems

Prior art to read before you start

engine health monitoring and fault prediction · remaining useful life estimation · physics-informed digital twin

Analysed by Claude Opus. Every score above is a judgment call with its reasoning attached — kindly cross-check this against the official statement on the SIH portal before your team commits to it.