The Defence Research and Development Organisation (DRDO) has issued a Request for Proposal (RFP) under its Technology Development Fund (TDF) scheme for creating a Digital Twin (DT) Framework tailored to an Aero Engine Health and Usage Monitoring System (HUMS).

This initiative targets the development of a high-fidelity virtual model for aero gas-turbine engines and their subsystems, capturing structural integrity, functional performance, and potential failure modes with precision.​

Funded through grant-in-aid provisions, the project emphasises indigenous innovation in defence aerospace technologies, aligning with DRDO's push for self-reliance in critical systems. Phase 1 focuses on constructing the engine's DT by blending physics-based simulations with data-driven artificial intelligence and machine learning models. These hybrid approaches will enable real-time health diagnostics, predictive maintenance, and simulation of adverse conditions without physical testing.​

Such virtual modelling draws from prior DRDO efforts, including virtual sensors for aero gas-turbine engines developed by firms like ChiStats Labs, which enhance data handling and operational reliability. The DT framework promises to extend engine longevity by identifying degradation early, processing vast datasets rapidly for accurate assessments. This builds on foundational work in AI/ML for comprehensive diagnostics across engine components.​

In Phase 2, the engine DT integrates with a broader aircraft DT to model full operational scenarios, incorporating environmental and usage data for holistic prognostics. This integration supports lifecycle management, from design certification to in-service maintenance, reducing costs and risks associated with physical prototypes. Applications extend beyond military aviation to civil sectors and power generation, fostering prescriptive maintenance strategies.​

The RFP underscores DRDO's strategic pivot towards digital engineering, enabling fleet-wide optimisations and sustainable practices in Indian defence aviation. Bidders must leverage multi-physics and multiscale modelling to address challenges like real-time data fusion and regulatory compliance. 

Successful development could revolutionise aero-engine reliability, mirroring global trends in predictive health monitoring for high-stakes platforms.​

IDN (With Agency Inputs)