A Blockchain-based Traceability System for AI-Driven Engine Blade Inspection

Aircraft engine blade maintenance relies on inspection records shared across manufacturers, airlines, maintenance organizations, and regulators. Yet current systems are fragmented, difficult to audit, and vulnerable to tampering. This paper presents BladeChain, a blockchain-based system providing immutable traceability for blade inspections throughout the component life cycle. BladeChain is the first system to integrate multi-stakeholder endorsement, automated inspection scheduling, AI model provenance, and cryptographic evidence binding, delivering auditable maintenance traceability for aerospace deployments. Built on a four-stakeholder Hyperledger Fabric network (OEM, Airline, MRO, Regulator), BladeChain captures every life-cycle event in a tamper-evident ledger. A chaincode-enforced state machine governs blade status transitions and automatically triggers inspections when configurable flight hour, cycle, or calendar thresholds are exceeded, eliminating manual scheduling errors. Inspection artifacts are stored off-chain in IPFS and linked to on-chain records via SHA-256 hashes, with each inspection record capturing the AI model name and version used for defect detection. This enables regulators to audit both what defects were found and how they were found. The detection module is pluggable, allowing organizations to adopt or upgrade inspection models without modifying the ledger or workflows. We built a prototype and evaluated it on workloads of up to 100 blades, demonstrating 100% life cycle completion with consistent throughput of 26 operations per minute. A centralized SQL baseline quantifies the consensus overhead and highlights the security trade-off. Security validation confirms tamper detection within 17~ms through hash verification.

💡 Research Summary

The paper introduces BladeChain, a permissioned blockchain framework designed to provide immutable, auditable traceability for aircraft engine blade inspections throughout the component’s entire life cycle. Recognizing that current maintenance records are scattered across paper forms, spreadsheets, and siloed databases—making reconciliation, accountability, and regulatory audit difficult—the authors propose a system that unifies data provenance, automated scheduling, AI model accountability, and cryptographic evidence binding.

BladeChain is built on a four‑stakeholder Hyperledger Fabric network comprising the Original Equipment Manufacturer (OEM), airline operators, Maintenance, Repair and Overhaul (MRO) organizations, and aviation regulators. Each stakeholder is represented by a distinct Membership Service Provider (MSP), and Fabric’s channel and endorsement policies enforce that no single organization can unilaterally create, modify, or delete records. A chaincode‑implemented finite‑state machine models the blade’s life‑cycle states (manufacture, in‑service, inspection‑due, inspection‑in‑progress, repair, retirement) and automatically transitions a blade to “inspection‑due” when any configurable threshold—flight hours, cycles, or calendar days—is exceeded. This automation eliminates the manual errors that plague traditional maintenance scheduling.

Inspection artifacts (borescope images, annotations, NDT reports) are stored off‑chain in the InterPlanetary File System (IPFS). For each inspection event, the system records on‑chain the IPFS Content Identifier (CID) together with a SHA‑256 hash of the artifact, the AI model name and version used for defect detection, the inspector’s identity, organization, and timestamps. By binding the hash and model metadata to the ledger, regulators can independently retrieve the artifact, recompute its hash, and verify that the reported defect was indeed produced by the claimed AI model version. The AI inspection engine is designed as a pluggable module, allowing organizations to upgrade or replace models without altering the ledger or workflow logic.

A prototype implementation uses Hyperledger Fabric 2.5, Docker containers, a Node.js API gateway, IPFS cluster, and a PyTorch‑based defect detection model. Experiments with up to 100 blades (over 1,000 transactions) demonstrate a stable throughput of 26 transactions per minute and 100 % life‑cycle completion. A baseline comparison with a centralized SQL database quantifies the consensus overhead: while Fabric introduces roughly double the latency, the trade‑off yields tamper‑evidence and multi‑party non‑repudiation. Security validation shows that hash‑based tamper detection occurs within an average of 17 ms, enabling near‑real‑time audit capabilities.

The authors position BladeChain against prior work that either focuses on parts provenance, maintenance record storage, or conceptual AI‑blockchain integrations. Existing systems lack the combined features of (1) multi‑organization endorsement for inspection events, (2) automated, threshold‑driven scheduling, and (3) explicit AI model provenance tied to immutable evidence. BladeChain fills this gap, delivering a regulator‑grade audit trail that covers both “what” was found and “how” it was found.

Limitations include the modest scale of the experimental setup and the reliance on a private network, which may not capture performance under large‑scale, multi‑airline deployments. Future research directions suggested are (i) scaling tests with thousands of blades and multiple Fabric channels, (ii) integrating predictive AI analytics that trigger inspections proactively, (iii) formal verification of the state‑machine logic, and (iv) extending the framework to other critical aerospace components such as turbine disks or avionics.

In summary, BladeChain represents a novel, end‑to‑end solution that merges permissioned blockchain consensus, off‑chain decentralized storage, and AI‑driven inspection into a single, auditable platform, thereby addressing a critical safety and compliance gap in modern aerospace maintenance operations.