HMGCC Co-Creation is seeking a machine learning-enabled solution to help engineers identify, characterise and understand electronic components using only x-ray images. This challenge is about developing machine learning algorithms that can identify and label electronic components from x-ray images while assessing their likely function within a circuit.
Up to £60,000 is available for projects of 12 weeks to deliver a demonstrator at TRL 5.
Essential Requirements
- Delivery of demonstration, along with software, source code and report detailing how it functions
- Use machine learning techniques to identify and analyse electronic
components - Ensure the software can be used by trained operators who are not electronic
component specialists - Provide traceability and explainability for outputs.
- Show confidence scores for identified components and extracted information.
- Run on commercially available hardware.
- Support multiple data types, particularly TIFF and JPEG files
- Demonstrate identification and analysis of through-hole components, such as capacitors and resistors.
Desirable Requirements
- Support offline or disconnected operation.
- Support retraining or refinement using additional labelled data.
- Demonstrate identification and analysis of surface mount components, such as microcontrollers, capacitors and resistors.
- Generate structured reports suitable for technical assessment activities.
Constraints
- Training data will be made available to the winning solution provider.
- Solutions should avoid reliance on proprietary datasets where possible.
- The solution must use x-ray images as its primary source of analysis.
- Solutions should provide evidence-backed outputs and clearly explain any uncertainty.
Submissions are due 29 October 2026.
Document
Challenge Document – AI-Enhanced X-Ray Imaging for Bomb Disposal – HMGCC – AI-enhanced XRay
