The SonicScan project aims at developing NDT methods based on ultrasonic testing that are suitable for primary structural parts. The main challenge is the compact shape of the parts and their high thickness. To address this problem the project will build upon the sampling phased array technology that allows the tomographic inspection of parts and combine it with a robotic handling system to move the sensor across the part. Particular emphasis will be put on the model-based, automatic planning of the robot's inspection path to ensure that all elements of the part are inspected. This will be based on methods developed by the project partners for image-based surface inspection robots and they will be adapted to volumetric inspection methods. Data analysis for automatic defect detection, segmentation and classification will be developed, including machine learning methods such as random forests.

The main result of the project will be an integrated inspection robot that will be demonstrated on landing gear components.

The technologies developed in the project will have impact on the manufacturing of structural composite parts, in particular on their quality control in series production, and on the efficient deployment of ultrasonic inspection robots, by increasing the usability of such robots through automatic adaptation to new part designs.

The consortium consists of two partners, covering the required expertise in ultrasonic testing of composite parts and in the automation of robotic inspection tasks. The partners will extend their business in the field of inspection robots by about 2M€ per year based on the developed technologies.