Autonomous ultrasonic inspection using Bayesian optimisation and robust outlier analysis

• Published in: Mechanical systems and signal processing 2020-11, Vol.145, p.106897, Article 106897
• Main Authors: Fuentes, R., Gardner, P., Mineo, C., Rogers, T.J., Pierce, S.G., Worden, K., Dervilis, N., Cross, E.J.
• Format: Article
• Language: English
• Subjects: Algorithms; Automation; Bayesian optimisation; Damage detection; Data analysis; Data collection; Destructive testing; Gaussian process (GP) regression; Inspection; Iterative methods; Non-destructive testing (NDT); Nondestructive testing; Optimization; Outlier analysis; Outliers (statistics); Robotics; Robustness; Statistical analysis; Structural health monitoring; Two dimensional models; Ultrasonic testing; Ultrasound
• ISSN: 0888-3270; 1096-1216
• DOI: 10.1016/j.ymssp.2020.106897

•A novel optimisation scheme enabling autonomous robotic inspection for NDT.•Demonstrated with an ultrasonic robotic inspection of an aerospace composite panel.•Optimiser guides robot exploration based on spatial model of robust novelty indices.•Gaussian process regression gives damage probability distribution at unscanned locals.•Total probability-of-damage field updated sequentially as observations gathered. The use of robotics is beginning to play a key role in automating the data collection process in Non Destructive Testing (NDT). Increasing the use of automation quickly leads to the gathering of large quantities of data, which makes it inefficient, perhaps even infeasible, for a human to parse the information contained in them. This paper presents a solution to this problem by making the process of NDT data acquisition an autonomous one as opposed to an automatic one. In order to achieve this, the robotic data acquisition task is treated as an optimisation problem, where one seeks to find locations with the highest indication of damage. The resulting algorithm combines damage detection technology from the field of data-driven Structural Health Monitoring (SHM) with novel ideas in uncertainty quantification which enable the optimisation routine to be probabilistic. The algorithm is sequential; a decision is made at every iteration regarding the next optimal physical location for making an observation. This is achieved by modelling a two-dimensional field of novelty indices across a part/structure which is derived from a robust outlier analysis procedure. The value of this autonomous approach is that the output is not only measured data, but the most desirable information from an NDT inspection – the probability that a component contains damage. Furthermore, the algorithm also minimises the number of observations required, thus minimising the time and cost of data gathering.