Autonomous ultrasonic inspection using Bayesian optimisation and robust outlier analysis

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.

[1]  Jeffrey T. Stetson,et al.  Robotic inspection of fiber reinforced composites using phased array UT , 2014 .

[2]  João Paulo Papa,et al.  Automatic microstructural characterization and classification using artificial intelligence techniques on ultrasound signals , 2013, Expert Syst. Appl..

[3]  Franck Schoefs,et al.  Assessment of ROC curves for inspection of random fields , 2009 .

[4]  Keith Worden,et al.  A probabilistic compressive sensing framework with applications to ultrasound signal processing , 2019, Mechanical Systems and Signal Processing.

[5]  M. Debruyne,et al.  Minimum covariance determinant , 2010 .

[6]  Simon Streltsov,et al.  A Non-myopic Utility Function for Statistical Global Optimization Algorithms , 1999, J. Glob. Optim..

[7]  Donald R. Jones,et al.  Efficient Global Optimization of Expensive Black-Box Functions , 1998, J. Glob. Optim..

[8]  Roger Woodard,et al.  Interpolation of Spatial Data: Some Theory for Kriging , 1999, Technometrics.

[9]  Hoon Sohn,et al.  Automated detection of delamination and disbond from wavefield images obtained using a scanning laser vibrometer , 2011 .

[10]  Robert Bogue,et al.  Industrial Robot : An International Journal The role of robotics in non-destructive testing , 2016 .

[11]  Keith Worden,et al.  Damage Detection Using Stress Waves and Multivariate Statistics: an Experimental Case Study of an Aircraft Component , 2007 .

[12]  Carl E. Rasmussen,et al.  A Unifying View of Sparse Approximate Gaussian Process Regression , 2005, J. Mach. Learn. Res..

[13]  Hamid Sheikhzadeh,et al.  Improving the time-resolution and signal-to-noise ratio of ultrasonic NDE signals , 2004 .

[14]  Alan E. Gelfand,et al.  Continuous Spatial Process Models for Spatial Extreme Values , 2010 .

[15]  Carmelo Mineo,et al.  Robotic path planning for non-destructive testing – A custom MATLAB toolbox approach , 2016 .

[16]  Cheng-Zhong Zhang,et al.  Sparse signal representation and its applications in ultrasonic NDE. , 2012, Ultrasonics.

[17]  Sylvia Richardson,et al.  A comparison of Bayesian spatial models for disease mapping , 2005, Statistical methods in medical research.

[18]  Steven R. Doctor,et al.  SAFT — the evolution of a signal processing technology for ultrasonic testing , 1986 .

[19]  M. Stein.  Large sample properties of simulations using latin hypercube sampling , 1987 .

[20]  Harold J. Kushner,et al.  A New Method of Locating the Maximum Point of an Arbitrary Multipeak Curve in the Presence of Noise , 1964 .

[21]  Christian Boller,et al.  Reliability considerations of NDT by probability of detection (POD) determination using ultrasound phased array , 2013 .

[22]  Richard E. Turner,et al.  A Unifying Framework for Gaussian Process Pseudo-Point Approximations using Power Expectation Propagation , 2016, J. Mach. Learn. Res..

[23]  Paul D. Wilcox,et al.  A probabilistic approach for the optimisation of ultrasonic array inspection techniques , 2014 .

[24]  Carl E. Rasmussen,et al.  Gaussian processes for machine learning , 2005, Adaptive computation and machine learning.

[25]  P. Rousseeuw.  Least Median of Squares Regression , 1984 .

[26]  Franck Schoefs,et al.  Characterization of random fields from NDT measurements: A two stages procedure , 2016 .

[27]  M. D. McKay,et al.  A comparison of three methods for selecting values of input variables in the analysis of output from a computer code , 2000 .

[28]  M. Jhun,et al.  Asymptotics for the minimum covariance determinant estimator , 1993 .

[29]  Douglas M. Hawkins,et al.  High Breakdown Regression and Multivariate Estimation , 1993 .

[30]  Caroline Uhler,et al.  Maximum likelihood estimation for linear Gaussian covariance models , 2014, 1408.5604.

[31]  A. O'Hagan,et al.  Curve Fitting and Optimal Design for Prediction , 1978 .

[32]  Jin Li,et al.  Spatial interpolation methods applied in the environmental sciences: A review , 2014, Environ. Model. Softw..

[33]  P. Rousseeuw,et al.  A fast algorithm for the minimum covariance determinant estimator , 1999 .

[34]  Dino Isa,et al.  Active incremental Support Vector Machine for oil and gas pipeline defects prediction system using long range ultrasonic transducers. , 2014, Ultrasonics.

[35]  Keith Worden,et al.  Robust methods of inclusive outlier analysis for structural health monitoring , 2014 .

[36]  Drai,et al.  Elaboration of some signal processing algorithms in ultrasonic techniques: application to materials NDT , 2000, Ultrasonics.

[37]  Yu Ding,et al.  Domain Decomposition Approach for Fast Gaussian Process Regression of Large Spatial Data Sets , 2011, J. Mach. Learn. Res..

[38]  S. Sambath,et al.  Automatic Defect Classification in Ultrasonic NDT Using Artificial Intelligence , 2011 .

[39]  Satish S. Udpa,et al.  Neural networks for the classification of nondestructive evaluation signals , 1991 .

[40]  Fabio Tozeto Ramos,et al.  Bayesian Optimisation for informative continuous path planning , 2014, 2014 IEEE International Conference on Robotics and Automation (ICRA).

[41]  James Hensman,et al.  A PROBABILISTIC APPROACH TO ROBOTIC NDE INSPECTION , 2010 .

[42]  Denys Breysse,et al.  New optimization algorithm for optimal spatial sampling during non-destructive testing of concrete structures , 2015 .

[43]  Douglas M. Hawkins,et al.  The feasible solution algorithm for the minimum covariance determinant estimator in multivariate data , 1994 .