Decision-Level Fusion of Spatially Scattered Multi-Modal Data for Nondestructive Inspection of Surface Defects.

René Heideklang,Parisa Shokouhi

doi:10.3390/s16010105

Abstract

This article focuses on the fusion of flaw indications from multi-sensor nondestructive materials testing. Because each testing method makes use of a different physical principle, a multi-method approach has the potential of effectively differentiating actual defect indications from the many false alarms, thus enhancing detection reliability. In this study, we propose a new technique for aggregating scattered two- or three-dimensional sensory data. Using a density-based approach, the proposed method explicitly addresses localization uncertainties such as registration errors. This feature marks one of the major of advantages of this approach over pixel-based image fusion techniques. We provide guidelines on how to set all the key parameters and demonstrate the technique’s robustness. Finally, we apply our fusion approach to experimental data and demonstrate its capability to locate small defects by substantially reducing false alarms under conditions where no single-sensor method is adequate.

Highlights

Industrial nondestructive testing (NDT) refers to the inspection of materials, parts or structures concerning their condition without compromising their structural integrity
This evaluation focuses on detectability, meaning the ability to distinguish between grooves and background in the fusion result
Our experiments demonstrate that our density-based approach is well-suited to incorporate indications from heterogeneous sensors

Summary

Introduction

Industrial nondestructive testing (NDT) refers to the inspection of materials, parts or structures concerning their condition without compromising their structural integrity. Near-surface cracks represent one class of flaws that are commonly encountered in critical machine parts under dynamic loading such as turbine blades and bearings. Among the NDT methods suitable for near-surface crack detection, special attention is paid to those that allow automatic data acquisition and provide accurate, quantitative and reproducible results in the form of digitized signals. This is because each method reacts to changes in specific physical properties of the tested structure in the presence of a defect, but the intrinsic material and geometry properties of the structure may produce similar and often indistinguishable changes in the recorded signals

Methods

Results

Conclusion