Fusion of multi-sensory NDT data for reliable detection of surface cracks: Signal-level vs. decision-level

Abstract

Abstract. We present and compare two different approaches for NDT multi-sensor data fusion at signal (low) and decision (high) levels. Signal-level fusion is achieved by applying simple algebraic rules to strategically post-processed images. This is done in the original domain or in the domain of a suitable signal transform. The importance of signal normalization for low-level fusion applications is emphasized in regard to heterogeneous NDT data sets. For fusion at decision level, we develop a procedure based on assembling joint kernel density estimation (KDE). The procedure involves calculating KDEs for individual sensor detections and aggregating them by applying certain combination rules. The underlying idea is that if the detections from more than one sensor fall spatially close to one another, they are likely to result from the presence of a defect. On the other hand, single-senor detections are more likely to be structural noise or false alarm indications. To this end, we design the KDE combination rules such that it prevents single-sensor domination and allows data-driven scaling to account for the influence of individual sensors. We apply both fusion rules to a three-sensor dataset consisting in ET, MFL/GMR and TT data collected on a specimen with built-in surface discontinuities. The performance of the fusion rules in defect detection is quantitatively evaluated and compared against those of the individual sensors. Both classes of data fusion rules result in a fused image of fewer false alarms and thus improved defect detection. Finally, we discuss the advantages and disadvantages of low-level and high-level NDT data fusion with reference to our experimental results.

Nondestructive Testing of Polymers and Polymer–Matrix Composites

“…NDT or NDE for aerospace applications will be discussed in more detail in section 10.4 below. A combination of techniques can be used either as a validation method for one or the other, as a benchmark, or the increased evidence of indications can be explored for a more detailed description of damage, for example by data fusion (327,328). Combinations reported include, among others, DSPI, X-ray CT and TSA (317); ultrasonic C-scan and shearography (318); ultrasound, thermography, vibration testing and embedded sensors (319); IRT and AE (329); IRT and DSPI (330); AE, ESPI and Superconducting Quantum Interference Device (SQUID) current mapping (331), and Electrical Potential Change method, AE and Lock-in Thermography applied to debonding monitoring of composite repairs (332).…”

A State-of-the-Art Review of Non-Destructive Testing Image Fusion and Critical Insights on the Inspection of Aerospace Composites towards Sustainable Maintenance Repair Operations

“…The basic mathematical fusion rules can also be used mainly for comparison or complementary with other fusion rules. A good example application of this is in [49], which includes the basic rules, wavelets and decision-level fusion (kernel density estimation (KDE)) together. A steel-bearing shell specimen with 15 surface grooves and specific dimensions was used experimentally.…”

Fusion Insights from Ultrasonic and Thermographic Inspections for Impact Damage Analysis

“…NDT fusion is a challenging subject given the dissimilar data acquisition environment of uni-modal inspections; there is some work on combining NDT techniques by fusion rules such as generic maximum, minimum or average merging by pixel-wise, principle component analysis (PCA) and wavelets, as well as AI-based approaches [10,[18][19][20][21]. In this study, we use the maximum combination rule, given in equations ( 1), as a simple yet effective synergistic approach to retrieve defect edges.…”

“…Data fusion is well-known for combining (fusing) data from various sensors (sources), in the context of NDT inspection data information from different inspection technologies. Several works in NDT fusion have already appeared in the literature that focus on various material types such as concrete [9], metallic [10], or composite [11] structures. Although not without challenges in its application, data fusion can potentially be used to enhance defect detection and characterization through advanced fusion operations.…”