Data fusion for automated non-destructive inspection

Abstract

In industrial non-destructive evaluation (NDE), it is increasingly common for data acquisition to be automated, driving a recent substantial increase in the availability of data. The collected data need to be analysed, typically necessitating the painstaking manual labour of a skilled operator. Moreover, in automated NDE a region of an inspected component is typically interrogated several times, be it within a single data channel due to multiple probe passes, across several channels acquired simultaneously or over the course of repeated inspections. The systematic combination of these diverse readings is recognized to offer an opportunity to improve the reliability of the inspection, but is not achievable in a manual analysis. This paper describes a data-fusion-based software framework providing a partial automation capability, allowing component regions to be declared defect-free to a very high probability while readily identifying defect indications, thereby optimizing the use of the operator's time. The system is designed to applicable to a wide range of automated NDE scenarios, but the processing is exemplified using the industrial ultrasonic immersion inspection of aerospace turbine discs. Results obtained for industrial datasets demonstrate an orders-of-magnitude reduction in false-call rates, for a given probability of detection, achievable using the developed software system.

Grain Scattering Noise Modeling and Its Use in the Detection and Characterization of Defects Using Ultrasonic Arrays

“…Although the threshold plays an important role in de-noising (and hence, detection) performance, its selection is somewhat arbitrary (e.g. small defects may become detectable using low threshold values, but this also results in high false alarm rates) [24]. More importantly, these filtering approaches have the fundamental limitation that they do not provide insight into the detection/characterisation problem as well as how the characterisation uncertainty can be evaluated given some measurement.…”

Quality control automated laser-ultrasonic method for solder joints of nozzles of chambers in liquid rocket engines

“…Анализ научно-технической ли-тературы [5][6][7] показал, что перспективным методом НК качества паяных соединений сопел камер ЖРД является лазерно-ультразвуковой метод, который позволяет не только определить наличие дефектов, но и измерить их геометрические характеристики [8]. Однако применение данного метода для контроля каче-ства паяных соединений сопла камеры ЖРД в ручном режиме связано со значительной трудоемкостью и, как следствие, высокой вероятностью ошибок оператора (дефектоскописта), что сказывается на точности измерений и достоверности результатов контроля и является сдерживающим фактором для внедрения данного метода.…”

Three-Dimensional Imaging With Multiple Degrees of Freedom Using Data Fusion

“…Other fields where image fusion from various data sources (sometimes referred as multimodal image fusion) is an active area of research include video processing [16], [17], biometric identification/classification [18]- [21], image fusion for visualization enhancement [22], industrial inspection [23], among others [24]- [27]. Image fusion methods might be also aimed at solving only one particular type of fusion problem, but current tendency is toward the creation of methodologies that may be able to solve image fusion problems in more than one area (fusion of medical images, or fusion of RGB and thermal images, using the same mathematical framework) [28]- [32].…”