Abstract
The detection and identification of internal defects in a material require the use of some technology that translates the hidden interior damages into observable signals with different signature-defect correspondences. We apply impact-echo techniques for this purpose. The materials are classified according to their defective status (homogeneous, one defect or multiple defects) and kind of defect (hole or crack, passing through or not). Every specimen is impacted by a hammer, and the spectrum of the propagated wave is recorded. This spectrum is the input data to a Bayesian classifier that is based on the modeling of the conditional probabilities with a mixture of Gaussians. The parameters of the Gaussian mixtures and the class probabilities are estimated using an extended expectation-maximization algorithm. The advantage of our proposal is that it is flexible, since it obtains good results for a wide range of models even under little supervision; e.g., it obtains a harmonic average of precision and recall value of 92.38% given only a 10% supervision ratio. We test the method with real specimens made of aluminum alloy. The results show that the algorithm works very well. This technique could be applied in many industrial problems, such as the optimization of the marble cutting process.
Highlights
The field of non-destructive testing (NDT) of materials is a wide area, including any technique that extracts information about the condition of a material specimen without altering its physical and/or chemical properties.Two main elements appear in NDT: sensors and data processing
Based on general techniques, these methods must take into account the specific context where the NDT is to be applied
We show an example of a piece under study in Figure 2: arrows point to the hammer and the accelerometers, while the red and white cables connect the accelerometers to the acquisition equipment
Summary
The field of non-destructive testing (NDT) of materials is a wide area, including any technique that extracts information about the condition of a material specimen without altering its physical and/or chemical properties (see, e.g., [1] for a survey of different NDT methods).Two main elements appear in NDT: sensors and data processing. While sensors are very application dependent and impose practical limits about monitoring resolution, data processing considers general techniques, which may find application in a variety of significantly different NDT problems. From another perspective, sensors are limited by the current sensor technology; data processing is only limited by the required computational resources. Based on general techniques, these methods must take into account the specific context where the NDT is to be applied. Once success is demonstrated in that specific context, the method could be extended to other significantly different NDT problems
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have