Assessment of Defects under Insulation Using K-Medoids Clustering Algorithm-Based Microwave Nondestructive Testing

Composite insulations, such as ceramics, are commonly utilized in the turbine system a thermal coating barrier to protect metal substrate against high temperatures and pressure. The presence of delamination composite insulations may cause failure, leading catastrophic accident. Thus, regular non-destructive testing is required detect evaluate insulation defects. Among techniques, microwave technique has emerged promising method for assessing defects ceramic coatings. Although promising, suffers from poor spatial imaging, making defect assessment challenging. In this paper, novel based on with k-medoids clustering algorithm detection proposed. representative sample scanned using Q-band open-ended rectangular waveguide 101 frequency points that operated between 33 50 GHz. measured data transformed domain time an inverse fast Fourier transform. principal component analysis then used reduce dimensionality steps into only 3 dominant attributes. attributes each inspected location classified or defect-free accurately detecting sizing insulation. results reported paper highlight superiority detection, accuracy rate 95.4%. This significant step forward compared earlier approaches identifying