Damage Identification of Flexible PVC Substrate Based on VMD-ELM Algorithm

The substrate material of flexible antenna was easy to generate holes and cracks in the harsh airborne environment, Lamb wave test technology was proposed to detect the damage in the structure of flexible polyvinyl chloride (PVC) substrate and quantitatively reconstruct the damage shape to realize a nondestructive test. The damage identification method combined the variational mode decomposition (VMD) and extreme learning machine (ELM) pattern recognition. The VMD algorithm extracted the features of the echo signal without damage, hole and groove damage, constructs the damage feature vector, and ELM trains and tests to classify the damage types. There was a damage identification platform to set up for the damage detection of flexible PVC substrate. The results showed that the characteristics of low-frequency slowly varying echo signals were obvious after ELM processing; The ELM and BP neural networks trained and tested, respectively, and the damage types are classified. The ELM classification accuracy reached 91.67%. The ELM was better than the BP neural network method, which verified the effectiveness of the VMD-ELM algorithm combined to identify the damage characteristics of flexible PVC substrate. This method has a good application prospect in the rapid detection of early damage of flexible electronic devices.