Citation:
Abstract:
This paper compares two approaches for detecting and analyzing acoustic microwaves in piezoelectric materials, specifically in Lithium Niobate (LiNbO3) substrates. The first method focuses on modeling the propagation of acoustic microwaves in piezoelectric structures, utilizing an interdigital transducer (IDT) to excite the electroelastic waves. This method investigates various wave types, such as secondary surface waves, leaky waves, bulk waves, and skimming bulk waves, and applies wavelet transform for efficient detection. Two wavelet functions—Mexican-hat and Morlet—are compared based on their ability to detect acoustic wave singularities, with an emphasis on their efficiency in processing microwave signals. The second method introduces a machine learning approach using support vector machines (SVM) to detect ultrasonic pulses and identify previously undetectable waves. By classifying real and imaginary parts of the coefficient attenuation and acoustic velocity, this method provides more accurate values and facilitates the modeling of ultrasonic pulse propagation. While the wavelet-based approach focuses on signal processing for wave detection, the SVM-based method excels in detecting complex wave patterns that traditional methods may overlook, offering higher precision in ultrasonic pulse modeling and the realization of acoustic microwave devices.