Abstract
When knocking at crack eggs and nondestructive egg, a flexible piezoelectric film sensor shall be adopted to obtain frequency domain characteristic signals. Consequently, the frequency domain characteristic curves of nondestructive eggs show obvious main frequency domain values, while those of crack eggs show multiple and irregular peak values. In accordance with equal interval frequencies, the first 16 maximum and minimum amplitude values are selected orderly as input vector training Generalized regression neural network .Its Predicted output vector is the egg cracks.. In order to improve prediction accuracy, smooth factor of GRNN neural network is calculated by Particle Swarm Optimization. The experimental result showed that accurate prediction rate of GRNN is up to 94%.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
