Abstract
The selection of parameters and structure are critical for wavelet neural networks (WNN) when they are used for fault diagnosis. Genetic algorithm is presented to optimize the structure and the parameters of WNN in the training process because of its good ability of global optimization. This method solves the main problem of easily falling into local extreme minimum to cause slow convergence when the classical gradient descent algorithm is employed for training WNN. A three-layer network trained with genetic algorithm is applied to fault diagnosis of analog circuits. Simulation results show that WNN adopting this scheme achieves a comparatively simple structure and fast convergence. It has excellent capability of fault identification and diagnosis for analog circuits. Comparing with non-genetic WNN with same structure, the proposed approach gains better diagnosis accuracy.
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.
