Abstract
Based on WNN, an improved model of High Voltage Switchgear temperature prediction is built. The model is optimized with hard threshold de-noising with wavelet package analysis, made an ultra-short term prediction loosely combines Elman neural network. However, the characteristics of the original signal are reserved and the noise interference is mostly eliminated. The experiment results show the processed sample as input one improves the prediction accuracy of Elman Network and reduces the root-mean-square error. And the prediction values show good coincidence to the measured ones that improves the reliability of early warning.
Full Text 
Sign-in/Register to access full text options
Sign-in/Register to access full text options 
Published version (
Free)
Free) 
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 call
