Abstract-A new method is presented to exactly forecast trend of running state trend for the microprocessor protective device based on LS-SVM to realize condition maintenance. LS-SVM is introduced to forecast state trend of the microprocessor protective device. The real-time current, history overhauling data of microprocessor protection deceive and fault corresponding running state are chosen as input value, and running state of the microprocessor protective device is chosen as output value. The experimental results indicate that accurate and generalized performance is better by LS-SVM to forecast state trend of the microprocessor protective device with the small training set of sample, and LS-SVM is higher forecast accuracy than the BP neural network. The comparison of different kernel functions of LS-SVM shows that RBF kernel function is most suitable for state trend forecasting of microprocessor protective device.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.