The fire detection methods by using pure flame or pure smoke often lead to the phenomenon of missing alarm. This paper presents a novel fire video recognition method based on both flame and smoke. Firstly, fire regions of interest are detected using Kalman Filter. Then, three major features of flame including flickering, spatio-temporal consistency and texture feature based on Local Binary Pattern (LBP) are extracted from flame-like regions. Three major features of smoke including flutter feature, energy analysis and color feature are extracted from smoke-like regions. Finally, D-S evidence theory fuses two evidences generated by Neural Network to recognize fire images. Experimental results show that the proposed method can significantly reduce missing alarm rate and false alarm rate.
This paper first provides a method for predicting fouling faults about flow passage of steam turbine based on kernel principal component analysis(KPCA) and least square support vector machine regression (LS-SVMR). First, KPCA is used to extract main features independent for each other from a lot of relaticve fault feature data. Afterwards, a model is established for predicting the trend of each main feature based on LS-SVMR in order to restruct feature vectors of fault classification. And then some typical fouling faults of steam turbine flow passage are identified by using SVM. Experimental results showed that the proposed method could effectively and efficiently forecast delitescent faults and typical fouling fault genres for the flow passage.
Research on turbo-generator fault prediction is one of theory bases for its fault self-recovery, however, the lack of fault samples and the incompletion of fault information make it full difficulties. This paper presents an efficient method for turbo-generator vibration fault prediction in which the new model of gray forecasting with first-order fitting parameter is established. On the basis of the first-order exponent flatness operation for the energies in different frequency bands extracted by wavelet packet decomposition, a new turbo-generator fault gray prediction model is established to reconstruct feature vectors consisting of the energies in different frequency bands. And then, five typical turbo-generator vibration faults are identified by using SVM. Experimental results showed that the proposed method could effectively and efficiently forecast delitescent faults and typical fault genres for the turbo-generator vibration.
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.