Research on The Detection Method of Rotary Kiln Working Condition Based on Kiln Image

In view of the problems of manpower consumption, material resources and low accuracy of the "manual fire watching" method adopted by many rotary kiln enterprises, the method of hog + elm is proposed to identify the flame image of rotary kiln. Because the pictures collected on the spot contain useless information, this paper first reduces the noise and divides the pictures collected on the spot, then uses the hog algorithm to extract the features of the pictures and obtain the feature data of the pictures, and finally uses the limit learning machine algorithm to train the picture features, obtain the training model, and test the training model. Experiments show that the method is efficient and accurate in flame recognition.