The invention belongs to the field of
image processing, and particularly relates to an evolution
analysis method of an ash deposition state image of an air pre-heater rotor. The method comprises the following steps: after acquiring an
infrared image of the air pre-heater rotor, transmitting the
infrared image to an
image processing module by an
infrared thermal imager; carrying out image preprocessing after receiving the image, and converting the preprocessed
infrared image into a gray scale curve image; enhancing the
grayscale curve image to highlight a target area; establishing a gray-levelco-occurrence matrix according to the enhanced gray-level curve image; analyzing
gray level co-occurrence matrix related statistics, and extracting
texture feature parameters; establishing a
deep belief network analysis model and carrying out training and testing; enabling the trained model to analyze the ash deposition state of the rotor of the air pre-heater according to the
texture feature parameters; effectively detecting and monitoring the
soot formation degree, and analyzing images to obtain the specific
soot formation state. According to the invention, the blockage possibility of the
air preheater can be predicted in advance, an operator is guided to optimally operate a
soot blowing
system, and therefore the working efficiency of the
air preheater in the normal operation period is improved.