Automatic Detection of Oil Level of Transformer Oil Conservator Based on Infrared Image Segmentation Technology

Oil level is one of the important monitoring parameters of Power Transformer, it is important to detect the oil level when it is too low or too high in time and take the appropriate measures to ensure the safe of power transformers. To be effective and accurate detection of oil level, this paper processed infrared image of the oil conservator with the improved Watershed segmentation algorithm, take the multi-scale morphological gradient image as access images of the segmentation algorithm. On the premise of focusing the areas´ Unicom, The algorithm made multi-scale morphological gradient image to binary map with the method of Otsu to obtain marked map. After the removal of false minimum marks, we use the exact minimum points of the final marked map as the starting point to transform the multi-scale morphological gradient image with Watershed algorithm to get the final segmentation results. Experimental results show that proposed method can effectively separate the oil level and reserve oil volume of oil conservator automatically. Therefore, it can be served as an important part of the substation online infrared monitoring system.