Water turbine cavitation discrimination method based on image recognition

• Main Authors: HUANG XI, LIANG QUANWEI, WANG GANG, WEN JUNJIE, LUO YANCHEN, REN PANQIU, WANG GUIHONG
• Format: Patent
• Language: Chinese; English
• Published: 23.05.2023
• Subjects: CALCULATING; COMPUTING; COUNTING; PHYSICS

The invention relates to the technical field of water turbine cavitation recognition, and discloses a water turbine cavitation judgment method based on image recognition, which comprises the following steps: acquiring an image of a target water turbine runner to be recognized, performing feature extraction on the image to construct a target feature matrix of the target image, and correcting the feature matrix of the target water turbine runner at first; and then, sending the cavitation identification matrix to a cavitation identification model, comparing the cavitation identification matrix with a template correction characteristic matrix of a template image stored in the model, and finally, realizing cavitation identification of the turbine runner. Compared with the existing method, the method provided by the invention not only can improve the cavitation judgment speed of the water turbine, but also can improve the judgment quality. 本申请涉及水轮机空化识别技术领域，公开了一种基于图像识别的水轮机空化判别方法，本方法通过采集待识别的目标水轮机转轮的图像，对图像进行特征提取构造目标图像