基于改进二维Otsu算法的电机故障识别研究  

Research on Motor Fault Identification Based on Improved 2D Otsu Algorithm

作　　者：张龙威 杨向宇[1] ZHANG Longwei;YANG Xiangyu(School of Electric Power Engineering,South China University of Technology,Guangzhou 510640)

机构地区：[1]华南理工大学电力学院,广州510640

出　　处：《舰船电子工程》2021年第12期98-104,共7页Ship Electronic Engineering

摘　　要：热成像图像处理技术已广泛应用于电机故障诊断中。在电机热成像灰度图像的基础上,采用二维Otsu图像阈值分割方法自动提取电机灰度图像的高温区域,针对传统二维Otsu图像阈值分割方法计算复杂、实时性差的缺点,论文提出一种以改进萤火虫算法为求优方式的二维Otsu图像分割算法,即引入模拟退火因子的萤火虫算法与二维Otsu图像阈值分割法相结合,经实验结果表明,改进后的算法图像分割效果良好,并且计算时间短,实时性好。Thermal imaging image processing technology has been widely used in motor fault diagnosis.Based on the thermal imaging gray image of motors,2D Otsu algorithm is used to automatically extract the high-temperature region of motors'gray image.In order to solve the problem of the traditional 2D Otsu algorithm such as complex computation,poor real-time performance,this paper presents a 2D Otsu image segmentation algorithm based on improved firefly algorithm,which the algorithm takes advantage of firefly algorithm combined with simulated annealing factor to search the optimal threshold of image classification.The experimental results show that the improved algorithm has good image segmentation performance,short calculation time and good real-time per⁃formance.

关 键 词：二维OTSU 灰度图 图像分割 萤火虫算法 电机故障 无损检测 

分 类 号：TP312[自动化与计算机技术—计算机软件与理论]