Support Vector Machine Model based on Glowworm Swarm Optimization in Application of Vibrant Fault Diagnosis for Hydro-turbine Generating Unit

摘要：

　　In view of the support vector machine(SVM)model applied in vibrant fault diagnosis for hydro-turbine generating unit,it exists problems of parameter settings and classification-plane incline due to unequal sample,which leads to lower diagnosis accuracy.As a new bionic intelligent optimization algorithm for glowworm swarm optimization(GSO),it has the characteristics of strong versatility and fast convergence speed.In this paper,GSO is first introduced into the field of hydropower unit vibration fault diagnosis,and GSO-SVM diagnosis model was established,which has realized the effective mapping for vibration characteristics into fault sets,and achieve the goal of fault diagnosis.The simulation results show that the established model has better convergence speed and global optimization ability as well as the higher calculation precision,providing an efficient and innovative solutions in the field of vibrant fault diagnosis for hydro-turbine generating unit.

关键词： Hydropower units Fault diagnosis Support vector machine (SVM) Glowworm swarm optimization Parameter optimization Classification-plane

作者: Xueqin Zheng Zhonghua Gui Yong Wang

作者单位: Technology center of State Grid Xinyuan Company Ltd.,Beijing,100061,China

会议类型: 国际会议

会议名称: 2017 IEEE 3rd Information Technology and Mechatronics Engineering Conference(ITOEC2017)(2017 IEEE 第3届信息技术与机电一体化工程国际学术会议)

会议地点: 重庆

会议语种:英文

页码: 238-241

在线出版日期: 2017-10-03（万方平台首次上网日期，不代表论文的发表时间）