机械与电子2025，Vol.43Issue(9)：45-50,6.
基于扩展隔离森林算法的小型水力发电系统故障检测研究
Research on Fault Detection in Small Hydropower Systems Based on Extended Isolation Forest Algorithm
谢长宁 1史宗尚1
作者信息
- 1. 国家能源集团四川发电有限公司南桠河水电分公司,四川雅安 625400
- 折叠
摘要
Abstract
The traditional fault diagnosis methods face significant challenges in handling nonlinear da-ta.To address this issue,this paper proposes a fault diagnosis method for small hydropower systems based on the Extended Isolation Forest(EIF)algorithm,aimed at enhancing the accuracy and real-time capabili-ties of fault detection.The EIF algorithm detects multidimensional data anomalies in system operations by constructing binary trees,flexibly partitioning the data using random slopes and intercepts,and training i-solation trees through random sampling.It calculates path lengths to determine the anomaly score for each data point.Experimental results demonstrate that the EIF algorithm achieves high accuracy and effectively predicts system faults,contributing to early warning and maintenance of the system.关键词
水力发电系统/故障诊断/随机斜率/扩展隔离森林Key words
hydropower system/fault diagnosis/random slopes/extended isolation forest分类
信息技术与安全科学引用本文复制引用
谢长宁,史宗尚..基于扩展隔离森林算法的小型水力发电系统故障检测研究[J].机械与电子,2025,43(9):45-50,6.
