首页|基于PSO-ELM的变压器油纸绝缘状态无损评估方法

基于PSO-ELM的变压器油纸绝缘状态无损评估方法

扫码查看
原文链接
  • 万方数据
  • 维普
油浸式电力变压器作为电网的重要组成部分,其可靠运行至关重要.针对变压器长期运行后无法定量评估其绝缘状态的问题,文中开展了油纸绝缘模型的加速老化及受潮试验,探究了油纸绝缘老化及受潮程度对其回复电压曲线的影响规律,并提出采用粒子群优化-极限学习机(particle swarm optimization-extreme learning machine,PSO-ELM)算法的参数预测方法,实现了基于回复电压曲线特征参量的油纸绝缘老化与受潮状态量化评估.由油纸绝缘模型理化性能分析的对比结果可知,基于PSO-ELM方法的预测值精度远高于传统ELM方法,油纸绝缘内含水率及纸板聚合度预测的绝对误差范围分别小于±0.4％、±30.
The assessment method of transformer oil-paper insulation state based on PSO-ELM
Oil-immersed power transformer is an important part of power grid,and its reliable operation plays a vital role in pomler system security.Aiming at the problem that the insulation state of transformer cannot be assessed quantitatively after long-term operation,the accelerated aging and damp tests of oil-paper insulation model are carried out in this paper.The influence of aging and damp of oil-paper insulation on its recovery voltage curves is explored.The particle swarm optimization(PSO)is used to improve the parameter prediction method of extreme learning machine(ELM),which realizes the quantitative assessment of aging and moisture of oil-paper insulation based on the characteristic parameters of the recovery voltage curve.By comparing the physical and chemical performance analysis of oil-paper insulation models,it is shown that the prediction accuracy of PSO-ELM method is much higher than that of traditional ELM method.The absolute error range for predicting the moisture content of oil-paper insulation the degree of polymerization(DP)of pressboard is less than±0.4％or±30,respectively.

oil-immersed transformeroil-paper insulationrecovery voltagepartical swarm optimization-extreme learning ma-chine(PSO-ELM)algorithmstate assessmentnon-destructive testing

张德文、张健、曲利民、吴迪星、刘贺千、张明泽

展开 >

国网黑龙江省电力有限公司电力科学研究院,黑龙江哈尔滨 150030

哈尔滨理工大学(工程电介质及其应用教育部重点实验室),黑龙江哈尔滨 150080

油浸式变压器 油纸绝缘 回复电压 粒子群优化-极限学习机(PSO-ELM)算法 状态评估 无损检测

国家电网科技项目国家自然科学基金

5500-202330167A-1-1-ZN52307164

2024

10.12158/j.2096-3203.2024.03.021

电力工程技术
江苏省电力公司 江苏省电机工程学会

电力工程技术

CSTPCD北大核心
影响因子：0.969
ISSN：2096-3203
年,卷(期)：2024.43(3)
  • 18