基于强化层次模糊熵的柴油机故障诊断方法
Diesel Engine Fault Diagnosis Method Based on Enhanced Hierarchical Fuzzy Entropy
宋业栋 1马光伟 1朱小龙 2张俊红2
作者信息
- 1. 内燃机可靠性国家重点实验室 潍坊,261061;潍柴动力股份有限公司 潍坊,261061
- 2. 天津大学内燃机燃烧学国家重点实验室 天津,300072
- 折叠
摘要
针对多尺度模糊熵(multi-scale fuzzy entropy,简称MFE)算法中多尺度化过程采用滑动均值滤波器导致原始信号高频信息丢失的问题,提出强化层次模糊熵方法(enhanced hierarchical fuzzy entropy,简称EHFE),用于表征原始信号中富含的高低频故障模式信息.结合萤火虫算法优化支持向量机(firefly algorithm optimized support vector machine,简称FAOSVM),提出一种基于EHFE和FAOSVM的柴油机故障诊断方法.柴油机试验数据对比分析表明:相比于现有方法,所提出方法能够充分表征柴油机故障信号富含的模式信息,并且能够有效识别柴油机正时齿轮故障,识别精度达到99.6%,在极小样本下也能达到较好的识别精度.
Abstract
In order to solve the problem that the high frequency information of the original signal is lost due to the use of moving mean filter in the multi-scale fuzzy entropy(MFE)algorithm,enhanced hierarchical fuzzy en-tropy(EHFE)algorithm is proposed to characterize the high and low frequency fault mode information rich in the original signal.Combined with firefly algorithm optimized support vector machine(FAOSVM),a diesel en-gine fault diagnosis method based on EHFE and FAOSVM is proposed.The experimental data of diesel engine are analyzed.The results show that compared with the existing methods,the proposed method can fully charac-terize the mode information of diesel engine fault signal,and effectively identify the fault of timing gear of diesel engine,and the identification accuracy reaches 99.6%.In particular,it can also achieve better recognition accu-racy under very small samples.
关键词
强化层次模糊熵/柴油机/正时齿轮/故障诊断/萤火虫算法优化支持向量机Key words
enhanced hierarchical fuzzy entropy(EHFE)/diesel engine/timing gear/fault diagnosis/firefly al-gorithm optimized support vector machine(FAOSVM)引用本文复制引用
基金项目
内燃机可靠性国家重点实验室开放基金(skler-202009)
天津市研究生科研创新资助项目(2021YJSB182)
出版年
2024
NETL
NSTL
万方数据