Research on equipment health of distributed energy power station based on improved Mahalanobis distance

CHEN Ziyang; PENG Daogang; XU Chunmei; ZHAO Huirong

doi:10.19666/j.rlfd.202212198

English Version Reader LoginJournal Login

您当前的位置：

首页 >

文章列表页 >

Research on equipment health of distributed energy power station based on improved Mahalanobis distance

更新时间：2025-09-28

- Research on equipment health of distributed energy power station based on improved Mahalanobis distance
- Thermal Power Generation Vol. 52, Issue 8, Pages: 188-196(2023)
- 作者机构：
  
  上海电力大学自动化工程学院
- 作者简介：
- 基金信息：
- DOI：10.19666/j.rlfd.202212198
  CLC： TM62;TP18
- Published：2023
- 稿件说明：
移动端阅览
CHEN Ziyang, PENG Daogang, XU Chunmei, et al. Research on equipment health of distributed energy power station based on improved Mahalanobis distance[J]. Thermal power generation, 2023, 52(8): 188-196.
DOI：

CHEN Ziyang, PENG Daogang, XU Chunmei, et al. Research on equipment health of distributed energy power station based on improved Mahalanobis distance[J]. Thermal power generation, 2023, 52(8): 188-196. DOI： 10.19666/j.rlfd.202212198.

摘要

分布式能源电站以其清洁环保、经济高效得到快速发展，但其电站设备用于故障诊断的数据较少，目前急需一种能够预测设备运行健康状态和老化程度的方法。基于此，提出一种能够分析设备运行状态、获取设备劣化演变趋势的预测模型。首先将设备多维数据进行预处理，采用层次分析法与高斯混合分布相结合，定量地构建一种基于改进马氏距离的分布式能源电站设备健康度模型；然后建立基于改进麻雀算法和长短时记忆神经网络的组合预测模型，对分布式能源电站设备的劣化情况做趋势预测及相关分析。实验结果表明，所提出的融合健康度模型在分布式能源电站实际故障数据不足的情况下，能够在设备出现异常时做出预测。

Abstract

Distributed energy power stations are developing rapidly because of their cleanliness

environmental protection

economy and high efficiency. However

there are few data used for fault diagnosis of plant equipment

so a method to predict the health state and aging degree of equipment is urgently needed. Based on this

a prediction model which can analyze the running state of equipment and obtain the deterioration trend of equipment is proposed.Firstly

multi-dimensional data of the equipment is preprocessed

and an improved Mahalanobis distance based equipment health model of distributed energy power station is constructed quantitatively by combining the analytic hierarchy process(AHP) with Gaussian mixture distribution. Then

the combined prediction model based on the improved sparrow algorithm and short and long time memory neural network is established to predict the trend and correlation analysis of the deterioration of distributed energy power plant equipment. The experimental results show that the proposed fusion health model can predict equipment anomalies in the case of insufficient actual fault data of distributed energy power stations.

关键词

Keywords

references

Views

167

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Online optimization for collaborative treatment of CO and multi-pollutant emission reduction based on particle swarm optimization

Short-term photovoltaic power generation forecast based on improved sparrow search algorithm optimized support vector machine

Research on deterioration trend of primary pipeline in nuclear power plant based on data-driven modeling

Combustion optimization of utility boilers based on ISSA and KELM

Related Author

QU Peipei

JIN Hangliang

XU Bitao

WU Jun

WU Yanyan

CHEN Linghong

KANG Ziwei

SHI Ruijing

Related Institution

College of Energy Engineering, Zhejiang University

Hangzhou Hanglian Thermal Power Co., Ltd

Hangzhou Heda Energy Co., Ltd

College of Electrical Engineering, Xinjiang University

Department of New Energy Science and Engineering, Xinjiang Institute of Technology

AI问答

⁰