Turbine data cleaning based on deep LSTM

XU Xiaogang; WANG Zhixiang; WANG Huijie

doi:10.19666/j.rlfd.202210213

English Version Reader LoginJournal Login

您当前的位置：

首页 >

文章列表页 >

Turbine data cleaning based on deep LSTM

更新时间：2025-09-28

- Turbine data cleaning based on deep LSTM
- Thermal Power Generation Vol. 52, Issue 8, Pages: 179-187(2023)
- 作者机构：
  
  1. 华北电力大学动力工程系
  2. 华北电力大学河北省低碳高效发电技术重点实验室
  3. 华北电力大学保定市低碳高效发电技术重点实验室
- 作者简介：
- 基金信息：
- DOI：10.19666/j.rlfd.202210213
  CLC： TM621;TP183
- Published：2023
- 稿件说明：
移动端阅览
XU Xiaogang, WANG Zhixiang, WANG Huijie. Turbine data cleaning based on deep LSTM[J]. Thermal power generation, 2023, 52(8): 179-187.
DOI：

XU Xiaogang, WANG Zhixiang, WANG Huijie. Turbine data cleaning based on deep LSTM[J]. Thermal power generation, 2023, 52(8): 179-187. DOI： 10.19666/j.rlfd.202210213.

摘要

汽轮机运行过程会产生多样且大量数据。为适应大数据驱动及仿真建模对高质量数据的要求，高效的数据清洗十分必要。利用长短记忆层对于时序数据出色的非线性拟合能力搭建了汽轮机半监督数据清洗模型。模型选取机组的3个边界条件作为输入，对待清洗数据进行预测，根据预测值与实际值的残差完成异常值剔除，之后选用模型的预测值进行数据填充，保证数据的完整性。利用模型对某电厂650 MW机组进行数据清洗，并且为克服样本失衡给清洗模型指标选取带来的问题，对准确率进行了改进并将其作为清洗效果的衡量指标。结果表明：深度长短记忆网络的数据清洗模型改进准确率高于其他3种常见清洗方法，可有效识别数据是否异常，且可利用预测值进行数据填充，保证清洗前后数据量一致。

Abstract

A large amount of data is generated during steam turbine operation. In order to meet the requirements of high quality data driven by big data and simulation modeling

efficient data cleaning is very necessary. The semisupervised data cleaning model of steam turbine is built by using the excellent nonlinear fitting ability of long and short memory layer for time series data. The model selects three boundary conditions of the unit as input to predict the cleaning data. Outliers are eliminated according to the residual difference between the predicted value and the actual value. Then

the predicted value of the model is used to fill the data to ensure the integrity of the data. The model is used to clean the data of a 650 MW unit in a power plant. To overcome the problems caused by sample imbalance in the selection of cleaning model indicators

the accuracy rate is improved and taken as the measurement index of cleaning effect. The results show that

the improved accuracy of the data cleaning model of the deep long and short memory network is higher than that of the other three common cleaning methods

which can effectively identify whether the data is abnormal

and can use the predicted value to fill the data to ensure the consistency of data before and after cleaning.

关键词

Keywords

references

Views

430

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Dynamic prediction of pollutants emission from circulating fluidized bed unit based on CNN-GRU-MHA

SIMPLIFIED FINITEELEMENT CALCULATION MODEL OF TEMPERATURE FIELD FOR STEAM TURBINE ROTOR

APPLICATION OF SOLID SELF-LUBRICATING TECHNOLOGY IN POWER PLANTS

STUDY ON CONTROL SYSTEM SETTING OF DOUBLE EXTRACTION ADJUSTABLE STEAM TURBINE

ANALYSIS OF FAULTS OCCURRED IN SYNCHRONIZATION WITH POWER NETWORK FOR TAKING INITIAL LOAD BY STEAM TURBINE OF A 180MW GAS AND STEAM TURBINE COMBINED CYCLE UNIT

Related Author

WANG Yongquan

GAO Mingming

WANG Weihua

ZHANG Pengxin

CHENG Yongqiang

LUO Juan

HU Niansu

QI Haitao

Related Institution

National Key Laboratory of New Energy Power System (North China Electric Power University)

School of Control and Computer Engineering (North China Electric Power University)

Wuhan University

Zhangze Power Plant

AI问答

⁰