Prediction of water wall temperature based on improved grey wolf optimizer and bidirectional long and short term memory network

ZHAN Yi; FENG Leihua; YANG Feng; ZHONG Xin

doi:10.19666/j.rlfd.202305076

English Version Reader LoginJournal Login

您当前的位置：

首页 >

文章列表页 >

Prediction of water wall temperature based on improved grey wolf optimizer and bidirectional long and short term memory network

更新时间：2025-09-28

- Prediction of water wall temperature based on improved grey wolf optimizer and bidirectional long and short term memory network
- Thermal Power Generation Vol. 53, Issue 1, Pages: 188-196(2024)
- 作者机构：
  
  1. 长沙理工大学能源与动力工程学院
  2. 华自科技股份有限公司
- 作者简介：
- 基金信息：
- DOI：10.19666/j.rlfd.202305076
  CLC： TP18;TM621
- Published：2024
- 稿件说明：
移动端阅览
ZHAN Yi, FENG Leihua, YANG Feng, et al. Prediction of water wall temperature based on improved grey wolf optimizer and bidirectional long and short term memory network[J]. Thermal power generation, 2024, 53(1): 188-196.
DOI：

ZHAN Yi, FENG Leihua, YANG Feng, et al. Prediction of water wall temperature based on improved grey wolf optimizer and bidirectional long and short term memory network[J]. Thermal power generation, 2024, 53(1): 188-196. DOI： 10.19666/j.rlfd.202305076.

摘要

提出一种基于改进灰狼（MGWO）算法优化双向长短时记忆（BiLSTM）神经网络的水冷壁壁温预测模型，灰狼算法采用非线性因子调整策略、自适应位置更新策略和动态权重修改策略进行改进以提升算法的全局寻优能力，利用改进灰狼算法优化BiLSTM模型的隐藏层数量、学习率和正则化参数以提高模型的预测精度，采用新疆某电厂的数据进行预测仿真，结果表明：改进后的算法预测精度更高，在机组升、降负荷时，均可以预测到壁温的变化趋势，模型的平均均方根误差相比于长短时记忆（LSTM）神经网络、BiLSTM模型分别降低了9.86%和3.69%，且可以提前预测到水冷壁壁温的超温情况，对于预防水冷壁超温有重要意义。

Abstract

An improved grey wolf optimizer(MGWO) is used to optimize BiLSTM to predict water wall temperature. The improved algorithm adopts nonlinear factor adjustment strategy

adaptive position update strategy and dynamic weight modification strategy to improve the global optimization ability of the GWO. The improved grey wolf optimizer is used to optimize the number of hidden layers

learning rate and regularization parameters of the BiLSTM model to improve the prediction accuracy of the model. The data of a power plant in Xinjiang are used for prediction simulation. The results show that

the improved optimizer has higher prediction accuracy

and can predict the change trend of wall temperature when the unit is lifting and lowering load. Compared with the LSTM and BiLSTM models

the average root mean square error of the model reduces by 9.86% and 3.69%

respectively

and the overtemperature of water wall temperature can be predicted in advance

which is of great significance for the prevention of overtemperature of water wall.

关键词

Keywords

references

Views

368

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

CAUSE ANALYSIS OF WATER-WALL TUBE BURST AND LEAKAGE FOR A 2100t/h BOILER

STUDY ON HIGH-TEMPERATURE CORROSION OF WATER-WALL IN UTILITY BOILER AND PREVENTION THEREOF

CAUSE ANALYSIS OF HIGH TEMPERATURE CORROSION ON WATER WALL OF SUPERCRITICAL ONCE-THROUGH BOILERS AND COUNTERMEASURES THEREOF

High temperature corrosion in wall-firing boiler:reason analysis and treatment

Flow distribution characteristics of water wall in a 600MW unit boiler in thermal state

Related Author

HE Wang-fei

YE Gang

FU Hong

ZHANG Bai-quan

LI YongChina Mining University

ZHONG Wan-li

WU Shi-deng

ZENG Fan-yun Guangdong Electric Power Science Research Institute

Related Institution

Guangdong Electric Power Test and Research Institute Dongguan

Shajiao C Power Plant

China University of Mining and Technology

Guangdong Electric Power Research Institute

AI问答

⁰