Influencing factors of air thermal deicing temperature based on BP neural network and multi-factor weight analysis

XU Yang; CAI Anmin; WU Ziqiu; LIN Weirong; ZHANG Linwei; LI Shuiqing

doi:10.19666/j.rlfd.202208162

English Version Reader LoginJournal Login

您当前的位置：

首页 >

文章列表页 >

Influencing factors of air thermal deicing temperature based on BP neural network and multi-factor weight analysis

更新时间：2025-09-28

- Influencing factors of air thermal deicing temperature based on BP neural network and multi-factor weight analysis
- Thermal Power Generation Vol. 51, Issue 12, Pages: 131-140(2022)
- 作者机构：
  
  1. 中国华能集团清洁能源技术研究院有限公司
  2. 清华大学能源与动力工程系
- 作者简介：
- 基金信息：
- DOI：10.19666/j.rlfd.202208162
  CLC： TM614;TP183
- Published：2022
- 稿件说明：
移动端阅览
XU Yang, CAI Anmin, WU Ziqiu, et al. Influencing factors of air thermal deicing temperature based on BP neural network and multi-factor weight analysis[J]. Thermal power generation, 2022, 51(12): 131-140.
DOI：

XU Yang, CAI Anmin, WU Ziqiu, et al. Influencing factors of air thermal deicing temperature based on BP neural network and multi-factor weight analysis[J]. Thermal power generation, 2022, 51(12): 131-140. DOI： 10.19666/j.rlfd.202208162.

摘要

对典型叶片的气热除冰系统，建立全尺寸三维换热模型，对流固耦合传热过程进行模拟观察，同时，简化并构建一维换热模型，探究了环境温度等关键参数对除冰气流温度的影响；基于BP神经网络，建立环境条件与最低除冰气流温度之间的对应关系。结果显示：在叶片铺层结构与叶片流道布置的综合影响下，叶片前缘中部处气热除冰难度最大；利用BP神经网络可实现不同条件下的最低除冰气流温度的快速计算和预测；多因素权重分析显示，环境温度、PVC材料导热系数是影响最低除冰气流温度的两大关键参数；对于0.2r～r范围内的除冰，叶片长度也是影响最低除冰气流温度的关键参数，其影响权重达到14.3%。

Abstract

A full-scale three-dimensional heat transfer model is established for a typical blade air thermal deicing system

and the convection of solid coupling heat transfer process is simulated and observed. At the same time

the one-dimensional heat transfer model is simplified and constructed

and the influence of key parameters such as ambient temperature on the temperature of deicing air flow is explored. On the basis of BP neural network

the corresponding relationship between the environmental conditions and the minimum deicing air flow temperature is established. The results show that

under the comprehensive influence of the blade layer structure and the blade channel arrangement

the air thermal deicing at the middle of the blade leading edge is the most difficult. With the help of BP neural network

the rapid calculation and prediction of the minimum deicing air flow temperature under different conditions can be realized. The multi-factor weight analysis shows that

the environmental temperature and the thermal conductivity of PVC material are the two key parameters affecting the minimum deicing air flow temperature. For deicing in the range of 0.2r～r

the blade length is also a key parameter affecting the minimum deicing air flow temperature

with influence weight up to 14.3%.

关键词

Keywords

references

Views

257

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Load prediction and analysis of wind turbine based on BP neural network and multi-factor weight method

STUDY ON NONLINEAR CALIBRATION OF THERMAL POWER INSTRUMENTS

STUDY ON REAL-TIME DATA NEURAL NETWORK PREDICTION MODEL USED IN THERMAL POWER PLANTS BASED ON THE L-M ALGORITHM

STUDY ON CHARACTERISTICS OF WASTE GASIFICATION BASED ON GREY RELATION ANALYSIS AND BP NEURAL NETWORK

PREDICTION OF NO_x EMISSION BASED ON PRINCIPAL COMPONENTS AND BAYESIAN REGULARIZATION

Related Author

LI Cheng

LI Yangchun

SHI Kedeng

YANG Yan-mei

CHEN Mei-qian

LIU JieBeijing University

LI Yan-ji1

LI Run-dong1

Related Institution

Zhejiang Thermal Power Construction Company

Beijing Jiaotong University

Shenyang Institute of Chemical Technology

Dalian University of Technology

AI问答

⁰