| 何成,游溢,王宗江,黄路遥,张强,陈云,卢壹梁,杨丙坤,王晓芳.电网碳钢材料腐蚀预测模型研究[J].装备环境工程,2025,22(2):151-159. HE Cheng,YOU Yi,WANG Zongjiang,HUANG Luyao,ZHANG Qiang,CHEN Yun,LU Yiliang,YANG Bingkun,WANG Xiaofang.Corrosion Prediction Model of Carbon Steel for Power Grid[J].Equipment Environmental Engineering,2025,22(2):151-159. |
| 电网碳钢材料腐蚀预测模型研究 |
| Corrosion Prediction Model of Carbon Steel for Power Grid |
| 投稿时间：2024-07-18 修订日期：2024-08-13 |
| DOI：10.7643/issn.1672-9242.2025.02.017 |
| 中文关键词: 电网 碳钢 大气腐蚀 机器学习 寿命预测 预测精度中图分类号:TG172 文献标志码:A 文章编号:1672-9242(2025)02-0151-09 |
| 英文关键词:power grid carbon steel atmospheric corrosion machine learning service life prediction prediction accuracy |
| 基金项目:国网新疆电力有限公司科技项目(5230DK230016) |
|
|
| Author | Institution |
| HE Cheng | Electric Power Science and Research Institute of State Grid Xinjiang Electric Power Co., Ltd., Urumqi 830011, China |
| YOU Yi | Electric Power Science and Research Institute of State Grid Xinjiang Electric Power Co., Ltd., Urumqi 830011, China |
| WANG Zongjiang | Electric Power Science and Research Institute of State Grid Xinjiang Electric Power Co., Ltd., Urumqi 830011, China |
| HUANG Luyao | China Electric Power Research Institute, Beijing 100192, China;State Grid Smart Grid Research Institute Co., Ltd., Beijing 102209, China |
| ZHANG Qiang | China Electric Power Research Institute, Beijing 100192, China;State Grid Smart Grid Research Institute Co., Ltd., Beijing 102209, China |
| CHEN Yun | China Electric Power Research Institute, Beijing 100192, China;State Grid Smart Grid Research Institute Co., Ltd., Beijing 102209, China |
| LU Yiliang | China Electric Power Research Institute, Beijing 100192, China;State Grid Smart Grid Research Institute Co., Ltd., Beijing 102209, China |
| YANG Bingkun | China Electric Power Research Institute, Beijing 100192, China;State Grid Smart Grid Research Institute Co., Ltd., Beijing 102209, China |
| WANG Xiaofang | China Electric Power Research Institute, Beijing 100192, China;State Grid Smart Grid Research Institute Co., Ltd., Beijing 102209, China |
|
| 摘要点击次数: |
| 全文下载次数: |
| 中文摘要: |
| 目的 研究新疆地区典型环境因素对典型电网用碳钢材料腐蚀的影响。方法 根据采集到的新疆地区155组腐蚀及环境数据，通过支持向量回归(SVR)、梯度提升算法(GBoost)、皮尔逊相关系数(PCC)、逐点互信息(PMI)和随机森林(RF)等5种方式对输入变量进行特征选择，分析11种典型环境因素对典型电网用碳钢材料腐蚀速率的影响，选择重要性排序前5输入变量并集，进行Sobol敏感性分析。采用经主成分分析进行降维处理构建的SVR模型和利用梯度提升算法优化损失函数构建的GBoost模型预测腐蚀速率，研究2种模型的性能和预测能力。结果 对新疆地区典型电网用碳钢材料碳钢大气腐蚀影响较为重要的前5个特征依次是年降水量、年均湿度、年均温差、PM10和O3，GBoost模型相比于SVR模型在预测影响碳钢腐蚀的环境因素方面表现出较高的准确性和可靠性。结论 GBoost模型具有更好地预测泛化能力和模型解释力，能够有效捕捉碳钢腐蚀速率与环境因素之间的复杂关系。 |
| 英文摘要: |
| The work aims to investigate the influence of typical environmental factors on the corrosion rate of carbon steel used in Xinjiang power grid. Based on 155 sets of corrosion and environmental data collected from Xinjiang, feature selection of input variables was accomplished through the application of five distinct methods, namely Support Vector Regression (SVR), Gradient Boosting algorithm (GBoost), Pearson Correlation Coefficient (PCC), Pointwise Mutual Information (PMI), and Random Forest (RF). The influence of 11 typical environmental factors on the corrosion rate of typical carbon steel used in power grids was analyzed. The top five input variables ranked by their significance, were chosen and amalgamated for the Sobol sensitivity examination. Principal component analysis (PCA) was conducted to construct a SVR model and GBoost was used to optimize loss function to construct a GBoost model to predict the corrosion rate. The performance and prediction ability of the two models were studied. The result showed that the top five environmental factors are, in turn, annual precipitation, annual humidity, annual temperature difference, PM10 and O3. Compared with the SVR model, the GBoost model shows higher accuracy and reliability in predicting the correction rate of carbon steel in Xinjiang. In conclusion, the GBoost model has better predictive generalization ability and model explanatory ability, and can effectively capture the complex relationship between the corrosion rate of carbon steel and environmental factors. |
| 查看全文 查看/发表评论 下载PDF阅读器 |
| 关闭 |
|
|
|
