华南理工大学学报(自然科学版) ›› 2025, Vol. 53 ›› Issue (11): 52-61.doi: 10.12141/j.issn.1000-565X.250086

• 计算机科学与技术 • 上一篇    下一篇

基于多源数据及机器学习的电厂CO2排放计量与预测

孙尊强1, 田一淳2, 苏楠2, 郑成航3, 张振4, 杨宏旻4, 高翔3   

  1. 1.国电环境保护研究院有限公司,江苏 南京 210031
    2.北京低碳清洁能源研究院,北京 102200
    3.浙江大学 能源工程学院,浙江 杭州 310027
    4.南京师范大学 能源与机械工程学院,江苏 南京 210042
  • 收稿日期:2025-03-31 出版日期:2025-11-25 发布日期:2025-07-01
  • 通信作者: 杨宏旻(1972—),男,教授,博士生导师,主要从事能源高效清洁利用研究。 E-mail:yanghongmin@njnu.edu.cn
  • 作者简介:孙尊强(1982—),男,博士生,高级工程师,主要从事电力环境保护设计研究。E-mail: sunzunqiang@126.com
  • 基金资助:
    国家重点研发计划项目(2022YFC3701504);国家能源集团科技项目(GJNY-23-82)

CO2 Emission Measurement and Forecasting for Power Plants Based on Multi-Source Data and Machine Learning

SUN Zunqiang1, TIAN Yichun2, SU Nan2, ZHENG Chenghang3, ZHANG Zhen4, YANG Hongmin4, GAO Xiang3   

  1. 1.State Power Environmental Protection Research Institute,Nanjing 210031,Jiangsu,China
    2.National Institute of Clean and Low-Carbon Energy,Beijing 102200,China
    3.College of Energy Engineering,Zhejiang University,Hangzhou 310027,Zhejiang,China
    4.School of Energy and Mechanical Engineering,Nanjing Normal University,Nanjing 210042,Jiangsu,China
  • Received:2025-03-31 Online:2025-11-25 Published:2025-07-01
  • Contact: 杨宏旻(1972—),男,教授,博士生导师,主要从事能源高效清洁利用研究。 E-mail:yanghongmin@njnu.edu.cn
  • About author:孙尊强(1982—),男,博士生,高级工程师,主要从事电力环境保护设计研究。E-mail: sunzunqiang@126.com
  • Supported by:
    the National Key Research & Development Program of China(2022YFC3701504)

摘要:

准确的CO2排放计量与动态预测对于推动我国“双碳”目标(碳达峰与碳中和)的实现至关重要。该文结合排放因子法、CO2-CEMS法和机器学习技术,提出了一种基于多源数据融合的CO2排放计量与预测方法,旨在为燃煤电厂提供一个高效且精确的碳排放监测工具。研究中通过对比不同方法的碳排放量计算结果,评估了不同机器学习算法的性能,并基于多源数据开发了一个动态预测模型。在国能集团有限公司河北某电厂1#和3#机组上的实验结果表明,排放因子法和CO2-CEMS法的CO2排放量计算相对偏差分别为1.63%和-1.27%,两种方法具有较好的互证性。对多种机器学习模型(如XGBoost、LightGBM、AdaBoost)的性能进行了对比,在决定系数(R²)和平均绝对百分比误差(MAPE)这两个常规评价指标之外,提出一个新的筛选标准——将已训练模型应用至其他机组得到的与实测值的均值偏差xc,将其用于机器学习算法的泛化能力评估及进一步筛选,发现AdaBoost算法在预测精度和稳定性方面表现最佳,并具有更好的泛化能力与鲁棒性。采用优选的AdaBoost算法进行CO2排放的动态预测,在训练集和测试集上的决定系数均大于0.99,MAPE低于2%,表明该算法具有很高的预测准确性和稳定性,并且具有极强的泛化能力和鲁棒性。该文提出的多源数据融合方法不仅有效克服了传统方法在动态变化中的局限性,还能根据实时数据进行小时级的CO2排放量精准预测。

关键词: 二氧化碳, 碳计量, 碳预测, 排放因子法, 机器学习

Abstract:

Accurate CO2 emission measurement and dynamic forecasting are crucial for achieving China’s “dual carbon” goals (carbon peak and carbon neutrality). This study integrates the emission factor method, CO2-CEMS and machine learning technologies to propose a CO2 emission measurement and forecasting method based on multi-source data fusion, for the purpose of providing an efficient and accurate carbon emission monitoring tool for coal-fired power plants. In the investigation, by comparing the CO2 emission calculation results obtained by different methods, the performances of different machine learning algorithms are evaluated, and a dynamic forecasting model based on multi-source data is developed. Experimental results in Units 1 and 3 of a power plant of Guoneng Group Co., Ltd. in Hebei, China show that the relative deviations of CO2 emission calculations between the emission factor method and CO2-CEMS for the two units are 1.63% and -1.27%, respectively, meaning that the two methods are of good cross-validation. By comparing the performance of various machine learning models (such as XGBoost, LightGBM, and AdaBoost), beyond the two conventional evaluation metrics, namely the determination coefficient (R²) and the mean absolute percentage error (MAPE), a new selection criterion, namely the mean deviation (xc), is proposed by applying trained models to other units. Then, xc is used to assess the generalization capability of machine learning algorithms for further model screening. The results reveal that AdaBoost exhibits superior performance in prediction accuracy and stability, along with higher generalization capability and robustness. The dynamic CO2 emission forecasting using the optimized AdaBoost algorithm achieves R² values greater than 0.99 on both the training and the testing sets, with a MAPE below 2%, which indicates that the algorithm is of high prediction accuracy, stability, generalization ability and robustness. The proposed multi-source data fusion method not only effectively overcomes the limitations of traditional methods in dynamic scenarios but also enables precise hourly CO2 emission forecasting based on real-time data.

Key words: carbon dioxide, carbon measurement, carbon forecasting, emission factor method, machine learning

中图分类号: