Prediction of CO?NO <sub> <i>x</i> </sub> Emissions from a Natural Gas Power Plant Using Proper Machine Learning Models
Prediction of CO?NO <sub> <i>x</i> </sub> Emissions from a Natural Gas Power Plant Using Proper Machine Learning Models
复制标题
使用适当的机器学习模型预测天然气发电厂的 CO?NO <sub> <i>x</i> </sub> 排放量
DOI：
10.1002/ente.202300041
复制
发表时间：
2023
影响因子：
3.8
通讯作者：
Kuo Po-Chih
中科院分区：
文献类型：
--
作者：
Wu Wei;Lin Yan-Ting;Liao Po-Hsuan;Aziz Muhammad;Kuo Po-Chih
实现了四种机器学习（ML）模型，包括深度神经网络，长短期记忆网络，随机森林（RF）和极端梯度提升，以预测天然气发电厂的CO-NOx排放量。一种新的特征优化方案（FOS）通过特征选择和超参数优化的顺序过程可以增强ML模型。通过训练、验证和测试过程，可靠的ML模型需要考虑高预测精度和快速训练。通过比较发现：1）FOS有效地提高了预测精度18%-67%; 2）基于FOS的RF模型是使用决策树分类器进行快速准确的CO-NOx排放预测的合适选择。
Four machine learning (ML) models including a deep neural network, a long short‐term memory network, a random forest (RF), and an extreme gradient boosting are implemented to predict CO–NOxemissions from a natural gas power plant. A new feature optimization scheme (FOS) via a sequencing process of feature selection and hyperparameter optimization can intensify the ML models. Through the procedures of training, validation, and testing, reliable ML models need to take high prediction accuracy and fast training into account. After a few comparisons, it is found that 1) the FOS effectively improves the prediction accuracy by 18%–67%; 2) the FOS‐based RF model is an appropriate option to carry out the fast and accurate prediction of CO–NOxemissions by using the decision tree classifiers.