Journal of Computer Applications ›› 2020, Vol. 40 ›› Issue (11): 3400-3406.DOI: 10.11772/j.issn.1001-9081.2020030291

• Frontier & interdisciplinary applications • Previous Articles     Next Articles

Data driven time delay identification and main steam temperature prediction in thermal power units

GUI Ning1, HUA Jingyun2   

  1. 1. School of Computer Science and Engineering, Central South University, Changsha Hunan 410083, China;
    2. School of Information Science and Technology, Zhejiang Sci-Tech University, Hangzhou Zhejiang 310038, China
  • Received:2020-03-16 Revised:2020-06-09 Online:2020-11-10 Published:2020-07-06
  • Supported by:
    This work is partially supported by Surface Program of the National Natural Science Foundation of China (61772473).

数据驱动下火电机组时延鉴别及主汽温度预测

桂宁1, 华菁云2   

  1. 1. 中南大学 计算机学院, 长沙 410083;
    2. 浙江理工大学 信息学院, 杭州 310038
  • 通讯作者: 华菁云(1994-),女,江苏无锡人,硕士,主要研究方向:工业大数据;huajingyun@hotmail.com
  • 作者简介:桂宁(1977-),男,湖南长沙人,副教授,博士,CCF会员,主要研究方向:可解释的工业智能
  • 基金资助:
    国家自然科学基金面上项目(N61772473)。

Abstract: With massive features and long unit delays, it is very difficult to effectively select the most appropriate features and corresponding delays during the modeling of the main steam temperature of thermal power unit. Therefore, a modeling method of the fusion model jointly considering feature selection and delay selection was proposed. Aiming at the high dimensionality of the features of thermal power units, the features highly associated with the main steam temperature were selected through the correlation coefficients and the feature selection of gradient boosting machine. For the delay identification, the Temporal Correlation Coefficient-based Time Delay(TD-CORT) calculation algorithm was designed to estimate the time delay between each parameter and the predicted target main steam temperature. And the automatic matching of the sliding window size was realized for the prediction target and the calculation complexity. Finally, the fusion model of Deep Neural Network (DNN) and Long Short-Term Memory (LSTM) was used to predict the main steam temperature of the thermal power unit. The deployment results on a 1 000 MW ultra-supercritical coal-fired unit in China show that the proposed method has the prediction Mean Absolute Error (MAE) value of 0.101 6, and the prediction accuracy 57.42% higher than the neural network without considering the delay.

Key words: thermal power unit, time delay calculation, main steam temperature, feature selection, deep learning

摘要: 针对传统的火电机组主汽温度建模时在海量特征和长机组延迟下的特征及对应时延的有效选择困难的问题,提出一种综合考虑特征选择和时延选择的融合模型的建模方法。针对火电机组特征的高维性,通过结合相关性系数和梯度提升机的特征选择以筛选出与主汽温度高相关的特征。针对时延鉴别,设计基于相关度的时延计算(TD-CORT)算法用以估计各参数与预测目标主汽温度之间的时延大小,并为预测目标和计算复杂度实现了滑动窗口大小的自动匹配。最后,采用深度神经网络(DNN)与长短期记忆(LSTM)的融合模型实现对火电机组主汽温度的预测。在国内某1 000 MW超超临界燃煤机组的部署结果表明,所提方法的预测平均绝对误差(MAE)值达到0.101 6,该方法相较未考虑时延的神经网络在预测准确度上提升了57.42%。

关键词: 火电机组, 时延计算, 主汽温度, 特征选择, 深度学习

CLC Number: