| 基于数据的改进回声状态网络在高炉煤气发生量预测中的应用 |
| |
| 引用本文： | 刘颖,赵珺,王伟,吴毅平,陈伟昌.基于数据的改进回声状态网络在高炉煤气发生量预测中的应用[J].自动化学报,2009,35(6):731-738. |
| |
| 作者姓名： | 刘颖 赵珺 王伟 吴毅平 陈伟昌 |
| |
| 作者单位： | 1.大连理工大学信息与控制研究中心 大连 116024 |
| |
| 基金项目： | 国家高技术研究发展计划(863计划) |
| |
| 摘 要： | 以钢铁企业高炉煤气系统这一复杂生产过程为背景, 针对高炉煤气发生量的预测问题, 提出一种基于数据的网络模型预测方法. 鉴于生产数据含噪高的特点, 采用经验模态分解将历史数据分解为若干独立的固有模态函数, 将小尺度函数经低通滤波器自适应去噪后, 再对数据重构以建立预测模型. 在建模过程中提出一种改进的回声状态网络, 通过奇异值分解求取网络输出权值, 克服了线性回归算法出现的病态问题, 提高了模型的预测精度. 现场实际数据预测结果表明所提出方法的有效性, 为制定煤气管网平衡调度方案提供科学的决策支持.
|
| 关 键 词： | 预测模型 回声状态网络 奇异值分解 经验模态分解 |
| 收稿时间： | 2008-12-15 |
| 修稿时间： | 2009-2-15 |
Improved Echo State Network Based on Data-driven and Its Application to Prediction of Blast Furnace Gas Output |
| |
| LIU Ying ZHAO Jun WANG Wei WU Yi-Ping CHEN Wei-Chang. Research Center of Information , Control,Dalian University of Technology,Dalian . Automation.Improved Echo State Network Based on Data-driven and Its Application to Prediction of Blast Furnace Gas Output[J].Acta Automatica Sinica,2009,35(6):731-738. |
| |
| Authors: | LIU Ying ZHAO Jun WANG Wei WU Yi-Ping CHEN Wei-Chang Research Center of Information Control Dalian University of Technology Dalian Automation |
| |
| Affiliation: | 1.Research Center of Information and Control, Dalian University of Technology, Dalian 116024;2.Automation Department, Shanghai Baosight Software Co., Ltd., Shanghai 201203;3.Energy Center, Shanghai Baosteel Co., Ltd., Shanghai 210900 |
| |
| Abstract: | Based on the complex process of blast furnace gas (BFG) system in steel industry, a network forecasting method based on data-driven is established in this paper for the prediction problem on BFG output. Since the practical data include a diversity of noises, an empirical mode decomposition approach is employed to decompose the time series signal into a group of independent intrinsic mode functions, and the formed small-scale intrinsic mode functions are de-noised by low-pass filter with an adaptive threshold. Then, the re-constructed signals are used to build the forecasting model, in which an improved echo state network is proposed and the network output weights are obtained by singular value decomposition. Therefore, the ill-conditioned problem of previous linear regression is overcome and the forecasting precision is increased. The prediction results using practical production data show the validity of the proposed method and also provide the scientific decision support for the gas resources scheduling. |
| |
| Keywords: | Prediction model echo state network (ESN) singular value decomposition (SVD) empirical mode decomposition (EMD) |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
| 点击此处可从《自动化学报》浏览原始摘要信息 |
|
点击此处可从《自动化学报》下载全文 |
|
