| 基于工厂数据的注意力LSTM网络辨识方法 |
| |
| 引用本文： | 王雅欣,徐宝昌,徐朝农,董秀娟,许立伟. 基于工厂数据的注意力LSTM网络辨识方法[J]. 化工学报, 2020, 71(12): 5664-5671. DOI: 10.11949/0438-1157.20201067 |
| |
| 作者姓名： | 王雅欣 徐宝昌 徐朝农 董秀娟 许立伟 |
| |
| 作者单位： | 1.中国石油大学（北京）信息科学与工程学院，北京 102249;2.中国石油北京天然气管道有限公司，北京 100012 |
| |
| 基金项目： | 中国石油天然气集团有限公司-中国石油大学(北京)战略合作科技专项 |
| |
| 摘 要： | 化工企业控制系统日益复杂,辨识被控对象模型是自动控制和优化设计的首要任务。针对化工过程多数辨识实验需要对过程施加测试信号,可能导致生产中断或引发安全事故的问题,利用长短时记忆(long short-term memory,LSTM)网络对含高维度、强耦合、非线性等特点的工厂时序数据具有的强适应性的特点,提出一种结合注意力机制思想的LSTM非线性动态模型辨识算法。该算法在LSTM模型基础上考虑输入变量对目标变量的重要性,为输入序列中影响输出结果的关键特征分配更多注意力,提高了LSTM模型的泛化能力。基于工厂日常运行数据构建LSTM网络模型可作为被辨识对象的数字化虚拟装置,利用人工测试信号在虚拟装置上离线辨识局部线性模型。在Tennessee-Eastman (TE)过程上的辨识实验验证了本文方法的有效性。
|
| 关 键 词： | 化工过程建模 系统辨识 非线性动态模型 长短时记忆 数字化虚拟装置 |
| 收稿时间： | 2020-07-30 |
Attention LSTM network identification method based on factory data |
| |
| WANG Yaxin,XU Baochang,XU Chaonong,DONG Xiujuan,XU Liwei. Attention LSTM network identification method based on factory data[J]. Journal of Chemical Industry and Engineering(China), 2020, 71(12): 5664-5671. DOI: 10.11949/0438-1157.20201067 |
| |
| Authors: | WANG Yaxin XU Baochang XU Chaonong DONG Xiujuan XU Liwei |
| |
| Affiliation: | 1.College of Information Science and Engineering，China University of Petroleum(Beijing), Beijing 102249, China;2.PetroChina Beijing Gas Pipeline Co. , Ltd. , Beijing 100012, China |
| |
| Abstract: | The control system of chemical enterprises is becoming more and more complex, and identifying the controlled object model is the primary task of automatic control and optimization design. In view of the problem that most chemical process identification experiments need to apply test signals to the process, which may lead to production interruption or safety accidents, a long short-term memory(LSTM) nonlinear dynamic model identification algorithm combined with attention mechanism is proposed to adapt to plant time series data with characteristics of high dimension, strong coupling and nonlinearity. Based on LSTM model, the algorithm considers the importance of the input variables to the target variables, pays more attention to the key features that affect the output results in the input sequence, and improves the generalization ability of the LSTM model. The LSTM network model based on the daily operation data of the plant can be used as the digital virtual device of the identified object, and the local linear model can be identified offline on the virtual device by using the designed test data. The identification experiments on Tennessee-Eastman (TE) process verify the effectiveness of this method. |
| |
| Keywords: | chemical process modeling system identification nonlinear dynamic model LSTM digital virtual device |
| 本文献已被 万方数据 等数据库收录！ |
| 点击此处可从《化工学报》浏览原始摘要信息 |
|
点击此处可从《化工学报》下载免费的PDF全文 |
|
