| 基于EMD和选择性集成学习算法的磨机负荷参数软测量 |
| |
| 引用本文： | 汤健, 柴天佑, 丛秋梅, 苑明哲, 赵立杰, 刘卓, 余文. 基于EMD和选择性集成学习算法的磨机负荷参数软测量. 自动化学报, 2014, 40(9): 1853-1866. doi: 10.3724/SP.J.1004.2014.01853 |
| |
| 作者姓名： | 汤健 柴天佑 丛秋梅 苑明哲 赵立杰 刘卓 余文 |
| |
| 作者单位： | 1.中国人民解放军92941部队 葫芦岛 125001, 中国;;;2.东北大学 自动化研究中心 沈阳 110004, 中国;;;3.中国科学院沈阳自动化研究所 信息服务与智能控制技术研究室 沈阳 110016, 中国;;;4.沈阳化工大学信息工程学院 沈阳 110142, 中国;;;5.墨西哥国立理工大学高级研究中心 墨西哥 07360, 墨西哥 |
| |
| 基金项目： | 国家自然科学基金（61034008，61004051，61203102，61020106003，61134006），111计划（B08015），国家支撑计划（2012-BAF19G00），中国博士后科学基金（2013M532118，2013M530953，2013M541820）资助 |
| |
| 摘 要： | 针对磨机筒体振动和振声信号组成复杂难以解释、蕴含信息存在冗余性和互补性、与磨机负 荷参数映射关系难以描述等问题，提出了基于经验模态分解（Empirical mode decomposition，EMD）技术和选择性集成学习算法分析 筒体振动与振声信号组成，建立磨机负荷参数软测量模型的新方法.首先从机理上定性分析了筒 体振动及振声信号组成的复杂性；然后采用EMD技术将原始信号自适应分解为具有不同时间尺度的系列组 成成分，即本征模态函数（Intrinsic mode function，IMF）；接着在频域内基于互信息（Mutual information，MI）方法分析并选择IMF频谱特征；最后采用基 于核偏最小二乘（Kernel partial least square，KPLS）建模方法、分支定界优化算法的选择性集成学习方法建立磨机负荷参数软测量模型，实现了多源多尺度频谱特征的选择性信息融合.基于实验球磨机的实际运行数据仿真验证了该方法的有效性.
|
| 关 键 词： | 经验模态分解 选择性集成建模 磨机负荷参数 选择性信息融合 频谱特征 |
| 收稿时间： | 2013-06-14 |
| 修稿时间： | 2013-11-26 |
Soft Sensor Approach for Modeling Mill Load Parameters Based on EMD and Selective Ensemble Learning Algorithm |
| |
| TANG Jian, CHAI Tian-You, CONG Qiu-Mei, YUAN Ming-Zhe, ZHAO Li-Jie, LIU Zhuo, YU Wen. Soft Sensor Approach for Modeling Mill Load Parameters Based on EMD and Selective Ensemble Learning Algorithm. ACTA AUTOMATICA SINICA, 2014, 40(9): 1853-1866. doi: 10.3724/SP.J.1004.2014.01853 |
| |
| Authors: | TANG Jian CHAI Tian-You CONG Qiu-Mei YUAN Ming-Zhe ZHAO Li-Jie LIU Zhuo YU Wen |
| |
| Affiliation: | 1. Unit 92941, PLA, Huludao 125001, China;;;2. Research Center of Automation, Northeastern University, Shenyang 110004, China;;;3. Deptartment of Information Service & Intelligent Control, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China;;;4. College of Information Engineering, Shenyang University of Chemical Technology, Shenyang 110142, China;;;5. Departamento de Control Automatico, CINVESTAV-IPN (National Polytechnic Institute), Av. IPN 2508, México City 07360, México |
| |
| Abstract: | The components of shell vibration and acoustical signals of ball mill are complexity and difficult to interpret. Moreover, the useful information contained in these signals is redundancy and complementary, and the mapping relationships between these signals and mill load parameters are difficult to describe. Aiming at these problems, a new soft sensor approach is proposed, which analyzes shell vibration and acoustical signals for modeling mill load parameters based on empirical mode decomposition (EMD) technology and selective ensemble learning algorithm. At first, the complexity of the shell vibration and acoustical signals are analyzed based on the production mechanism. Then, these signals are adaptive decomposed into a number of intrinsic mode functions (IMFs) with different time-scales using EMD technology, and the spectral features of IMFs are analyzed and selected based on the mutual information (MI) method. At last, the selective ensemble learning algorithm based on kernel partial least square modeling approach and the brand and bound optimal algorithm are used to construct soft sensor models of mill load parameters. Thus, the selective information fusion based on multi-source frequency spectrum features is realized. The simulation results based on operating data from the laboratory ball mill validate the proposed approach. |
| |
| Keywords: | Empirical mode decomposition (EMD) selective ensemble learning mill load parameters selective information fusion frequency spectrum |
| 本文献已被 CNKI 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 |
|
