基于多元时序驱动的ELM全流程故障预测及其应用

doi:10.11949/j.issn.0438-1157.20141452

化工学报 ›› 2015, Vol. 66 ›› Issue (1): 351-256.DOI: 10.11949/j.issn.0438-1157.20141452

基于多元时序驱动的ELM全流程故障预测及其应用

徐圆, 卢玉帅, 才轶

北京化工大学信息与科学技术学院, 北京 100029

收稿日期:2014-09-25 修回日期:2014-10-05 出版日期:2015-01-05 发布日期:2015-01-05
通讯作者: 徐圆
基金资助:
国家自然科学基金项目(61104131);北京市自然科学基金项目(4142039);北京市优秀人才培养资助D类(2013D009016000004)。

Multiple timing-driven based extreme learning machine whole process fault prediction and its application

XU Yuan, LU Yushuai, CAI Yi

College of Information Science & Technology, Beijing University of Chemical Technology, Beijing 100029, China

Received:2014-09-25 Revised:2014-10-05 Online:2015-01-05 Published:2015-01-05
Supported by:
supported by the National Natural Science Foundation of China (61104131), the Natural Science Foundation of Beijing (4142039) and the Programs for Beijing Excellent Talents D (2013D0009016000004).

摘要/Abstract

摘要：

多元时序驱动建模方法是复杂系统故障预测和系统状态评估的一种有效途径, 其中人工神经网络作为一种数据驱动的处理非线性问题的有效建模工具, 近年来在处理多元时序建模这个问题上得到了较广泛的关注。从全流程的角度出发, 首先, 运用k-近邻互信息方法对多元时序变量进行降维与相关性计算, 从而选择特征变量;其次, 提出了一种改进的趋势分析方法对系统的状态进行实时监测, 并对系统运行状态进行有效细分;最后, 针对系统潜在故障阶段, 应用极限学习机(extreme learning machine, ELM)神经网络方法对其进行故障预测。通过对青霉素发酵过程(penicillin fermentation process)进行仿真实验, 结果验证了所提方法的有效性。

关键词: 极限学习机, 互信息, 故障预测, 多元时序, 趋势分析

Abstract:

A multiple timing-driven modeling method is an effective way for fault prediction and state evaluation of complex system, in which the artificial neural network is an effective data-driven modeling tool to deal with the nonlinear problems. Recently, it has been widely concerned on the multiple timing-driven modeling problems. In the paper, from the perspective of the whole process, the k-nearest neighbor mutual information method is firstly used to reduce the dimension of the multiple timing variables and calculate the correlation among the variables, so as the select the characteristic variable. Second, an improved trend analysis method is proposed to monitor the system state in real time and segment the system operation state. Finally, aiming at the potential fault stage, extreme learning machine (ELM) neural network is used for fault prediction. Through the simulation experiment on penicillin fermentation process, the results verify the effectiveness of the proposed method.

Key words: extreme learning machine, mutual information, fault prediction, multi-timing, trend analysis

中图分类号:

TP206⁺.3

徐圆, 卢玉帅, 才轶. 基于多元时序驱动的ELM全流程故障预测及其应用[J]. 化工学报, 2015, 66(1): 351-256.

XU Yuan, LU Yushuai, CAI Yi. Multiple timing-driven based extreme learning machine whole process fault prediction and its application[J]. CIESC Journal, 2015, 66(1): 351-256.

参考文献 20

[1]	Ai Hong(艾红), Zhou Donghua(周东华). Fault prediction approach for dynamic system [J]. Journal of Huazhong University of Science and Technology: Natural Science Edition (华中科技大学学报:自然科学版), 2009, 37(1): 222-225
[2]	Sun Qiang(孙强), Yue Jiguang(岳继光). Review on fault prognostic methods based on uncertainty [J]. Control and Decision(控制与决策), 2014, 29(5): 1-10
[3]	Xu Yuan(徐圆), Liu Ying(刘莹), Zhu Qunxiong(朱群雄). A complex process fault prognosis approach based on multivariate delayed sequences [J]. CIESC Journal(化工学报), 2013, 64(12): 4290-4295
[4]	Zhang Zhengdao(张正道), Hu Shousong(胡寿松). Fault prediction for nonlinear time series based on unknown input observer [J]. Control and Decision(控制与决策), 2005, 20(7): 769-772
[5]	Hu Shousong(胡寿松), Zhang Zhengdao(张正道). Fault prediction for nonlinear time series based on neural network [J]. Acta Automatica Sinica (自动化学报), 2007, 33(7): 744-748
[6]	Zhang Zhengdao(张正道), Cui Baotong (崔宝同). On-line fault prediction of system based on hiding semi Markov model [J]. Control and Decision(控制与决策), 2010, 25(12): 1853-1856
[7]	De Carvalho A B, Pozo A, Vergilio S R. A symbolic fault-prediction model based on multiobjective particle swarm optimization [J]. Journal of Systems and Software, 2010, 83(5): 868-882
[8]	Si X S, Hu C H, Yang J B, et al. On the dynamic evidential reasoning algorithm for fault prediction [J]. Expert Systems with Applications, 2011, 38(5): 5061-5080
[9]	Kim H E, Tan A C C, Mathew J, et al. Bearing fault prognosis based on health state probability estimation [J]. Expert Systems with Applications, 2012, 39(5): 5200-5213
[10]	Herman G, Zhang B, Wang Y, et al. Mutual information-based method for selecting informative feature sets [J]. Pattern Recognition, 2013, 46(12): 3315-3327
[11]	Lü Ning(吕宁), Yu Xiaoyang(于晓洋). Fault diagnosis in TE process based on feature selection via second order mutual information [J]. CIESC Journal(化工学报), 2009, 60(9): 2252-2258
[12]	Liu Xiaoxin(刘晓欣). Correlation analysis and variable selection for multivariate time series based on mutual information [D]. Dalian :Dalian University of Technology, 2013
[13]	Charbonnier S, Garcia-Beltan C, Cadet C, et al. Trends extraction and analysis for complex system monitoring and decision support [J]. Engineering Applications of Artificial Intelligence, 2005, 18(1): 21-36
[14]	Charbonnier S, Portet F. A self-tuning adaptive trend extraction method for process monitoring and diagnosis[J]. Journal of Process Control, 2012, 22(6): 1127-1138
[15]	Gao Guangyong(高光勇), Jiang Guoping(蒋国平). Prediction of multivariable chaotic time series using optimized extreme learning machine [J]. Acta Physica Sinica(物理学报), 2012, 61(4): 1-9
[16]	Wong P K, Yang Z, Vong C M, et al. Real-time fault diagnosis for gas turbine generator systems using extreme learning machine [J]. Neurocomputing, 2013, 128(3): 249-257
[17]	Peng Di(彭荻), He Yanlin(贺彦林), Xu Yuan(徐圆), Zhu Qunxiong(朱群雄). Research and chemical application of feature extraction based AANN-ELM neural network [J]. CIESC Journal(化工学报), 2012,63(9): 2920-2925
[18]	Liu Yi(刘毅), Wang Haiqing(王海清). Pensim simulator and its application in penicillin fermentation process [J]. Journal of System Simulation(系统仿真学报), 2007, 18(12): 3524-3527
[19]	Birol G, Ündey C, Cinar A. A modular simulation package for fed-batch fermentation: penicillin production [J]. Computers & Chemical Engineering, 2002, 26(11): 1553-1565
[20]	Xiong Weili(熊伟丽), Wang Xiao(王肖), Chen Minfang(陈敏芳), Xu Baoguo(徐保国). Modeling for penicillin fermentation process based on weighted LS-SVM [J]. CIESC Journal(化工学报), 2012, 63(9): 2913-2919

基于多元时序驱动的ELM全流程故障预测及其应用

Multiple timing-driven based extreme learning machine whole process fault prediction and its application

PDF (PC)

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献 20

相关文章 15

编辑推荐

Metrics

本文评价

[1]	尹刚, 李伊惠, 何飞, 曹文琦, 王民, 颜非亚, 向禹, 卢剑, 罗斌, 卢润廷. 基于KPCA和SVM的铝电解槽漏槽事故预警方法[J]. 化工学报, 2023, 74(8): 3419-3428.
[2]	郑书闽, 郭鹏程, 颜建国, 王帅, 李文博, 周淇. 微小通道内过冷流动沸腾阻力特性实验及预测研究[J]. 化工学报, 2023, 74(4): 1549-1560.
[3]	代学志,熊伟丽. 基于核极限学习机的快速主动学习方法及其软测量应用[J]. 化工学报, 2020, 71(11): 5226-5236.
[4]	于蕾, 邓晓刚, 曹玉苹, 路凯琪. 基于变量分组DTW-MCVA的不等长间歇过程故障检测方法[J]. 化工学报, 2019, 70(9): 3441-3448.
[5]	杨新, 麻哲瑞, 申赫男, 陈鸿伟. 基于多尺度特征能量-核极限学习机的双循环流化床气流堵塞故障智能诊断[J]. 化工学报, 2019, 70(7): 2616-2625.
[6]	李文静, 李萌, 乔俊飞. 基于互信息和自组织RBF神经网络的出水BOD软测量方法[J]. 化工学报, 2019, 70(2): 687-695.
[7]	张晓晗, 汪平江, 顾祥柏, 徐圆, 贺彦林, 朱群雄. 基于主元提取的鲁棒极限学习机研究及其化工建模应用[J]. 化工学报, 2019, 70(2): 475-480.
[8]	赵荣荣, 赵忠盖, 刘飞. 基于k-近邻互信息的发酵过程高斯过程回归建模[J]. 化工学报, 2019, 70(12): 4741-4748.
[9]	牛培峰, 王枭飞, 刘楠, 王愿宁, 常玲芳, 张先臣. ASOS-ELM建模方法及在汽轮机热耗率预测中的应用[J]. 化工学报, 2018, 69(9): 3924-3931.
[10]	许玉格, 孙称立, 赖春伶, 罗飞. 基于不平衡学习的集成极限学习机污水处理故障诊断[J]. 化工学报, 2018, 69(7): 3114-3124.
[11]	张雷, 张小刚, 陈华. 基于Gath-Geva算法和核极限学习机的多阶段间歇过程软测量[J]. 化工学报, 2018, 69(6): 2576-2585.
[12]	徐圆, 张伟, 张明卿, 贺彦林. 基于FEEMD-AE与反馈极限学习机组合模型预测研究与应用[J]. 化工学报, 2018, 69(3): 1064-1070.
[13]	赵帅, 宋冰, 侍洪波. 基于加权互信息主元分析算法的质量相关故障检测[J]. 化工学报, 2018, 69(3): 962-973.
[14]	刘厦, 刘石, 任婷. 基于SA-ELM的声学层析成像温度分布重建算法[J]. 化工学报, 2017, 68(6): 2434-2446.
[15]	易维淋, 田学民, 张汉元. 基于重构的半监督ELM及其在故障诊断中的应用[J]. 化工学报, 2017, 68(6): 2447-2454.