全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...
化工学报  2015 

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, PP. 351-256

Keywords: 极限学习机,互信息,故障预测,多元时序,趋势分析

Full-Text   Cite this paper   Add to My Lib

Abstract:

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(extremelearningmachine,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(penicillinfermentationprocess)进行仿真实验,结果验证了所提方法的有效性。

References

[1]  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
[2]  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
[3]  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
[4]  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
[5]  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
[6]  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
[7]  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
[8]  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
[9]  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
[10]  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
[11]  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
[12]  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
[13]  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
[14]  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
[15]  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
[16]  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
[17]  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
[18]  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
[19]  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
[20]  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

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133