复杂生产过程的小故障检测与分类方法

张敏; 程文明; 刘娟

doi:10.3969/j.issn.0258-2724.2014.05.016

复杂生产过程的小故障检测与分类方法

doi: 10.3969/j.issn.0258-2724.2014.05.016

基金项目:

中央高校基本科研业务费专项资金资助项目（2682014BR022）

国家自然科学基金资助项目（51205328，51175442）

教育部人文社会科学研究青年基金资助项目（12YJCZH296）

计量
- 文章访问数: 789
- HTML全文浏览量: 56
- PDF下载量: 548
- 被引次数: 0
出版历程
- 收稿日期: 2013-09-20
- 刊出日期: 2014-10-25

Small Fault Detection and Classification Method for Complex Production Process

摘要

摘要: 为监测复杂生产过程的状态，根据多元统计过程控制方法和支持向量机理论，将累积和控制图原理扩展为多变量的形式对过程数据进行预处理，并通过主元分析方法提取复杂生产过程的关键信息，得到有效的小故障数据，进而构建计算正常数据的统计量阀值及故障数据的Hotelling T平方统计值（T2）和平方预测误差值，实现了复杂生产过程的小故障模式检测，并采用支持向量机多分类方法将检测到的故障进行了分类.沥青混合料生产过程的仿真研究表明：在集料均值发生小波动、周期性上升和下降3种小故障模式下，故障检测识别率均达到95%，与主元分析方法相比平均提高了75%；分类准确率达到92.5%，与BP神经网络方法相比提高了19.3%.
- 故障检测与分类 /
- 主元分析 /
- 支持向量机 /
- 多变量累积和
Abstract: In order to monitor the condition of a complex production process, based on the multivariate statistical process control and support vector machine theory, the cumulative control chart principle was extended to multivariate form for data preprocessing, and the principal component analysis (PCA) was utilized to extract significant information from the complex production process. The effective data of small fault was obtained. Then, the statistical threshold values of normal data, statistic T2, and squared prediction error (SPE) of corresponding fault data were constructed to realize the small fault detection of the complex production process, and the support vector machine (SVM) multi-classification method was used to classify the detected fault modes. The simulation results of a hot mix asphalt production process show that in cases of small fluctuation, cyclical rise and fall respectively, the small fault detection recognition rate is about 95%, with an average improvement of 75% over the PCA method; the classification accuracy rate reaches 92.5%, improved 19.3% compared with the BP neural networks method.
- small fault detection and classification /
- principal component analysis /
- support vector machine /
- multivariate cumulative sum

HTML全文

参考文献(15)

RUNGER G C, ALT F B, MONTGOMERY D C. Contributors to a multivariate statistical process control chart signal[J]. Communications in Statistics: Theory and Methods, 1996, 25(10): 2203-2213.

WESTERHUIS J, GURDEN S P, SMILDE A K. Generalized contribution plots in multivariate statistical process monitoring[J]. Chemometrics and Intelligent Laboratory Systems, 2000, 51(1): 95-114.

LIEFTUCHT D, KRUGER U, XIE L, et al. Statistical monitoring of dynamic multivariate processes, part 2: identifying fault magnitude and signature[J]. Industrial and Engineering Chemistry Research, 2006, 45(5): 1677-1688.

钱淑华,王新晴,李焕良. 二次型时频分布在机械故障诊断中的应用[J]. 西南交通大学学报,2003, 38(5): 578-580. QIAN Shuhua, WANG Xinqing, LI Huanliang. Application of quadric time-frequency distribution to mechanical fault diagnosis[J]. Journal of Southwest Jiaotong University, 2003, 38(5): 578-580.

WANG H Q, SONG Z H, LI P. Fault detection behavior and performance analysis of principal component analysis based process monitoring methods[J]. Industrial and Engineering Chemistry Research, 2002, 41(10): 2455-2464.

GE Zhiqiang, SONG Zhihuan, YANG Chujie. Small shift detection based on MCUSUM-ICA-PCA[J]. Journal of Zhejiang University: Engineering Science, 2008, 42(3): 373-411.

ZHANG Min, CHENG Wenming. Fault diagnosis method based on wavelet packet transform and kernel principal component analysis[J]. Journal of Compu-tational Information Systems, 2012, 8(14): 5835-5842.

邱天,白晓静,郑茜予,等. 多元指数加权移动平均主元分析的微小故障检测[J]. 控制理论与应用,2014,31(1): 19-26. QIU Tian, BAI Xiaojing, ZHENG Xiyu, et al. Incipient fault detection of multivariate exponentially weighted moving average principal component analysis[J]. Control Theory and Applications, 2014, 31(1): 19-26.

张杰,阳宪惠. 多变量统计过程控制[M]. 北京:化学工业出版社,2000: 30-70.

LAU K W, WU Q H. Online training of support vector classifier[J]. Pattern Recognition, 2003, 36(8): 1913-1920.

COSTACHE G N, CORCORAN P, PUSLECKI P. Combining PCA-based datasets without retraining of the basis vector set[J]. Pattern Recognition Letters, 2009, 30(16): 1441-1447.

TAMURA M, TSUJITA S. A study on the number of principal components and sensitivity of fault detection using PCA[J]. Computers and Chemical Engineering, 2007, 31(9): 1035-1046.

RANAEE V, EBRAHIMZADEH A, GHADERI R. Application of the PSO-SVM model for recognition of control chart patterns[J]. ISA Transaction, 2010, 49(4): 577-586.

秦娜,金炜东,黄进,等. 基于EEMD样本熵的高速列车转向架故障特征提取[J]. 西南交通大学学报,2014,49(1): 27-32. QIN Na, JIN Weidong, HUANG Jin, et al. Feature extraction of high speed train bogie based on ensemble empirical mode decomposition and sample entropy[J]. Journal of Southwest Jiaotong University, 2014, 49(1): 27-32.

ABADURMUS O, PATHAK O, SMITH J S, et al. A simulation methodology for online process control of hot mix asphalt (HMA) production[C]//Proceedings of the 2010 Winter Simulation Conference. Baltimore:[s.n.], 2010: 522-1533.

施引文献

附加材料(0)

访问统计

点击查看大图

计量

文章访问数: 789
HTML全文浏览量: 56
PDF下载量: 548
被引次数: 0

复杂生产过程的小故障检测与分类方法

doi: 10.3969/j.issn.0258-2724.2014.05.016

计量

出版历程

Small Fault Detection and Classification Method for Complex Production Process

计量

出版历程

目录