k近邻补值方法在工业过程故障诊断中的应用

上海交通大学学报（自然版） ›› 2015, Vol. 49 ›› Issue (06): 830-836.

• 自动化技术、计算机技术 • 上一篇下一篇

k近邻补值方法在工业过程故障诊断中的应用

李元1，吴杰1，王国柱2

（1.沈阳化工大学信息工程学院, 沈阳 110142；2.东北大学信息科学与工程学院, 沈阳 110819）

收稿日期:2014-12-02 出版日期:2015-06-29 发布日期:2015-06-29
基金资助:
国家自然科学基金重点项目（61034006），国家自然科学基金项目（61174119,60774070）

k-Nearest Neighbor Imputation Method and Its Application in Fault Diagnosis of Industrial Process

LI Yuan1,WU Jie1,WANG Guozhu2

(1. College of Information Engineering, Shenyang University of Chemical Technology, Shenyang 110142, China; 2. College of Information Science and Engineering, Northeastern University, Shenyang 110819, China)

Received:2014-12-02 Online:2015-06-29 Published:2015-06-29

摘要/Abstract

摘要：

摘要：针对贡献图分析方法在故障分离方面存在拖尾效应以及不能准确定位故障变量的问题，提出一种将k近邻（kNearest Neighbor, kNN）补值与传统贡献图相结合的故障定位方法.首先利用主成分分析建模并求取综合控制指标；然后将kNN方法与综合控制指标相结合初步提取故障变量；最终用贡献图从初步提取的故障变量中确定故障根源，该方法有效地避免了正常变量的贡献值对最终诊断结果的影响.本文运用数值算例和TE过程进行仿真，并将该方法与基于重构的贡献方法比较，验证了算法的准确性和有效性.

关键词: k最近邻, 重构贡献, 贡献图, 故障诊断

Abstract:

Abstract： Aimed at the smearing effect in contribution plot method and the falt that fault variables cannot be located, this paper proposed a kNN imputation method for fault diagnosis, combining k-nearest neighbor and the contribution plot algorithm. First, PCA was adopted to build an evaluation model and calculate the combined index. Secondly, knearest neighbor imputation method and the control index were combined to extract preliminary faulty variables. Finally, the contribution plots were employed to find the fundamental faulty variables from the preliminary faults. The proposed method can avoid the influence of contribution values of normal variables effectively. A numerical example and Tennessee Eastman (TE) process were given to verify the effectiveness and accuracy of the proposed method, compared with the reconstruction-based method.

Key words: k-nearest neighbor(kNN), reconstruction-based contribution(RBC), contribution plot, fault diagnosis

中图分类号:

TP 274

李元1，吴杰1，王国柱2. k近邻补值方法在工业过程故障诊断中的应用[J]. 上海交通大学学报（自然版）, 2015, 49(06): 830-836.

LI Yuan1,WU Jie1,WANG Guozhu2. k-Nearest Neighbor Imputation Method and Its Application in Fault Diagnosis of Industrial Process[J]. Journal of Shanghai Jiaotong University, 2015, 49(06): 830-836.

参考文献

［1］Wise B M, Ricker N L, Veltkamp D F, et al. A theoretical basis for the use of principal component models for monitoring multivariate processes［J］. Process Control and Quality,1990(1):4151.

［2］S. Joe Qin. Statistical process monitoring: basics and beyond［J］. Journal of Chemometrics,2003,17:480502.

［3］Hopkins R W, Miller P, Scheible J J, et al. Method of controlling a manufacturing process using multivariate analysis: U S. Patent 5,442,562［P］.1995815.

［4］Alcala C F, Qin S J. Reconstructionbased contribution for process monitoring［J］. Automatica,2009,45(7):15931600.

［5］Dunia R, Joe Qin S. Subspace approach to multidimensional fault identification and reconstruction［J］. AIChE Journal, 1998,44(8):18131831.

［6］Yue H H, Qin S J. Reconstructionbased fault identification using a combined index［J］. Industrial & Engineering Chemistry Research,2001,40(20):44034414.

［7］Alcala C F, S. Joe Qin. Analysis and generalization of fault diagnosis methods for process monitoring［J］. Journal of Process Control, 2011,21(3):322330.

［8］周东华,李钢,李元.数据驱动的过程故障检测与诊断技术［M］.北京：科学出版社,2011.

［9］Guozhu Wang, Jianchang Liu, Yuan Li. A progressive fault detection and diagnosis method based on dissimilarity of process data［C］∥Proceeding of the IEEE International Conference on Information and Automation. Hailar,China,July 2014,12111216.

［10］Zhao C, Sun Y, Gao F. A multipletimeregion (MTR)based fault subspace decomposition and reconstruction modeling strategy for online fault diagnosis［J］. Industrial & Engineering Chemistry Research,2012,51(34):1120711217.

［11］Cover T, Hart P. Nearest neighbor pattern classification［J］. Information Theory, IEEE Transactions on,1967, 13(1):2127.

［12］He Q P, Wang J. Fault detection using the knearest neighbor rule for semiconductor manufacturing processes［J］. Semiconductor Manufacturing, IEEE Transactions on,2007,20(4):345354.

［13］CHEN H, GUO J, XIE Y. kNN Fault Detection Based on Improved Kmeans Clustering［J］. Journal of Shenyang University of Chemical Technology,2013,27(1):6973.

［14］Li Y, Zhang X. Diffusion maps based knearestneighbor rule technique for semiconductor manufacturing process fault detection［J］. Chemometrics and Intelligent Laboratory Systems,2014,136:4757.

［15］Wang Q, Liu Y B, He X, et al. Fault diagnosis of bearing based on KPCA and KNN method［J］. Advanced Materials Research,2014,986:14911496.

［16］Downs J J, Vogel E F. A plantwide industrial process control problem［J］. Computers & Chemical Engineering,1993,17(3):245255.

[1]	潘美琪, 贺兴. 基于零样本学习的风力机故障诊断方法[J]. 上海交通大学学报, 2025, 59(5): 561-568.
[2]	薛贵挺, 刘哲, 韩兆儒, 石访, 王倜, 王晓. 开关投切过程建模及其在配网故障诊断算法测试中的应用[J]. 上海交通大学学报, 2024, 58(9): 1381-1389.
[3]	张宝雷, 吴禹轲, 唐雨风. 基于CART决策树的FPSO单点系泊系统电滑环故障诊断[J]. 海洋工程装备与技术, 2024, 11(2): 95-100.
[4]	郭俊锋, 王淼生, 王智明. 基于对不平衡数据集进行二次迁移学习的滚动轴承剥落类故障诊断方法[J]. 上海交通大学学报, 2023, 57(11): 1512-1521.
[5]	刘家赫, 胡彭炜, 程海龙. 基于性能退化的复杂系统视情维修技术研究[J]. 空天防御, 2023, 6(1): 56-62.
[6]	许勇, 蔡云泽, 宋林. 基于数据驱动的核电设备状态评估研究综述[J]. 上海交通大学学报, 2022, 56(3): 267-278.
[7]	刘秀丽, 徐小力. 基于特征金字塔卷积循环神经网络的故障诊断方法[J]. 上海交通大学学报, 2022, 56(2): 182-190.
[8]	马航宇, 周笛, 卫宇杰, 吴伟, 潘尔顺. 变工况下基于自适应深度置信网络的轴承智能故障诊断[J]. 上海交通大学学报, 2022, 56(10): 1368-1377.
[9]	胡晓强，仲训昱，张霄力，彭侠夫，何荧. 基于支持向量机辅助的四轴陀螺两级故障诊断方法[J]. 上海交通大学学报, 2020, 54(11): 1151-1156.
[10]	逯程1，徐廷学1，王虹2. 基于属性粒化聚类与回声状态网络的末制导雷达故障诊断[J]. 上海交通大学学报（自然版）, 2018, 52(9): 1112-1119.
[11]	贾雷，董炜，孙新亚，吉吟东，陈华. 基于节点电压增量方程的含容差轨道电路软故障诊断[J]. 上海交通大学学报（自然版）, 2017, 51(6): 679-685.
[12]	徐兵1,2，朱亚橙2，苏俊2，范秋敏2. 基于特征Petri网建模的冷水机组故障诊断系统[J]. 上海交通大学学报（自然版）, 2015, 49(06): 923-928.
[13]	李雄杰1,2，周东华2. 混杂系统故障诊断的粒子滤波器方法[J]. 上海交通大学学报（自然版）, 2015, 49(06): 849-854.
[14]	杨旭1，彭开香1，罗浩2，KRUEGER Minjia2,宗大桥1，DING Steven X2. 基于EEMD和SVM的冷轧机垂直振动相关故障的诊断[J]. 上海交通大学学报（自然版）, 2015, 49(06): 751-756.
[15]	王秀青1，侯增广2，曾慧3，吕锋1，潘世英1. 基于多传感器信息融合的机器人故障诊断[J]. 上海交通大学学报（自然版）, 2015, 49(06): 793-798.

k近邻补值方法在工业过程故障诊断中的应用

k-Nearest Neighbor Imputation Method and Its Application in Fault Diagnosis of Industrial Process

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价