Novel Pattern Recognition Using Bootstrap-Based Discriminant Locality-Preserving Projection and Its Application to Fault Diagnosis
Novel Pattern Recognition Using Bootstrap-Based Discriminant Locality-Preserving Projection and Its Application to Fault Diagnosis
复制标题
基于Bootstrap的判别局部保持投影的新型模式识别及其在故障诊断中的应用
DOI：
10.1021/acs.iecr.9b03752
复制
发表时间：
2019-09
影响因子：
4.2
通讯作者：
Qun-Xiong Zhu
中科院分区：
文献类型：
--
作者：
Yan-Lin He;Xiaona Yan;Qun-Xiong Zhu
为了保证复杂过程工业的安全，准确的故障诊断是非常重要和必要的。基于模式识别的故障诊断技术已被广泛应用于故障诊断领域。提出了一种基于Bootstrap的判别式局部保持投影的模式识别方法。在所提出的基于引导的判别局部保持投影方法中，引导被用于重新采样和构造类内数据组。因此，判别式保局投影的矩阵分解问题可以借助于类内数据来解决。此外，该模型还采用了一种新的邻接图，该邻接图由一个k-最近邻图和一个k-最远邻图组成，以寻找最能区分不同类别的子空间，使类间距离最大化，类内距离最小化.为了验证所提出的基于Bootstrap的判别局部保持投影方法的性能，使用二维合成数据集和田纳西伊士曼过程进行了案例研究。仿真结果表明，与其他方法相比，Bootstrap-DLPP方法具有更好的直观性和更高的故障诊断准确率。
For the sake of ensuring the safety of complex process industries, accurate fault diagnosis is very important and necessary. Pattern recognition-based techniques have been successfully and widely applied to fault diagnosis. In this article, a novel pattern recognition method using bootstrap-based discriminant locality-preserving projection is proposed. In the proposed bootstrap-based discriminant locality-preserving projection method, a bootstrap is used to resample and construct groups of within-class data. As a result, the matrix decomposition problem of the discriminant locality- preserving projection can be solved with the aid of within-class data. In addition, a novel adjacency graph consisting of a k-nearest-neighbor graph and a k-furthest-neighbor graph is adopted in the proposed model to seek the subspace that best discriminates the different classes, where the distance between class is maximized, while the distance within class is minimized. To verify the performance of the proposed bootstrap-based discriminant locality-preserving projection method, case studies using a two-dimensional synthetic dataset and the Tennessee Eastman process are carried out. Simulation results indicate that compared with some other methods, the proposed Bootstrap-DLPP method can achieve a better visual intuition and a higher accuracy in fault diagnosis.
登录
查看更多内容
DOI：
10.1109/tpami.2005.55
发表时间：
2005-03-01
影响因子：
23.6
作者：
He, XF;Yan, SC;Zhang, HJ
通讯作者：
Zhang, HJ
影响因子：
4.2
作者：
Leo H. Chiang;Benben Jiang;Xiaoxiang Zhu;Dexian Huang;R. Braatz
通讯作者：
Leo H. Chiang;Benben Jiang;Xiaoxiang Zhu;Dexian Huang;R. Braatz
影响因子：
2.4
作者：
Barker, M;Rayens, W
通讯作者：
Rayens, W
影响因子：
4.3
作者：
Komulainen, T;Sourander, M;Jämsä-Jounela, SL
通讯作者：
Jämsä-Jounela, SL
影响因子：
4.2
作者：
S. Stubbs;Jie Zhang;Julian Morris
通讯作者：
S. Stubbs;Jie Zhang;Julian Morris