A journal of IEEE and CAA , publishes high-quality papers in English on original theoretical/experimental research and development in all areas of automation
Advanced Search
Volume 6 Issue 5
Sep.  2019

IEEE/CAA Journal of Automatica Sinica

  • JCR Impact Factor: 15.3, Top 1 (SCI Q1)
    CiteScore: 23.5, Top 2% (Q1)
    Google Scholar h5-index: 77， TOP 5
Turn off MathJax
Article Contents
Article Navigation >  IEEE/CAA Journal of Automatica Sinica  > 2019  >  6(5): 1268-1280
Xiaogang Wang, Xiyu Liu and Yu Li, "An Incremental Model Transfer Method for Complex Process Fault Diagnosis," IEEE/CAA J. Autom. Sinica, vol. 6, no. 5, pp. 1268-1280, Sept. 2019. doi: 10.1109/JAS.2019.1911618
Citation: Xiaogang Wang, Xiyu Liu and Yu Li, "An Incremental Model Transfer Method for Complex Process Fault Diagnosis," IEEE/CAA J. Autom. Sinica, vol. 6, no. 5, pp. 1268-1280, Sept. 2019. doi: 10.1109/JAS.2019.1911618
shu

An Incremental Model Transfer Method for Complex Process Fault Diagnosis

doi: 10.1109/JAS.2019.1911618

  • College of Information Science and Engineering, Northeastern University, Shenyang 110819, China

More Information
    Abstract
  • Fault diagnosis is an important measure to ensure the safety of production, and all kinds of fault diagnosis methods are of importance in actual production process. However, the complexity and uncertainty of production process often lead to the changes of data distribution and the emergence of new fault classes, and the number of the new fault classes is unpredictable. The reconstruction of the fault diagnosis model and the identification of new fault classes have become core issues under the circumstances. This paper presents a fault diagnosis method based on model transfer learning and the main contributions of the paper are as follows: 1) An incremental model transfer fault diagnosis method is proposed to reconstruct the new process diagnosis model. 2) Breaking the limit of existing method that the new process can only have one more class of faults than the old process, this method can identify M faults more in the new process with the thought of incremental learning. 3) The method offers a solution to a series of problems caused by the increase of fault classes. Experiments based on Tennessee-Eastman process and ore grinding classification process demonstrate the effectiveness and the feasibility of the method.

     

    • FullText(HTML)
  • loading
    • References(26)
  • [1]
    W. C. Sang, H. P. Jin, and I. B. Lee, "Process monitoring using a gaussian mixture model via principal component analysis and discriminant analysis, " Computers & Chemical Engineering, vol. 28, no. 8, pp. 1377-1387, 2004. http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=65dba41b16cab1ad18e6181b8673da19
    [2]
    V. Venkatasubramanian, R. Rengaswamy, K. Yin, and S. N. Kavuri, "A review of process fault detection and diagnosis: part Ⅰ: quantitative model-based methods, " Computers & Chemical Engineering, vol. 27, no. 3, pp. 293-311, 2003. http://d.old.wanfangdata.com.cn/OAPaper/oai_doaj-articles_672e437ca64c6970ffd6c1d01ad2d258
    [3]
    C. Tong and X. Yan, "Statistical process monitoring based on a multimanifold projection algorithm, " Chemometrics & Intelligent Laboratory Systems, vol. 130, no. 2, pp. 20-28, 2014.
    [4]
    X. Wang, H. Feng, and Y. Fan, "Fault detection and classification for complex processes using semi-supervised learning algorithm, " Chemometrics & Intelligent Laboratory Systems, vol. 149, pp. 24-32, 2015. http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=82ca5a4ad55c1a1329b652f15d109671
    [5]
    H. V. Khang, R. Puche-Panadero, J. S. L. Senanayaka, and K. G. Robbersmyr, "Bearing fault detection of gear-box drive train using active filters, " in Proc. Int. Conf. on Electrical Machines & Systems, 2016.
    [6]
    D. Aguado and C. Rosen, "Multivariate statistical monitoring of continuous wastewater treatment plants, " Engineering Applications of Artificial Intelligence, vol. 21, no. 7, pp. 1080-1091, 2008. doi: 10.1016/j.engappai.2007.08.004
    [7]
    Y. Hu, H. Ma, and H. Shi, "Local model based kpls with application to fault detection of batch process, " in Proc. Control and Decision Conf., 2013, pp. 1097-1103.
    [8]
    K. H. Hui, H. L. Meng, M. S. Leong, and S. M. Al-Obaidi, "Dempstershafer evidence theory for multi-bearing faults diagnosis, " Engineering Applications of Artificial Intelligence, vol. 57, pp. 160-170, 2017. doi: 10.1016/j.engappai.2016.10.017
    [9]
    K. H. Sorsa T, Koivo H N, "Neural networks in process fault diagnosis, " IEEE Transactions Systems Man & Cybernetics, vol. 21, no. 4, pp. 815-825, 1991. http://d.old.wanfangdata.com.cn/OAPaper/oai_doaj-articles_0ad8c1ae40e777ef590f62d2dd20f5ab
    [10]
    H. Wang, S. Fan, J. Song, Y. Gao, and X. Chen, "Reinforcement learning transfer based on subgoal discovery and subtask similarity, " IEEE/CAA Journal of Automatica Sinica, vol. 1, no. 3, pp. 257-266, 2015. http://www.ieee-jas.org/en/article/id/adcd1be6-2455-4465-95ee-be31144eb2d6
    [11]
    S. T. E., "Transfer learning progress and potential, " AI Magazine, vol. 32, no. 1, pp. 84-86, 2011.
    [12]
    Y. Q. Pan S J, "A survey on transfer learning, " IEEE Transactions on Knowledge & Data Engineering, vol. 22, no. 10, pp. 1345-1359, 2010. http://d.old.wanfangdata.com.cn/OAPaper/oai_doaj-articles_84078f189d8147bc08febd7908b6de2b
    [13]
    X. Wang, J. Ren, and S. Liu, "Distribution adaptation and manifold alignment for complex processes fault diagnosis, " Knowledge-Based Systems, 2018. http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=1d389eb6824347d977c688f11423490c
    [14]
    R. Y. Siyu S, Stephen M A, "Highly-accurate machine fault diagnosis using deep transfer learning, " IEEE Transactions on Industrial Informatics, 2018.
    [15]
    L. Wen, L. Gao, X. Li, L. Wen, L. Gao, and X. Li, "A new deep transfer learning based on sparse auto-encoder for fault diagnosis, " IEEE Transactions on Systems Man & Cybernetics Systems, pp. 1-9, 2017.
    [16]
    D. Hu, A. Sarosh, and Y. F. Dong, "A novel kfcm based fault diagnosis method for unknown faults in satellite reaction wheels, " ISA Transactions, vol. 51, no. 2, pp. 309-316, 2012. doi: 10.1016/j.isatra.2011.10.005
    [17]
    I. Kuzborskij, F. Orabona, and B. Caputo, "From N to N+1: multiclass transfer incremental learning, " IEEE Computer Vision and Pattern Recognition, 2013, pp. 3358-3365.
    [18]
    J. Lu, K. Yao, and F. Gao, "Process similarity and developing new process models through migration, " Aiche Journal, vol. 55, no. 10, pp. 2318-2328, 2010. http://d.old.wanfangdata.com.cn/NSTLQK/NSTL_QKJJ0210968209/
    [19]
    N. Segevetal, M. Harel, S. Mannor, K. Crammer, and R. Elyaniv, "Learn on source, refine on target: a model transfer learning framework with random forests, " IEEE Transactions on Pattern Analysis & Machine Intelligence, pp. 1-1, 2016.
    [20]
    T. Tommasi, F. Orabona, and B. Caputo, "Safety in numbers: learning categories from few examples with multi model knowledge transfer, " in Proc. Computer Vision and Pattern Recognition, 2010, pp. 3081-3088.
    [21]
    C. Chen, F. Shen, and R. Yan, "Enhanced least squares support vector machine-based transfer learning strategy for bearing fault diagnosis, " Chinese Journal of Scientific Instrument, vol. 38, no. 1, pp. 33-40, 2017. http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=yqyb201701005
    [22]
    G. C. Cawley, "Leave-One-Out cross-validation based model selection criteria for weighted ls-svms, " in Proc. IEEE Int. Joint Conf. on Neural Network Proc., 2006, pp. 1661-1668.
    [23]
    J. Luo, T. Tommasi, and B. Caputo, "Multiclass transfer learning from unconstrained priors, " in Proc. Int. Conf. on Computer Vision, 2011, pp. 1863-1870.
    [24]
    S. J. Pan, I. W. Tsang, J. T. Kwok, and Q. Yang, "Domain adaptation via transfer component analysis, " in Proc. Int. Jont Conf. on Artifical Intelligence, 2009, pp. 1187-1192.
    [25]
    Z. Wu, "Research on fault detection method based on tennessee-eastman process, " Ph.D. dissertation, East China Jiaotong University, 2016.
    [26]
    X. Y. Ning Lv, "Fault diagnosis of te process based on two order mutual information feature selection, " Journal of Chemical Industry, vol. 60, no. 9, pp. 2252-2258, 2009.
    • Related Articles
    • Supplements(0)

Catalog

    通讯作者: 陈斌, bchen63@163.com
    • 1. 

      沈阳化工大学材料科学与工程学院 沈阳 110142

    1. 本站搜索
    2. 百度学术搜索
    3. 万方数据库搜索
    4. CNKI搜索

    Figures(30)  / Tables(4)

    Get Citation
    PDF
    XML

    Article Metrics

    Article views (1400) PDF downloads(84) Cited by()

    Highlights

    • Introducing model transfer into fault diagnosis field, IMTL achieves fault diagnosis with very few labeled samples. And fault detection and classification are achieved at the same time.
    • Combining model transfer with incremental learning, the proposed method (IMTL) achieves the extension from identifying the existing N faults in the old process to N+M faults in the new process, where M is the number of new faults in the new process.
    • Breaking the limit of [17] that the new process can only have one more class of faults than the old process, IMTL can identify M faults more in the new process.
    • IMTL gives a solution to a series of problems caused by the increase of fault classes.

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return