Online sequential extreme learning machines for fault detection

In this paper, we propose the application of a new fault detection approach with a sequential updating function under new operating conditions or natural evolving degradation processes. The proposed approach is based on Online Sequential Extreme Learning Machines (OS-ELM). OS-ELM have the advantages of a strong learning ability, very fast training, and online learning. The concept of applying OS-ELM to fault detection is demonstrated on an artificial case study. We expect that OS-ELM can contribute to improve the fault detection and also the associated initiation of maintenance activities for engineering components working in an evolving environment such as electric components, bearings, gears, alternators, shafts and pumps, in which the monitored signals are not only significantly affected by working load and surrounding environment but may also experience some modifications due to a slow aging and degradation process.

[1]  Narasimhan Sundararajan,et al.  A generalized growing and pruning RBF (GGAP-RBF) neural network for function approximation , 2005, IEEE Transactions on Neural Networks.

[2]  Hongming Zhou,et al.  Extreme Learning Machine for Regression and Multiclass Classification , 2012, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[3]  Jason L. Speyer,et al.  A generalized Shiryayev sequential probability ratio test for change detection and isolation , 1999, IEEE Trans. Autom. Control..

[4]  Khashayar Khorasani,et al.  Fault detection and isolation of a dual spool gas turbine engine using dynamic neural networks and multiple model approach , 2014, Inf. Sci..

[5]  Srinivas Katipamula,et al.  Review Article: Methods for Fault Detection, Diagnostics, and Prognostics for Building Systems—A Review, Part I , 2005 .

[6]  Guang-Bin Huang,et al.  Extreme learning machine: a new learning scheme of feedforward neural networks , 2004, 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541).

[7]  Enrico Zio,et al.  Comparison of Data-Driven Reconstruction Methods For Fault Detection , 2015, IEEE Transactions on Reliability.

[8]  Inseok Hwang,et al.  A Survey of Fault Detection, Isolation, and Reconfiguration Methods , 2010, IEEE Transactions on Control Systems Technology.

[9]  Paramasivan Saratchandran,et al.  Performance evaluation of a sequential minimal radial basis function (RBF) neural network learning algorithm , 1998, IEEE Trans. Neural Networks.

[10]  Narasimhan Sundararajan,et al.  A Fast and Accurate Online Sequential Learning Algorithm for Feedforward Networks , 2006, IEEE Transactions on Neural Networks.

[11]  Jingyu Zhou,et al.  Test Generation Algorithm for Fault Detection of Analog Circuits Based on Extreme Learning Machine , 2014, Comput. Intell. Neurosci..

[12]  Kjersti Engan,et al.  Recursive Least Squares Dictionary Learning Algorithm , 2010, IEEE Transactions on Signal Processing.

[13]  João Gama,et al.  Learning with Drift Detection , 2004, SBIA.

[14]  Yanyang Zi,et al.  Wind turbine fault detection using multiwavelet denoising with the data-driven block threshold , 2014 .

[15]  David Shan-Hill Wong,et al.  Fault Detection Based on Statistical Multivariate Analysis and Microarray Visualization , 2010, IEEE Transactions on Industrial Informatics.

[16]  Hamid Reza Karimi,et al.  Data-driven design of robust fault detection system for wind turbines , 2014 .

[17]  Narasimhan Sundararajan,et al.  On-Line Sequential Extreme Learning Machine , 2005, Computational Intelligence.

[18]  E. Zio,et al.  Robust signal reconstruction for condition monitoring of industrial components via a modified Auto Associative Kernel Regression method , 2015 .

[19]  Visakan Kadirkamanathan,et al.  A Function Estimation Approach to Sequential Learning with Neural Networks , 1993, Neural Computation.

[20]  Guang-Bin Huang,et al.  Trends in extreme learning machines: A review , 2015, Neural Networks.