Studies on Prediction Method of Multi-Transform Domains and Non-Linear Fault Trend Oriented to Wind Turbine

Abstract:

Chinese wind power industry is in the ascendant. The hidden fault development trend prediction technology will become increasingly important for improving the efficiency of wind turbines. Faced to the changing condition and non-stationary character of equipment, this paper proposed a data-based multi-transform domains non-linear fault trend prediction technique. The mechanical systems physical information and failure prediction value information was integrated in this technique. Multi-transform domains and non-linear dimensionality reduction method used to analysis equipment working state and extract failure feature of topology domain. This technique try to solve the problem that fault development information is often flooded by irregular state change information.

• Periodical: Advanced Materials Research (Volumes 503-504)
• Pages: 1154-1157
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.503-504.1154
• Online since: April 2012
• Authors: Xiao Li Xu, Zhang Lei Jiang, Yun Bo Zuo
• Keywords: Fault Trend Prediction, Multi-Transform Domains, Nonlinear

References

[1] Xiaoli Xu, hongjun Wang: Large rotating machinery running state trend forecasting(Science Press, Beijing 2011), in Chinese.

[2] Xiaoli Xu, Tao Chen and Shaohong Wang: Research on data-driven nonlinear fault prediction methods in multi-transform domains for electromechanical equipment, proceeding of the fourth world congress on engineering asset management (2009).

DOI: 10.1007/978-0-85729-320-6_71

[3] Tao Chen, Xiaoli Xu, Shaohong Wang and Sanpeng Deng: The construction and application of remote monitoring and diagnosis platform for large flue gas turbine unit, Proceeding of the fourth world congress on engineering asset management(2009).

DOI: 10.1007/978-0-85729-320-6_67

[4] Xiaoli Xu and Tao Chen: ISOMAP algorithm-based feature extraction for electromechanical equipment fault prediction, Proceedings of the 2009 2nd international congress on image and signal processing(IEEE Press 2009).

DOI: 10.1109/cisp.2009.5304349

[5] Claypoole R L, Davis G M and Sweldens W: Nonlinear wavelet transforms for image coding via lifting (IEEE transactions on image processing 2003).

DOI: 10.1109/tip.2003.817237