Sensor Fault Diagnosis Based on SOFM Neural Network

Abstract:

Traditional sensor fault diagnosis is mainly based on statistical classification methods. The discriminant functions in these methods are extremely complex, and typical samples of reference modes are not easy to get, therefore it is difficult to meet the actual requirements of a project. In view of the deficiencies of conventional sensor fault diagnosis technologies, a fault diagnosis method based on self-organizing feature map (SOFM) neural network is presented in this paper. And it is applied to the fault diagnosis of pipeline flow sensor in a dynamic system. The simulation results show that the fault diagnosis method based on SOFM neural network has a fast speed, high accuracy and strong generalization ability, which verifies the practicality and effectiveness of the proposed method.

• Periodical: Applied Mechanics and Materials (Volumes 511-512)
• Pages: 193-196
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.511-512.193
• Online since: February 2014
• Authors: Shuo Ding, Xiao Heng Chang, Qing Hui Wu
• Keywords: Generalization Ability, MATLAB, Sensor Fault Diagnosis, Simulation, SOFM Neural Network

References

[1] XU Tao , WANG Qi. Sensor fault diagnosis based on pattern recognition [J]. Control and Decision, Vol. 22 (2007), pp.783-786. (in Chinese).

[2] DING Shuo, CHANG Xiao-heng and WU Qing-hui. Application of Probabilistic Neural Network in Pattern Classification[J]. Applied Mechanics and Materials, Vols. 441 (2014), pp.738-741.

DOI: 10.4028/www.scientific.net/amm.441.738

[3] DING Shuo, CHANG Xiao-heng and WU Qing-hui. Pattern Classification Based on Self-organizing Feature Mapping Neural Network[J]. Applied Mechanics and Materials, Vols. 448-453 (2014), pp.3645-3649.

DOI: 10.4028/www.scientific.net/amm.448-453.3645

[4] ZHANG J，WALTER G. Wavelet Neural Network for Function Learning [J]. IEEE Trans on Signal Processing, Vol. 43(2005) : 1485-1497.