Research on data fusion of multi-sensors based on fuzzy preference relations
- 45 Downloads
For the data fusion of multi-sensors, the determination of weight directly affects the accuracy and performance of the fusion algorithm. In order to improve the accuracy of fusion algorithm, an adaptive weighted algorithm based on fuzzy preference relations is proposed. The degree of preference between signals is represented by introducing the improved logsig function, and then, the weight is calculated by fuzzy preference relations. Simulation results show that the proposed algorithm is significantly better than the mean value method, and the accuracy is basically equivalent to the method based on correlation function. The analysis of the actual vibration signals in axis system verifies the validity of the algorithm in the practical application. The algorithm in this paper has good dynamic performance and is easy to be implemented. It can be applied to the actual multi-vibration signal estimation to provide more accurate parameters for the next step of fault diagnosis.
KeywordsFuzzy preference relations Weight Data fusion Multi-sensors signals Adaptive weighted estimate algorithm
This work was supported by the National key R & D plan (Grant: 2017YFD0710201 and 2016YFD0702103), Shandong Province Natural Science Foundation of China (Grant: 2017GGX30105, 2018CXGC0601 and 2017CXGC0903), Innovation plan of agricultural machinery and equipment in Shandong province (Grant: 2018YZ002 and 2017YF006-02).
- 6.Sun G, Lei G, Wang L et al (2016) Method for fault diagnosis based on multi-sensor information fusion. J Shanghai Inst Technol (Nat Sci) 16(1):22–25Google Scholar
- 7.Ding H, Zhong Y, Zhang J et al (2016) Multi-sensor adaptive weighted fusion algorithm based on correlation function. J Chongqing Univ Technol (Nat Sci) 30(2):114–118Google Scholar
- 11.Zhai Y, Dai Y (1998) Study of adaptive weighted fusion estimated algorithm of multisensor data. Acta Metrol Sin 19(1):69–75Google Scholar
- 12.Huadong WANG, Dayu WANG (2015) An improved multiple wireless sensor data batch estimation adaptive weighted fusion algorithm. Chin J Sens Actuators 28(8):1239–1243Google Scholar
- 15.Yi H, Xiusheng D, Shiyu S et al (2017) A study of training algorithm in deep neural networks based on sigmoid activation function. Comput Meas Control 25(2):126–129Google Scholar