Optimal sensor placement based on Fuzzy C-means clustering algorithm

To obtain the best information for fault diagnosis, and achieve a large amount of information with a limited number of sensors while information redundancy can be avoided effectively, a new sensor placement method based on Fuzzy C-means was presented. Firstly, the structural modal analysis was conducted, and mode shapes were extracted. Then, according to the dynamic similarity of the mode shape values at important modes, the degrees of freedom (DOFs) were clustered using Fuzzy C-means clustering algorithm. The DOFs with much information were chosen from each cluster as candidate test points. The objective functions were established based on modal assurance criterion (MAC). Genetic algorithm was adopted to solve this objective optimization. The sensor's locations were optimized. Finally, MAC criterion, Fisher information criterion and singular value ratio of modal matrix were used to comprehensively evaluate different optimization results. Taking a locomotive pump body as an example, the simulation results show that the proposed method can effectively avoid measuring points aggregation and overcome information redundancy while complete information is obtained.