Multi-sensor Information Fusion Algorithm Based on Power-Average Operator and D-S Evidence Theory

Data fusion algorithm based on power-average operator and D-S evidential theory is proposed to solve the problem of information loss or low accuracy in single sensor data acquisition, which is based on multi-sensor information. Firstly, the outliers of multi-sensor data are removed. Considering the problem of the increase of computation caused by the overuse of redundant information, a dynamic sliding window method is proposed to reduce the data usage. Then, the first data fusion is carried out by using the power average operator. Finally, a hierarchical decision-making method is proposed, according to the characteristics of wireless sensor networks, and the conflict of D-S evidence theory is processed by setting the evidence threshold. The simulation results show that this method can solve the problems of inaccurate information loss and D-S evidence theory conflict in single sensor information acquisition. compared with other algorithms, the recognition rate of \(H_{1}\) is 0.81, the decision-making effect is good, and it has the advantages of relatively simple calculation.