Abstract: In order to determine the reliability of each sensor and how to fuse the data measured by sensors, a multi-sensor data fusion method based on fuzzy theory is proposed and its measurement application is studied. Firstly, the sensors consistency is obtained from the admissible function and the measurement error data are deleted. Then the measurement data are fuzzied. Finally, the fusion result could be produced on the basis of fuzzy similarity degree. The method is computationally simple and can objectively reflect the reliability and consistency between these sensors. A measurement example proves that the method is feasible, it can give higher priority to stable and reliable sensor, and it is simple and efficient for real-time measurement.