Load event identification is one of the key steps in a non-intrusive event-based load monitoring approach. In this paper, we propose a load event recognition method with fused decision making, and the final recognition results are obtained by voting the recognition results of three load event recognition algorithms with different principles. Compared with separate recognition algorithms, the method can effectively improve the accuracy of load event recognition. In addition, the method can determine abnormal load events based on the different results of the three algorithms.