Sensor placement for leakage localization in water supply networks of public buildings often suffers from reduced sensitivity and poor localization accuracy due to the limitations of detection range and threshold. To address this issue， an optimization method for sensor placement is proposed. Firstly， based on the distance between sensors and leakage points， the detection range and threshold are determined by using the wind pressure balance law， and the optimal number of sensors is calculated according to the detection probability of target points. Secondly， a multi-objective optimization model is established to minimize localization failure probability and maximize localization accuracy. Finality， the artificial fish swarm algorithm is adopted to solve the model and obtain the optimal placement scheme. The proposed method is validated by using a small-scale water supply network model. The results show that the optimized scheme achieves higher localization accuracy and better optimization performance for network leakage points.