为研究智能优化算法在室内到达时间差（time difference of arrival, TDOA）定位方面的应用效果。首先，分别使用白鲨优化算法（white shark optimizer, WSO）、变色龙优化算法（chameleon swarm algorithm, CSA）、蛇优化算法（snake optimizer, SO）、鲸鱼优化算法（whale optimization algorithm, WOA）、灰狼优化算法（grey wolf optimizer, GWO）、麻雀优化算法（sparrow search algorithm, SSA）这6种智能优化算法进行室内的二维TDOA定位，对比分析上述算法在室内定位领域的表现，并和传统的Taylor算法的定位误差进行对比；接下来，使用SOA算法对BP神经网络进行优化，使用优化后的SOA-BP进行定位，与基础的BP神经网络的定位误差进行对比。结果表明：所使用的6种智能优化算法在室内定位领域有着不错的表现，各智能优化算法的效果相似，平均定位误差为0.44 m，相较于传统的Taylor算法提升约9.2%；SOA-BP的定位误差相较于基础的BP神经网络降低超过30%。

To investigate the effectiveness of intelligent optimization algorithms in indoortime difference of arrival (TDOA) localization. Firstly, six intelligent optimization algorithms, namelywhite shark optimizer (WSO), chameleon swarm algorithm (CSA), snake optimizer (SO), whale optimization algorithm (WOA), grey wolf optimizer (GWO), sparrow search algorithm (SSA), were used for two-dimensional indoor TDOA localization. A comparative analysis of these algorithms was conducted in the indoor localization domain, and their performance was compared with the traditional Taylor algorithm in terms of localization error. Subsequently, the SOA algorithm was employed to optimize a back propagation (BP) neural network, and the optimized SOA-BP was used for localization. A comparison was made between the localization error of SOA-BP and the basic BP neural network. The results show that the six intelligent optimization algorithms use exhibit promising performance in indoor localization, with similar effects. The average localization error for each intelligent optimization algorithm is 0.44 m, representing an improvement of about 9.2% compared to the traditional Taylor algorithm. Furthermore, the localization error of SOA-BP is reduced by more than 30% when compared to the basic BP neural network.