Wireless Position Method for Indoor Personnel Based on Improved Neural Network by Chaotic Whale Optimization Algorithm

Abstract

The positioning accuracy of the indoor personnel positioning system is low, which cannot meet the needs of an intelligent transformer substation. Therefore, a wireless positioning method for indoor personnel based on the Elman neural network (ENN) using chaotic whale optimization algorithm (CWOA) was proposed. Firstly, a certain number of sample fingerprint databases were collected by wireless terminals in the wireless network on indoor personnel. Secondly, CWOA was used to optimize the weights and self-connected feedback gain factor of the ENN. Thirdly, the fingerprint database was used to train and test the optimized ENN, and the position algorithm model of the neural network was established. Finally, the real-time position was achieved with the neural network location algorithm model through the fingerprint data of the position point collected by the wireless terminal. The results show that the average position error of this indoor wireless positioning method is 1.24 m; ENN position algorithm by the CWOA has a stronger global search ability and is more suitable for the application in the time-varying indoor environment.