Research on multi-sensor data fusion technology based on PSO-RBF neural network

The paper mainly aims at cross sensitivity problems in the measurement process with pressure sensor. Cross sensitivity problems are mainly manifested in the following aspects: pressure measurement is affected by target quantity and interfered by non-target quantity synchronously, such as temperature and other factors. New thought is provided for sensor data fusion due to continuous development of artificial neural network technology. In the paper, multi-sensor data fusion algorithm based on PSO-RBF neural network is proposed on the basis of technology for studying commonly used data fusion methods. PSO Particle Swarm Optimization is utilized for optimizing weight and base width of RBF neural network. Influence of non-target quantity can be eliminated through RBF neural network algorithm under the precondition of fully considering non-target quantities, such as temperature, etc. thereby improving measurement precision of pressure sensor.