A Data Fusion Algorithm of the Improved BP Neural Network by Particle Swarm Optimization

• Published in: 2021 CAA Symposium on Fault Detection, Supervision, and Safety for Technical Processes (SAFEPROCESS) pp. 1 - 8
• Main Authors: Wang, Jidong, Zhang, Bangcheng, Gao, Siyang, Yu, Aijun
• Format: Conference Proceeding
• Language: English
• Published: IEEE 17.12.2021
• Subjects: Bayes methods; Bayesian data fusion; BP neural network; Data fusion; Data integration; Multi-sensor; Neural networks; Particle swarm optimization; Safety; Simulation; Training; Training data
• DOI: 10.1109/SAFEPROCESS52771.2021.9693692

In order to further improve the accuracy of multi-sensor data fusion, this paper presents a multisensor data fusion algorithm based on improved BP neural network by particle swarm optimization through the optimization of network input. It canprevent network convergence, accelerate the convergence speed of the network, and improve the network performance. Algorithm fusion method is verified by the particle, and fused with BP neural network and the Bayesian data fusion algorithm are compared. The simulation results show that the particle swarm optimization BP neural network improved data fusion of sensor data can improve the accuracy of data fusion, so the algorithm can be widely used in multi-sensor data fusion.