Surface settlement monitoring in green mining areas based on PSO-BP neural network algorithm

• Main Authors: Zhang, Junwen, Wang, Bao
• Format: Conference Proceeding
• Language: English
• Published: SPIE 19.07.2024
• ISBN: 1510680446; 9781510680449
• ISSN: 0277-786X
• DOI: 10.1117/12.3031165

A neural network algorithm based on Small Baseline Subsets Interferometric Synthetic Aperture Radar (SBAS-InSAR) and Particle Swarm Optimization-Back Propagation (PSO-BP) is proposed. Aperture Radar (SBAS-InSAR) and Particle Swarm Optimization-Back Propagation (PSO-BP) neural network algorithms are proposed as a model for surface settlement monitoring in mining areas. Firstly, the SBAS-InSAR technology is used to obtain the monitoring values of mine surface settlement; then, the PSO-BP prediction model is constructed from a multi-factor perspective by selecting the influencing factors of mine surface settlement and the obtained settlement monitoring values; finally, the validity and reasonableness of this method are analyzed. The experimental results show that SBAS-InSAR can effectively monitor the long-time subsidence of the mine surface, and with the increase of training samples, the residual difference between the PSO-BP prediction value and the SBAS-InSAR subsidence value gradually decreases, and the algorithm convergence iteration speeds up, and the mean-square error decreases. Comparison with the existing monitoring methods and prediction models proves the advantages of SBAS-InSAR in the monitoring of long-time surface subsidence in mining areas.