XRF element quantitative analysis method based on AOG-BP neural network
Through the BP neural network optimized by alternating generations (AOG-BP), the problem of mutual interference of element peaks caused by the background effect in XRF element quantitative analysis was solved, the accuracy and efficiency of element quantitative prediction were improved, and the operation process was simplified.
Patent Information
- Application Number
- CN202210992195.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-08-18
- Publication Date
- 2025-09-23
- Estimated Expiration
- 2042-08-18
AI Technical Summary
In the existing technology, the mutual interference of element peaks caused by the background effect makes the inversion prediction of element content in XRF element quantitative analysis more difficult. The optimization algorithm introduces random numbers and conditional branch structures, making the convergence process cumbersome and inefficient.
The BP neural network with alternating generations optimization (AOG-BP) is adopted. By alternating between the whale optimization algorithm and the particle swarm optimization algorithm, and combining the fitness function of the determination coefficient R2 and the absolute value of the error, the weights and thresholds of the BP neural network are optimized to avoid fast convergence and falling into the local optimum.
It improves the accuracy and efficiency of element quantitative prediction, simplifies the operation process, and realizes efficient element component value inversion and quantitative analysis.
Smart Images

Figure CN115541641B_ABST
Abstract
Citation Information
Patent Citations
Coal seam gas content prediction method based on PSO-BP model and seismic attribute parameters
CN111045080A
XRF element quantitative analysis method based on SSA-BP neural network
CN114839210A