2026-10-12T10:35:36Z https://www.scidb.cn/oai

10.57760/sciencedb.j00186.01110 2026-06-10T13:39:47Z

2026-06-10 Accurate prediction of copper content in low-grade copper ore using PGNAA and an ACNN algorithm doi:10.57760/sciencedb.j00186.01110 en Accurate determination of mineral grade is crucial for mineral exploration and mining operations. To predict the copper content of low-grade copper ore in blast holes, this study proposes an Attention Convolutional Neural Network (ACNN) model by integrating a Convolutional Neural Network (CNN) with an attention mechanism. First, based on Prompt Gamma Neutron Activation Analysis (PGNAA), a copper-ore measurement system equipped with 252Cf source and a bismuth germanate (BGO) detector was established. The gamma spectra were obtained by measuring laboratory-prepared copper-ore samples with this system. Subsequently, the Discrete Cosine Transform (DCT) was applied to the spectral data for feature extraction. The hyperparameters of the ACNN model were optimized using Bayesian optimization. The SVR, GBRT, and CNN methods were used as benchmark models to evaluate the ACNN model. The results show that the ACNN model can efficiently predict copper content, achieving a R2 of 0.9776, an RMSE of 0.1068, and an MAE of 0.0449. attention mechanism; prompt gamma neutron activation analysis; convolutional neural network; copper content; discrete cosine transform ChongGui Zhong PUBLIC https://creativecommons.org/licenses/by/4.0/ dataset Science Data Bank