Search

Wolframite image recognition is an efficient way to replace the concentrator for manual sorting, but the problem is that wolframite and the surrounding rock cannot be recognised. In this paper, convolutional neural network in deep learning was used to solve the problem. This method is fast convergence, small data set and accurate classification. Firstly, the RGB image of wolframite was augmented by rotation and translation to reduce sample imbalance. Secondly, the neural network optimised in this paper is used for new training based on Keras framework. Finally, the results show that Wu-VGG19 has the highest recognition rate of 97.51% in wolframite and surrounding rock recognition. In addition, a quartz gangue category is added to continue the experiment, and the final result shows that the improved inception Wu-v3 has the highest ore recognition rate, 99.6%., Wolframite image recognition is an efficient way to replace the concentrator for manual sorting, but the problem is that wolframite and the surrounding rock cannot be recognised. In this paper, convolutional neural network in deep learning was used to solve the problem. This method is fast convergence, small data set and accurate classification. Firstly, the RGB image of wolframite was augmented by rotation and translation to reduce sample imbalance. Secondly, the neural network optimised in this paper is used for new training based on Keras framework. Finally, the results show that Wu-VGG19 has the highest recognition rate of 97.51% in wolframite and surrounding rock recognition. In addition, a quartz gangue category is added to continue the experiment, and the final result shows that the improved inception Wu-v3 has the highest ore recognition rate, 99.6%.

The model was developed using 3-D deposit modelling technology and the Micromine software. A block model of the deposit was evaluated based on geostatistical information, and a statistical analysis carried out of the mineral reserves. The model results showed good agreement with actual production reserves., The model was developed using 3-D deposit modelling technology and the Micromine software. A block model of the deposit was evaluated based on geostatistical information, and a statistical analysis carried out of the mineral reserves. The model results showed good agreement with actual production reserves.

To dynamically update the shape of an orebody according to the knowledge of a structural geologist's insight, an approach of orebody implicit modelling was presented from raw drillhole data using the generalised radial basis function interpolant. A variety of constraint rules, including geology trend line, geology constraint line, geology trend surface, geology constraint surface and anisotropy, which can be converted into interpolation constraints, were developed to dynamically control the geology trends. Combined with the interactive tools of constraint rules, this method can simplify the modelling process of orebody and avoid the shortcomings of the explicit modelling method based on the contour stitching, such as poor model quality and difficult to update dynamically. The results of numerical experiments show that the 3D ore body model can be reconstructed quickly, accurately and dynamically by the implicit modelling method., To dynamically update the shape of an orebody according to the knowledge of a structural geologist's insight, an approach of orebody implicit modelling was presented from raw drillhole data using the generalised radial basis function interpolant. A variety of constraint rules, including geology trend line, geology constraint line, geology trend surface, geology constraint surface and anisotropy, which can be converted into interpolation constraints, were developed to dynamically control the geology trends. Combined with the interactive tools of constraint rules, this method can simplify the modelling process of orebody and avoid the shortcomings of the explicit modelling method based on the contour stitching, such as poor model quality and difficult to update dynamically. The results of numerical experiments show that the 3D ore body model can be reconstructed quickly, accurately and dynamically by the implicit modelling method.