Mineral particle size is an important parameter in the mineral beneficiation process. In industrial processes, the grinding process produces pulp with qualified particle size for subsequent flotation processes. In this paper, a hierarchical intelligent control method for mineral particle size based on machine learning is proposed. In the machine learning layer, artificial intelligence technologies such as long and short memory neural networks (LSTM) and convolution neural networks (CNN) are used to solve the multi-source ore blending prediction and intelligent classification of dry and rainy season conditions, and then the ore-feeding intelligent expert control system and grinding process intelligent expert system are used to coordinate the production of semi-autogenous mill and Ball mill and Hydrocyclone (SAB) process and intelligently adjust the control parameters of DCS layer. This paper presents the practical application of the method in the SAB production process of an international mine to realize automation and intelligence. The process throughput is increased by 6.05%, the power consumption is reduced by 7.25%, and the annual economic benefit has been significantly improved.

There has been growing interest in applying the DEM (discrete element method) to study the charging and burden distribution in a BF (blast furnace). In practice, the real particles in a BF are non-spherical. However, spherical particles have mostly been used in previous DEM investigations. Furthermore, various particle models have been developed to describe non-spherical particles. However, the effects of using different particle models on particle behavior in a BF are still unclear. Therefore, a comparative study of how the particle shape model impacts the burden charging in a BF was conducted. Specifically, the DEM using a multi-sphere model, polyhedral model, and super-ellipsoid model was first established. Then, experiments and DEM simulations of the charging and burden distribution of non-spherical quartz sand particles in a lab-scale bell-less top BF were performed. The results indicated that the number of sub-spheres, the principle of creating the particle for multi-spheres, the number of planes for polyhedrons, and the shape indices for super-ellipsoids could all affect the accuracy and efficiency. Moreover, applying the super-ellipsoid model and multi-sphere model could achieve reasonable accuracy and efficiency, with the highest simulation accuracy for the polyhedral model but at the cost of a rather heavy computational burden.

The grinding process is a key link in mineral processing production and a typical complex, controlled process. The steady-state model is limited by its model structure and thus difficult to applyied in a control system. A hybrid modeling method driven by multi-source compensation is proposed in this paper based on the mechanism model using key equipment in the grinding and classification process, addressing the uncertainties which affect the stability of the control systems. This method combines the relevant multi-source signals with uncertainties by using a priori knowledge, extracts the nonlinear feature vector in the signal through an unsupervised depth network, and constructs a compensation model based on dynamic radial basis function network to realize the integration of mechanism modeling and data-driven compensation modeling. The simulation results show that the model has a high degree of fit to the real physical system; the industrial validation was conducted at a gold concentrator, the grinding product quality was predicted and controlled with the model.

This study focused on the intelligent model for ore pulp density in the hydrometallurgical process. However, owing to the limitations of existing instruments and devices, the feed ore pulp density of thickener, a key hydrometallurgical equipment, cannot be accurately measured online. Therefore, aiming at the problem of accurately measuring the feed ore pulp density, we proposed a new intelligent model based on the long short-term memory (LSTM) and hybrid genetic algorithm (HGA). Specifically, the HGA refers to a novel optimization search algorithm model that can optimize the hyperparameters and improve the modeling performance of the LSTM. Finally, the proposed intelligent model was successfully applied to an actual thickener case in China. The intelligent model prediction results demonstrated that the hybrid model outperformed other models and satisfied the measurement accuracy requirements in the factory well.