Soft-sensing Prediction of Mining SAG Mill Load

Taking the semi-autogenous mill, a commonly used equipment in the grinding process, as the research object, the problem of continuous and stable operation of the production process in the best working conditions is discussed to improve the utilization rate of resource and achieve the purpose of coordinating energy saving and production capacity. The main reason why the semi-autogenous mill cannot achieve economical operation is that its load is difficult to realize on-line detection. In order to ensure the continuous operation of grinding production and prevent the occurrence of empty grinding and full grinding, the staff can only conservatively feed the mine through experience, resulting in unbalanced operating efficiency. The proposed PSPCAW-SVM composite soft-sensing algorithm is selected, and the soft-sensing model of the semi-autogenous mill load is established according to the sample data of the process, which is used for the online monitoring of the mill load, and the accuracy and stability of model is evaluated through the calculation of simulation prediction results and performance indicators.