Research on load identification of mine hoist based on improved support vector machine

Abstract

To solve the problem of indirect identification of dynamic load of a mine hoist, a novel identification method based on running speed is proposed. In this paper, the simulation model with variable frequency speed regulation by vector control was established in Matlab/Simulink. By setting the acceleration of different time periods, the mine hoist running characteristics under different loads can be accurately simulated, and the coupling relationship between the running speed characteristic and the system load characteristic can be obtained. The support vector machine (SVM) with grid search(GS)/genetic algorithms (GA)/ particle swarm optimization (PSO) is used to estimate the mine hoist load. Grid search turns out to be a better optimizing method than either GA or PSO. It is found that by adjusting the proportional relationship of the dependent variable and then doing the load identification by SVM of GS, the load identification effect can be greatly improved. The method is also applicable when dealing with similar data distributions.