Evaluation of Operating Performance of Backfilling Hydraulic Support Using Six Hybrid Machine Learning Models

Previously conducted studies have established that surface subsidence is typically avoided by filling coal mined-out areas with solid waste. Backfilling hydraulic supports are critically important devices in backfill mining, whose operating performance can directly affect mining efficiency. To accurately evaluate the performance, this paper proposes hybrid machine learning models for states. An analysis of factors influence provides eight indices evaluating backfilling supports. Based on data obtained from Creo simulation model and field measurement, six were constructed combining swarm intelligent algorithms support vector machines (SVM). Models SVM optimized modified sparrow search algorithm shown improved convergence performance. The results show has a prediction accuracy 95.52%. related evaluation fit well actual intervals support.