Random Forest and Whale Optimization Algorithm to Predict the Invalidation Risk of Backfilling Pipeline

The problem of backfilling pipeline invalidation has become a bottleneck restricting the application and development technology. This study applied whale optimization algorithm random forest (WOA–RF) to predict risk pipelines based on 59 datasets from actual mines. Eight influencing factors were chosen as input parameters WOA–RF model, level was selected output model. Furthermore, forest, decision tree, artificial neural network, k-nearest neighbor, support vector machine models also established according collected datasets. prediction performance six classification compared. evaluated results showed that hybrid model best highest accuracy (0.917) compared other models, with kappa value (0.8846) MCC (0.8932). In addition, performed sensitivity analysis deviation rate is most important factor, followed by internal diameter pipeline. Eventually, used failure nine mines in Sichuan, China. field through investigation, engineering verification carried out. research show reasonable effective for risk, it can provide novel solution invalidation, good practicability.