Ensemble prediction modeling of flotation recovery based on machine learning

Abstract

With the rise of artificial intelligence (AI) in mineral processing, predicting the flotation indexes has attracted significant research attention. Nevertheless, current prediction models suffer from low accuracy and high prediction errors. Therefore, this paper utilizes a two-step procedure. First, the outliers are processed using the box chart method and filtering algorithm. Then, the decision tree (DT), support vector regression (SVR), random forest (RF), and the bagging, boosting, and stacking integration algorithms are employed to construct a flotation recovery prediction model. Extensive experiments compared the prediction accuracy of six modeling methods on flotation recovery and delved into the impact of diverse base model combinations on the stacking model’s prediction accuracy. In addition, field data have verified the model’s effectiveness. This study demonstrates that the stacking ensemble approaches, which uses ten variables to predict flotation recovery, yields a more favorable prediction effect than the bagging ensemble approach and single models, achieving MAE, RMSE, R2, and MRE scores of 0.929, 1.370, 0.843, and 1.229%, respectively. The hit rates, within an error range of ±2% and ±4%, are 82.4% and 94.6%. Consequently, the prediction effect is relatively precise and offers significant value in the context of actual production.