Using deep neural networks coupled with principal component analysis for ore production forecasting at open-pit mines

Ore production is usually affected by multiple influencing inputs at open-pit mines.Nevertheless,the complex nonlinear relationships between these inputs and ore production remain unclear.This becomes even more challenging when training data(e.g.truck haulage information and weather conditions)are massive.In machine learning(ML)algorithms,deep neural network(DNN)is a superior method for processing nonlinear and massive data by adjusting the amount of neurons and hidden layers.This study adopted DNN to forecast ore production using truck haulage information and weather conditions at open-pit mines as training data.Before the prediction models were built,principal component analysis(PCA)was employed to reduce the data dimensionality and eliminate the multicollinearity among highly correlated input variables.To verify the superiority of DNN,three ANNs containing only one hidden layer and six traditional ML models were established as benchmark models.The DNN model with multiple hidden layers performed better than the ANN models with a single hidden layer.The DNN model outperformed the extensively applied benchmark models in predicting ore production.This can provide engineers and researchers with an accurate method to forecast ore production,which helps make sound budgetary decisions and mine planning at open-pit mines.

A machine learning model to predict unconfined compressive strength of alkali-activated slag-based cemented paste backfill

The unconfined compressive strength(UCS)of alkali-activated slag(AAS)-based cemented paste backfill(CPB)is influenced by multiple design parameters.However,the experimental methods are limited to understanding the relationships between a single design parameter and the UCS,independently of each other.Although machine learning(ML)methods have proven efficient in understanding relationships between multiple parameters and the UCS of ordinary Portland cement(OPC)-based CPB,there is a lack of ML research on AAS-based CPB.In this study,two ensemble ML methods,comprising gradient boosting regression(GBR)and random forest(RF),were built on a dataset collected from literature alongside two other single ML methods,support vector regression(SVR)and artificial neural network(ANN).The results revealed that the ensemble learning methods outperformed the single learning methods in predicting the UCS of AAS-based CPB.Relative importance analysis based on the bestperforming model(GBR)indicated that curing time and water-to-binder ratio were the most critical input parameters in the model.Finally,the GBR model with the highest accuracy was proposed for the UCS predictions of AAS-based CPB.