Introducing a New Model for Prediction of Mean Cutting Forces Acting on Conical Pick Cutters

Conical pick cutters are by far the most common type of rock cutting tools used on variety of excavation equipment in mining and civil applications. Prediction of the forces acting on pick cutters when cutting rock can be an important input towards cutterhead design and performance estimation for such equipment. The cutting forces are a function of the rock strength and pick tip geometry, which is impacted by the bit wear. To develop a prediction model, a database of mean cutting force (MCF) measured in full-scale testing has been compiled and subsequently analyzed using regression methods to find the empirical equations linking MCF to the bit, cutting geometry and rock properties. Full-scale cutting tests are known to offer precise measurement of the cutting forces for a given bit geometry, cutting geometry (spacing between the cuts and depth of penetration), and combined rock mechanic characteristics of the sample; consequently, the information can be used to develop models of prediction of cutting forces. Linear and log-linear regression and tree-based machine learning models (random forest, decision tree, and extreme gradient boost) were used for the analysis of the experimental data. The results demonstrated that while using input parameters including uniaxial compressive strength (UCS), spacing, Brazilian tensile strength (BTS), penetration, and pick cutter's tip radius and tip angle, models can offer a reasonable prediction of the cutting forces. Among the models that have been examined, regression tree models, especially extreme gradient boost shows the highest coefficient of determination (R2), and the lowest mean absolute error (MAE). The key input parameters that affect MCF are recognized, and their influence on MCF is thoroughly examined.The most important parameters for predicting cutting forces are UCS, tip angle, penetration, and BTS.Tree-based machine learning models demonstrate superior performance in predicting MCF.