Strength prediction and cuttability identification of rock based on monitoring while cutting (MWC) by using conical pick

Real-time identification of rock strength and cuttability based on the monitoring while cutting (MWC) during excavation is the foundation of some key procedures such as the precise adjustment of excavation parameters and the in-situ modification of hard rocks. This study proposed an intelligent approach for predicting rock strength and cuttability. A database with 132 sets of data containing cutting parameters (such as cutting depth and pick angle), cutting responses (such as specific energy and instantaneous cutting rate), and rock mechanical parameters collected from conical pick cutting experiments is first established. The aforementioned parameters are employed as input features with the objective of predicting the uniaxial compressive and tensile strength of rocks, by using fitting regression and machine learning methodologies. In addition, the rock cuttability is classified by using the combination of analytic hierarchy process and fuzzy comprehensive evaluation method (AHP-FCE), and then is identified by machine learning approaches. During the prediction and identification processes, the performances of various models are compared to determine the optimal model. The results indicate that the optimal models for uniaxial compressive strength prediction, tensile strength prediction and rock cuttability classification are RA-BP and RBNN models, respectively.