Deep phosphorite rock burst tendency evaluation method based on neural network

• Main Authors: CHAI XIUWEI, SHENG YIMING
• Format: Patent
• Language: Chinese; English
• Published: 01.12.2023
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR

The invention discloses a deep phosphorite rock burst tendency evaluation method based on a neural network. The method comprises the following steps: selecting rock uniaxial compressive strength sigma c, a brittleness coefficient B, a rock mass integrity coefficient KV and a ratio T of tangential stress to the uniaxial compressive strength as input layer indexes; the rockburst tendency grades are divided into four types of rockburst-free, weak rockburst, medium rockburst and strong rockburst as output layer indexes; the node number of the middle layer is set to be n, and n is an integer from 4 to 12; using round and rand functions in excel to perform random valuing in an input layer index limit range corresponding to each rockburst tendency grade to generate a learning sample; a Bayesian Regulation mathematical model of an MATLAB neural network toolbox is called for training, an expected error sum of squares index err-goal is set to be equal to 0.01 until a target error requirement is met, and a trained neura