Mine earthquake prediction method of RFM network

• Main Authors: LI HONGBIN, PAN YISHAN, ZHANG HUAN, LUO HAO, LIU ZHONGYI, ZHAO LIKE
• Format: Patent
• Language: Chinese; English
• Published: 24.05.2024
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; DETECTING MASSES OR OBJECTS; ELECTRIC DIGITAL DATA PROCESSING; GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; MEASURING; PHYSICS; TESTING

The invention discloses a mine earthquake prediction method of an RFM network. The mine earthquake prediction method comprises the following steps: 1) dividing original mine earthquake data into a training set and a test set according to a proportion of 7: 3; 2) using an improved artificial rabbit optimization algorithm IARO to optimize two parameters, namely the number K of modal components of the VMD and a penalty factor alpha, required by the training set; (3) VMD decomposition is conducted on the mine earthquake data of the training set, after the optimal combination of K and alpha in the step (2) is obtained, VMD is used for decomposing the mine earthquake time sequence, and the decomposed data comprise a plurality of IMF components with high regularity; 4) inputting the data decomposed in the step 3) into an RFM network for training; and 5) performing parameter optimization on the data of the test set by using the IARO again, performing VMD decomposition, and inputting the decomposed data into the train