Identification on rock and soil parameters for vibration drilling rock in metal mine based on fuzzy least square support vector machine
来源期刊:中南大学学报(英文版)2014年第3期
论文作者:ZUO Hong-yan(左红艳) LUO Zhou-quan(罗周全) GUAN Jia-lin(管佳林) WANG Yi-wei(王益伟)
文章页码:1085 - 1090
Key words:rock and soil; fuzzy theory; vibration excavation; least squares-support vector machine; identification
Abstract: A single freedom degree model of drilling bit-rock was established according to the vibration mechanism and its dynamic characteristics. Moreover, a novel identification method of rock and soil parameters for vibration drilling based on the fuzzy least squares (FLS)-support vector machine (SVM) was developed, in which the fuzzy membership function was set by using linear distance, and its parameters, such as penalty factor and kernel parameter, were optimized by using adaptive genetic algorithm. And FLS-SVM identification on rock and soil parameters for vibration drilling was made by changing the input/output data from single freedom degree model of drilling bit-rock. The results of identification simulation and resonance column experiment show that relative error of natural frequency for some hard sand from identification simulation and resonance column experiment is 1.1% and the identification precision based on the fuzzy least squares-support vector machine is high.
ZUO Hong-yan(左红艳)1, 2, LUO Zhou-quan(罗周全)1, GUAN Jia-lin(管佳林)1, WANG Yi-wei(王益伟)1
(1. School of Resource and Safety Engineering, Central South University, Changsha 410083, China;
2. School of Business, Hunan International Economics University, Changsha 410205, China)
Abstract:A single freedom degree model of drilling bit-rock was established according to the vibration mechanism and its dynamic characteristics. Moreover, a novel identification method of rock and soil parameters for vibration drilling based on the fuzzy least squares (FLS)-support vector machine (SVM) was developed, in which the fuzzy membership function was set by using linear distance, and its parameters, such as penalty factor and kernel parameter, were optimized by using adaptive genetic algorithm. And FLS-SVM identification on rock and soil parameters for vibration drilling was made by changing the input/output data from single freedom degree model of drilling bit-rock. The results of identification simulation and resonance column experiment show that relative error of natural frequency for some hard sand from identification simulation and resonance column experiment is 1.1% and the identification precision based on the fuzzy least squares-support vector machine is high.
Key words:rock and soil; fuzzy theory; vibration excavation; least squares-support vector machine; identification