首页|基于PSO-ELM算法的煤泥浮选加药量预测研究

基于PSO-ELM算法的煤泥浮选加药量预测研究

扫码查看
为了提高煤泥浮选加药量的预测精度,基于粒子群极限学习机(PSO-ELM)算法对煤泥浮选加药量进行预测.以浮选时的煤浆原煤量、原煤灰分和煤种作为模型输入变量,药剂的添加量作为输出变量建立PSO-ELM预测模型,对内部参数进行训练并进行仿真验证和对比实验.结果表明:采用PSO-ELM预测模型的药剂添加量预测精度更高,达到96.94%,能够在保证产品质量的前提下有效降低捕收剂和起泡剂的消耗量,进而提高精煤的产量.
Research on Prediction of Coal Slime Flotation Dosage Based on PSO-ELM Algorithm
In order to improve the prediction accuracy of coal slime flotation dosage,this paper predicts coal slime flotation dosage based on Particle Optimization Swarm Extreme Learning Machine(PSO-ELM)algorithm.A PSO-ELM prediction model is estab-lished using the coal slurry raw coal quantity,raw coal ash content,and coal type during flotation as input variables,and the dos-age of reagents as output variables.The internal parameters are trained,and the simulation verification and comparative experi-ments are carried out.The results show that the PSO-ELM prediction model has a higher accuracy in predicting the dosage of re-agents.It can effectively reduce the consumption of collectors and foaming agents while ensuring product quality,thereby improv-ing the production of clean coal.

coal slime flotationneural networkELM algorithmparticle swarm optimizationdosing prediction

王昱晨、孙涛、岳耀辉、曹英华、鹿新建、秦录芳

展开 >

盐城工学院 机械工程学院,江苏 盐城 224051

徐州工程学院 机电工程学院,江苏 徐州 221018

江苏仕能工业技术有限公司,江苏 徐州 221000

煤泥浮选 神经网络 ELM算法 粒子群优化 加药预测

2024

盐城工学院学报(自然科学版)
盐城工学院

盐城工学院学报(自然科学版)

影响因子:0.133
ISSN:1671-5322
年,卷(期):2024.37(2)