|
| 基于PSO-ELM算法的煤泥浮选加药量预测研究 |
| Research on Prediction of Coal Slime Flotation Dosage Based on PSO‐ELM Algorithm |
| |
| DOI：10.16018/j.cnki.cn32-1650/n.202402005 |
| 中文关键词: 煤泥浮选 神经网络 ELM算法 粒子群优化 加药预测 |
| 英文关键词: coal slime flotation neural network ELM algorithm particle swarm optimization dosing prediction |
| 基金项目: |
|
| 摘要点击次数: 54 |
| 全文下载次数: 67 |
| 中文摘要: |
| 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。 |
| 英文摘要: |
| 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 established using the coal slurry raw coal quantity, raw coal ash content, and coal type during flotation as input variables, and the dosage of reagents as output variables. The internal parameters are trained, and the simulation verification and comparative experiments are carried out. The results show that the PSO-ELM prediction model has a higher accuracy in predicting the dosage of reagents. It can effectively reduce the consumption of collectors and foaming agents while ensuring product quality, thereby improving the production of clean coal. |
|
查看全文
查看/发表评论 下载PDF阅读器 |
| 关闭 |