首页|基于Wasserstein GAN数据增强的矿物浮选纯度预测

基于Wasserstein GAN数据增强的矿物浮选纯度预测

扫码查看
原文链接
  • 国家科技期刊平台
  • NETL
  • NSTL
  • 万方数据
在选矿行业中，准确地预测精矿品位可以帮助工程师提前调整工艺参数，提高浮选性能。但在实际选矿过程中，采集数据存在样本量少、维度高、时序相关性复杂等问题，限制了精矿品位的预测精度。针对小样本数据的预测问题，提出了一种将Wasserstein生成对抗网络(Wasserstein generative adversarial network，Wasserstein GAN)和长短期记忆网络(long short-term memory，LSTM)相结合的时间序列数据生成模型LS-WGAN，主要利用LSTM网络来获取选矿数据中的时间相关性，再通过Wasserstein GAN网络生成与原始数据分布相似的样本进行数据增强;为了更加准确地预测精矿品位，建立了浮选预测模型C-LSTM，并基于真实泡沫浮选工艺数据实验验证了所提出方法的预测准确性。
Froth flotation purity prediction based on Wasserstein GAN data augmentation
In the mineral processing industry,accurately predicting concentrate grade can help engineers adjust process parameters in advance and improve flotation performance. However,the prediction accuracy of concentrate grade has been restricted by small sample sizes,high-dimensional data,and complex temporal correlations in actual mineral processing. To address the predication challenges associated with small sample data,a time-series data generation model called LS-WGAN is proposed,which combines the Wasserstein generative adversarial network (Wasserstein GAN) and long short-term memory (LSTM) neural network. The LSTM network is mainly used to capture the time correlation in mineral processing data,while the Wasserstein GAN generates samples similar to the original data distribution for data augmentation. To improve the prediction accuracy of the concentrate grade,a mineral processing prediction model called C-LSTM is established. The prediction accuracy of the proposed method is verified through experiments based on real froth flotation process data.

prediction of concentrate gradeWasserstein generative adversarial networklong short-term memory (LSTM)data augmentationdeep learning

吴浩生、江沛、王作学、杨博栋

展开 >

重庆大学机械与运载工程学院,重庆 400044

精矿品位预测 Wasserstein生成对抗网络 LSTM 数据增强 深度学习

中央高校基本科研业务费专项资金资助项目重庆市自然科学基金面上项目

2022CDJKYJH0242022NSCQ-MSX1629

2024

10.11835/j.issn.1000-582X.2023.107

重庆大学学报
重庆大学

重庆大学学报

CSTPCD北大核心
影响因子：0.601
ISSN：1000-582X
年,卷(期)：2024.47(9)