使用超参数调整的人工神经网络预测烧结矿性能,ACS Omega

当前位置： X-MOL 学术 › ACS Omega › 论文详情

Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)

使用超参数调整的人工神经网络预测烧结矿性能
ACS Omega ( IF 3.7 ) Pub Date : 2023-03-21 , DOI: 10.1021/acsomega.2c05980
Soumya Sahoo ₁ , Ashutosh Pare ₁ , Subhabrata Mishra _{2,

3} , Shatrughan Soren ₁ , Surendra Kumar Biswal ₄

Affiliation

目前的工作旨在使用人工神经网络 (ANN) 对焦炭分层和非分层混合球团烧结矿 (HPS) 的物理特性进行预测验证。对两种 HPS 产品进行了物理性质分析。然后使用网格搜索超参数调整方法训练 ANN 模型以获得最佳预测结果。学习率、动量常数和神经元数量在指定范围内变化。二元变量转换用于评估两个烧结过程。碱度为 1.75 的 4 毫米微球团和使用 8% 焦炭的非层状 HPS 产品显示出良好的物理性能组合，而碱度为 1.5 的 4 毫米微球团的 HPS 使用 4% 焦炭作为燃料和 2% 焦炭作为分层在物理特性。HPS产品的成品率为96.07%，破碎指数（SI）、转鼓指数（TI）和磨损指数（AI）值分别为86.12、79.60和5.74%。因此，通过实现焦粉的分层，可以优选HPS。预测分析表明，具有 4-29-5 结构的多层感知器模型 (MLP) 网络的预测精度超过 99.99%，均方误差 (MSE) 为 2.87 × 10^–4。它验证了超参数调整的人工神经网络模型的准确性和预测有效性。

"点击查看英文标题和摘要"

Prediction of Sinter Properties Using a Hyper-Parameter-Tuned Artificial Neural Network

The present work aims at performing prediction validation for the physical properties of coke layered and nonlayered hybrid pelletized sinter (HPS) using artificial neural networks (ANNs). Physical property analyses were experimentally performed on the two HPS products. The ANN model was then trained to obtain the best prediction results with the grid-search hyper-parameter tuning method. The learning rate, momentum constant, and the number of neurons varied over specified ranges. The binary variable conversion was utilized to assess the two sintering processes. The nonlayered HPS product of 4 mm micropellets at basicity 1.75 and using 8% coke shows a good combination of physical properties, whereas HPS of 4 mm micropellets at 1.5 basicity using 4% coke as fuel and 2% coke as layering gives a radical improvement in physical properties. The yield of the HPS product is 96.07%, with the shatter index (SI), tumbler index (TI), and abrasion index (AI) values being 86.12, 79.60, and 5.74%, respectively. Hence, HPS can be preferred by implementing the layering of coke powder. The prediction analyses showed that the multilayer perceptron model (MLP) network with a 4-29-5 structure showed prediction accuracies of over 99.99% and a mean squared error (MSE) of 2.87 × 10^–4. It verifies the accuracy and prediction effectiveness of the hyper-parameter-tuned ANN model.

更新日期：2023-03-21

点击分享查看原文

点击收藏

公开下载

阅读更多本刊新发论文本刊介绍/投稿指南