| 171 | 0 | 4 |
| 下载次数 | 被引频次 | 阅读次数 |
提出了一个大数据驱动的湿法冶金全流程优化控制模型，首先构建基于注意力机制改进的LSTM模型，通过自注意力机制增强模型对关键时间步的关注提高预测精度；其次，采用优先经验回放改进的DDQN算法实现实时生产参数的动态调整与控制；最后，设计全流程经济效益最优化控制模型获得最优解。结果表明：所提出模型在不同的数值仿真中的决定系数R2达0.92,0.90,0.92,表明该模型在多个方面优于传统方法。
Abstract：A big data-driven hydrometallurgical full-process optimization control model was proposed.Firstly, a LSTM model based on improved attention mechanism was constructed, and the self-attention mechanism was used to enhance the model's attention to key time steps to improve the prediction accuracy.Secondly, the dynamic adjustment and control of real-time production parameters are realized by using DDQN algorithm improved by priority experience playback.Finally, the optimal control model of economic benefit of the whole process is designed to obtain the optimal solution.The results show that the coefficient of determination R2 of the model is 0.92,0.90,0.92 in different numerical simulations, which shows that the model is superior to the traditional method in many aspects.
[1] 臧雅丽.湿法冶金全流程运行优化控制研究[D].沈阳：东北大学，2020.
[2] 李春林，林语宸，张其炀，等.数字化与智能化技术在湿法冶金强化搅拌工艺研发中的应用[J].有色金属(冶炼部分),2023(6):1-22.LI Chunlin,LIN Yuchen,ZHANG Qiyang,et al.Application of digital and intelligent technology in the research and development of hydrometallurgical intensive mixing process[J].Nonferrous Metals(Extractive Metallurgy),2023(6):1-22.
[3] 邓文艳.湿法冶金设备运行状态的多特征融合检测优化仿真[J].湿法冶金，2023,42(6):666-670.DENG Wenyan.Optimization simulation of multi-feature fusion detection for the operating state of hydrometallurgical equipment[J].Hydrometallurgy of China,2023,42(6):666-670.
[4] 宋长山，张春燕，王新燕，等.新能源汽车废旧锂电池资源回收方法研究[J].再生资源与循环经济，2023,16(5):12-14.SONG Changshan,ZHANG Chunyan,WANG Xinyan,et al.Research on recycling method of used lithium batteries for new energy vehicles[J].Recycling Resources and Circular Economy,2023,16(5):12-14.
[5] 常玉清，王姝，王福利，等.基于多PCA模型的过程监测方法[J].仪器仪表学报，2014,35(4):901-908.CHANG Yuqing,WANG Shu,WANG Fuli,et al.Process monitoring method based on multiple PCA models[J].Chinese Journal of Scientific Instrument,2014,35(4):901-908.
[6] 方文，徐宁，谢典顺，等.基于负载动态平衡过程控制在湿法冶金中的应用[J].山东工业技术，2014(17):1-2.FANG Wen,XU Ning,XIE Dianshun,et al.Application of load dynamic balance process control in wet metallurgy[J].Journal of Shandong Industrial Technology,2014(17):1-2.
[7] 张凯.可持续发展背景下的绿色冶金技术及其应用[J].山西冶金，2024(1):91-92.ZHANG Kai.Green metallurgical technology and its application in the context of sustainable development[J].Shanxi Metallurgy,2024(1):91-92.
[8] 李树青.基于注意力机制的改进LSTM模型的地铁客流预测研究[J].工业控制计算机，2023,36(11):124-125.LI Shuqing.Passenger flow prediction based on improved LSTM model under attention mechanism[J].Industrial Control Computer,2023,36(11):124-125.
[9] 代学武，吴越，石琦，等.基于优先经验回放可迁移深度强化学习的高铁调度[J].控制与决策，2023,38(8):2375-2388.DAI Xuewu,WU Yue,SHI Qi,et al.A transferable deep reinforcement learning high-speed railway rescheduling method based on prioritized experience replay[J].Control and Decision,2023,38(8):2375-2388.
[10] 李姣姣，何利力，郑军红.基于DDQN的生鲜农产品零售商库存成本控制模型[J].智能计算机与应用，2023,13(10):60-64.LI Jiaojiao,HE Lili,ZHENG Junhong.Inventory cost control model of fresh agricultural retail based on DDQN[J].Intelligent Computer and Applications,2023,13(10):60-64.
[11] 李志星，余跃，王涛，等.TensorFlow开源软件社区中贡献修订的实证研究[J].软件学报，2023,34(9):4056-4068.LI Zhixing,YU Yue,WANG Tao,et al.Empirical study on pull-request revisions in open source software community of TensorFlow[J].Journal of Software,2023,34(9):4056-4068.
[12] 董庆伟.基于Keras深度学习算法在结构化数据分类中的应用研究[J].佳木斯大学学报(自然科学版),2022(4):47-49.DONG Qingwei.Research on application of Keras deep learning algorithm in structured data classification[J].Journal of Jiamusi University (Natural Science Edition),2022(4):47-49.
基本信息:
DOI：10.13355/j.cnki.sfyj.2025.05.015
中图分类号:TF111.3;TP311.13
引用信息:
[1]蔡云龙.大数据驱动的湿法冶金全流程优化控制模型及实证研究[J].湿法冶金,2025,44(05):692-697.DOI:10.13355/j.cnki.sfyj.2025.05.015.
基金信息: