Author:
Chen Bo-Lun,Hua Yong,Zhu Guo-Chang,Ji Min,Zhu Hong-Fei,Yu Yong-Tao
Abstract
AbstractIn the multi-effect evaporation salt making process, the smooth operation of the salt making process is crucial. As the salt production process continues, many unstable factors will cause the salt production process not to proceed smoothly. These factors can be discovered in advance by predicting the salt production data, thus, it is of great significance to predict the multi-effect evaporation salt production data. In the process of multi-effect evaporation and salt production, the multiple salt-making devices make the influence between the parameters closer, and the influence of a single parameter on itself is sometimes ductile. Therefore, the data of multi-effect evaporation and salt production have the characteristics of high dimensions, high complexity and temporal information. If the historical salt production data is used for data prediction directly, the prediction model will take a long time and the prediction effect is not good. Thus, how to predict the multi-effect evaporation salt production data is the main research problem of this paper. In view of the above problems, according to the characteristics of multi-effect evaporation salt production data, this paper analyzes and improves the self encoder for feature extraction of multi effect-evaporation salt production data, so as to solve the problem of high dimensions and high complexity of salt production data. On this basis, combined with the time-series information contained in the salt production data, a multi-effect evaporation salt production data prediction model is proposed based on long-term and short-term memory cycle neural network to solve the prediction problem of time-series salt production data. Experiments show that the prediction model can predict and prevent the problems in salt production line in advance. It has a certain theoretical research value and application value in the intelligent production process and production line optimization of salt chemical industry.
Funder
National Natural Science Foundation of China
Publisher
Springer Science and Business Media LLC
Reference34 articles.
1. Kong, W. et al. Short-term residential load forecasting based on lstm recurrent neural network. IEEE Trans. Smart Grid 10, 841–851 (2019).
2. Zheng, J., Xu, C., Zhang, Z. & Li, X. Electric load forecasting in smart grids using long-short-term-memory based recurrent neural network, 1–6 (2017).
3. Wang, J., Zheng, V. W., Liu, Z. & Chang, K. C. Topological recurrent neural network for diffusion prediction, 475–484 (2017).
4. Donkers, T., Loepp, B. & Ziegler, J. Sequential user-based recurrent neural network recommendations, 152–160 (2017).
5. Sherstinsky, A. Fundamentals of recurrent neural network (rnn) and long short-term memory (lstm) network. Physica D Nonlinear Phenom. 404, 132306 (2020).
Cited by
2 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献