Comprehensive Evaluation of Electrolytic Cell State Based on Fuzzy Clustering
| Autor: | Qingbao Huang, Chun Xie, Xin Yu, Shaojian Song, Chenhua Xu |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
0209 industrial biotechnology
Fuzzy clustering Artificial neural network Computer science Process (computing) Stability (learning theory) 02 engineering and technology computer.software_genre Fuzzy logic 020901 industrial engineering & automation 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing State (computer science) Data mining Cluster analysis computer Energy (signal processing) |
| Zdroj: | 2018 Chinese Automation Congress (CAC). |
| Popis: | In the process of electrolytic aluminum, analysis of electrolytic cell's operation state is key to its optimization and control. To improve the accuracy of cell state evaluation, a method of comprehensive evaluation based on fuzzy clustering is proposed in this paper. First, the comprehensive index is defined, which reflects energy balance, material balance and stability. Then, the cell state evaluation model based on fuzzy c-means clustering algorithm is established to classify the cell states into three categories, including good, normal and poor. Finally, the cell state prediction model based on fuzzy neural network is designed to predict the cell state after 24 hours. The experimental results show that the proposed method can accurately evaluate the current cell state and predict the future cell state, which is of great significant to the stability, energy saving and consumption reducing of production. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|