Data-driven-based adaptive fuzzy neural network control for the antimony flotation plant |
| |
| Institution: | 1. School of Information Science and Engineering, Central South University, Hunan 410083, China;2. College of Physics and Electronics Science, Hunan University of Arts and Sciences, Hunan 415000, China;1. School of Information Science and Engineering, Northeastern University, Shenyang 110004, China;2. BGRIMM Technology Group, Beijing 100160, China;3. State Key Laboratory of Process Automation in Mining & Metallurgy, Beijing 102628, China;4. Beijing Key Laboratory of Process Automation in Mining & Metallurgy, Beijing 102628, China;1. School of Information Science and Engineering, Central South University, Changsha 410083, China;2. Texas A&M Energy Institute, Texas A&M University, College Station, TX 77843, USA;1. School of Information and Electrical Engineering, Hunan University of Science and Technology, Xiangtan 411201, China;2. School of Information Science and Engineering, Central South University, Changsha 410083, China |
| |
| Abstract: | Due to the unknown system structure of the froth flotation process and frequent fluctuations in production conditions, design of control strategy is a challenging problem. As a result, manual operation is still widely applied in practice by observing froth image features. However, since the manual observation is subjective and the production conditions are time-varying, the manual operation cannot make decisions quickly and accurately. In this paper, a data-driven-based adaptive fuzzy neural network control strategy is developed to implement the automatic control of the antimony flotation process. The strategy is composed of fuzzy neural network (FNN) controllers, a data-driven model, and an on-line adaptive algorithm. The FNN is constructed to derive the control laws of the reagent dosages. The parameters of the FNN controllers are tuned by gradient descent algorithm. To obtain the real-time error feedback information, the data-driven model is established, which integrates the long short term memory (LSTM) network and radial basis function neural network (RBFNN). The LSTM network is utilized as a primary model, and the RBFNN is used as an error compensation model. To handle the challenges of the frequent fluctuations in the production conditions, the on-line adaptive algorithm is proposed to tune the parameters of the FNN controllers. Simulations and experiments are carried out in a real-world antimony flotation plant in China. The results demonstrate that the proposed adaptive fuzzy neural network control strategy produces better control performance than the other two existing methods. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
