PH prediction of a neutral leaching process using adaptive-network-based fuzzy inference system and reaction kinetics. Issue 2 (2020)

• Record Type: Journal Article
• Authors: Long, Shuang; Li, Weijian; Yang, Wei; Sun, Bei; Yang, Chunhua; Gui, Weihua
• Is Part Of: IFAC-PapersOnLine. Volume 53:Issue 2(2020)
• Page Start: 11901
• Page End: 11906
• Publication Date: 2020
• Subjects: hydrometallurgy -- neutral leaching -- mechanism model -- ANFIS -- running condition -- fuzzy membership; Automatic control -- Periodicals; 629.805
• DOI: 10.1016/j.ifacol.2020.12.708
• Languages: English
• ISSNs: 2405-8963

Abstract

Abstract: PH value is an important index to measure the quality of product in neutral leaching process (NLP). However, due to the harsh production environment, there is almost no pH measuring device that can be applied to the site for a long time. To solve this problem, an effective pH prediction method for NLP is proposed in this paper. Firstly, the reaction kinetics of the NLP was researched, and the mechanism models under different running conditions were established. Secondly, ANFIS (Adaptive-Network-Based Fuzzy Inference System) is used to establish the data models of the process based on the idea of fuzzy training. Finally, according to the characteristics of two models and the "model mismatch" phenomenon in NLP, an effective model integration method based on fuzzy membership of running conditions is proposed, and the optimal integration was realized. Data show that the integrated model has better predictive performance than a single one, and pH predictive output of the model can also provide effective guidance for NLP.