Abstract
This paper develops an abnormity control scheme based on fuzzy Bayesian network (BN) for the thickening process of gold hydrometallurgy. By analyzing the causes and corresponding solutions of the abnormity, the operator experience of removing the abnormity is transformed to construct the BN. The BN combines the expert knowledge with quantitative data analysis to make decisions and remove the abnormity. The BN is established off-line and used to infer on-line. Because the observable variables extracted from sensors are continuous in practical application, we use fuzzy set theory to discretize the continuous variables. After receiving abnormal phenomena as soft evidences, the posterior probabilities of the decision variables with different grades can be obtained by BN reasoning, which provide real-time safety analysis. The application results show that the proposed approach can make effective decisions for the abnormity in the thickening process.