Bayesian Network-based Technical Index Estimation for Industrial Flotation Process under Incomplete Data

Due to the lack of detection instruments or long measurement cycles in the industrial flotation process, accurate and real-time estimation of the technical index is of great significance for optimizing flotation performance and operational adjustment. In the real-world flotation process, incomplete data is a widespread phenomenon owing to hardware sensor failures and other reasons. To this end, this paper proposes a Bayesian network (BN)-based concentrate grade estimation method under incomplete data. The real-time froth image information and the concentrate grades of the previous periods are taken as the input of the BN model, and the current concentrate grade is the output of the BN model. The expectation maximum (EM) algorithm is used to estimate the model parameters. The application results show the proposed method can accurately estimate the concentrate grade even if some data are missing.