A dynamic size-based time series feature and application in identification of zinc flotation working conditions
- PDF / 2,775,207 Bytes
- 15 Pages / 595.22 x 842 pts (A4) Page_size
- 12 Downloads / 112 Views
A dynamic size-based time series feature and application in identification of zinc flotation working conditions FAN Ying(范影), GUO Yu-qian(郭宇骞), TANG Zhao-hui(唐朝晖), LUO Jin(罗金), ZHANG Guo-yong(张国勇) School of Automation, Central South University, Changsha 410083, China © Central South University Press and Springer-Verlag GmbH Germany, part of Springer Nature 2020 Abstract: Conventional feature description methods have large errors in froth features due to the fact that the image during the zinc flotation process of froth flotation is dynamic, and the existing image features rarely have time series information. Based on the conventional froth size distribution characteristics, this paper proposes a size trend core feature (STCF) considering the froth size distribution, i.e., a feature centered on the time series of the froth size distribution. The core features of the trend are extracted, the inter-frame change factor and the inter-frame stability factor are given and two calculation methods of the feature factors are proposed. Meanwhile, the STCF feature algorithm was established based on the core features by adding the inter-frame change factor and the inter-frame stability factor. Finally, a flotation condition recognition model based on BP neural network was established. The experiments show that the recognition model has achieved excellent results, proving that the method proposed effectively overcomes the limitation of the lack of dynamic information in the existing traditional size distribution features and the introduction of the two factors can improve the classification accuracy to varying degrees. Key words: froth flotation process; froth size distribution; working condition identification Cite this article as: FAN Ying, GUO Yu-qian, TANG Zhao-hui, LUO Jin, ZHANG Guo-yong. A dynamic size-based time series feature and application in identification of zinc flotation working conditions [J]. Journal of Central South University, 2020, 27(9): 2696−2710. DOI: https://doi.org/10.1007/s11771-020-4492-x.
1 Introduction Froth flotation is a mineral separation method widely used in mineral production and processing. The flotation process is an industrial process with complex, nonlinear and multivariable characteristics. The quality of the flotation conditions directly affects the level of concentrate grade. Proper identification of working conditions is the basis and key for operators to achieve optimal operation. Accurate working condition
identification is of great significance to promote intelligent manufacturing in the metallurgical industry and can reduce labor intensity. The froth is a comprehensive reflection of the flotation working conditions [1]. The state of the bubble layer provides centralized information on the state of production. The size distribution of the bubbles in the bubble layer and the strength or fragility of the bubble can be visualized as a reflection of the current working state [2−4]. In the past, industrial production has relied heavily on the subjective experience of workers to
Foundatio
Data Loading...
