Intelligent, machine vision based control for a flotation process

Keywords: machine vision, image analysis, mineral flotation, process modelling, process control

Mineral flotation is one of the most common methods used to separate the valuable minerals from the rock produced by the mine. Flotation, however, is very complex and chaotic process and one of the most important indicators of the state of the process is the visual appearance of the flotation froth. Thus the objective of the research is to design and construct an on-line machine vision based analyzator that is able to analyze simultaneosly image information from several different flotation cells. Also, a control strategy that utilizes the variables obtained from the images will be developed. Since the mathematical modelling of the flotation process is nearly impossible due to its chaotic nature, the control strategy will be based on the logical reasoning of the plant operators. Also a machine vision based on-line grain size analyzer/controller for the crushing phase will be developed

Publications

• Jani Kaartinen, Jari Hätönen, Martti Larinkari, Heikki Hyötyniemi and Jorma Miettunen,
  "Image analysis based control of copper flotation,"
  in Preprints of the 16th IFAC World Congress, P Horacek, M Simandl and P Zitek (eds.), Prague, Czech Republic: IFAC, 2005, 6 pp.
• Jani Kaartinen, Martti Larinkari, Heikki Hyötyniemi and Jari Hätönen,
  "Shadow detection based estimator for particle size distribution of crushed ore,"
  Machine Vision News, Vol. 10, pp. 13, 2005.
• Martti Larinkari, Jani Kaartinen and Jorma Miettunen,
  Modeling and simulation of particle size distribution in a mining process,
  , 03.11.2004, Sim-Serv, 2004.
  Electronic publication
• Heikki Hyötyniemi and Jorma Miettunen,
  "Towards smart devices: enhancing measurements by automated data reconciliation,"
  in Proceedings of the IASTED International Conference on Intelligent Systems and Control, M. H Hamza (ed.), Anaheim, Calgary, Zurich: IASTED, ACTA Press, 2003, pp. 383-388.
• Jani Kaartinen and Heikki Hyötyniemi,
  "Determination of ore size distribution with image analysis,"
  in Proceedings of the IASTED International Conference on Intelligent Systems and Control, M. H Hamza (ed.), Anaheim, Calgary, Zurich: IASTED, ACTA Press, 2003, pp. 406-411.
• Olli Ojala, Heikki Hyötyniemi and Jorma Miettunen,
  "Deterministic-stochastic subspace identification for filtering of X-ray analyzer measurements,"
  in Proceedings of the IASTED International Conference on Intelligent Systems and Control, M. H Hamza (ed.), Anaheim, Calgary, Zurich: IASTED, ACTA Press, 2003, pp. 337-343.
• Olli Ojala, Jani Kaartinen and Jorma Miettunen,
  "Multi-camera system - additional information from the flotation process,"
  in Automaatio 03 Seminaaripäivät, 9.-11.9.2003 - Automation Makes it Work!, Reijo Tuokko (ed.), Helsinki: Suomen Automaatioseura ry, 2003, s. 223-228.
• Jani Kaartinen, Jari Hätönen, Jorma Miettunen and Olli Ojala,
  "Image analysis based control of zinc flotation ­- A multi-camera approach,"
  in Proceedings of the 7th International Conference on Control, Automation, Robotics and Vision, Singapore: School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore; IEEE, 2002, 6 pp.
• J Miettunen, J Kaartinen and J Hätönen,
  "Image analysis based control of zinc flotation,"
  in Proceedings of the 4th Regional Symposium on Computer Applications in the Minerals Industries, P Eloranta and P Särkkä (eds.), Helsinki University of Technology, Rock Engineering, Finland: Helsinki University of Technology, 2001, pp. 267-275.