Al Techniques for Adapting to the Dynamic Mining Environment.
Lever-PJA; Gordon-A; King-RH
Computer Appl in Min Ind : Proceeds 2nd Canadian Conf Cim 1:230-242
The mine environment constantly changes. New equipment, different equipment operators, modified layouts, and variable geological conditions make monitoring and control systems difficult to apply without continual software maintenance. This paper reports on algorithms that were developed, encoded with knowledge craft tools, and tested on underground coal mine machine data to adapt to the dynamic environment. The system receives data from sensors in near real time. The data are reduced and patterns in the data are recognized. Then the data are automatically checked to determine the present operating mode by comparing a set of mode features. If the operating mode has changes from the previous shifts, the system automatically learns the new mode characteristics and uses that mode context for further data analysis. The ai based system can produce reports that are tailored to a manager's interest. It uses a difference-detection module to locate interesting differences from previous data and a diagnosis module that determines the reason for the difference. The concepts presented in this paper are applicable to a wide variety of mining scenarios, not just to underground coal mining.
OP; Final Contract Report;
Computer Appl. in Min. Ind.: Proceeds 2nd Canadian Conf.; Cim, V. 1, PP. 230-242