R. Ganguli et Jc. Yingling, Algorithms to control coal segregation under non-stationary conditions - Part I: Moving window and SPC-based updating methods, INT J MINER, 61(4), 2001, pp. 241-259
With highly heterogeneous run of mine coal streams, physical segregation. u
sing on-line quality measurements, can serve as an economically important f
irst stage of the mineral beneficiation process. Segregation enables high q
uality fractions of the stream to bypass cleaning operations, thereby savin
g cleaning costs and avoiding the yield Losses inherent in any downstream s
eparation process. This paper develops control strategies that address the
objectives of quality targeting of the no-wash coal to meet desired quality
specifications while maximizing yield of the segregation process to the no
-wash stock. It extends earlier work by the authors to deal with the case w
here the stochastic nature of the quality levels is non-stationary over tim
e, a situation any practical segregation system should accommodate. Two tec
hniques, involving the use of moving windows and auto-correlated statistica
l process control techniques, are employed to define intervals of time wher
e the process might be considered as "locally" stationary. Subsequently, tw
o different methods, involving the use of empirical and Gaussian distributi
ons, are used to characterize the distribution of quality levels over these
intervals. Given this characterization, a special decision criterion is ap
plied to make segregation decisions that enables one to meet the control ob
jectives stated above. Performance of different variants of these control s
trategies are compared with each other and to an existing industrial segreg
ation algorithm using data obtained at a representative mine. The methods s
how dramatically improved capability to control quality targets and increas
e yields. Moreover, different variants of the algorithms are more effective
in different application circumstances. (C) 2001 Elsevier Science B.V. All
rights reserved.