Algorithms to control coal segregation under non-stationary conditions Part II: Time series based methods

摘要

In this paper, procedures involving the use of time series models are developed for coal segregation control. In contrast to the methods of Part I of this paper, time series models directly accommodate the auto-correlated nature of the coal quality levels when estimating parameters to characterize the process. Moreover, they also provide forecasting capability that is useful in segregation control. Special attention is given in the paper to development of viable parameter updating strategies in order to deal with non-stationary applications. Performance of the time series methods is evaluated, and it compares favorably to the methods developed in Part I. Although more complicated to implement than the Part I methods, time series methods have the potential to be extended to applications where quality targets are to be maintained over small batches of coal (homogeneity control), whereas the other methods only apply to large batch quality targeting.