The statistical design and analysis of an experiment has been described to establish an empirical regression relationship between parameters of a typical shot peening process and measures of residual stress. In this study, practical constraints led to the choice of a non-orthogonal design for the experiment, the implications of non-orthogonality are discussed, and a multiple regression model was fitted to the results. The residuals from the regression model were better modelled by a Laplace distribution than a Gaussian distribution, so Huber robust estimates of the coefficients in the regression model were substituted for the least-squares estimates. The robust regression relationship is used to optimize the settings of process parameters. The optimization has resulted in an estimated increase of 15 per cent in the maximum residual stress.

This case study is a based on measurements made approximately at 20cm lengths along a down-the-hole diamond drill core from a pyrite mine in South Australia. The measurements are the P-wave velocity, magnetic susceptibility and impedance. The trivariate distribution is modelled using Gaussian, Student-t and vine copulas and the results are compared in terms of goodness of fit and differences in extreme values from distributions obtained by simulation from the copulas. The vine copula provides the best fit for the variables. Trivariate linear spatial Gaussian, Student-t and vine copulas are used to predict magnetic susceptibility one step below the depth of the drill core. The vine copula allows for more detailed modelling of the error structure, and so

We compare four strategies for ensuring a reliable just-in-time supply from a seat production line, which is prone to machine failure, to a car assembly line, which is assumed to operate at a constant speed over single shifts. The strategies are as follows: holding buffer stock; duplication of the least reliable machine; duplication of the production line as a stand-by; and running two production lines concurrently. Times between machine failures are assumed to have independent exponential distributions. A general distribution of repair times is allowed for by using phase-type representations. We show the stationary distribution for these models, and compare stationary distributions with average times within levels over shifts conditional on all machines working at the start of a shift. We compute moments of sojourn times within an arbitrary subset of states, which are relevant when cost is a non-linear function of downtime. We use first passage time results to obtain probabilities of line failure within a shift, and use these results to compare the four strategies.Mathematics Subject Classification Primary 60K10, 90B25; Secondary 90B30.

The accurate modelling of geometallurgical data can significantly improve decision-making and help optimize mining operations. This case study compares models for predicting copper recovery from three indirect test measurements that are typically available, to avoid the cost of direct measurement of recovery. Geometallurgical data from 930 drill core samples, with an average length of 19 m, from an orebody in South America have been analysed. The data includes copper recovery and the results of three other tests: Bond mill index test; resistance to abrasion and breakage index; and semi-autogenous grinding power index test. A genetic algorithm is used to impute missing data at some locations so as to make use of all 930 samples. The distribution of the variables is modelled with D-vine copula and predictions of copper recovery are compared with those from regressions fitted by ordinary least squares and generalized least squares. The D-vine copula model had the least mean absolute error.