Abrasive wear of steel during rolling-sliding contact with rock counterfaces

In many mining operations (e.g. excavation, drilling, tunnelling, rock crushing) metallic components are forced against abrasive rocks in a complex motion. This study examines the relative importance of combined rolling and sliding motion in the two-body abrasive wear of a low carbon tempered martensitic steel against rock counterfaces. A novel wear test rig has been used to vary the amount of rolling and sliding motion between a rotating steel cylinder and a counter-rotating sandstone (highly abrasive) or limestone (much less abrasive) disc. Weight-loss measurements reveal that the wear rate of the steel increases as the amount of motion against the rock counterface is reduced from pure sliding to approximately 50% sliding (and approximately 50% rolling). Scanning electron microscopy shows that when the amount of motion is reduced from pure sliding to approximately 50% sliding the topographical and sub-surface physical properties of the worn steel and rock surfaces are modified.

Recurrent input transformations for Hidden Markov models

This paper presents a new architecture which integrates recurrent input transformations (RIT) and continuous density HMMs. The basic HMM structure is extended to accommodate recurrent neural networks which transform the input observations before they enter the Gaussian output distributions associated with the states of the HMM. During training the parameters of both HMM and RIT are simultaneously optimized according to the Maximum Mutual Information (MMI) criterion. Results are presented for the E-set recognition task which demonstrate the ability of recurrent input transformations to exploit longer term correlations in the speech signal and to give improved discrimination.