Effect of reinforcement and heat treatment on elevated temperature sliding of electroless Ni–P/SiC composite coatings

The investigation is focused on the wear behaviour at elevated test temperature of composite Ni–P/SiC deposit, with varying concentration of the reinforcing SiC particles. The phase evolution measured by X-ray diffraction suggests slight crystallisation during wear testing at 200 °C. In coating without reinforcing particles, adhesive wear is accompanied by microcracks. The thermal heat generated and the cyclic loading could have induced sub-surface microcracks. Owing to the effective matrix-ceramics system in composite coatings, fine grooves, abrasive polishing and uniform wearing are observed. Reinforcing particles in the matrix hinder microcrack formation and significantly reduce the wear rate. Triboxidation is confirmed from energy dispersive X-ray spectrometry.

Directed Selection using Reinforcement Learning for the Examination Timetabling Problem

Traditional heuristic approaches to the Examination Timetabling Problem normally utilize a stochastic method during Optimization for the selection of the next examination to be considered for timetabling within the neighbourhood search process. This paper presents a technique whereby the stochastic method has been augmented with information from a weighted list gathered during the initial adaptive construction phase, with the purpose of intelligently directing examination selection. In addition, a Reinforcement Learning technique has been adapted to identify the most effective portions of the weighted list in terms of facilitating the greatest potential for overall solution improvement. The technique is tested against the 2007 International Timetabling Competition datasets with solutions generated within a time frame specified by the competition organizers. The results generated are better than those of the competition winner in seven of the twelve examinations, while being competitive for the remaining five examinations. This paper also shows experimentally how using reinforcement learning has improved upon our previous technique.