Reaction Pathways in the Oxydehydrogenation of Ammonia At Cu(110) Surfaces
Özet
The activation of ammonia by oxygen at Cu(110) has been investigated by X-ray photoelectron and electron energy loss spectroscopies. The chemistry observed is dependent on the temperature, whether oxygen is preadsorbed and its surface coverage, or whether the oxygen is coadsorbed with ammonia. Amide species NH2(a) are formed only when adsorbed ammonia is exposed to dioxygen at low temperatures. With increasing temperature further step-wise dehydrogenation occurs to give imide NH(a) and nitrogen adatoms N(a). For an ammonia-rich dioxygen-ammonia mixture a facile reaction to form exclusively bent imide species occurs at 295 K with no evidence for chemisorbed oxygen being present until theta(NH) approaches unity. A hot transient O-(s) species is implicated in the reaction mechanism. On the other hand for theta(oxygen) --> 1.0 the oxygen overlayer is relatively unreactive, imide formation being kinetically slow and limited in extent. Furthermore there is no evidence in the HREEL spectra for a loss peak characteristic of delta(NH) although a nu(NH) loss peak is present. This suggests a linear form of NH(a) in contrast to the bent form generated by coadsorption of ammonia and dioxygen. Two different oxygen species can exist at the copper surface: one that is highly reactive to ammonia and undergoes chemisorptive replacement, the other inactive. We suggest that the former is O--like and associated with isolated oxygen atoms and the latter O2--like and associated with multi-oxygen atom copper nuclei. High catalytic oxydehydrogenation activity can be maintained during the coadsorption of dioxygen and ammonia, provided the development of O2- species (oxide growth associated with surface reconstruction) is suppressed. The latter has been shown to occur even at low oxygen coverages (theta almost-equal-to 0.1) the ammonia molecule acting as a sensitive and specific probe for the isolated O--like species. The O-(s) species are therefore transients in the development of the chemisorbed oxygen overlayer and characterised by high chemical reactivity. Support for this model comes from recent scanning tunnelling microscope studies of the Al(111)-oxygen system of Ertl and coworkers [Phys. Rev. Lett. 68 (1992) 624] (ref. [1]).
