Control of a copper laser using neural networks

Urenco (Capenhurst) Ltd., has been running high-power copper lasers for several years owing to an interest in selective photo-ionisation for commercial enrichment. The main advantages of these lasers as pump sources for this process are their efficiency at high power and their high pulse repetition frequency. However, certain load discharge conditions have been found to greatly reduce the lifetimes of expensive laser modulator components and therefore increase the running costs and downtime of the lasers. This article describes the use of multiple coupled neural networks which, trained by humans with the required experience, are first able to identify load conditions likely to result in a reduction in the lifetime of the modulator components and then alter the load conditions to minimise the stress placed on the modulator.