Centrifugal pumps are the most common type of kinetic pumps, and are used most often in applications with moderate to high flow and low head. In order to increase the reliability of the pumps, researches have been conducted on pump design and maintenance approaches in recent years in order to reduce their failure rates. In this article, Genetic Algorithm (GA) is used to find the optimum value for the total failure rate of a centrifugal pump. The total failure rate of the pump is modeled here as a combination of the failure rates of its individual components such as pump seals, shaft, bearings, casing and fluid driver ( by a weakest link model).

Considering that all failure modes are statistically independent and any component failure breaks down the pump, the pump total failure rate is the sum of the components’ failure rates. The failure rate function of seals, shaft, bearings, casing, and fluid driver components which are given in [1], are used as objective functions in the optimization problem. Finally, the optimized parameters and failure rate value of the pump’s specific components are obtained.

This content is only available via PDF.
You do not currently have access to this content.