Customer Brief: Cornell

Cornell Pump Company has been helping set the industry standard for premium quality, efficient centrifugal pumps since 1946. Cornell pumps are used for raw water intake, water processing, pressure boosting, refineries, energy recovery, cooling towers, distillation systems, wastewater processing, food processing, DAF systems, and power plants.

Known for innovative designs and adopting leading edge technology, Cornell was eager to add the high-performance computing (HPC) module to their already successful CFdesign implementation.

On the first project using the new HPC module, the lead design engineer, Andrew Enterline, experienced a 100 times performance increase over previous simulations. The performance is made possible by a combination of CFdesign with the HPC and motion modules and cluster computing configured by R Systems on Windows HPC Server 2008.

Complete Pump Performance Curve in 2 hours

“We now have the ability to go from 200 hours of compute time to generate a pump curve simulation to only two hours,” says Enterline, design engineer at Cornell Pump.

It typically takes about 300 iterations to provide enough data for Cornell to evaluate a pump design.  At about 1.5 iterations per hour before the HPC project, evaluation of a single design took around 200 hours.

Enterline's project was to run simulations for a centrifugal pump in development for the agricultural market.  Initial results showed a 1.5 times speed-up.  Enterline was happy with the results, as it would decrease computing time for each pump curve from about 200 hours to 136 hours.  But, the Blue Ridge team had loftier goals.

After a few test jobs to verify performance and scalability, R Systems helped setup a test system to run the simulations on eight nodes of its Microsoft Windows HPC 2008 cluster. Test results showed that the 300 iterations typically needed to evaluate a design could be done in two hours with the combination of the new CFdesign HPC and motion modules and the R Systems’ cluster.

Reduced Development Time by 3 Months

For Cornell Pumps, the performance increases from HPC and new rotational algorithms for CFdesign will have major implications for development of new pumps.  Beyond cutting computer simulation time from weeks to hours, it is expected to reduce the number of pump castings that have to be made for physical testing.  Eliminating just one of the physical tests could save as much as three months of development time.