The encyclopedia · Engineering & Operations · Technical decision · 1998–2002
PSA rebuilt car-body lines on simulation models worth $130M in a year
After a 1998 management change, PSA modeled bottleneck car-body shops with simulation and Markov chains - 75% of cars on improved lines, $130M added in 2001.
PSA Peugeot Citroen
the move
In 1998, after a change in top management, the new CEO of PSA Peugeot Citroen set ambitious targets for growth, innovation, and profitability.
PSA focused on its car-body shops, the bottlenecks of its plants, and an R&D team built analytic operations research tools combining simulation and Markov-chain models of series-parallel systems.
More than 75 percent of PSA's cars are manufactured on lines the tools designed and continually improved. Throughput rose with minimal capital investment and no quality compromise, contributing US$130 million to the bottom line in 2001 alone.
why it works
- Markov models captured station dependencies and variability
- Simulation let engineers test changes before spending capital
- Focusing on the bottleneck line leveraged the whole plant
- Suppliers adopted the tools voluntarily, spreading the gain
what transfers
When a plant's bottleneck is dependent stations, simulation plus Markov models lets engineers test changes before spending capital; small per-line gains compound across 75% of production.
what came after
The project was a 2002 Franz Edelman Award finalist. PSA's suppliers acquired the tools without being asked, extending the improvement beyond the automaker's own plants; the Interfaces paper reported the US$130 million contribution for 2001.
references
spotted an error? The archive wants to know.