We propose a method to solve industrial problems and to take into account r
andom events. It is called the triple coupling. It is based on stochastic a
lgorithms, a simulation model and the multi-agents model of artificial inte
lligence. The method we propose is easy to use and allows us to take into a
ccount most of the constraints found in manufacturing systems. Experts look
for solutions to increasing the capacity of production. But the production
can be disturbed by random events experienced by the system. Industrial ex
perts need schedules which prevent the consequences of random events. Minim
izing such consequences is very important to increasing system delivery. Ca
pital investment is often very high in factories and the cost of the invest
ment goes on regardless of whether the resources are running or not. The mu
lti-agent approach is used to determine schedules for which the consequence
s of random events are low, and a stochastic algorithm is proposed which pe
rmits us to optimize a random variable. We prove that this algorithm finds,
with probability one, the schedule of the production for which the consequ
ences of random events are the lowest. We propose to measure the consequenc
es of random events using an influence ratio. Our approach has been used to
study the consequences of random events in Peugeot sand foundries of Sept-
Fons (France). A benchmark test is presented to prove the efficiency of our
solution. For the Peugeot sand foundry of Sept-Fond, random events increas
e the production time by about 20% compared with the production time withou
t any random events occurring. We have determined schedules of production f
or which the consequences of random events are about 0.5%.