In　an　assembly　line　system,　the　production　process　may　suffer　a　sudden　disruption,　and　this　may　call　for　rebalancing.　In　this　paper,　the　assembly　line　rebalancing　problem　is　set　in　a　multiperiod　context　considering　stochastic　processing　times.　It　is　assumed　that　there　are　specific　moments　in　time　chosen　for　rebalancing　the　line　(if　necessary).　Two　policies,　a　periodic　rebalancing　policy　and　a　data-driven　rebalancing　policy,　are　proposed　to　solve　the　rebalancing　problem.　The　goal　is　to　minimize　the　total　cost,　which　include　production　and　rebalancing　costs.　An　empirical　study　is　conducted,　and　several　results　are　achieved:　rebalancing　an　assembly　line　is　sometimes　worse　than　not　rebalancing　it;　rebalancing　an　assembly　line　too　often　may　not　be　beneficial;　and　the　new　data-driven　policy　introduced　is　better　than　the　plain　multiperiod　policy.