A multi-agent system to construct production orders by employing an expert system and a neural network

摘要: The authors describe the implementation of a multi-agent system, whose goal is to enhance production planning i.e. improve construction orders. This task has been carried out traditionally by module known as activity control (PAC). However, classic PAC systems lack adaptive techniques and intelligent behaviour. As result they are mostly unfit handle NP Hard combinatorial problem underlying right To overcome this situation, we illustrate how an collaborative system (MAS) obtains correct order coordinating two different emulate intelligence. One technique performed feed-forward neural network (FANN), which embedded in machine agent, objective being determine appropriate fulfil clients' requirements. Also, expert provided tool turn charge inferring tooling. entire MAS consists coordinator, spy, scheduler. coordinator agent responsibility flow messages among agents, whereas spy constantly reading Enterprise Information System. scheduler programs We achieve realistic that fully automates dispatch valid orders factory dedicated produce labels.