Abstract: A production line operation forecast method and a production line operation forecast system are provided. The production line operation forecast method includes the following steps: obtaining an online production line work-in-process map at a time point, generating candidate simulated dispatch decisions based on the online production line work-in-process map, and inferring production-line work-in-process map changes of the candidate simulated dispatch decisions at a next time point; inputting the production-line work-in-process map changes to a forecast model, such that the forecast model outputs simulated production line operation health indicators of the candidate simulated dispatch decisions at the next time point; and selecting one of the candidate simulated dispatch decisions as a scheduling dispatch decision.

Abstract: A scheduling method using a knowledge graph (KG) performs following steps by a processor: obtaining an initial scheduling solution of the production system; converting the initial scheduling solution into triples to form the KG, each triples includes two entities and a relationship of the production system, the two entities indicate two production resources; embedding triples into a vector space to generate embedded vectors by a KG embedding technique; generating embedded vector combinations according to the embedded vectors and computing a distance of each of embedded vector combinations; and performing a scheduling algorithm to generate a target scheduling solution according to the embedded vector combinations, and providing reference information when the scheduling algorithm generates a schedule of a station, wherein the reference information comprises at least one of the embedded vector combinations associated with the station, and the distance corresponding to said at least one embedded vector combinatio

Abstract: A production line scheduling method, adapted to a plurality of jobs passing a bottleneck station having at least one manufacturing machine, the jobs respectively correspond to a plurality of job conditions, and the method comprises: performing a plurality of times of a schedule simulation algorithm on the jobs to sequentially establish a plurality of schedule simulation trees, and obtaining a job schedule and a simulated finishing period of each job based on the schedule simulation trees, wherein each schedule simulation tree comprises at least one scheduling route, and each scheduling route is generated from one schedule simulation algorithm; and calculating a plurality of expected feeding times of each job at a plurality of stations comprising the bottleneck station, wherein the schedule simulation algorithm comprises: performing a node expansion step based on at least one node expansion condition and the job conditions to obtain the scheduling route.