Dispatching rules are commonly used for job shop scheduling in industries because they are easy to implement, and they yield reasonable solutions within a very short computational time. Many dispatching rules have been developed but they can only perform well in specific scenarios. This is because a dispatching rule or a combination of dispatching rules always pursues a single or multiple fixed production objectives. A lot of approaches (e.g. simulation based or machine learning based approaches) have been published in the literatures attempted to solve the problem of selecting the proper dispatching rules for a given production objective. To select a combination of dispatching rules per randomly selected combination of objectives, this paper investigates a novel semantics-based dispatching rule selection system. Each of the dispatching rules and production objectives relates to a set of scheduling parameters like processing time, remaining work, total work, due date, release date, tardiness, etc. These parameters are semantically interrelated so that a dispatching rule and a production objective can also be semantically related through their semantic expressions. A semantic similarity value can be calculated by comparing their semantic expressions. Based on this idea, a semantics-based dispatching rule selection system for job shop scheduling is developed to generate a combination of dispatching rules given randomly selected combination of production objectives. A proof-of-concept verification process is provided at the end of the paper.
- Dispatching rule selection
- Job shop scheduling
- Randomly selected production objectives
- Semantic similarity
ASJC Scopus subject areas
- Industrial and Manufacturing Engineering
- Artificial Intelligence