Cigarette Production Scheduling by Combining Workflow Model and Immune Algorithm

Cigarette production scheduling is vital in improving production efficiency and reducing supply delay. In this paper, a workflow model combined with an immune algorithm is proposed to solve this problem for improving production efficiency. First, the problem is formulated as a mixed-integer quadratically constrained programming model. Afterwards, the problem is transformed into a workflow resource allocation one. Based on this model, an immune algorithm is presented to find a set of activity priorities that are combined with dispatching rules to allocate resources. Activity priorities are represented by antibodies and evaluated by simulation runs on the workflow model. The proposed approach is applied to several production scheduling instances, and results are compared with other approaches. Experiments show that the result from the proposed approach is substantially better than those obtained from other approaches. It is demonstrated that our approach can effectively reduce production tardiness and improve efficiency. Note to Practitioners-The key issue of the cigarette production scheduling problem is to effectively schedule the primary processing line, cut-tobacco silos, and cigarette making machines. In many tobacco companies, these steps are done manually based on experiences. In this paper, we propose a systematic method to schedule these components by combining a workflow model and an immune algorithm. The model and algorithm are used to model cigarette production process and find a good scheduling solution, respectively. The advantage of such model is that it has an intuitive structure that is easily used by industrial practitioners. It is also convenient to use the model to describe more complex problems because of its description capability. The algorithm can find activity priorities quickly, and then dispatching rules combined with these priorities are used to schedule resources in a real-time manner. This approach can greatly improve the quality of scheduling scheme, and reduce the time spent in finding one.