Single Machine Scheduling with Firefly Algorithm and Machine Failure Prediction with Data Mining Approach

One of the problems in the industry is the forecast of unexpected events, and in this article we consider the single machine scheduling problem with considering to machine failure, and also looking for the minimizing tardiness and earliness penalties. In this research, a mathematical model for this problem is presented in which the processing times, idle time, release time and failure time as well as the availability time of the machine after repairs and maintenance are taken into article that failure times are predicted using machine learning algorithms. The results show that the proposed model is suitable for small dimensions with the desired parameters and to solve this problem in larger dimensions, the meta-heuristic algorithm has been used in this research. This research presents this problem in two parts: the first part is related to failure prediction and the second part is the sequence of single machine scheduling operations. In the first part, after receiving the previous data, we predict machine failures using machine learning algorithms and achieve a set of rules for process modification, and in the second part, we use the number programming model. Correctly mixed and considering these breakdowns and lack of access to machines in a single machine schedule.