Flexible Job-Shop Scheduling in Smart Manufacturing

Production scheduling problems encountered more complexity with the digital manufacturing. Classic Flexible Job Shop Scheduling (FJSSP) gained dynamic manner due to the alternative process planning abled to machine the same part with different routing of one job. A single job is a routing processing operations done on a sequencing features. Features precedence in turn constrains the job routing diversity. The problem is as NP-hard complexity. Hence, this study concentrates on correctness the features precedence to be able to decrease the consuming time of optimization for FJSSP. The study deployed a two stage meta-heuristic model to optimize the scheduling paying attention to the processing make span and granularity penalty. The machine state as well plays a crucial rule within scheduling routing prediction. A comparison between the modified approach and the classic Genetic Algorithms (GA) based is introduced within experimental results to demonstrate each parameter effect.