Minimization of Makespan and Total Tardiness in a Flow Shop Scheduling Using Artificial Neural Network

The paper makes an attempt to minimize the makespan and total tardiness in the flow shop scheduling using Artificial Neural Network (ANN). A feed forward back propagation neural network is implemented for the optimal solution of the problem. The network has been trained with the optimal sequences for different jobs on five machines problem. The trained network is further considered for solving the problem of flow shop scheduling. The analysis of all the algorithms that are implemented is carried out using Nawaz, Enscore and Ham (NEH) heuristic for 5 to 10 jobs with 5 machines under Sequence Dependent Set-up Time (SDST) environment with due dates and weights allotted to each job. With the help of NEH heuristic, different sequences have been generated for the considered problem. The number of sequences obtained is assembled in 270 × 10 matrix for the input of neural network. The network is trained with Baygon regression training algorithm and finally the results obtained from the neural network are found to be 93% accurate