ABSTRACT

This project presents a artificial neural network (ANN) to solve a generalized job-shop scheduling problem, one of NP-complete (nondeterministic polynomial time complete) constraint satisfaction problems. The proposed NN is embedded with predefined criteria which is relevant to determine starting time of various operations within a job. The output of the NN is used to detect the precedence order of each operation within a job and schedule each operation on respective machine without violating the detected precedence order (precedence constraint) and resource constraint. The key findings reveal that the NN plays a decisive role to estimate the starting time of each operation within a job before the operations are scheduled on a respective machine. Simulations of the proposed scheduler have shown that the NN approach is efficient with respect to the quality of expected solutions and the solving speed. Key words and phrases: Neural network, backpropagation, precedence constraint, resource constraint, completion time, spent time, starting time.

Click Here to download full report.