Optimisation of Parallel Machine Scheduling Using Neuro-Fuzzy Approach

The present globalized environment has brought in a tough competition among manufacturers. The jobs are to be manufactured in varieties and in different quantities with the available resources. The manufacturer has to focus on balancing the work among the available machines and at the same time it has to reduce the completion time of the jobs, in order to deliver it on the due date.

Workflow balancing on a shop floor helps to remove bottlenecks present in the manufacturing system .Workflow refers to the total time during which the work centers are busy. Earlier researchers have not specified the method for jobs to be executed in parallel in order to balance the workflow to each machine. In parallel machine scheduling there are m machines to which n jobs are to be assigned based on different priority strategies.

The procedure is based on the idea of balancing the workload among machines. 5 different priority strategies are followed for the selection of jobs namely RANDOM, SPT, LPT, FCFS, LCFSfor the selection of jobs for workflow balancing. The Relative Percentage of Imbalance (RPI) is adopted among the parallel machines to evaluate the performance of these strategies in a standard manufacturing environment using Neuro-Fuzzy approach.

            The practical benefit of neural network approach is that it incrementally learns the sequencing knowledge and can apply the knowledge for sequencing a set of jobs on a real time basis. The fuzzy logic approach is used to train the uncertain weights which are not trained by using neural network The Neural Network approach further improves solution quality by combining with fuzzy logic. The Neuro-Fuzzy approach is quite effective and efficient for selecting the best strategies and their optimal sequence for a given scheduling problem.

Tags :
Your rating: None Average: 3.5 (2 votes)

Posted by

Tue, 12/04/2011 - 08:15