No abstract

The implementation of artificial intelligence techniques is increasing rapidly in recent years to solve numerous engineering problems. Assembly sequence planning is one of the prominent complex combinatorial problem draw attention of industrial engineers to economize the overall manufacturing cost by minimizing the assembly time and energy. Due to large search space and multiple assembly predicate criteria, researchers are motivated towards efficient utilization of AI techniques to address the problem. Literature review on various artificial intelligence techniques for obtaining the optimal assembly sequence planning are analyzed and the limitations of the existed methodologies are discussed in detail. This review provides an outlook for the researchers on various artificial intell1igent techniques which will be useful to carry out research for obtaining the optimum assembly sequence planning while qualifying various assembly predicate criteria.

No abstract

No abstract

Assembly sequence planning is one of the multi-model optimization problems, in which more than one objective function has to be optimized at a time to obtain the quality assembly sequence. Moreover obtaining the feasible sequences from the possible finite set of sequences is a difficult task as the assembly sequence planning problem is N-P hard combinatorial problem. To solve the assembly sequence planning problem, researchers have developed various techniques to obtain the optimum solution. The developed methodologies have many drawbacks like struck at local optima, poor performance, huge search space and many more. To overcome these difficulties, the current research work aims to use stability graph to generate stable assembly subsets for obtaining the optimum assembly sequences. In the proposed methodology, to reduce the search space and to obtain the quality assembly sequences, stability graph is considered. Moreover, the fitness of assembly subsets is evaluated according to the user weights at each level before proceeding to the higher levels. Due to this, the higher fitness value subsets are eliminated at each stage by which time of execution will reduce enormously. The proposed methodology has implemented on various industrial products and compared the results with the various well-known algorithms.