Multi-criteria assembly sequencing
Computers and Industrial Engineering - Special issue: new advances in analysis of manufacturing systems
An evaluation methodology for disassembly processes
Proceedings of the 21st international conference on Computers and industrial engineering
Immune algorithms-based approach for redundant reliability problems with multiple component choices
Computers in Industry - Special issue: Application of genetics algorithms in industry
Using memetic algorithms with guided local search to solve assembly sequence planning
Expert Systems with Applications: An International Journal
Information Sciences: an International Journal
Learning and optimization using the clonal selection principle
IEEE Transactions on Evolutionary Computation
Nested partitions method for assembly sequences merging
Expert Systems with Applications: An International Journal
Relationship matrix based automatic assembly sequence generation from a CAD model
Computer-Aided Design
Mechanical assembly planning using ant colony optimization
Computer-Aided Design
| Hi-index | 0.02 |
Assembly sequence planning (ASP) needs to take relevant constraint factors such as the geometric characteristics and tool factors into consideration so as to work out a particular assembly sequence. At last, a product will come into being through the assembly of each part according to the assembly sequence. A problem encountered in ASP is that a larger number of components will cause more constraints to assembly a product, thus increasing the complexity of assembly problem. Therefore, it has been an objective for researchers to look for suitable methods for the solution space of feasible solutions. Among them, traditional genetic algorithms (GAs) belong to a random searching method. When the constraints are complicated in ASP, GAs often come out with a large number of solutions not feasible. Consequently, previous research results have proposed some approaches such as Guided genetic algorithms (Guided-GAs) or memetic algorithms (MAs) to enhance the structure of GAs to cope with the complexity of constraints in ASP problems. In this study, artificial immune systems (AIS) were proposed to help solve the assembly sequence problem. In AIS algorithm, the antibody (Ab) in the immune system is simulated to encounter one or more unknown antigens (Ags). Moreover, the clonal selection concept is employed in the immune system in which a better antibody will be selected in each generation of revolution and different antibodies will be cloned to protect the infection of the original antigen. With this mechanism, the shortcoming such as the traditional GAs to converge in local optimal solution will be overcome. Practical examples have demonstrated that AIS can solve the ASP problem with complicated constraints. Compared with guided genetic algorithms and memetic algorithms, AIS can generate the same or better solutions in terms of quality and searching time.