Abstract
Combining the advantages of a genetic algorithm and an artificial immune system, a novel genetic algorithm named immune genetic algorithm based on quasi secondary response (IGA-QSR) is proposed. IGA-QSR employs a database to simulate the standard secondary response and the quasi secondary response. Elitist strategy, automatic extinction, clonal propagation, diversity guarantee, and selection based on comprehensive fitness are also used in the process of IGA-QSR. Theoretical analysis, numerical examples of three benchmark mathematical optimization problems and a traveling salesman problem all demonstrate that IGA-QSR is more effective not only on convergence speed but also on convergence probability than a simple genetic algorithm with the elitist strategy (SGA-ES). Besides, IGA-QSR allows the designers to stop and restart the optimization process freely without losing the best results that have already been obtained. These properties make IGA-QSR be a feasible, effective and robust search algorithm for complex engineering problems. Copyright.
| Original language | English |
|---|---|
| Pages (from-to) | 4-13 |
| Number of pages | 10 |
| Journal | Journal of Beijing Institute of Technology (English Edition) |
| Volume | 20 |
| Issue number | 1 |
| Publication status | Published - Mar 2011 |
Keywords
- Comprehensive fitness
- Database
- Elitist strategy
- Immune genetic algorithm
- Secondary response