Abstract
Evolutionary algorithms have proven to be very successful in solving multi-objective optimization problems (MOPs). However, their performance often deteriorates when constraints are introduced. This paper proposes a hybrid heuristic intelligence (HHI) approach to remedy this issue. First, a classification operator is designed to sort individuals by their relative constraint values, which enlarges the size of feasible solutions in the early process. Then, by combining constraints with the non-dominated sorting method, we define a new selection operator to increase the probability of selecting individuals who have low constraint values but high objective values. Finally, we use hybrid optimized operations to simultaneously enhance the convergence and diversity performance by performing different operators in a certain domain. The proposed method achieves state-of-the-art performance on test functions ZDT1, Binh2, and OSY, with a remarkable decrease of 24% in the inverted generational distance (IGD) on OSY. For further applications, our method is also tested with an engineering model established for the design of the nuclear essential service water system (SEC). The final result shows that without taking hundreds of hours, the final solution of HHI has met all constraints and reduced the total cost by 8.9%© YEAR The Authors. Published by Elsevier Ltd.
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call