Search

This paper proposes an improved epsilon constraint-handling mechanism and combines it with a decomposition-based multi-objective evolutionary algorithm (MOEA/D) to solve constrained multi-objective optimization problems (CMOPs). The proposed constrained multi-objective evolutionary algorithm (CMOEA) is named MOEA/D-IEpsilon. It adjusts the epsilon level dynamically according to the ratio of feasible to total solutions in the current population. In order to evaluate the performance of MOEA/D-IEpsilon, a new set of CMOPs with two and three objectives is designed, having large infeasible regions (relative to the feasible regions), and they are called LIR-CMOPs. Then, the 14 benchmarks, including LIR-CMOP1-14, are used to test MOEA/D-IEpsilon and four other decomposition-based CMOEAs, including MOEA/D-Epsilon, MOEA/D-SR, MOEA/D-CDP and CMOEA/D. The experimental results indicate that MOEA/D-IEpsilon is significantly better than the other four CMOEAs on all of the test instances, which shows that MOEA/D-IEpsilon is more suitable for solving CMOPs with large infeasible regions. Furthermore, a real-world problem, namely the robot gripper optimization problem, is used to test the five CMOEAs. The experimental results demonstrate that MOEA/D-IEpsilon also outperforms the other four CMOEAs on this problem. [ABSTRACT FROM AUTHOR]

Designing and setting manipulator trajectories in a programming system can be a tedious and time-consuming task for manufacturers. In this paper, one kind of six degree-of-freedom (DOF) teaching manipulator is designed and developed for conveniently setting and recording trajectories for industrial robots. A constrained multi-objective optimization problem is formulated to optimize the design of the teaching manipulator. Two performance indexes, i.e. the magnitude of the peak operating force and difference between the maximum and minimum magnitude of operating forces are adopted as the objectives. Two PPS-based (push and pull search) algorithms, including PPS-MOEA/D and PPS-M2M, are suggested to solve the formulated CMOP. Several state-of-the-art CMOEAs, including MOEA/D-ACDP, MOEA/D-CDP, NSGA-II-CDP and CM2M, are also tested. The experimental results indicate that PPS-MOEA/D has the best performance among the six compared algorithms, and the PPS-based methods as a group outperform their counterparts without adopting the PPS framework, which demonstrates the superiority of the PPS framework for solving real-world optimization problems. [ABSTRACT FROM AUTHOR]