The values and velocities of a Particle swarm optimization (PSO) algorithm can be recorded as series of matrix and its population diversity can be considered as an observation of the distribution of... Show More

The values and velocities of a Particle swarm optimization (PSO) algorithm can be recorded as series of matrix and its population diversity can be considered as an observation of the distribution of matrix elements. Each dimension is measured separately in the dimension-wise diversity, on the contrary, the element-wise diversity measures all dimension together. In this paper, PSO algorithm is first represented in the matrix format, then based on the analysis of the relationship between pairs of vectors in PSO solution matrix, different normalization strategies are utilized for dimension-wise and element-wise population diversity, respectively. Experiments on benchmark functions are conducted. Based on the simulation results of ten benchmark functions (include unimodal/multimodal function, separable/non-separable function), the properties of normalized population diversities are analyzed and discussed.

Population-Based Incremental Learning (PBIL) is a relatively new class of Evolutionary Algorithms (EA) that has been recently applied to a range of optimization problems in engineering with... Show More

Population-Based Incremental Learning (PBIL) is a relatively new class of Evolutionary Algorithms (EA) that has been recently applied to a range of optimization problems in engineering with promising results. PBIL combines aspects of Genetic Algorithm with competitive learning. The learning rate in the standard PBIL is generally fixed which makes it difficult for the algorithm to explore the search space effectively. In this paper, a PBIL with adapting learning rate is proposed. The Adaptive PBIL (APBIL) is able to thoroughly explore the search space at the start of the run and maintain the diversity consistently during the run longer than the standard PBIL. The proposed algorithm is validated by applying it to power system controller parameters optimization problem. Simulation results show that the Adaptive PBIL based controller performs better than the standard PBIL based controller, in particular under small disturbance.

Swarm Intelligence algorithms have been extensively applied to solve optimization problems. However, in some domains even well-established techniques such as Particle Swarm Optimization (PSO) may... Show More

Swarm Intelligence algorithms have been extensively applied to solve optimization problems. However, in some domains even well-established techniques such as Particle Swarm Optimization (PSO) may not present the necessary ability to generate diversity during the process of the swarm convergence. Indeed, this is the major difficulty to use PSO to tackle dynamic problems. Many efforts to overcome this weakness have been made. One of them is through the hybridization of the PSO with other algorithms. For example, the Volitive PSO is a hybrid algorithm that presents as good performance on dynamic problems by applying a very interesting feature, the collective volitive operator, which was extracted from the Fish School Search algorithm and embedded into PSO. In this paper, the authors investigated further hybridizations in line with the Volitive PSO approach. This time they used the Heterogeneous PSO instead of the PSO, and named this novel approach Volitive HPSO. In the paper, the authors investigate the influence of the collective volitive operator (of FSS) in the HPSO. The results show that this operator significantly improves HPSO performance when compared to the non-hybrid approaches of PSO and its variations in dynamic environments.

Remanufacturing has become a superior option for product recovery management system. It mainly consists of three stages: retrieval, reproduction, and redistribution. So far, many different... Show More

Remanufacturing has become a superior option for product recovery management system. It mainly consists of three stages: retrieval, reproduction, and redistribution. So far, many different approaches have been followed in order to improve the efficiency of a remanufacturing process. However, as the complexity increases, the use of computational intelligence (CI) in those problems is becoming a unique tool of imperative value. In this paper, different CI methods, such as artificial neural network (ANN), ant colony optimization (ACO), biogeography-based optimization (BBO), cuckoo search (CS) and fuzzy logic (FL), are utilized to solve the problems involved in retrieval and reproduction stages for remanufacturing. The key issues in implementing the proposed approaches are discussed, and finally the applicability of the proposed methods are illustrated through different examples.