Yanan Bai

A Robust Metaheuristic Combining Clonal Colony Optimization and Population-Based Incremental Learning Methods

To provide a fast robust optimizer for numerical solutions of inverse problems, a metaheuristic combining a clonal colony optimization methodology and a population based incremental learning method is proposed. In the proposed algorithm, a real-valued probability vector is introduced for the extension of each colony; a tournament-based mechanism is employed in a colony to destruct/discard plants to evolve the colony toward a promising space; and a new reallocation operator is designed. The numerical results on two case studies are reported to positively showcase the feasibilities and merits of the proposed metaheuristic.

An Ant Colony Algorithm for Both Robust and Global Optimizations of Inverse Problems

To address the computational inefficiencies of available robust oriented optimizers, a fast optimal algorithm based on ant colony optimization (ACO) algorithm for both robust and global optimizations of inverse problems is proposed. In the proposed algorithm, the structures of the algorithm are redesigned, and methodologies for efficient computations of the robust performance parameters are proposed. Numerical results are reported to positively showcase the merits of the proposed algorithm.

Integration of Directed Searches in Particle Swarm Optimization for Multi-Objective Optimization

While a wealth of endeavors in optimization studies are devoted to the realization of the two ultimate goals, which are: 1) to minimize the distance between the found solutions from the true Pareto front and 2) to maximize the diversity among the found Pareto solutions in both objective and parameter spaces; only lukewarm efforts are given to the development and utilization of approximating techniques of non-dominated sets in continuous multi-objective optimization studies. In this regard, a directed search method embedded in a vector particle swarm optimization (PSO) algorithm, as an exploiting search phase to improve the efficiency of the algorithm, is proposed to steer the searches toward the desired direction. The proposed strategy excludes gradient computations of the Jacobian in determining the corresponding desired direction in the parameter space. The components of the PSO algorithm are also redesigned accordingly. The performances with the application of the proposed algorithm on two case studies are reported and compared with those of three well developed vector evolutionary algorithms.

Temperature Field Optimization and Magnetic Nanoparticles Optimal Approximation of MFH for Cancer Therapy

The magnetic nanoparticles (MNPs) in ac alternating magnetic fields will produce a sufficient amount of heats owing to the Néel and Brown relaxations. Magnetic fluid hyperthermia (MFH), based on this mechanism, is a new promising approach for tumor treatments. The temperature field distribution in the cancer and its neighbor regions have a significant effect on the therapeutic effect of MFH. As a result, it is generally required to maintain the temperature in the cancer in the range of 42 °C-90 °C while guaranteeing a sharp temperature gradient in the neighbor regions of the cancer and healthy tissues. This paper provides an automated shape and MNP volume fraction solid design optimization methodology with finite element analysis, coupled field analysis, and an enhanced multiobjective quantum particle swarm optimization, to realize the aforementioned two ultimate goals. Moreover, an optimal radial basis function approximation technique is proposed to approximate the distribution of the optimized nanoparticles volume fraction solids to give a smooth and implementable nanoparticles distribution.

A New Methodology for Robust Optimizations of Optimal Design Problems Under Interval Uncertainty

To consider the interval uncertainty in a practical optimal design problem, a new methodology for efficient robust optimizations is proposed. The proposed methodology uses a constrained formulation for robust performances not only in alleviating the inefficiency of the existing approaches in modeling interval uncertainties but also in avoiding the deficiency in the biasing force selection. The gradient information is used as both a trigger to activate the uncertain quantification procedure and the steepest increment direction to develop a fast searching phase. The stochastic approximation method is employed to minimize the computational burdens in computing the gradients. The numerical results on a case study are reported to validate the proposed methodology.

A Direct Coupled Solution Methodology for Efficient Robust Optimizations of Inverse Problems Under Uncertainty

In the existing resolution methodology for robust design optimizations, the procedures for solving robust optimization and uncertainty quantization as well as the use of high fidelity models are completely decoupled and independent from each other. As a result, the overall cost is typically the product of the costs of the three approaches. Such methodology is simple but more expensive than necessary. To develop an efficient robust optimizer, a direct coupled solution methodology based on an evolutionary algorithm is proposed. Stochastic approximation method is employed to minimize the computational burdens when computing the gradient information in designing the exploiting phase. Numerical results are reported to showcase the merits of the proposed methodology.

A Real Coded Vector Population-Based Incremental Learning Algorithm for Multi-Objective Optimizations of Electromagnetic Devices

Even though evolutionary algorithm (EA) has now become the standard and paradigm for solving multi-objective design problems, the complexity of its genetic operation is, however, limiting its popularity in engineering applications. Hitherto, there has been insufficient research that addresses the inadequacy of EAs in extracting the characteristic landscape features of an objective function. However, increasing attentions have now been devoted to EAs based on probabilistic models (EAPMs) in computational intelligence studies. A real coded scalar population-based incremental learning algorithm, an EAPM, is proposed for multi-objective optimizations of electromagnetic devices. Major improvements include the design of a generating mechanism for new intermediate solutions, the selection of elite solutions to update the probability matrix, matrix updating formulations, and refinement mechanism for intervals to precisely generate intermediate solution. Also, a methodology to consider quantitatively both the number of improved objectives and the amount of improvements in a specified objective of multi-objective design problems is introduced in fitness assignments. Numerical results on a high frequency and a low inverse problem are reported to showcase the merits of the proposed algorithm.

A Fast Methodology for Topology Optimizations of Electromagnetic Devices

To alleviate the excessive computational burden involved in topology optimizations, an efficient methodology for topology optimization is proposed. In the proposed methodology, a multi-scale on/off method is designed to avoid using infinite number of decision parameters; and a stochastic approximation method is employed to minimize the computational costs when computing the sensitivity information. Numerical results are reported to showcase the merits of the proposed methodology.

A Wind Driven Optimization-Based Methodology for Robust Optimizations of Electromagnetic Devices under Interval Uncertainty

A methodology based on a new uncertainty quantization formulation and an improved wind driven optimization (WDO) algorithm is proposed for robust optimizations of electromagnetic devices under interval uncertainties. In the proposed methodology, the robust performances are enforced as the constraint functions, and the objective function is selected as the biasing force to evolve the iteration procedures. The WDO method is also improved to guarantee a good balance between the exploration and exploitation searches. Numerical results on a case study are reported to showcase the feasibility and merit of the proposed methodology in solving practical engineering design problems.