•The circular genetic operators based RNA genetic algorithm (cRNA-GA) is proposed.•Inspired by the biological RNA, the double-loop crossover operator is design.•The adaptive mutation probabilities and the implement of cRNA-GA are presented.•The efficiency of cRNA-GA is demonstrated for PEMFC model parameter estimation.Inspired by the biological RNA, a circular genetic operators based RNA genetic algorithm (cRNA-GA) is proposed to estimate the model parameters of the proton exchange membrane fuel cell (PEMFC). To maintain the population diversity and avoid premature convergence, we design the novel genetic operator of the double-loop crossover operator. To allow the algorithm to jump out of local optima, the adaptive mutation probabilities are presented and the stem-loop mutation operator is adopted with the other mutation operators. The simulated annealing method is also incorporated into the cRNA-GA to improve local search ability. Performance tests conducted on some typical benchmark functions have witnessed the validity of cRNA-GA. The cRNA-GA is also applied to estimate the parameters of the PEMFC model and the satisfactory results have shown its effectiveness.

•We proposed a new optimization strategy for parameter identification of SOFC.•Cooperative coevolution framework was applied for problem decomposition.•Barebone PSO with hybrid learning was presented to optimize each sub-problem.•Nine optimization algorithms were used for performance comparisons.Solid oxide fuel cell (SOFC) has been widely recognized as one of the most promising fuel cells. The SOFC performance is highly influenced by several parameters associated with the internal multi-physicochemical processes. In this work, the optimal modeling strategy is designed to determine the parameters of SOFC using a simple and efficient barebone particle swarm optimization (BPSO) algorithm. The cooperative coevolution strategy is applied to divide the output voltage function into four subfunctions based on the interdependence among variables. To the nonlinear characteristic of SOFC model, a hybrid learning strategy is proposed for BPSO to ensure a good balance between exploration and exploitation. The experimental results illustrate the effectiveness of the proposed algorithm. The comparisons also indicate that cooperative coevolution strategy and hybrid learning improve the performance of original PSO algorithm, offering better approximation effect and stronger robustness.

Cooperative coevolution (CC) was used to improve the performance of evolutionary algorithms (EAs) on complex optimization problems in a divide-and-conquer way. In this paper, we show that the CC framework can be very helpful to improve the performance of particle swarm optimization (PSO) on clustering high-dimensional datasets. Based on CC framework, the original partitional clustering problem is first decomposed to several subproblems, each of which is then evolved by an optimizer independently. We employ a very simple but efficient optimization algorithm, namely bare-bone particle swarm optimization (BPSO), as the optimizer to solve each subproblem cooperatively. In addition, we design a new centroid-based encoding schema for each particle and apply the Chernoff bounds to decide a proper population size. The experimental results on synthetic and real-life datasets illustrate the effectiveness and efficiency of the BPSO and CC framework. The comparisons show the proposed algorithm significantly outperforms five EA-based clustering algorithms, i.e., PSO, SRPSO, ACO, ABC and DE, and K-means on most of the datasets.

The accurate electrochemical model plays an important role in design and analysis of hydrogen fuel cell systems. For the purpose of estimating parameters of the proton exchange membrane fuel cell (PEMFC) model, and inspired by the foraging behavior of bacteria and bees, a hybrid artificial bee colony (HABC) algorithm is proposed. The HABC uses an improved solution search equation that mimics the chemotactic effect of bacteria to enhance the local search ability. To avoid premature convergence and improve search accuracy, the adaptive Boltzmann selection scheme is adopted, which adjusts selective probabilities in different stages. Performance testing has been conducted on some typical benchmark functions. The results demonstrate that the HABC outperforms other methods (BIPOA, PSOPS and two improved GAs) in both convergence speed and accuracy. The proposed approach is applied to estimate the PEMFC model parameters and the satisfactory model predictive curves are obtained. More experimental results in different search ranges and validate strategies indicate that HABC is an efficient technique for the parameter estimation problem of PEMFC.Graphical abstractHighlights► Inspired by foraging behavior of bacteria and bees, HABC algorithm is proposed. ► The chemotactic effect greatly enhanced local search ability and the accuracy. ► Numerical test results reveal the superiority of HABC over the referenced methods. ► Better agreement shows HABC is effective for PEMFC model parameter estimation.

The accurate mathematical model is the key issue to simulation and design of the fuel cell power systems. Aiming at estimating the proton exchange membrane fuel cell (PEMFC) model parameters, an adaptive RNA genetic algorithm (ARNA-GA) which is inspired by the mechanism of biological RNA is proposed. The ARNA-GA uses the RNA strands to represent the potential solutions and new genetic operators are designed for improving the global searching ability. In order to maintain the population diversity and avoid premature convergence, on the basis of the dissimilarity coefficient, the adaptive genetic strategy that allows the algorithm dynamically select crossover operation or mutation operation to execute is proposed. Numerical experiments have been conducted on some benchmark functions with high dimensions. The results indicate that ARNA-GA has better search capability and a higher quality of solutions. Finally, the proposed approach has been applied for the parameter estimation of PEMFC model and the satisfactory results are reached.Graphical abstractHighlights► Inspired by biological RNA mechanism, an adaptive RNA-GA is proposed. ► Two mutation operators are designed for improving the global searching ability. ► The adaptive strategy by which genetic operation is executed is presented. ► Numerical results show its superiority over the referenced methods. ► ARNA-GA is demonstrated effectively for parameter estimation of PEMFC model.

Accurate kinetic models are of great significance for the simulation and analysis for hydrogen fuel cells. The proton exchange membrane (PEM) fuel cell is a complex nonlinear, multi-variable system. The mathematical modeling of PEM fuel cell usually leads to nonlinear parameter estimation problems which often contain more than one minimum. In this paper, a novel bio-inspired P systems based optimization algorithm, named BIPOA, is proposed to solve PEM fuel cell model parameter estimation problems. In BIPOA, the nested membrane structure and new rules such as adaptive mutation rule, partial migration rule and autophagy rule are combined to improve the algorithm's global search capacities and convergence accuracy. Studies on some benchmark test functions indicate that the BIPOA outperforms the other two methods (PSOPS and GAs) in both convergence speed and accuracy. In addition, experimental results reveal that the model predictive outputs are in better agreement with the actual experimental data. Therefore, the BIPOA is a helpful and reliable technique for estimating the PEM fuel cell model parameters and is available to other complex parameter estimation problems of fuel cell models.Highlights► A novel P systems based optimization algorithm (BIPOA) is proposed. ► The novel bio-inspired rules greatly improved global search capacities and accuracy. ► Numerical simulation results show its superiority over the referenced methods. ► Better agreement shows that BIPOA is effective for PEMFC model parameter estimation.

A hybrid optimization method combining an improved bioinspired algorithm based on membrane computing (IBIAMC) with a sequential quadratic programming (SQP) algorithm (HBS) is proposed to overcome difficulties in solving complex constrained problems. The netted membrane structure of HBS is based on the distributed parallel computational mode of membrane computing (MC) and inspired by the shape, structure, and function of the Golgi apparatus of eukaryotic cells. The different localized subalgorithms in the proposed hybrid method are translated from the different local rules used in different membranes. When this hybrid method is applied to solve optimization problems, these subalgorithms operate in an orderly fashion on the objects containing a tentative solution in accordance with their probabilities; simultaneously, the communication object comprising best objects is transferred between different membranes according to the communication rule. The search capacity of the proposed method is ensured by both the global search subalgorithm of the improved BIAMC and the local search subalgorithm of SQP. Eight benchmark constrained problems are used to test the performance of the hybrid method, and then two simulation examples of the gasoline blending scheduling problem and the process design of the Williams−Otto flow sheet are applied to validate the proposed algorithms.