Application of improved particle swarm optimization in system identification

ABSTRACTWith the rapid development of the computational technology, computational fluid dynamics (CFD) tools have been widely used to evaluate the ship hydrodynamic performances in the hull forms optimization. However, it is very time consuming since a great number of the CFD simulations need to be performed for one single optimization. It is of great importance to find a high-effective method to replace the calculation of the CFD tools. In this study, a CFD-based hull form optimization loop has been developed by integrating an approximate method to optimize hull form for reducing the total resistance in calm water. In order to improve the optimization accuracy of particle swarm optimization (PSO) algorithm, an improved PSO (IPSO) algorithm is presented where the inertia weight coefficient and search method are designed based on random inertia weight and convergence evaluation, respectively. To improve the prediction accuracy of total resistance, a data prediction method based on IPSO-Elman neural network (NN) is proposed. Herein, IPSO algorithm is used to train the weight coefficients and self-feedback gain coefficient of ElmanNN. In order to build IPSO-ElmanNN model, optimal Latin hypercube design (Opt LHD) is used to design the sampling hull forms, and the total resistance (objective function) of these hull forms are calculated by Reynolds averaged Navier–Stokes (RANS) method. For the purpose of this article, this optimization framework has been employed to optimize two ships, namely, the DTMB5512 and WIGLEY III, and these hull forms are changed by arbitrary shape deformation (ASD) technique. The results show that the optimization framework developed in this study can be used to optimize hull forms with significantly reduced computational effort.

In the area of cloud computing load balancing, the Particle Swarm Optimization (PSO) algorithm is neoteric and now praised highly, but recently a more neoteric algorithm which deploys the classifier into load balancing is presented. Besides, an algorithm called red-black tree which is aiming at improving the efficiency of resource dispatching is also praised. But the 3 algorithms all have different disadvantages which cannot be ignored. For example, the dispatch efficiency of PSO algorithm is not satisfying; although classifier and red-black tree algorithm improve the efficiency of dispatching tasks, the performance in load balancing is not that good, as a result the improved PSO algorithm is presented. Some researches are designed to get the advantages of new algorithm. First of all, the time complexity and performance for each algorithm in theory are computed; and then actual data which are generated in experiments are given to demonstrate the performance. And from the experiment result, it can be found that for the speed of algorithm itself PSO is the lowest, and the improved PSO solve this problem in some degree; improved PSO algorithm has the best performance in task solving and PSO is the second one, the red-black and Naive Bayes algorithm are much slower; PSO and improved PSO algorithm perform well in load balancing, while the other two algorithms do not do well.

Aiming at the situation of local shading and multi-peak output characteristic P-U curve in the practical application of photovoltaic array, a hybrid algorithm is proposed, which uses the “three-step” strategy to quickly and accurately search the global maximum power point. The Hermite interpolation disturbance algorithm is used to select a large step size and search to the vicinity of the maximum power point through a small number of iterations. Then it is switched to the improved particle swarm optimization algorithm to find the maximum power point. When the result converges or reaches the maximum number of iterations, the voltage value near the global extremum point is output. Finally, the Hermite interpolation disturbance algorithm is carried out, and the small step length is selected to quickly and accurately stabilize at the global extremum point. This hybrid algorithm makes up for the shortcomings of a single algorithm. The advantages and disadvantages of particle swarm optimization algorithm and perturbation method complement each other, avoid falling into the local optimal value and reduce the convergence time, improve the speed and accuracy of the system, and evade the energy loss caused by oscillation. Simulink simulation verifies that the proposed hybrid algorithm has better tracking performance and response speed.

It is of great significance to study how to use intelligent algorithm to optimize the scheduling of microgrid, so as to improve the operation efficiency of microgrid. In this paper, particle swarm optimization(PSO) algorithm is improved by nonlinearly decreasing inertia weight and nonlinearly dynamic adjusting learning factors. Compared with PSO, the global search ability of the improved particle swarm optimization(IPSO) algorithm is improved. IPSO is used to optimize the scheduling of the microgrid grid connection model. The example results show that nonlinearly decreasing inertia weight and nonlinearly dynamic adjusting learning factors can obviously improve PSO. IPSO has faster convergence and lower comprehensive cost of microgrid scheduling. This paper provides an effective method for the day ahead economic scheduling of microgrid.

The pKa value of drugs is an important parameter in drug design and pharmacology. In this paper, an improved particle swarm optimization (PSO) algorithm was proposed based on the population entropy diversity. In the improved algorithm, when the population entropy was higher than the set maximum threshold, the convergence strategy was adopted; when the population entropy was lower than the set minimum threshold the divergence strategy was adopted; when the population entropy was between the maximum and minimum threshold, the self-adaptive adjustment strategy was maintained. The improved PSO algorithm was applied in the training of radial basis function artificial neural network (RBF ANN) model and the selection of molecular descriptors. A quantitative structure-activity relationship model based on RBF ANN trained by the improved PSO algorithm was proposed to predict the pKa values of 74 kinds of neutral and basic drugs and then validated by another database containing 20 molecules. The validation results showed that the model had a good prediction performance. The absolute average relative error, root mean square error, and squared correlation coefficient were 0.3105, 0.0411, and 0.9685, respectively. The model can be used as a reference for exploring other quantitative structure-activity relationships.

Although there are many methods or models widely applied to evaluate water resources carrying capacity, the evaluation result is qualitative not quantitative. In order to quantificationally evaluate groundwater carrying capacity in irrigation district, multi-objective evaluation model of groundwater carrying capacity was established, which includes four objectives, i.e., GDP, grain yield, population and COD emissions. The multi-objectives model can factually describe groundwater carrying capacity for social economy subsystem and ecological environment subsystem in irrigation district. The improved Particle Swarm Optimization (PSO) algorithm was built and adopted to solving the groundwater carrying capacity multi-objective model. In the improve PSO algorithm, linear inertia weight and chaos variation operator are employed to improve basic algorithm global searching capacity. The model was applied to quantificationally evaluate groundwater carrying capacity of People's Victory Canal irrigation district in current year and in 2010 level year.

This paper deals with the optimal path planning problem for mobile robot which are drove in obstacle environment. Specially, we aim at solving the deadlock problem using grid network and improved particle swarm optimization algorithm. The proposed method is different from traditional particle swarm optimization method, which generally has high-computational complexity and local deadlock. Instead, we utilize the integrated grid network and improved particle swarm optimization algorithm. By the grid network, the long path in the whole workspace with obstacles is divided into multi-segment continuous short paths. The improved particle swarm optimization is used in the short paths by the robot. Then the grids are prioritized and according to the grids priority in the short path, an integrated algorithm is proposed. By applying the proposed algorithm, the mobile robot move to the target along the optimal path without obstacle collision and deadlock. Finally, some experiments are provided to demonstrate the effectiveness of our proposed algorithm.

A methodology for measurement-based load modeling based on integrating dynamic models is presented in this paper. A composite load model (CLM) and an exponential recovery load (ERL) model are combined and used as a model structure for load representation coupled with a heuristic criterion. An improved particle swarm optimization (IPSO) algorithm that considers a speed update modification to enhance its global search capabilities is used to identify the model's parameters. Several simulations are performed in two test systems, using load response measurements after small and severe disturbances, considering noise measurement to simulate monitoring devices. Results verify that the proposed load model has a better performance than the individual load models, and also IPSO algorithm is adequate for parameter identification.

Ultra-high performance concrete has excellent mechanical properties such as ultra-high strength and high durability, and has a broad application prospect in the field of bridge engineering. To make full use of the superior mechanical properties of UHPC and reduce the cost of the bridge, the particle swarm optimization algorithm is used to optimize the structural design of the UHPC beam bridge; Aiming at the problem that the traditional particle swarm optimization algorithm is easy to fall into local optimum, the nonlinear adaptive weight update method is used to improve the particle swarm optimization algorithm. Based on the above-mentioned improved particle swarm optimization algorithm, the optimal design method of ordinary reinforced UHPC beams and prestressed UHPC beams with commonly used highway spans is studied. The reliability of the optimized structural limit state is analyzed by Monte Carlo (MC) importance sampling method. The results show that compared with the traditional particle swarm optimization algorithm, the improved particle swarm optimization algorithm has higher convergence speed and convergence accuracy. The optimal height-span ratio of ordinary reinforced UHPC beams decreases with the increase of the span, and the construction cost gradually increases; The optimal height-span ratio of the prestressed beam decreases first and then increases with the increase of the span, and the construction cost gradually increases. The calculation results of load capacity reliability indexes of optimization results are all higher than the target reliability indexes of similar components stipulated in China’s “Uniform Standard for Structural Reliability Design of Highway Engineering”.

The reconstruction algorithm has a hot research in compressed sensing. Matching pursuit algorithm has a huge computational task, when particle swarm optimization has been put forth to find the best atom, but it due to the easy convergence to local minima, so the paper proposed a algorithm ,which based on improved particle swarm optimization. The algorithm referred above combines K-mean and particle swarm optimization algorithm. The algorithm not only effectively prevents the premature convergence, but also improves the K-mean’s local. These findings indicated that the algorithm overcomes premature convergence of particle swarm optimization, and improves the quality of image reconstruction.

Combined with the research status of springback of sheet metal form in drawing, an neural network modeling method based on improved particle swarm optimization (IPSO) algorithm is proposed to solve the problem that tradition neural network optimal algorithm is easy to fall into local searching. In order to avoid the particles falling into local searching and improve the particles convergence rate, a new the strategy is put forward to update the particle's velocity and location. The training samples of the neural network are obtained by numerical simulation, and then prediction model of ANN is established based on neural network, of which the process parameters are input and resilience value is output. On this basis, process parameters of sheet metal forming in drawing process are optimized using IPSO. The results show that IPSO can not only improve springback prediction accuracy, but also provide a new research approach to the process parameters of sheet metal forming in drawing.

BackgroundGene selection is one of the critical steps in the course of the classification of microarray data. Since particle swarm optimization has no complicated evolutionary operators and fewer parameters need to be adjusted, it has been used increasingly as an effective technique for gene selection. Since particle swarm optimization is apt to converge to local minima which lead to premature convergence, some particle swarm optimization based gene selection methods may select non-optimal genes with high probability. To select predictive genes with low redundancy as well as not filtering out key genes is still a challenge.ResultsTo obtain predictive genes with lower redundancy as well as overcome the deficiencies of traditional particle swarm optimization based gene selection methods, a hybrid gene selection method based on gene scoring strategy and improved particle swarm optimization is proposed in this paper. To select the genes highly related to out samples’ classes, a gene scoring strategy based on randomization and extreme learning machine is proposed to filter much irrelevant genes. With the third-level gene pool established by multiple filter strategy, an improved particle swarm optimization is proposed to perform gene selection. In the improved particle swarm optimization, to decrease the likelihood of the premature of the swarm the Metropolis criterion of simulated annealing algorithm is introduced to update the particles, and the half of the swarm are reinitialized when the swarm is trapped into local minima.ConclusionsCombining the gene scoring strategy with the improved particle swarm optimization, the new method could select functional gene subsets which are significantly sensitive to the samples’ classes. With the few discriminative genes selected by the proposed method, extreme learning machine and support vector machine classifiers achieve much high prediction accuracy on several public microarray data, which in turn verifies the efficiency and effectiveness of the proposed gene selection method.

In order to improve the efficiency and reduce energy consumption of unmanned sailing boats for water quality inspection and sampling, particle swarm optimization was used for global path planning. The traditional particle swarm optimization algorithm has the problem of premature convergence because it is easy to fall into the local optimal solution. To solve this problem, an improved particle swarm optimization algorithm is proposed. Based on the traditional particle swarm optimization algorithm, the crossover and mutation operations in genetic algorithm are introduced. Firstly, the particle swarm was initialized and the fitness of the particle was calculated, and the individual optimal value and local optimal value were updated. Then crossover and mutation operations are introduced to update the particle velocity and position according to the results. Finally, the convergence of the algorithm is judged according to the decision criteria. The simulation results show that compared with the traditional particle swarm optimization algorithm, this algorithm can effectively avoid the algorithm falling into the local optimal solution, and greatly shorten the overall path length and reduce path planning time.

Police UAV plays an increasingly important role in improving new quality combat capability of public security organs. To solve the path planning problem of police UAV (PU3P), this paper proposed a police UAV path planning method based on an improved Particle Swarm Optimization (PSO) using AFS and HJS. Firstly, a specific Adaptive Factor Strategy (AFS) was introduced into original PSO in order to strengthen overall exploration capability while Half Jumping Strategy (HJS) was adopted to enhance it local exploitation level, thus an improved PSO(AFS-HJS-PSO) using AFS and HJS was proposed. Secondly, a police UAV path planning method (AFS-HJS-PSO-PU3P) was proposed by utilizing AFS-HJS-PSO to optimize police UAV path planning fitness function (UPPF) abstracted from PU3P,devoted to get the global best solution for police UAV path planning. Finally, comparative experiments among PSO, Generic Algorithm (GA),Simulated Annealing Algorithm (SAA), a Nonlinear Programming Solver: FMINCON, AFS-PSO and AFS-HJS-PSO were independently conducted 30 times on 20 classical benchmark functions as well as the ones among PSO-PU3P,GA-PU3P,SAA-PU3P,AFS-PSO-PU3P and AFS-HJS-PSO-PU3P were conducted 30 times on UPPF, theoretical research and experimental results indicate that new proposed AFS-HJS-PSO is superior to PSO, GA, SAA, FMINCON in optimization accuracy, convergence speed and stability as well as AFS-HJS-PSO-PU3P can better solve PU3P than other compared methods.

Efficient multiprocessor scheduling is essentially the problem of allocating a set of computational jobs to a set of processors to minimize the overall execution time. The main issue is how jobs are partitioned in which total finishing time and waiting time is minimized. Minimization of these two criteria simultaneously, is a multi objective optimization problem. There are many variations of this problem, most of which are NP-hard problem, so we must rely on heuristics to solve the problem instances. Many heuristic-based approaches have been applied to finding schedules that minimize the execution time of computing tasks on parallel processors. Particle swarm optimization (PSO) is currently employed in several optimization and search problems due to its ease and ability to find solutions successfully. A variant of PSO, called as improved particle swarm optimization (ImPSO) has been developed in this paper and is hybridized with the ant colony optimization (ACO) to achieve better solutions. The proposed hybrid algorithm effectively exploits the capabilities of distributed and parallel computing of swarm intelligence approaches. In addition hybrid algorithm using improved particle swarm optimization (ImPSO) with artificial immune system (AIS) is also implemented for the same set of problems to compare with the proposed hybrid algorithm (ImPSO with ACO). It was observed that the proposed hybrid approach (Improved PSO with ACO) gives better results in experiments and reduces finishing and waiting time simultaneously. Key words: Particle swarm optimization (PSO), improved particle swarm optimization (ImPSO), ant colony optimization (ACO), job scheduling, finishing time, waiting time.