Papers by Keyword: Particle Swarm Algorithm

Abstract: For vehicles in use, may be due to an engine misfire malfunction problem, a new and improved intelligent diagnosis method. The establishment of a volume fraction and fire fault automobile exhaust gases generated mapping between various reasons for data normalization processing for machine training, the trained models relevance vector machine used in failure analysis, classification diagnosis. The algorithm of the penalty factor and radial basis kernel function parameters on classification accuracy rate has a great impact, the use of super-particle swarm optimization parameters. Relevance vector machine model to optimize the trained and now mature neural networks and genetic algorithms support vector machine method were compared with experimental results show that the new method than the traditional methods have some improvement in diagnostic accuracy and robustness aspects .

Abstract: In this paper, we propose a fast multiobjective particle swarm optimization algorithm (called CBR-fMOPSO for short). In the algorithm, a case-based reasoning (CBR) technique is used to retrieve history optimization results and experts’ experience and add them into the population of multiobjective particle swarm optimization algorithm (MOPSO) in dynamic environment. The optimal solutions found by CBR-fMOPSO are used to mend the case library to improve the accuracy of solving based on CBR in next solving. The results from a suit of experiments in electric furnaces show that the proposed algorithm maintains good performances however the environment changes.

Abstract: The traditional evolutionary algorithm is cannot converge faster to solve the path optimization problems, and the path that is computed is not the shortest path, in allusion to the disadvantage of this algorithm, a mutation particle swarm optimization algorithm is proposed. The algorithm introduces the adaptive mutation strategy, and accelerated the speed to search for the global optimal solution. For seven examples experiment in standard database, the result shows that the algorithm is more efficient..

Abstract: Particle swarm algorithm is an efficient evolutionary computation method and wildly used in various disciplines. But as a random global search algorithm, particle swarm algorithm easily falls into the local optimal solution for its rapid propagation in populations and in order to overcome these shortcomings, a novel particle swarm algorithm is presented and used in classifying online trading customers. The corresponding improvements include improving the speed update formula of particles and improving the balance between the development and detection capability of original algorithm and redesigning the calculation flow of the improved algorithm. Finally after designing 21 customer classification indicators, the improved algorithm is realized for customer classification of a certain E-commerce enterprise and experimental results show that the algorithm can improve classification accuracy and decreases the square errors.

Abstract: K-means algorithm is a traditional cluster analysis method, has the characteristics of simple ideas and algorithms, and thus become one of the commonly used methods of cluster analysis. However, the K-means algorithm classification results are too dependent on the choice of the initial cluster centers for some initial value, the algorithm may converge in general suboptimal solutions. Analysis of the K-means algorithm and particle swarm optimization based on a clustering algorithm based on improved particle swarm algorithm. The algorithm local search ability of the K-means algorithm and the global search ability of particle swarm optimization, local search ability to improve the K-means algorithm to accelerate the convergence speed effectively prevent the occurrence of the phenomenon of precocious puberty. The experiments show that the clustering algorithm has better convergence effect.

Abstract: In precision machining field,lighting quality has an important influence on subjective visual experience and job performance. Therefore,it has great significance that the effective assessment of illumination uniformity.In connection with illumination uniformity assessment which is a nonlinear optimization problem, a evaluation method of illuminance uniformity based on improved particle swarm optimization algorithm is proposed.under the premise of elaborate the basic principles of the algorithm and implementation steps. The paper has given its optimized objective function and fitness function of the algorithm.what’s more, the feasibility and accuracy of the algorithm is verified.The results that illumination uniformity function of the simulation show that this method not only improves the calculation accuracy and reduces the possibility of local convergence.

Abstract: The classification and prediction of load is very important, in the power market .In order to improve the accuracy and speed of forecast, it is proposed that the mixed algorithm of particle swarm and back propagation network and model. And model is established on the basis of one city electric power bureaus electric power load data. Using the PSO - BP algorithm to the load for forecasting .According to the results of prediction, this method converges fast, prediction accuracy improved significantly. Application in the power market analysis and forecasting have very good effect and prospect.

Abstract: This paper establishes a power planning model based on minimization of the initial investment cost. The model includes the initial investment cost of wind turbines, photovoltaic cells, batteries, and biomass generators, diesel generators, power electronic devices and communications facilities in the objective function. In consideration of some constraint conditions, using the principle of priority of biomass generators, we use the particle swarm algorithm to solve the model. Through the calculation of actual examples, we simulate to find optimal solutions. Finally, we conclude that it should be possible to use biomass power generation and diesel generator power.

Abstract: This paper establishes a power planning model based on minimizing operation and maintenance cost. The model take into account the costs of the wind turbines, photovoltaic cells, batteries, biomass generators, diesel generators, power electronics devices and communications facilities operation and maintenance, credit them in the objective function, and considering some certain constraints, use particle swarm algorithm model, by calculating and, simulating examples , to find the optimal solution, Finally to find the conclusion that to use wind turbines, photovoltaic cells and batteries for electric as much as possible.

Abstract: A design method of PID controller based on particle swarm algorithm is proposed to solve the difficult problems of parameter tuning on PID controller in automatic control system. And the specific experimental structure is also given. The transfer function of DC servo generator was found with identification of system parameters, and the PID parameters were searched by particle swarm algorithm. MATLAB simulation was used to demonstrate the feasibility and advantages of this approach. The simulation result was compared to the result of searching PID parameters based on genetic algorithm, and it is show that the seeking time to tune the PID parameters by using the particle swarm algorithm is faster than by using the genetic algorithm method.