An algorithm for solving FEVM problem based on SPSO algorithm
- PDF / 1,104,430 Bytes
- 6 Pages / 595.276 x 790.866 pts Page_size
- 86 Downloads / 266 Views
SPECIAL ISSUE
An algorithm for solving FEVM problem based on SPSO algorithm Ning Xiao1 Received: 21 April 2020 / Revised: 17 July 2020 / Accepted: 28 August 2020 © Springer-Verlag GmbH Germany, part of Springer Nature 2020
Abstract To solve fuzzy expected value model problem that widely exists in fuzzy programming field, a new hybrid intelligence algorithm based on Stochastic Particle Swarm Optimization (SPSO) algorithm is put forward in this article. Fuzzy simulation is used to get training samples for multi-layer (BP) Back Propagation artificial neural networks and multi-layer BP artificial neural networks is used to approximate fuzzy expected value function when SPSO algorithm is used to find the optimal value, the trained multi-layer BP artificial neural networks is used to calculate fuzzy expected function’s fitness value and detail steps are designed. Compared with the hybrid intelligence algorithm based on the classical Genetic Algorithm, the proposed algorithm overcomes some defects, such as taking a long time, computing complexity, easy being immersed in local extremum. The results are justified with the help of two numerical illustrations for fuzzy expected value model problem, the effectiveness of our new approach is demonstrated and it has determinate practical value. Keywords SPSO · Fuzzy expected value model · Multi-layer BP artificial neural networks · Fuzzy simulation
1 Introduction In order to adapt to the research and solution of fuzzy programming problems in uncertain programming field, Liu proposed fuzzy programming theory, established corresponding models and solving algorithms based on classical Genetic Algorithm (GA) [1–3], plenty of fuzzy programming problems have also been solved effectively [4–8]. However, genetic operation procedure is complicated, and has slow convergence and low precision, it is also easy to fall into local optimum. Currently, many researchers are devoting themselves to investigating more effective method to solve this kind problem. Particle Swarm Optimization (PSO) algorithm, an original swarm intelligence technique, was firstly developed by scholar: Kennedy and Eberhart, in which global searching tactics based upon swarm was utilized. It resembles GA. Nevertheless, PSO merely employs Velocity-Situation model to search optimal solution, the fewer parameters only need setting, it possesses many advantages, for instance, simplicity, fast convergence rate, better accuracy etcetera, and its * Ning Xiao [email protected] 1
dominant position has been manifested in resolving various sorts problems,such as, deep feature learning for dummies, rolling element bearing fault diagnosis, the text and emotion classification and so on [9–15]. The author of this paper also did some research work on uncertain programming problems’ solving algorithm [16–19]. In order to find a more better solving algorithm, this paper utilizes Stochastic Particle Swarm Optimization [20] (SPSO) and combines fuzzy simulation technology, multi-layer BP artificial neural networks to solve Fuzzy Expected
Data Loading...
