Electromagnetic scattering for large problems with the Physical Optics - MultiLevel - Binary Space Partitioning (PO-ML-BSP) algorithm

2006 ◽  
Author(s):  
Jose Angel Martinez Lorenzo ◽  
Javier Gutierrez Meana ◽  
Fernando Las Heras Andres ◽  
Antonio Garcia Pino
Keyword(s):  
Electromagnetic Scattering ◽  
Physical Optics ◽  
Space Partitioning ◽  
Binary Space Partitioning

scholarly journals Multispecies Coevolution Particle Swarm Optimization Based on Previous Search History

2017 ◽  
Vol 2017 ◽  
pp. 1-22
Author(s):  
Danping Wang ◽  
Kunyuan Hu ◽  
Lianbo Ma ◽  
Maowei He ◽  
Hanning Chen
Keyword(s):  
Particle Swarm Optimization ◽  
Statistical Tests ◽  
Particle Swarm ◽  
Local Optimum ◽  
Space Partitioning ◽  
Swarm Optimization ◽  
Real World Problem ◽  
Binary Space Partitioning ◽  
Solution Accuracy ◽  
Search History

A hybrid coevolution particle swarm optimization algorithm with dynamic multispecies strategy based on K-means clustering and nonrevisit strategy based on Binary Space Partitioning fitness tree (called MCPSO-PSH) is proposed. Previous search history memorized into the Binary Space Partitioning fitness tree can effectively restrain the individuals’ revisit phenomenon. The whole population is partitioned into several subspecies and cooperative coevolution is realized by an information communication mechanism between subspecies, which can enhance the global search ability of particles and avoid premature convergence to local optimum. To demonstrate the power of the method, comparisons between the proposed algorithm and state-of-the-art algorithms are grouped into two categories: 10 basic benchmark functions (10-dimensional and 30-dimensional), 10 CEC2005 benchmark functions (30-dimensional), and a real-world problem (multilevel image segmentation problems). Experimental results show that MCPSO-PSH displays a competitive performance compared to the other swarm-based or evolutionary algorithms in terms of solution accuracy and statistical tests.

Hierarchical Neuro-Fuzzy Systems Part II

2011 ◽  
pp. 817-824
Author(s):  
Marley Vellasco ◽  
Marco Pacheco ◽  
Karla Figueiredo ◽  
Flavio Souza
Keyword(s):  
Reinforcement Learning ◽  
State Space ◽  
Learning Process ◽  
Fuzzy Systems ◽  
Space Partitioning ◽  
Learning Methods ◽  
New Class ◽  
Neuro Fuzzy ◽  
Binary Space Partitioning ◽  
Priori Information

This paper describes a new class of neuro-fuzzy models, called Reinforcement Learning Hierarchical Neuro- Fuzzy Systems (RL-HNF). These models employ the BSP (Binary Space Partitioning) and Politree partitioning of the input space [Chrysanthou,1992] and have been developed in order to bypass traditional drawbacks of neuro-fuzzy systems: the reduced number of allowed inputs and the poor capacity to create their own structure and rules (ANFIS [Jang,1997], NEFCLASS [Kruse,1995] and FSOM [Vuorimaa,1994]). These new models, named Reinforcement Learning Hierarchical Neuro-Fuzzy BSP (RL-HNFB) and Reinforcement Learning Hierarchical Neuro-Fuzzy Politree (RL-HNFP), descend from the original HNFB that uses Binary Space Partitioning (see Hierarchical Neuro-Fuzzy Systems Part I). By using hierarchical partitioning, together with the Reinforcement Learning (RL) methodology, a new class of Neuro-Fuzzy Systems (SNF) was obtained, which executes, in addition to automatically learning its structure, the autonomous learning of the actions to be taken by an agent, dismissing a priori information (number of rules, fuzzy rules and sets) relative to the learning process. These characteristics represent an important differential when compared with existing intelligent agents learning systems, because in applications involving continuous environments and/or environments considered to be highly dimensional, the use of traditional Reinforcement Learning methods based on lookup tables (a table that stores value functions for a small or discrete state space) is no longer possible, since the state space becomes too large. This second part of hierarchical neuro-fuzzy systems focus on the use of reinforcement learning process. The first part presented HNFB models based on supervised learning methods. The RL-HNFB and RL-HNFP models were evaluated in a benchmark control application and a simulated Khepera robot environment with multiple obstacles.

Numerical Simulation of Thermal Stress for a Liquid-Cooled Exhaust Manifold

2008 ◽  
Author(s):  
Dong Fu ◽  
Dui Huang ◽  
Ahmed Juma ◽  
Curtis M. Schreiber ◽  
Xiuling Wang ◽  
...  
Keyword(s):  
Thermal Stress ◽  
Material Behavior ◽  
Nonlinear Material ◽  
Large Temperature ◽  
Space Partitioning ◽  
Experiment Data ◽  
Industrial Experiment ◽  
Binary Space Partitioning ◽  
Current Design ◽  
Computational Fluid Dynamics Cfd

Liquid-cooled exhaust manifolds are widely used in turbocharged diesel engines. The large temperature gradient in the overall manifold will cause remarkable thermal stress. The objective of the project is to modify the current design for preventing the high thermal stress and extending the life span of the manifold. To achieve the objective, the combination between Computational Fluid Dynamics (CFD) with Finite Element (FE) is introduced. Firstly, CFD analysis is conducted to obtain temperature distribution, providing boundary conditions of the thermal load on the FE mesh. Afterward, FE analysis is carried out to determine the thermal stress. The interpolation of the temperature data from CFD to FE is done by Binary Space Partitioning (BSP) tree algorithm. To accurately quantify the thermal stress, nonlinear material behavior is considered. The computational results are compared with that of Number of Transfer Units (NTU) method, and are further verified with industrial experiment data. All these comparisons indicate that present investigation reasonably predicts the thermal stress behavior. Based on the results, recommendations are given to optimize the manifold design.

scholarly journals Modelo Neuro-Fuzzy Hierárquico Politree com aprendizado por reforço para agentes inteligentes

2007 ◽  
Vol 18 (2) ◽  
pp. 234-250 ◽  
Author(s):  
Karla Figueiredo ◽  
Marley Vellasco ◽  
Marco Pacheco ◽  
Flávio Souza
Keyword(s):  
Reinforcement Learning ◽  
Space Partitioning ◽  
Neuro Fuzzy ◽  
Binary Space Partitioning

Este trabalho apresenta um novo modelo híbrido neuro-fuzzy para aprendizado automático de ações efetuadas por agentes. O objetivo do modelo é dotar um agente de inteligência, tornando-o capaz de, através da interação com o seu ambiente, adquirir e armazenar o conhecimento e raciocinar (inferir uma ação). Este novo modelo, denominado Reinforcement Learning Neuro-Fuzzy Hierárquico Politree (RL-NFHP), descende dos modelos neuro-fuzzy hierárquicos NFHB, os quais utilizam aprendizado supervisionado e particionamento BSP (Binary Space Partitioning) do espaço de entrada. Com o uso desse método hierárquico de particionamento, associado ao Reinforcement Learning, obteve-se uma nova classe de Sistemas Neuro-Fuzzy (SNF) que executam, além do aprendizado da estrutura, o aprendizado autônomo das ações a serem tomadas por um agente. Essas características representam um importante diferencial em relação aos sistemas de aprendizado de agentes inteligentes existentes. O modelo RL-NFHP foi testado em diferentes problemas benchmark e em uma aplicação de robótica (robô Khepera). Os resultados obtidos mostram o potencial do modelo proposto, que dispensa informações preliminares como número e formato das regras, e número de partições que o espaço de entrada deve possuir.

Sign in / Sign up

Export Citation Format

Share Document