Optimization Design of Structure and Parameters for RBF Neural Network Using Hybrid Hierarchy Genetic Algorithm

2014 ◽  
Vol 951 ◽  
pp. 274-277 ◽  
Author(s):  
Xu Sheng Gan ◽  
Can Yang ◽  
Hai Long Gao
Keyword(s):  
Neural Network ◽  
Genetic Algorithm ◽  
Optimization Design ◽  
Rbf Neural Network ◽  
Hybrid Genetic Algorithm ◽  
Proposed Model ◽  
Crossover Probability ◽  
Ga Algorithm ◽  
The Hierarchical Structure ◽  
Adaptive Crossover

To improve the optimization design of Radial Basis Function (RBF) neural network, a RBF neural network based on a hybrid Genetic Algorithm (GA) is proposed. First the hierarchical structure and adaptive crossover probability is introduced into the traditional GA algorithm for the improvement, and then the hybrid GA algorithm is used to optimize the structure and parameters of the network. The simulation indicates that the proposed model has a good modeling performance.

scholarly journals Hybrid Genetic Algorithm Model in Neuro Symbolic Integration

2020 ◽  
Vol 9 (4) ◽  
pp. 2144-2149
Keyword(s):  
Neural Network ◽  
Genetic Algorithm ◽  
Hamming Distance ◽  
Hybrid Genetic Algorithm ◽  
Hopfield Neural Network ◽  
Computational Time ◽  
Agent Based ◽  
Proposed Model ◽  
Network Studies ◽  
Minimum Ratio

The development of artificial neural network and logic programming plays an important part in neural network studies. Genetic Algorithm (GA) is one of the escorted randomly searching technicality that uses evolutional concepts of the natural election as a stimulus to solve the computational problems. The essential purposes behind the studies of the evolutional system is for developing adaptive search techniques which are robust. In this paper, GA is merged with agent based modeling (ABM) by using specified proceedings to optimise the states of neurons and energy function in the Hopfield neural network (HNN). Hence, it is observed that the GA provides the best solutions in affirming optimal states of neurons and thus, enhancing the performance of Horn Satisfiability logical program (HornSAT) in Hopfield neural network. This is due to the fact that the GA lesser susceptive to be restricted in the local optimal or in any suboptimal solutions. NETLOGO version 6.0 will be used as a dynamic platform to test our proposed model. Hence, the computer simulations will be carried out to substantiate and authenticate the efficiency of the proposed model. The results are then tabulated by evaluating the global minimum ratio, computational time and hamming distance

Design of Intelligent Controller for Ship Motion with Input Saturation Based on Optimized Radial Basis Function Neural Network

2020 ◽  
Vol 13 ◽  
Author(s):  
Renqiang Wang ◽  
Qinrong Li ◽  
Shengze Miao ◽  
Keyin Miao ◽  
Hua Deng
Keyword(s):  
Neural Network ◽  
Genetic Algorithm ◽  
Sliding Mode Control ◽  
Intelligent Control ◽  
Control Algorithm ◽  
Sliding Mode ◽  
Rbf Neural Network ◽  
Input Saturation ◽  
Ship Motion ◽  
Mode Control

Abstract: The purpose of this paper was to design an intelligent controller of ship motion based on sliding mode control with a Radial Basis Function (RBF) neural network optimized by the genetic algorithm and expansion observer. First, the improved genetic algorithm based on the distributed genetic algorithm with adaptive fitness and adaptive mutation was used to automatically optimize the RBF neural network. Then, with the compensation designed by the RBF neural network, anti-saturation control was realized. Additionally, the intelligent control algorithm was introduced by Sliding Mode Control (SMC) with the stability theory. A comparative study of sliding mode control integrated with the RBF neural network and proportional–integral–derivative control combined with the fuzzy optimization model showed that the stabilization time of the intelligent control system was 43.75% faster and the average overshoot was reduced by 52% compared with the previous two attempts. Background: It was known that the Proportional-Integral-Derivative (PID) control and self-adaptation control cannot really solve the problems of frequent disturbance from external wind and waves, as well as the problems with ship nonlinearity and input saturation. So, the previous ship motion controller should be transformed by advanced intelligent technology, on the basis of referring to the latest relevant patent design methods. Objective: An intelligent controller of ship motion was designed based on optimized Radial Basis Function Neural Network (RBFNN) in the presence of non-linearity, uncertainty, and limited input. Methods: The previous ship motion controller was remodeled based on Sliding Mode Control (SMC) with RBFNN optimized by improved genetic algorithm and expansion observer. The intelligent control algorithm integrated with genetic neural network solved the problem of system model uncertainty, limited control input, and external interference. Distributed genetic with adaptive fitness and adaptive mutation method guaranteed the adequacy of search and the global optimal convergence results, which enhanced the approximation ability of RBFNN. With the compensation designed by the optimized RBFNN, it was realized anti-saturation control. The chattering caused by external disturbance in SMC controller was reduced by the expansion observer. Results: A comparative study with RBFNN-SMC control and fuzzy-PID control, the stabilization time of the intelligent control system was 43.75% faster, the average overshoot was reduced by 52%, compared to the previous two attempts. Conclusion: The intelligent control algorithm succeed in dealing with the problems of nonlinearity, uncertainty, input saturation, and external interference. The intelligent control algorithm can be applied into research and development ship steering system, which would be created a new patent.

scholarly journals Deep convolutional tree-inspired network: a decision-tree-structured neural network for hierarchical fault diagnosis of bearings

2021 ◽  
Author(s):  
Xu Wang ◽  
Hongyang Gu ◽  
Tianyang Wang ◽  
Wei Zhang ◽  
Aihua Li ◽  
...  
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Decision Tree ◽  
Structural Characteristics ◽  
Proposed Model ◽  
The Hierarchical Structure ◽  
Hierarchical Decision ◽  
Tree Methods ◽  
New Perspective ◽  
Simple Combination

AbstractThe fault diagnosis of bearings is crucial in ensuring the reliability of rotating machinery. Deep neural networks have provided unprecedented opportunities to condition monitoring from a new perspective due to the powerful ability in learning fault-related knowledge. However, the inexplicability and low generalization ability of fault diagnosis models still bar them from the application. To address this issue, this paper explores a decision-tree-structured neural network, that is, the deep convolutional tree-inspired network (DCTN), for the hierarchical fault diagnosis of bearings. The proposed model effectively integrates the advantages of convolutional neural network (CNN) and decision tree methods by rebuilding the output decision layer of CNN according to the hierarchical structural characteristics of the decision tree, which is by no means a simple combination of the two models. The proposed DCTN model has unique advantages in 1) the hierarchical structure that can support more accuracy and comprehensive fault diagnosis, 2) the better interpretability of the model output with hierarchical decision making, and 3) more powerful generalization capabilities for the samples across fault severities. The multiclass fault diagnosis case and cross-severity fault diagnosis case are executed on a multicondition aeronautical bearing test rig. Experimental results can fully demonstrate the feasibility and superiority of the proposed method.

The Optimization Design of the Cross-Sectional Layout of an Umbilical Based on the Hybrid Genetic Algorithm

2021 ◽  
Author(s):  
Xu Yin ◽  
Zhixun Yang ◽  
Dongyan Shi ◽  
Jun Yan ◽  
Lifu Wang ◽  
...  
Keyword(s):  
Genetic Algorithm ◽  
Cross Sections ◽  
Optimization Design ◽  
Mechanical Performance ◽  
Fitness Function ◽  
Hybrid Genetic Algorithm ◽  
Optimization Strategy ◽  
Cross Sectional ◽  
Great Probability ◽  
The Cross

Abstract The umbilical which consists of hydraulic tubes, electrical cables and optical cables is a key equipment in the subsea production system. Each components perform different physical properties, so different cross-sections will present different geometrical characteristic, carrying capacities, the cost and the ease of manufacture. Therefore, the cross-sectional layout design of the umbilical is a typical multi-objective optimization problem. A mathematical model of the cross-sectional layout considering geometric and mechanical properties is proposed, and the genetic algorithm is introduced to copy with the optimization model in this paper. A steepest descent operator is embedded into the basic genetic algorithm, while the appropriate fitness function and the selection operator are advanced. The optimization strategy of the cross-sectional layout based on the hybrid genetic algorithm is proposed with the fast convergence and the great probability for global optimization. Finally, the cross-section of an umbilical case is performed to obtain the optimal the cross-sectional layout. The geometric and mechanical performance of results are compared with the initial design, which verify the feasibility of the proposed algorithm.

Sign in / Sign up

Export Citation Format

Share Document