scholarly journals The Parameters Selection of PSO Algorithm influencing On performance of Fault Diagnosis

2016 ◽  
Vol 63 ◽  
pp. 02019 ◽  
Author(s):  
Yan He ◽  
Wei Jin Ma ◽  
Ji Ping Zhang
Keyword(s):  
Fault Diagnosis ◽  
Pso Algorithm ◽  
Parameters Selection ◽  
Selection Of

Hyper-Parameters Selection of LS-SVM Based on PSO Algorithm with Multi-Particles Sharing Strategy

2014 ◽  
Vol 1049-1050 ◽  
pp. 1654-1657
Author(s):  
Jie Liu ◽  
Xu Sheng Gan ◽  
Wen Ming Gao
Keyword(s):  
Particle Swarm Optimization ◽  
Particle Swarm ◽  
Pso Algorithm ◽  
Optimal Parameters ◽  
Swarm Optimization ◽  
Improved Particle Swarm Optimization ◽  
Parameters Selection ◽  
Sharing Strategy ◽  
Selection Of

To optimize the parameters of LS-SVM effectively, an improved Particle Swarm Optimization (PSO) algorithm is proposed to select the optimal parameters combination. For the improvement of the precocity in PSO algorithm, an multi-particles sharing strategy is introduced in simple PSO algorithm to enhance the convergence. The simulation indicates that the proposed PSO algorithm has a better selection on LS-SVM parameters.

A HYBRID PSO-SA OPTIMIZING APPROACH FOR SVM MODELS IN CLASSIFICATION

2013 ◽  
Vol 06 (05) ◽  
pp. 1350036 ◽  
Author(s):  
HUIYAN JIANG ◽  
LINGBO ZOU
Keyword(s):  
Operating Characteristic ◽  
Fitness Function ◽  
Pso Algorithm ◽  
Optimization Method ◽  
Identification Accuracy ◽  
Support Vector ◽  
Swarm Optimization ◽  
Receiver Operating Characteristic Curves ◽  
Parameters Selection ◽  
Selection Of

Support vector machine (SVM) is a widely used tool in the field of image processing and pattern recognition. However, the parameters selection of SVMs is a dilemma in disease identification and clinical diagnosis. This paper proposed an improved parameter optimization method based on traditional particle swarm optimization (PSO) algorithm by changing the fitness function in the traditional evolution process of SVMs. Then, this PSO method was combined with simulated annealing global searching algorithm to avoid local convergence that traditional PSO algorithms usually run into. And this method has achieved better results which reflected in the receiver-operating characteristic curves in medical images classification and has gained considerable identification accuracy in clinical disease detection.

scholarly journals Vibration-Based Fault Diagnosis of Commutator Motor

2018 ◽  
Vol 2018 ◽  
pp. 1-10 ◽  
Author(s):  
Adam Glowacz ◽  
Witold Glowacz
Keyword(s):  
Fault Diagnosis ◽  
Extraction Methods ◽  
Total Efficiency ◽  
Practical Application ◽  
Backpropagation Neural Network ◽  
Vibration Signals ◽  
Linear Discriminant ◽  
Recognition Efficiency ◽  
Signal Processing Methods ◽  
Selection Of

This paper presents a study on vibration-based fault diagnosis techniques of a commutator motor (CM). Proposed techniques used vibration signals and signal processing methods. The authors analysed recognition efficiency for 3 states of the CM: healthy CM, CM with broken tooth on sprocket, CM with broken rotor coil. Feature extraction methods called MSAF-RATIO-50-SFC (method of selection of amplitudes of frequencies ratio 50 second frequency coefficient), MSAF-RATIO-50-SFC-EXPANDED were implemented and used for an analysis. Feature vectors were obtained using MSAF-RATIO-50-SFC, MSAF-RATIO-50-SFC-EXPANDED, and sum of RSoV. Classification methods such as nearest mean (NM) classifier, linear discriminant analysis (LDA), and backpropagation neural network (BNN) were used for the analysis. A total efficiency of recognition was in the range of 79.16%–93.75% (TV). The proposed methods have practical application in industries.

scholarly journals Fault Diagnosis of Transmission Line using Feed Forward Neural Network

2019 ◽  
Vol 8 (9S2) ◽  
pp. 263-268
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Transmission Lines ◽  
Field Work ◽  
Neural Nets ◽  
Feed Forward Neural Network ◽  
Training Time ◽  
Optimum Result ◽  
Human Effort ◽  
Selection Of

The implementation of neural network for the fault diagnosis is to improve the dependability of the proposed scheme by providing a more accurate, faster diagnosis relaying scheme as compared with the conventional relaying schemes. It is important to improve the relaying schemes regarding the shortcoming of the system and increase the dependability of the system by using the proposed relaying scheme. It also provide more accurate, faster relaying scheme. It also gives selective schemes as compared to conventional system. The techniques for survey employed some methods for the collection of data which involved a literature review of journals, from review on books, newspaper, magazines as well as field work, additional data was collected from researchers who are working in this field. To achieve optimum result we have to improve following things: (i) Training time, (ii) Selection of training vector, (iii) Upgrading of trained neural nets and integration of technologies. AI with its promise of adaptive training and generalization deserves scope. As a result we obtain a system which is more reliable, more accurate, and faster, has more dependability as well as it will selective according to the proposed relaying scheme as compare to the conventional relaying scheme. This system helps us to reduce the shortcoming like major faults which we faced in the complex system of transmission lines which will helps in reducing human effort, saves cost for maintaining the transmission system.

scholarly journals Best Selection of Generative Adversarial Networks Hyper-Parameters using Genetic Algorithm

2020 ◽  
Author(s):  
Fajr Alarsan ◽  
Mamoon Younes
Keyword(s):  
Genetic Algorithm ◽  
Programming Language ◽  
Loss Function ◽  
Generative Adversarial Networks ◽  
Accuracy Function ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Adversarial Networks ◽  
Parameters Selection ◽  
Selection Of

Abstract Generative Adversarial Networks (GANs) are most popular generative frameworks that have achieved compelling performance. They follow an adversarial approach where two deep models generator and discriminator compete with each other In this paper, we propose a Generative Adversarial Network with best hyper-parameters selection to generate fake images for digits number 1 to 9 with generator and train discriminator to decide whereas the generated images are fake or true. Using Genetic Algorithm technique to adapt GAN hyper-parameters, the final method is named GANGA:Generative Adversarial Network with Genetic Algorithm. Anaconda environment with tensorflow library facilitates was used, python as programming language also used with needed libraries. The implementation was done using MNIST dataset to validate our work. The proposed method is to let Genetic algorithm to choose best values of hyper-parameters depending on minimizing a cost function such as a loss function or maximizing accuracy function. GA was used to select values of Learning rate, Batch normalization, Number of neurons and a parameter of Dropout layer.

Sign in / Sign up

Export Citation Format

Share Document