Studies of Synchronous Rotor Gear Monitoring Technique Based on Ant Colony Neural Network

2011 ◽  
Vol 121-126 ◽  
pp. 382-386
Author(s):  
Yi Jun Chen ◽  
Qing Hai Zhao
Keyword(s):  
Neural Network ◽  
Ant Colony Algorithm ◽  
Accurate Determination ◽  
Ant Colony ◽  
Local Minima ◽  
Characteristic Parameters ◽  
Monitoring Technique ◽  
The Neural Network ◽  
Failure Types

In this paper, the nonlinear mapping relationship between characteristic parameters of failures and failure types is realized by using neural network through extracting characteristic variables of failures during operation of the gear. Aiming at the problems of neutral network such as slow convergence speed and existence of local minima, the neural network is optimized and the ant colony neural network is established by using the ant colony algorithm to realize rapid and accurate determination of failure status of a gear from characteristic parameters of failures. In addition, validity of the established model is verified through experiments.

Motor Failure Diagnosis Based on ant Colony Algorithm and BP Neural Network

2011 ◽  
Vol 42 (11) ◽  
pp. 51-56 ◽  
Author(s):  
Jian-Ping WANG ◽  
Xiao-Min Li ◽  
Yong HANG
Keyword(s):  
Neural Network ◽  
Bp Neural Network ◽  
Ant Colony Algorithm ◽  
Ant Colony ◽  
Failure Diagnosis ◽  
Normal Operation ◽  
Mechanical Equipment ◽  
The Neural Network ◽  
Trained Neural Network ◽  
Motor Failure

As the main measure to protect the normal operation of mechanical equipment, motor failure diagnosis is very important. This paper proposes failure diagnosis based on the combination of ant colony algorithm and BP neural network towards motor failure. Here, the ant colony algorithm is used for training the neural network in order to diagnosis the motor failure. By testing the algorithm it is found that the ant colony algorithm trained neural network has the characteristics of wide mapping capability, faster convergence speed, and high accuracy of failure diagnosis. The algorithm can diagnose motor failure effectively, and improve the efficiency and quality of diagnosis, to avoid the problem of slow convergence and the tendency to fall into the local minima point by just using BP neural network.

Electromagnetic Nondestructive Testing in Cracked Defects of Oil-Gas Casing Based on Ant Colony Neural Network

2012 ◽  
Vol 605-607 ◽  
pp. 760-763 ◽  
Author(s):  
Wei Zhang ◽  
Yi Bing Shi ◽  
Yan Jun Li
Keyword(s):  
Neural Network ◽  
Quantitative Analysis ◽  
Magnetic Flux ◽  
Ant Colony Algorithm ◽  
Fem Simulation ◽  
Ant Colony ◽  
Working Environment ◽  
Magnetic Flux Leakage ◽  
The Neural Network ◽  
Flux Leakage

In this paper, a new method on quantitative analysis of magnetic flux leakage signal by ant colony neural network is proposed. Firstly, the parameters of the magnetic flux leakage signal which can reflect the various characteristics of cracked defects are determined by finite element method (FEM) simulation. Secondly, based on the study of the ant colony algorithm, the neural network model is established for the magnetic flux leakage signals processing. Finally, in the simulated working environment, the performance of the neural network is tested with the different signal features as input. The experimental results proved the feasibility of the ant colony neural network, verified the increases of the convergence rate and the accuracy of the neural network, and improved the efficiency as well as the quality of the quantitative analysis for the magnetic flux leakage signals.

scholarly journals Network-based Observability and Controllability Analysis of Dynamical Systems: the NOCAD toolbox

F1000Research ◽  
2019 ◽  
Vol 8 ◽  
pp. 646
Author(s):  
Dániel Leitold ◽  
Ágnes Vathy-Fogarassy ◽  
János Abonyi
Keyword(s):  
Neural Network ◽  
Caenorhabditis Elegans ◽  
Dynamical Systems ◽  
Network Science ◽  
Sensor Placement ◽  
Life Sciences ◽  
The Neural Network ◽  
Structural Controllability ◽  
Controllability And Observability

The network science-based determination of driver nodes and sensor placement has become increasingly popular in the field of dynamical systems over the last decade. In this paper, the applicability of the methodology in the field of life sciences is introduced through the analysis of the neural network of Caenorhabditis elegans. Simultaneously, an Octave and MATLAB-compatible NOCAD toolbox is proposed that provides a set of methods to automatically generate the relevant structural controllability and observability associated measures for linear or linearised systems and compare the different sensor placement methods.

scholarly journals Is the Skip Connection Provable to Reform the Neural Network Loss Landscape?

2020 ◽  
Author(s):  
Lifu Wang ◽  
Bo Shen ◽  
Ning Zhao ◽  
Zhiyuan Zhang
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Level Sets ◽  
Theoretical Explanation ◽  
Learning Ability ◽  
Local Minima ◽  
Global Minima ◽  
Residual Network ◽  
The Neural Network ◽  
Hidden Nodes

The residual network is now one of the most effective structures in deep learning, which utilizes the skip connections to “guarantee" the performance will not get worse. However, the non-convexity of the neural network makes it unclear whether the skip connections do provably improve the learning ability since the nonlinearity may create many local minima. In some previous works [Freeman and Bruna, 2016], it is shown that despite the non-convexity, the loss landscape of the two-layer ReLU network has good properties when the number m of hidden nodes is very large. In this paper, we follow this line to study the topology (sub-level sets) of the loss landscape of deep ReLU neural networks with a skip connection and theoretically prove that the skip connection network inherits the good properties of the two-layer network and skip connections can help to control the connectedness of the sub-level sets, such that any local minima worse than the global minima of some two-layer ReLU network will be very “shallow". The “depth" of these local minima are at most O(m^(η-1)/n), where n is the input dimension, η<1. This provides a theoretical explanation for the effectiveness of the skip connection in deep learning.

Cluster Based Medical Image Registration Using Optimized Neural Network

2017 ◽  
pp. 1437-1467
Author(s):  
Joydev Hazra ◽  
Aditi Roy Chowdhury ◽  
Paramartha Dutta
Keyword(s):  
Neural Network ◽  
Genetic Algorithm ◽  
Image Registration ◽  
Convergence Rate ◽  
Optimization Algorithm ◽  
Clustering Algorithms ◽  
Data Sets ◽  
Learning Method ◽  
Local Minima ◽  
The Neural Network

Registration of medical images like CT-MR, MR-MR etc. are challenging area for researchers. This chapter introduces a new cluster based registration technique with help of the supervised optimized neural network. Features are extracted from different cluster of an image obtained from clustering algorithms. To overcome the drawback regarding convergence rate of neural network, an optimized neural network is proposed in this chapter. The weights are optimized to increase the convergence rate as well as to avoid stuck in local minima. Different clustering algorithms are explored to minimize the clustering error of an image and extract features from suitable one. The supervised learning method applied to train the neural network. During this training process an optimization algorithm named Genetic Algorithm (GA) is used to update the weights of a neural network. To demonstrate the effectiveness of the proposed method, investigation is carried out on MR T1, T2 data sets. The proposed method shows convincing results in comparison with other existing techniques.

Synthesis, spectral description, and lipophilicity parameters determination of phenylcarbamic acid derivatives with integrated N-phenylpiperazine moiety in the structure

2006 ◽  
Vol 60 (1) ◽  
Author(s):  
I. Malík ◽  
E. Sedlárová ◽  
J. Csöllei ◽  
F. Andriamainty ◽  
P. Kurfürst ◽  
...  
Keyword(s):  
Neural Network ◽  
Spectral Data ◽  
1H Nmr ◽  
Elemental Analysis ◽  
Computer Programs ◽  
Mass Spectral Data ◽  
Mass Spectral ◽  
The Neural Network ◽  
Lipophilicity Parameters

AbstractThe phenylcarbamic acid derivatives with N-phenylpiperazine moiety in the molecule have been prepared. The structure has been confirmed by elemental analysis, IR, 1H NMR, and mass spectral data. For the prepared set of the compounds the lipophilicity parameters have been determined. The experimentally obtained lipophilicity parameters have been correlated with theoretical entries obtained by different computer programs based on the neural network and fragmental methods.

Sign in / Sign up

Export Citation Format

Share Document