Forecasting of the Fatigue Life of Metal Weld Joints Based on Combined Genetic Neural Network

2010 ◽  
Vol 439-440 ◽  
pp. 195-201 ◽  
Author(s):  
Dan Ma ◽  
Zhan Qing Chen ◽  
Xian Lei Shan
Keyword(s):  
Neural Network ◽  
Fatigue Life ◽  
Forecast Accuracy ◽  
Linear Mapping ◽  
Learning Ability ◽  
Weld Joints ◽  
Non Linear ◽  
Genetic Neural Network ◽  
Artificial Neural Network Ann ◽  
Metal Weld

For metal weld joints, due to the complex non-linear relationship among the factors which influence the fatigue performance, so it is hard to establish an accurate theoretical model to forecast its fatigue life. Based on the self-learning ability and approximation of non-linear mapping capability of the artificial neural network (ANN) and the powerful ability of global optimization of the genetic algorithm (GA), the paper through optimizing the ANN by GA, establishes combined genetic neural network (GA–ANN). The method establishes the mapping relationship between the fatigue life of metal weld joints and a variety of influencing factors, having greatly increased the computational efficiency for the fatigue life of metal weld joints, also had a higher forecast accuracy. The superiority of this method had been tested by the forecast of the fatigue life of weld joints in different process parameters, the new method to forecast the fatigue life of metal weld joints is proposed.

The Identification of the Natural Frequency of Rolling Bearing Rotor System Based on Combined Genetic Neural Network

2010 ◽  
Vol 29-32 ◽  
pp. 436-441
Author(s):  
Tian Ran Ma ◽  
Xian Lei Shan ◽  
Hao Nan Liang ◽  
Zhong Chen Xiang ◽  
Rui Xue Liu ◽  
...  
Keyword(s):  
Neural Network ◽  
Natural Frequency ◽  
Rolling Bearing ◽  
Linear Mapping ◽  
Rotor System ◽  
Learning Ability ◽  
Non Linear ◽  
Genetic Neural Network ◽  
Predicted Values ◽  
Artificial Neural Network Ann

During identifying the natural frequency of the rolling bearing rotor system, due to the complex non-linear relationship between the factors which influence the natural frequency, it is hard to establish a complete and accurate theoretical model. Based on the self-learning ability and approximation of non-linear mapping capability of the artificial neural network (ANN) and the powerful ability of global optimization of the genetic algorithm (GA), the paper establishes combined genetic neural network (GA–ANN) through optimizing the ANN by GA. This method establishes the mapping between a rolling bearing rotor system natural frequency and the various parameters, which reduces the calculation of the workload greatly for the study of the similar rotor structure’s natural frequency. Through using the network model to predict the natural frequency of rolling bearing rotor system under different parameters, we finally find that the predicted values are in good agreement with the experimental data, which indicates that the method is powerful in identification.

scholarly journals Application of Artificial Neural Network in Distillation System: A Critical Review of Recent Progress

2021 ◽  
pp. 8-16
Author(s):  
Chunli Li ◽  
Chunyu Wang
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Dynamic Performance ◽  
Linear Mapping ◽  
Research Progress ◽  
Non Linear ◽  
Input Parameters ◽  
Multiple Variables ◽  
Artificial Neural ◽  
Artificial Neural Network Ann

Distillation is a unit operation with multiple input parameters and multiple output parameters. It is characterized by multiple variables, coupling between input parameters, and non-linear relationship with output parameters. Therefore, it is very difficult to use traditional methods to control and optimize the distillation column. Artificial Neural Network (ANN) uses the interconnection between a large number of neurons to establish the functional relationship between input and output, thereby achieving the approximation of any non-linear mapping. ANN is used for the control and optimization of distillation tower, with short response time, good dynamic performance, strong robustness, and strong ability to adapt to changes in the control environment. This article will mainly introduce the research progress of ANN and its application in the modeling, control and optimization of distillation towers.

Predicting Fatigue Life of Pre-Corroded LC4 Aluminum Alloy by Artificial Neural Network

2010 ◽  
Vol 118-120 ◽  
pp. 221-225 ◽  
Author(s):  
Cheng Long Xu ◽  
Sheng Li Lv ◽  
Zhen Guo Wang ◽  
Wei Zhang
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Aluminum Alloy ◽  
Fatigue Life ◽  
Network Architecture ◽  
Fatigue Tests ◽  
Data Sets ◽  
Absolute Relative Error ◽  
Artificial Neural ◽  
Artificial Neural Network Ann

The purpose of this work was to predict the fatigue life of pre-corroded LC4 aluminum alloy by applying artificial neural network (ANN). Specimens were exposed to the same corrosive environment for 24h, 48h, and 72h. Fatigue tests were conducted under different stress levels. The existing experimental data sets were used for training and testing the construction of proposed network. A suitable network architecture (2-15-1) was proposed with good performance in this study. For evaluating the method efficiency, the experimental results have been compared to values predicted by ANN. The maximum absolute relative error for predicted values does not exceed 5%. Therefore it can be concluded that using neural networks to predict the fatigue life of LC4 is feasible and reliable.

scholarly journals Comparing the Prediction Capabilities of Artificial Neural Network (ANN) and Nonlinear Regression Models in Pet-Poy Yarn Characteristics and Optimization of Yarn Production Conditions

2017 ◽  
Vol 12 (3) ◽  
pp. 155892501701200 ◽  
Author(s):  
Kenan Yıldirimm ◽  
Hamdi Ogut ◽  
Yusuf Ulcay
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Linear Regression ◽  
Nonlinear Regression ◽  
Fine Tuning ◽  
Draw Force ◽  
Non Linear ◽  
Artificial Neural ◽  
Artificial Neural Network Ann ◽  
Production Conditions

In the manufacture of yarn, predicting the effect of changing production conditions is vital to reducing defects in the end product. This study compares, for the first time, non-linear regression and artificial neural network (ANN) models in predicting 10 yarn properties shaped by the influence of winding speed, quenching air temperature and/or quenching air speed during production. A multilayer perceptron ANN model was created by training 81 patterns using the Broyden-Fletcher-Goldfarb-Shanno (BFGS) algorithm. The hyperbolic tangent, or TanH, activation function and logistic activation functions were used for the hidden and output layers respectively. Results showed that the ANN approach exhibited a greater prediction capability over the nonlinear regression method. ANN simultaneously predicted all of the 10 final properties of a yarn; tensile strength, tensile strain, draw force, crystallinity ratio, dye uptake based on the colour strengths (K/S), brightness, boiling shrinkage and yarn evenness, more accurately than the non-linear regression model (R2=0.97 vs. R2=0.92). These results lend support to the idea that the ANN analysis combined with optimization can be used successfully to prevent production defects by fine tuning the production environment.

An Improved Artificial Neural Network for Recognition of Beam Pump Dynamometer Card

2012 ◽  
Vol 524-527 ◽  
pp. 1331-1334
Author(s):  
Jun Ni ◽  
Zhan Li Ren ◽  
Guo Qing Han
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Back Propagation ◽  
Linear Mapping ◽  
Back Propagation Algorithm ◽  
Propagation Algorithm ◽  
Beam Pump ◽  
Artificial Neural ◽  
Artificial Neural Network Ann ◽  
Dynamometer Card

Beam pump dynamometer card plays an important role in identifying the production state of oil wells. With an ability to reflect any non-linear mapping relationship, the artificial neural network (ANN) can be used in pattern recognition. This paper illuminates ANN realization in identifying fault kinds of dynamometer cards, including a back-propagation algorithm, characteristics of the Dynamometer card and some examples. It is concluded that the buildup of a neural network and the abstract of dynamometer cards are important to successful application.

A Non-Linear Auto-Regressive With Exogenous Inputs (NARX) Artificial Neural Network (ANN) Model for Building Thermal Load Prediction

2019 ◽  
Author(s):  
Byeongho Yu ◽  
Dongsu Kim ◽  
Heejin Cho ◽  
Pedro Mago
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Artificial Neural Network ◽  
Nonlinear System ◽  
Prediction Model ◽  
Thermal Load ◽  
Ann Model ◽  
Load Prediction ◽  
Non Linear ◽  
Artificial Neural Network Ann

Abstract Thermal load prediction is a key part of energy system management and control in buildings, and its accuracy plays a critical role to improve and maintain building energy performance and efficiency. To address this issue, various types of prediction model have been considered and studied, such as physics-based, statistical, and machine learning models. Physical models can be accurate but require extended lead time for model development. Statistical models are relatively simple to develop and require less computation time than other models, but they may not provide accurate results for complex energy systems with an intricate nonlinear dynamic behavior. This study proposes an Artificial Neural Network (ANN) model, one of the prevalent machine learning methods to predict building thermal load, combining with the concept of Non-linear Auto-Regression with Exogenous inputs (NARX). NARX-ANN prediction model is distinguished from typical ANN models due to the fact that the NARX concept can address nonlinear system behaviors effectively based on recurrent architectures and time indexing features. To examine the suitability and validity of NARX-ANN model for building thermal load prediction, a case study is carried out using field data of an academic campus building at Mississippi State University. Results show that the proposed NARX-ANN model can provide an accurate prediction performance and effectively address nonlinear system behaviors in the prediction.

scholarly journals Attention-based Convolutional Neural Network for MRI Gibbs-ringing Artifact Suppression

2020 ◽  
pp. paper34-1-paper34-12
Author(s):  
Maksim Penkin ◽  
Andrey Krylov ◽  
Alexander Khvostikov
Keyword(s):  
Neural Network ◽  
Fourier Transform ◽  
Convolutional Neural Network ◽  
High Frequency ◽  
Gibbs Phenomenon ◽  
Linear Mapping ◽  
Full Spectrum ◽  
Non Linear ◽  
Ringing Artifact ◽  
Artifact Suppression

Gibbs-ringing artifact is a common artifact in MRI image processing. As MRI raw data is taken in a frequency domain, 2D in- verse discrete Fourier transform is applied to visualize data. Inability to take inverse Fourier transform of full spectrum (full k-space) leads to the insufficient sampling of the high frequency data and results in a well-known Gibbs phenomenon. It is worth to notice that truncation of high frequency information generates a significant blur, thus some techniques from other image restoration problems (for example, image deblur task) can be successfully used. We propose attention-based convolutional neural network for Gibbs-ringing reduction which is the extension of recently proposed GAS-CNN (Gibbs-ringing Artifact Suppression Convolutional Neural Network). Proposed method includes simplified non-linear mapping, amended by LRNN (Layer Recurrent Neural Network) refinement block with feature attention module, controlling the correlation between input and output tensors of the refinement unit. The research shows that the proposed post-processing refinement construction considerably simplifies the non-linear mapping.

scholarly journals New Regression models for Estimation daily temperature of Karachi and its Neural Network analysis

2021 ◽  
Keyword(s):  
Neural Network ◽  
Temperature Distribution ◽  
Regression Models ◽  
Daily Temperature ◽  
Good Prediction ◽  
Distribution Models ◽  
Average Daily Temperature ◽  
Non Linear ◽  
Artificial Neural Network Ann

<p>This study presents the determination of the average daily temperature distribution for Karachi city. Artificial Neural Network (ANN) has been used to predict the average daily temperature of 2018, 2019, and 2020. Two regression models (linear and non-linear) were also developed. These models are based on relative humidity and dew points. Karachi's six-year environmental datasets were used for the case study location and to establish temperature distribution models. In ANN three years, temperature data (2015-2017) was used to train and validate the NN model. The same data was used to find the regression coefficients of each model. Both models and NN are then used to estimate the average daily temperature of years 2018-2020. The statistical errors are also calculated for comparison and to evaluate the performance of both models; an excellent agreement was found between recorded and ANN estimates. Both regression models predict average daily temperature with reasonable uncertainties. However, the non-linear regression model predictions are better. The results show that the models provide a good prediction of temperature distribution.</p>

scholarly journals Comparison of different artificial neural network (ANN) training algorithms to predict the atmospheric temperature in Tabuk, Saudi Arabia

MAUSAM ◽  
2021 ◽  
Vol 71 (2) ◽  
pp. 233-244
Author(s):  
PERERA ANUSHKA ◽  
AZAMATHULLA HAZI MD. ◽  
RATHNAYAKE UPAKA
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Saudi Arabia ◽  
Conjugate Gradient ◽  
Atmospheric Temperature ◽  
Training Algorithms ◽  
Non Linear ◽  
Ann Models ◽  
Artificial Neural ◽  
Artificial Neural Network Ann

Use of Artificial neural network (ANN) models to predict weather parameters has become important over the years. ANN models give more accurate results in weather and climate forecasting among many other methods. However, different models require different data and these data have to be handled accordingly, but carefully. In addition, most of these data are from non-linear processes and therefore, the prediction models are usually complex. Nevertheless, neural networks perform well for non-linear data and produce well acceptable results. Therefore, this study was carried out to compare different ANN models to predict the minimum atmospheric temperature and maximum atmospheric temperature in Tabuk, Saudi Arabia. ANN models were trained using eight different training algorithms. BFGS Quasi Newton (BFG), Conjugate gradient with Powell-Beale restarts (CGB), Levenberg-Marquadt (LM), Scaled Conjugate Gradient (SCG), Fletcher-Reeves update Conjugate Gradient algorithm (CGF), One Step Secant (OSS), Polak-Ribiere update Conjugate Gradient (CGP) and Resilient Back-Propagation (RP) training algorithms were fed to the climatic data in Tabuk, Saudi Arabia. The performance of the different training algorithms to train ANN models were evaluated using Mean Squared Error (MSE) and correlation coefficient (R). The evaluation shows that training algorithms BFG, LM and SCG have outperformed others while OSS training algorithm has the lowest performance in comparison to other algorithms used.

Sign in / Sign up

Export Citation Format

Share Document