A Computationally Efficient Methodology for Generating Training Data for a Transient Neural Network of a Tip-Jet Reaction Drive System

2011 ◽  
Vol 133 (12) ◽  
Author(s):  
Brian K. Kestner ◽  
Jimmy C.M. Tai ◽  
Dimitri N. Mavris
Keyword(s):  
Neural Network ◽  
Steady State ◽  
Network Model ◽  
Neural Network Model ◽  
Operating Conditions ◽  
Drive System ◽  
Training Data ◽  
Computationally Efficient ◽  
Model Based Control ◽  
Training Methodology

This paper presents a computationally efficient methodology for generating training data for a transient neural network model of a tip-jet reaction drive system for potential use as an onboard model in a model based control application. This methodology significantly reduces the number of training points required to capture the transient performance of the system. The challenge in developing an onboard model for a tip-jet reaction drive system is that the model has to operate over the whole flight envelope, to account for the different dynamics present in the system, and to adjust to system degradation or potential faults. In addition, the onboard model must execute in less time than the update interval of the controller. To address these issues, a computationally efficient training methodology and neural network surrogate model have been developed that captures the transient performance of the tip-jet reaction system. As the number of inputs to a neural network becomes large, the computational time needed to generate the number of training points required to accurately represent the range of operating conditions of the system may become quite large also. A challenge for the tip-jet reaction drive system is to minimize the number of neural network training points, while maintaining the high accuracy. To address this issue, a novel training methodology is presented which first trains a steady-state neural network model and uses deviations from steady-state operating conditions to define the transient portion of the training data. The combined results from both the transient and the steady-state training data can then be used to create a single transient neural network of the system. The results in this paper demonstrate that a transient neural network using this new computationally efficient training methodology has the potential to be a feasible option for use as an onboard real-time model for model based control of a tip-jet reaction drive system.

Neural Network Bushing Model Development Using Simulation

2010 ◽  
Author(s):  
Jennifer L. Johrendt ◽  
Peter R. Frise
Keyword(s):  
Neural Network ◽  
Network Model ◽  
Neural Network Model ◽  
Model Development ◽  
Training Data ◽  
Computationally Efficient ◽  
Training Set ◽  
Physical Prototype ◽  
Rubber Bushing ◽  
Output Load

Neural networks are computationally efficient mathematical models that can be used to model quantitative and qualitative data. A neural network can be created through training with known input and output load-deflection data such that it learns to generalize the material characteristics without over-predicting the training data and losing its ability to anticipate behavior outside the training set. The challenge in creating a neural network model of a rubber bushing in a virtual model of a prototype assembly, for instance, is the lack of a physical prototype assembly. This paper describes a method by which data can be measured from a virtual prototype and used to define an appropriate data acquisition for the physical bushing. Training data can then be acquired using these guidelines and used for neural network model development. Subsequently, the enhanced model can then be used in the virtual simulation environment to increase the accuracy of the simulation results.

scholarly journals A Graph Neural Network for Predicting Energy and Stability of Known and Hypothetical Crystal Structures

2021 ◽  
Author(s):  
Shubham Pandey ◽  
Jiaxing Qu ◽  
Vladan Stevanovic ◽  
Peter St. John ◽  
Prashun Gorai
Keyword(s):  
Neural Network ◽  
Total Energy ◽  
Network Model ◽  
Neural Network Model ◽  
Density Functional ◽  
Failure Modes ◽  
Inorganic Materials ◽  
Training Data ◽  
The Neural Network ◽  
Unique Graph

The discovery of new inorganic materials in unexplored chemical spaces necessitates calculating total energy quickly and with sufficient accuracy. Machine learning models that provide such a capability for both ground-state (GS) and higher-energy structures would be instrumental in accelerating the screening for new materials over vast chemical spaces. Here, we develop a unique graph neural network model to accurately predict the total energy of both GS and higher-energy hypothetical structures. We use ~16,500 density functional theory calculated total energy from the NREL Materials Database and ~11,000 in-house generated hypothetical structures to train our model, thus making sure that the model is not biased towards either GS or higher-energy structures. We also demonstrate that our model satisfactorily ranks the structures in the correct order of their energies for a given composition. Furthermore, we present a thorough error analysis to explain several failure modes of the model, which highlights both prediction outliers and occasional inconsistencies in the training data. By peeling back layers of the neural network model, we are able to derive chemical trends by analyzing how the model represents learned structures and properties.

scholarly journals A Graph Neural Network for Predicting Energy and Stability of Known and Hypothetical Crystal Structures

2021 ◽  
Author(s):  
Shubham Pandey ◽  
Jiaxing Qu ◽  
Vladan Stevanovic ◽  
Peter St. John ◽  
Prashun Gorai
Keyword(s):  
Neural Network ◽  
Total Energy ◽  
Network Model ◽  
Neural Network Model ◽  
Density Functional ◽  
Failure Modes ◽  
Inorganic Materials ◽  
Training Data ◽  
The Neural Network ◽  
Unique Graph

The discovery of new inorganic materials in unexplored chemical spaces necessitates calculating total energy quickly and with sufficient accuracy. Machine learning models that provide such a capability for both ground-state (GS) and higher-energy structures would be instrumental in accelerating the screening for new materials over vast chemical spaces. Here, we develop a unique graph neural network model to accurately predict the total energy of both GS and higher-energy hypothetical structures. We use ~16,500 density functional theory calculated total energy from the NREL Materials Database and ~11,000 in-house generated hypothetical structures to train our model, thus making sure that the model is not biased towards either GS or higher-energy structures. We also demonstrate that our model satisfactorily ranks the structures in the correct order of their energies for a given composition. Furthermore, we present a thorough error analysis to explain several failure modes of the model, which highlights both prediction outliers and occasional inconsistencies in the training data. By peeling back layers of the neural network model, we are able to derive chemical trends by analyzing how the model represents learned structures and properties.

scholarly journals A Comparison of Regularization Techniques in Deep Neural Networks

Symmetry ◽  
2018 ◽  
Vol 10 (11) ◽  
pp. 648 ◽  
Author(s):  
Ismoilov Nusrat ◽  
Sung-Bong Jang
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Network Model ◽  
Neural Network Model ◽  
Data Augmentation ◽  
Training Data ◽  
Regularization Techniques ◽  
Performance Results ◽  
Normalization Scheme ◽  
Significant Attention

Artificial neural networks (ANN) have attracted significant attention from researchers because many complex problems can be solved by training them. If enough data are provided during the training process, ANNs are capable of achieving good performance results. However, if training data are not enough, the predefined neural network model suffers from overfitting and underfitting problems. To solve these problems, several regularization techniques have been devised and widely applied to applications and data analysis. However, it is difficult for developers to choose the most suitable scheme for a developing application because there is no information regarding the performance of each scheme. This paper describes comparative research on regularization techniques by evaluating the training and validation errors in a deep neural network model, using a weather dataset. For comparisons, each algorithm was implemented using a recent neural network library of TensorFlow. The experiment results showed that an autoencoder had the worst performance among schemes. When the prediction accuracy was compared, data augmentation and the batch normalization scheme showed better performance than the others.

Fracture Design Parameters of Middle Carbon Steel in Extra-Low Cycle Bend Torsion Loading

2014 ◽  
Vol 574 ◽  
pp. 342-346
Author(s):  
Hong Yan Duan ◽  
Huan Rong Zhang ◽  
Ming Zheng ◽  
Xiao Hong Wang
Keyword(s):  
Neural Network ◽  
Carbon Steel ◽  
Network Model ◽  
Neural Network Model ◽  
Network Architecture ◽  
Training Data ◽  
Design Parameters ◽  
Ann Model ◽  
Approximate Methods ◽  
The Neural Network

The fracture problems of medium carbon steel under extra-low cycle bend torsion fatigue loading were studied using artificial neural networks (ANN) in this paper. The ANN model exhibited excellent comparison with the experimental results. It was concluded that predicted fracture design parameters by the trained neural network model seem more reasonable compared to approximate methods. It is possible to claim that, ANN is fairly promising prediction technique if properly used. Training ANN model was introduced at first. And then the Training data for the development of the neural network model was obtained from the experiments. The input parameters, the presetting deflection and notch open angle, and the output, the cycle times of fracture were used during the network training. The neural network architecture is designed. The ANN model was developed using back propagation architecture with three layers jump connections, where every layer was connected or linked to every previous layer. The number of hidden neurons was determined according to special formula. The performance of system is summarized at last. In order to facilitate the comparisons of predicted values, the error evaluation and mean relative error are obtained. The result show that the training model has good performance, and the experimental data and predicted data from ANN are in good coherence.

Application of ANN Back-Propagation for Fracture Design Parameters of Middle Carbon Steel in Extra-Low Cycle Bend Torsion Loading

2013 ◽  
Vol 345 ◽  
pp. 272-276 ◽  
Author(s):  
Hong Yan Duan ◽  
You Tang Li ◽  
Zhi Jia Sun ◽  
Yang Yang Zhang
Keyword(s):  
Neural Network ◽  
Carbon Steel ◽  
Network Model ◽  
Neural Network Model ◽  
Network Architecture ◽  
Back Propagation ◽  
Training Data ◽  
Design Parameters ◽  
Ann Model ◽  
The Neural Network

The fracture problems of medium carbon steel (MCS) under extra-low cycle bend torsion loading were studied using artificial neural networks (ANN) in this paper. The training data were used in the formation of training set of ANN. The ANN model exhibited excellent comparison with the experimental results. It was concluded that predicted fracture design parameters by the trained neural network model seem more reasonable compared to approximate methods. It is possible to claim that, ANN is fairly promising prediction technique if properly used. Training ANN model was introduced at first. And then the Training data for the development of the neural network model was obtained from the experiments. The input parameters, notch depth and tip radius of the notch, and the output, the cycle times of fracture were used during the network training. The neural network architecture is designed. The ANN model was developed using back propagation architecture with three layers jump connections, where every layer was connected or linked to every previous layer. The number of hidden neurons was determined according to special formula. The performance of system is summarized at last. In order to facilitate the comparisons of predicted values, the error evaluation and mean relative error are obtained. The result show that the training model has good performance, and the experimental data and predicted data from ANN are in good coherence.

scholarly journals Evaluation of Neural Network Model for Estimating Pile Load Capacity

2021 ◽  
Vol 21 (5) ◽  
pp. 221-228
Author(s):  
Byungsik Lee
Keyword(s):  
Neural Network ◽  
Network Model ◽  
Neural Network Model ◽  
Load Capacity ◽  
Absolute Error ◽  
Descent Method ◽  
Training Data ◽  
Gradient Descent Method ◽  
Neural Network Models ◽  
Data Set

Neural network models based on deep learning algorithms are increasingly used for estimating pile load capacities as supplements of bearing capacity equations and field load tests. A series of hyperparameter tuning is required to improve the performance and reliability of developing a neural network model. In this study, the number of hidden layers and neurons, the activation functions, the optimizing algorithms of the gradient descent method, and the learning rates were tuned. The grid search method was applied for the tuning, which is a hyperpameter optimizer supplied by the developing platform. The cross-validation method was applied to enhance reliability for model validation. An appropriate number of epochs was determined using the early stopping method to prevent the overfitting of the model to the training data. The performance of the tuned optimum model evaluated for the test data set revealed that the model could estimate pile load capacities approximately with an average absolute error of 3,000 kN and a coefficient of determinant of 0.5.

Sign in / Sign up

Export Citation Format

Share Document