MODELING AND CALIBRATION OF UNCERTAINTY IN MATERIAL PROPERTIES OF ADDITIVELY MANUFACTURED COMPOSITES

2021 ◽  
Author(s):  
EMIL PITZ ◽  
SEAN ROONEY ◽  
KISHORE POCHIRAJU
Keyword(s):  
Neural Networks ◽  
Structural Response ◽  
Correlation Coefficients ◽  
Optimization Methods ◽  
Strength Distribution ◽  
Rotation Parameter ◽  
Image Correlation ◽  
Model Parameters ◽  
Strain Fields ◽  
Correlation Lengths

Simulations quantifying the uncertainty in structural response and damage evolution require accurate representation of the randomness of the underlying material stiffness and strength behaviors. In this paper, the mean and variance descriptions of variability of strength and stiffness of additively manufactured composite specimens are augmented with random field correlation descriptors that represent the process dependence on the property heterogeneity through microstructure variations. Two correlation lengths and a rotation parameter are introduced into randomized stiffness and strength distribution fields to capture the local heterogeneities in the microstructure of Additively Manufactured (AM) composites. We formulated a simulation and Artificial Intelligence (AI)-based technique to calibrate the correlation length and rotation parameter measures from relatively few samples of experimentally obtained strain field observations using Digital Image Correlation (DIC). The neural networks used for calibrating the correlation lengths of Karhunen-Loève Expansion (KL expansion) from the DIC images are trained using simulated stiffness and strength fields that have known correlation coefficients. A virtual DIC filter is used to add the noise and artifacts from typical DIC analysis to the simulated strain fields. A Deep Neural Network (DNN), whose architecture is optimized using Efficient Neural Architecture Search (ENAS), is trained on 150,000 simulated DIC images. The trained DNN is then used for calibration of KL expansion correlation lengths for additively manufactured composite specimens. The AM composites are loaded in tension and DIC images of the strain fields are generated and presented to the DNNs, which produce the correlation coefficients for the random fields as outputs. Compared to classical optimization methods to calibrate model parameters iteratively, neural networks, once trained, efficiently and quickly predict parameters without the need for a robust simulator and optimization methods.

scholarly journals Application of Artificial Neural Networks to Streamline the Process of Adaptive Cruise Control

2021 ◽  
Vol 13 (8) ◽  
pp. 4572
Author(s):  
Jiří David ◽  
Pavel Brom ◽  
František Starý ◽  
Josef Bradáč ◽  
Vojtěch Dynybyl
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Adaptive Cruise Control ◽  
Control Unit ◽  
Driving Safety ◽  
Model Parameters ◽  
Cruise Control ◽  
Artificial Neural ◽  
Dynamic Obstacle ◽  
Braking Process

This article deals with the use of neural networks for estimation of deceleration model parameters for the adaptive cruise control unit. The article describes the basic functionality of adaptive cruise control and creates a mathematical model of braking, which is one of the basic functions of adaptive cruise control. Furthermore, an analysis of the influences acting in the braking process is performed, the most significant of which are used in the design of deceleration prediction for the adaptive cruise control unit using neural networks. Such a connection using artificial neural networks using modern sensors can be another step towards full vehicle autonomy. The advantage of this approach is the original use of neural networks, which refines the determination of the deceleration value of the vehicle in front of a static or dynamic obstacle, while including a number of influences that affect the braking process and thus increase driving safety.

scholarly journals Trigonometric Inference Providing Learning in Deep Neural Networks

2021 ◽  
Vol 11 (15) ◽  
pp. 6704
Author(s):  
Jingyong Cai ◽  
Masashi Takemoto ◽  
Yuming Qiu ◽  
Hironori Nakajo
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Deep Neural Networks ◽  
Activation Function ◽  
Trigonometric Approximation ◽  
Model Parameters ◽  
Training Algorithms ◽  
Activation Functions ◽  
Classical Training ◽  
Sum Formula

Despite being heavily used in the training of deep neural networks (DNNs), multipliers are resource-intensive and insufficient in many different scenarios. Previous discoveries have revealed the superiority when activation functions, such as the sigmoid, are calculated by shift-and-add operations, although they fail to remove multiplications in training altogether. In this paper, we propose an innovative approach that can convert all multiplications in the forward and backward inferences of DNNs into shift-and-add operations. Because the model parameters and backpropagated errors of a large DNN model are typically clustered around zero, these values can be approximated by their sine values. Multiplications between the weights and error signals are transferred to multiplications of their sine values, which are replaceable with simpler operations with the help of the product to sum formula. In addition, a rectified sine activation function is utilized for further converting layer inputs into sine values. In this way, the original multiplication-intensive operations can be computed through simple add-and-shift operations. This trigonometric approximation method provides an efficient training and inference alternative for devices with insufficient hardware multipliers. Experimental results demonstrate that this method is able to obtain a performance close to that of classical training algorithms. The approach we propose sheds new light on future hardware customization research for machine learning.

scholarly journals Explaining Neural Networks Using Attentive Knowledge Distillation

Sensors ◽  
2021 ◽  
Vol 21 (4) ◽  
pp. 1280
Author(s):  
Hyeonseok Lee ◽  
Sungchan Kim
Keyword(s):  
Neural Networks ◽  
Model Prediction ◽  
Saliency Map ◽  
Model Parameters ◽  
Learning Capability ◽  
Fine Grained ◽  
Network Layers ◽  
Saliency Maps ◽  
Novel Approach ◽  
Knowledge Distillation

Explaining the prediction of deep neural networks makes the networks more understandable and trusted, leading to their use in various mission critical tasks. Recent progress in the learning capability of networks has primarily been due to the enormous number of model parameters, so that it is usually hard to interpret their operations, as opposed to classical white-box models. For this purpose, generating saliency maps is a popular approach to identify the important input features used for the model prediction. Existing explanation methods typically only use the output of the last convolution layer of the model to generate a saliency map, lacking the information included in intermediate layers. Thus, the corresponding explanations are coarse and result in limited accuracy. Although the accuracy can be improved by iteratively developing a saliency map, this is too time-consuming and is thus impractical. To address these problems, we proposed a novel approach to explain the model prediction by developing an attentive surrogate network using the knowledge distillation. The surrogate network aims to generate a fine-grained saliency map corresponding to the model prediction using meaningful regional information presented over all network layers. Experiments demonstrated that the saliency maps are the result of spatially attentive features learned from the distillation. Thus, they are useful for fine-grained classification tasks. Moreover, the proposed method runs at the rate of 24.3 frames per second, which is much faster than the existing methods by orders of magnitude.

scholarly journals Influence of Selected Model Parameters on the Electromagnetic Levitation Melting Efficiency

2021 ◽  
Vol 11 (9) ◽  
pp. 3827
Author(s):  
Blazej Nycz ◽  
Lukasz Malinski ◽  
Roman Przylucki
Keyword(s):  
Electromagnetic Levitation ◽  
Optimization Methods ◽  
Calculation Model ◽  
Model Parameters ◽  
Starting Point ◽  
Low Efficiency ◽  
The Relationship ◽  
Reactive Metals ◽  
Electromagnetic Levitation Melting ◽  
Metal Melting

The article presents the results of multivariate calculations for the levitation metal melting system. The research had two main goals. The first goal of the multivariate calculations was to find the relationship between the basic electrical and geometric parameters of the selected calculation model and the maximum electromagnetic buoyancy force and the maximum power dissipated in the charge. The second goal was to find quasi-optimal conditions for levitation. The choice of the model with the highest melting efficiency is very important because electromagnetic levitation is essentially a low-efficiency process. Despite the low efficiency of this method, it is worth dealing with it because is one of the few methods that allow melting and obtaining alloys of refractory reactive metals. The research was limited to the analysis of the electromagnetic field modeled three-dimensionally. From among of 245 variants considered in the article, the most promising one was selected characterized by the highest efficiency. This variant will be a starting point for further work with the use of optimization methods.

Effect of buckling-restrained brace model parameters on seismic structural response

2014 ◽  
Vol 98 ◽  
pp. 100-113 ◽  
Author(s):  
Quan Gu ◽  
Alessandro Zona ◽  
Yi Peng ◽  
Andrea Dall'Asta
Keyword(s):  
Structural Response ◽  
Model Parameters ◽  
Buckling Restrained Brace

Simulating and analyzing artificial nonstationary earthquake ground motions

1982 ◽  
Vol 72 (2) ◽  
pp. 615-636
Author(s):  
Robert F. Nau ◽  
Robert M. Oliver ◽  
Karl S. Pister
Keyword(s):  
Difference Equations ◽  
Kalman Filters ◽  
Ground Motions ◽  
Structural Response ◽  
Model Parameters ◽  
Time Varying ◽  
Nonparametric Method ◽  
Linear Difference Equations ◽  
Earthquake Ground Motions ◽  
Earthquake Accelerograms

Abstract This paper describes models used to simulate earthquake accelerograms and analyses of these artificial accelerogram records for use in structural response studies. The artificial accelerogram records are generated by a class of linear linear difference equations which have been previously identified as suitable for describing ground motions. The major contributions of the paper are the use of Kalman filters for estimating time-varying model parameters, and the development of an effective nonparametric method for estimating the variance envelopes of the accelerogram records.

Optimization methods for deep neural networks

2021 ◽  
Author(s):  
Rajendra P. ◽  
Hanumantha Ravi. P. V. N. ◽  
Gunavardhana Naidu T.
Keyword(s):  
Neural Networks ◽  
Deep Neural Networks ◽  
Optimization Methods
Sign in / Sign up

Export Citation Format

Share Document