Combined Machine-Learning and Finite-Element Approach for Multiscale 3D Stress Modeling

2021 ◽  
pp. 1-20
Author(s):  
Xavier Garcia-Teijeiro ◽  
Adrian Rodriguez-Herrera
Keyword(s):  
Neural Network ◽  
Mechanical Properties ◽  
Finite Element ◽  
High Resolution ◽  
Stress Field ◽  
Large Scale ◽  
Spatial Scales ◽  
Rock Properties ◽  
Fine Scale ◽  
The Neural Network

Summary In this paper, we propose a methodology that combines finite-element modeling with neural networks in the numerical modeling of systems with behavior that involves a wide span of spatial scales. The method starts by constructing a high-resolution model of the subsurface, including its elastic mechanical properties and pore pressures. A second model is also constructed by scaling up mechanical properties and pressures into a coarse spatial resolution. Inexpensive finite-element solutions for stress are then obtained in the coarse model. These stress solutions aim at capturing regional trends and large-scale stress correlations. Finite-element solutions for stress are also obtained in high resolution, but only in a small subvolume of the 3D model. These stress solutions aim at estimating fine-grained details of the stress field introduced by the heterogeneity of rock properties at the fine scale. A neural network is then trained to infer the transformation rules that map stress solutions between different scales. The inputs to the training are pressure and mechanical properties in high and low resolutions. The output is the fine-scale stress computed in the subvolume of the high-resolutionmodel. Once trained, the neural network can be used to approximate a high-resolution stress field in the entire 3D volume using the coarse-scale solution and only providing high-resolution material properties and pressures. The results obtained indicate that when the coarse finite-element solutions are combined with the neural-network estimates, the results are within a 2 to 4% error of the results that would be computed with high-resolutionfinite-element models, but at a fraction of the cost in time and computational resources. This paper discusses the benefits and drawbacks of the method and illustrates its applicability by means of a worked example.

Back-Analysis on Initial Ground Stress of Underground Workshop Region of Shenzhen Pumped Storage Power Station

2012 ◽  
Vol 170-173 ◽  
pp. 1634-1637
Author(s):  
An Jing Zhang ◽  
Zheng Xia Gao
Keyword(s):  
Neural Network ◽  
Finite Element ◽  
Stress Field ◽  
Back Analysis ◽  
Power Station ◽  
The Neural Network ◽  
Measured Stress ◽  
Ground Stress ◽  
Set Up ◽  
Pumped Storage

Abstract. This article based on the underground workshop region of the Shenzhen pumped storage power station, carrying on back-analysis for the initial geostress field of the region of station with method of this article, and then we can obtained the actual initial ground stress.This article based on the measured ground stress data, a 3D non-linear finite element back analysis numerical model for ground stress is set up and the landforms is simulated. This thesis has used ANSYS to do finite element calculation for rocks and soils, the corresponding sample of neural network have been gained. By setting the parameters, the neural network is optimized, then the network is trained with the optimized result. Finally, the initial ground stress field is back-analyzed with in-situ measured stress values. The result is compared with measured value, which meets the requirement for accuracy, showing the reasonabilily of the rock ground stress field obtained.

scholarly journals Repeated surveying over 6 years reveals that fine-scale habitat variables are key to tropical mountain ant assemblage composition and functional diversity

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Mulalo M. Muluvhahothe ◽  
Grant S. Joseph ◽  
Colleen L. Seymour ◽  
Thinandavha C. Munyai ◽  
Stefan H. Foord
Keyword(s):  
Climate Change ◽  
Species Composition ◽  
High Altitude ◽  
Functional Diversity ◽  
Large Scale ◽  
Climate Models ◽  
Spatial Scales ◽  
Abiotic Factors ◽  
Composition Analysis ◽  
Fine Scale

AbstractHigh-altitude-adapted ectotherms can escape competition from dominant species by tolerating low temperatures at cooler elevations, but climate change is eroding such advantages. Studies evaluating broad-scale impacts of global change for high-altitude organisms often overlook the mitigating role of biotic factors. Yet, at fine spatial-scales, vegetation-associated microclimates provide refuges from climatic extremes. Using one of the largest standardised data sets collected to date, we tested how ant species composition and functional diversity (i.e., the range and value of species traits found within assemblages) respond to large-scale abiotic factors (altitude, aspect), and fine-scale factors (vegetation, soil structure) along an elevational gradient in tropical Africa. Altitude emerged as the principal factor explaining species composition. Analysis of nestedness and turnover components of beta diversity indicated that ant assemblages are specific to each elevation, so species are not filtered out but replaced with new species as elevation increases. Similarity of assemblages over time (assessed using beta decay) did not change significantly at low and mid elevations but declined at the highest elevations. Assemblages also differed between northern and southern mountain aspects, although at highest elevations, composition was restricted to a set of species found on both aspects. Functional diversity was not explained by large scale variables like elevation, but by factors associated with elevation that operate at fine scales (i.e., temperature and habitat structure). Our findings highlight the significance of fine-scale variables in predicting organisms’ responses to changing temperature, offering management possibilities that might dilute climate change impacts, and caution when predicting assemblage responses using climate models, alone.

A Model on the Correlation between Composition and Mechanical Properties of Mg-Al-Zn Alloys by Using Artificial Neural Network

2005 ◽  
Vol 488-489 ◽  
pp. 793-796 ◽  
Author(s):  
Hai Ding Liu ◽  
Ai Tao Tang ◽  
Fu Sheng Pan ◽  
Ru Lin Zuo ◽  
Ling Yun Wang
Keyword(s):  
Neural Network ◽  
Mechanical Properties ◽  
Artificial Neural Network ◽  
Magnesium Alloys ◽  
Tensile Yield Strength ◽  
Data Set ◽  
The Neural Network ◽  
Artificial Neural ◽  
Prediction Of Mechanical Properties ◽  
Artificial Neural Network Ann

A model was developed for the analysis and prediction of correlation between composition and mechanical properties of Mg-Al-Zn (AZ) magnesium alloys by applying artificial neural network (ANN). The input parameters of the neural network (NN) are alloy composition. The outputs of the NN model are important mechanical properties, including ultimate tensile strength, tensile yield strength and elongation. The model is based on multilayer feedforward neural network. The NN was trained with comprehensive data set collected from domestic and foreign literature. A very good performance of the neural network was achieved. The model can be used for the simulation and prediction of mechanical properties of AZ system magnesium alloys as functions of composition.

Linear Static Response of Suspension Arm Based on Artificial Neural Network Technique

2011 ◽  
Vol 213 ◽  
pp. 419-426
Author(s):  
M.M. Rahman ◽  
Hemin M. Mohyaldeen ◽  
M.M. Noor ◽  
K. Kadirgama ◽  
Rosli A. Bakar
Keyword(s):  
Neural Network ◽  
Finite Element Analysis ◽  
Finite Element ◽  
Network Model ◽  
Neural Network Model ◽  
Mesh Size ◽  
Maximum Displacement ◽  
Element Analysis ◽  
The Neural Network ◽  
The Finite Element Analysis

Modeling and simulation are indispensable when dealing with complex engineering systems. This study deals with intelligent techniques modeling for linear response of suspension arm. The finite element analysis and Radial Basis Function Neural Network (RBFNN) technique is used to predict the response of suspension arm. The linear static analysis was performed utilizing the finite element analysis code. The neural network model has 3 inputs representing the load, mesh size and material while 4 output representing the maximum displacement, maximum Principal stress, von Mises and Tresca. Finally, regression analysis between finite element results and values predicted by the neural network model was made. It can be seen that the RBFNN proposed approach was found to be highly effective with least error in identification of stress-displacement of suspension arm. Simulated results show that RBF can be very successively used for reduction of the effort and time required to predict the stress-displacement response of suspension arm as FE methods usually deal with only a single problem for each run.

scholarly journals An Industrial Micro-Defect Diagnosis System via Intelligent Segmentation Region

Sensors ◽  
2019 ◽  
Vol 19 (11) ◽  
pp. 2636 ◽  
Author(s):  
Xia Fang ◽  
Wang Jie ◽  
Tao Feng
Keyword(s):  
Neural Network ◽  
Defect Detection ◽  
Large Scale ◽  
Detection System ◽  
Scale Production ◽  
System Matrix ◽  
Rotating Platform ◽  
Limited Region ◽  
The Neural Network ◽  
Large Scale Production

In the field of machine vision defect detection for a micro workpiece, it is very important to make the neural network realize the integrity of the mask in analyte segmentation regions. In the process of the recognition of small workpieces, fatal defects are always contained in borderline areas that are difficult to demarcate. The non-maximum suppression (NMS) of intersection over union (IOU) will lose crucial texture information especially in the clutter and occlusion detection areas. In this paper, simple linear iterative clustering (SLIC) is used to augment the mask as well as calibrate the score of the mask. We propose an SLIC head of object instance segmentation in proposal regions (Mask R-CNN) containing a network block to learn the quality of the predict masks. It is found that parallel K-means in the limited region mechanism in the SLIC head improved the confidence of the mask score, in the context of our workpiece. A continuous fine-tune mechanism was utilized to continuously improve the model robustness in a large-scale production line. We established a detection system, which included an optical fiber locator, telecentric lens system, matrix stereoscopic light, a rotating platform, and a neural network with an SLIC head. The accuracy of defect detection is effectively improved for micro workpieces with clutter and borderline areas.

scholarly journals Large-scale atmospheric forcing and topographic modification of precipitation rates over High Asia – a neural-network-based approach

2015 ◽  
Vol 6 (1) ◽  
pp. 61-81 ◽  
Author(s):  
L. Gerlitz ◽  
O. Conrad ◽  
J. Böhner
Keyword(s):  
Neural Network ◽  
High Resolution ◽  
Spatial Resolution ◽  
Large Scale ◽  
Local Scale ◽  
Predictor Variables ◽  
High Mountain ◽  
Target Area ◽  
Monthly Precipitation ◽  
Highly Nonlinear

Abstract. The heterogeneity of precipitation rates in high-mountain regions is not sufficiently captured by state-of-the-art climate reanalysis products due to their limited spatial resolution. Thus there exists a large gap between the available data sets and the demands of climate impact studies. The presented approach aims to generate spatially high resolution precipitation fields for a target area in central Asia, covering the Tibetan Plateau and the adjacent mountain ranges and lowlands. Based on the assumption that observed local-scale precipitation amounts are triggered by varying large-scale atmospheric situations and modified by local-scale topographic characteristics, the statistical downscaling approach estimates local-scale precipitation rates as a function of large-scale atmospheric conditions, derived from the ERA-Interim reanalysis and high-resolution terrain parameters. Since the relationships of the predictor variables with local-scale observations are rather unknown and highly nonlinear, an artificial neural network (ANN) was utilized for the development of adequate transfer functions. Different ANN architectures were evaluated with regard to their predictive performance. The final downscaling model was used for the cellwise estimation of monthly precipitation sums, the number of rainy days and the maximum daily precipitation amount with a spatial resolution of 1 km2. The model was found to sufficiently capture the temporal and spatial variations in precipitation rates in the highly structured target area and allows for a detailed analysis of the precipitation distribution. A concluding sensitivity analysis of the ANN model reveals the effect of the atmospheric and topographic predictor variables on the precipitation estimations in the climatically diverse subregions.

scholarly journals Flood Risk Assessment and Quantification at the Community and Property Level in the State of Iowa

2021 ◽  
Author(s):  
Enes Yildirim ◽  
Ibrahim Demir
Keyword(s):  
Risk Assessment ◽  
High Resolution ◽  
Flood Risk ◽  
Large Scale ◽  
Spatial Scales ◽  
The United States ◽  
Flood Risk Assessment ◽  
Study Region ◽  
Study Results ◽  
Flood Maps

Flood risk assessment contributes to identifying at-risk communities and supports mitigation decisions to maximize benefits from the investments. Large-scale risk assessments generate invaluable inputs for prioritizing regions for the distribution of limited resources. High-resolution flood maps and accurate parcel information are critical for flood risk analysis to generate reliable outcomes for planning, preparedness, and decision-making applications. Large-scale damage assessment studies in the United States often utilize the National Structure Inventory (NSI) or HAZUS default dataset, which results in inaccurate risk estimates due to the low geospatial accuracy of these datasets. On the other hand, some studies utilize higher resolution datasets, however they are limited to focus on small scales, for example, a city or a Hydrological United Code (HUC)-12 watershed. In this study, we collected extensive detailed flood maps and parcel datasets for many communities in Iowa to carry out a large-scale flood risk assessment. High-resolution flood maps and the most recent parcel information are collected to ensure the accuracy of risk products. The results indicate that the Eastern Iowa communities are prone to a higher risk of direct flood losses. Our model estimates nearly $10 million in average annualized losses, particularly in large communities in the study region. The study highlights that existing risk products based on FEMA's flood risk output underestimate the flood loss, specifically in highly populated urban communities such as Bettendorf, Cedar Falls, Davenport, Dubuque, and Waterloo. Additionally, we propose a flood risk score methodology for two spatial scales (e.g., HUC-12 watershed, property) to prioritize regions and properties for mitigation purposes. Lastly, the watershed-scale study results are shared through a web-based platform to inform the decision-makers and the public.

Tail Deviation Mechanism and Neural Network Control of the Tandem Rolling Strap

2011 ◽  
Vol 103 ◽  
pp. 488-492
Author(s):  
Guang Bin Wang ◽  
Xian Qiong Zhao ◽  
Yi Lun Liu
Keyword(s):  
Neural Network ◽  
Finite Element ◽  
Finite Element Model ◽  
Control Policy ◽  
Element Model ◽  
Rolling Process ◽  
Network Control ◽  
Neural Network Control ◽  
The Neural Network ◽  
The Finite Element Model

In the rolling process, deviation is the phenomenon that the strap width direction's centerline deviates from rolling system setting centerline,serious deviation will cause product quality drop and rolling equipment fault. This paper has established the finite element model to the hot tandem rolling aluminum strap, analyzed the strap’s deviation rule under four kinds of incentives,obtained the neural network predictive model and the control policy of the tail deviation.The result to analyze a set of fact deviation data shows this method may control tail deviation in preconcerted permission range.

scholarly journals High-Resolution Sea Surface Temperature and Salinity in the Global Ocean from Raw Satellite Data

2019 ◽  
Vol 11 (19) ◽  
pp. 2191 ◽  
Author(s):  
Encarni Medina-Lopez ◽  
Leonardo Ureña-Fuentes
Keyword(s):  
Neural Network ◽  
High Resolution ◽  
Satellite Data ◽  
Google Earth ◽  
Sea Surface ◽  
Global Ocean ◽  
The Neural Network ◽  
Wide Range ◽  
Sentinel 2

The aim of this work is to obtain high-resolution values of sea surface salinity (SSS) and temperature (SST) in the global ocean by using raw satellite data (i.e., without any band data pre-processing or atmospheric correction). Sentinel-2 Level 1-C Top of Atmosphere (TOA) reflectance data is used to obtain accurate SSS and SST information. A deep neural network is built to link the band information with in situ data from different buoys, vessels, drifters, and other platforms around the world. The neural network used in this paper includes shortcuts, providing an improved performance compared with the equivalent feed-forward architecture. The in situ information used as input for the network has been obtained from the Copernicus Marine In situ Service. Sentinel-2 platform-centred band data has been processed using Google Earth Engine in areas of 100 m × 100 m. Accurate salinity values are estimated for the first time independently of temperature. Salinity results rely only on direct satellite observations, although it presented a clear dependency on temperature ranges. Results show the neural network has good interpolation and extrapolation capabilities. Test results present correlation coefficients of 82 % and 84 % for salinity and temperature, respectively. The most common error for both SST and SSS is 0.4 ∘ C and 0 . 4 PSU. The sensitivity analysis shows that outliers are present in areas where the number of observations is very low. The network is finally applied over a complete Sentinel-2 tile, presenting sensible patterns for river-sea interaction, as well as seasonal variations. The methodology presented here is relevant for detailed coastal and oceanographic applications, reducing the time for data pre-processing, and it is applicable to a wide range of satellites, as the information is directly obtained from TOA data.

Sign in / Sign up

Export Citation Format

Share Document