scholarly journals Effective thermal conductivity of unsaturated soils based on deep learning algorithm

2020 ◽  
Vol 205 ◽  
pp. 04006
Author(s):  
Zarghaam Haider Rizvi ◽  
Syed Jawad Akhtar ◽  
Wurood Talib Sabeeh ◽  
Frank Wuttke
Keyword(s):  
Thermal Conductivity ◽  
Deep Learning ◽  
Effective Thermal Conductivity ◽  
Unsaturated Soils ◽  
Learning Algorithm ◽  
Critical Role ◽  
Degree Of Saturation ◽  
Ann Model ◽  
Soil Thermal Conductivity ◽  
Validation Data

Soil thermal conductivity plays a critical role in the design of geo-structures and energy transportation systems. Effective thermal conductivity (ETC) of soil depends primarily on the degree of saturation, porosity and mineralogical composition. These controlling parameters have nonlinear dependencies, thus making prediction a nontrivial task. In this study, an artificial neural network (ANN) model is developed based on the deep learning (DL) algorithm to predict the effective thermal conductivity of unsaturated soil. A large dataset is constructed including porosity, degree of saturation and quartz content from literature to train and validate the developed model. The model is constructed with a different number of hidden layers and neurons in each hidden layer. The standard errors for training and testing are calculated for each variation of hidden layers and neurons. The network with the least error is adopted for prediction. Two sand types independent of training and validation data reported in the literature are considered for prediction of the ETC. Five simulation runs are performed for each sand, and the computed results are plotted against the reported experimental results. The results conclude that the developed ANN model provides an efficient, easy and straightforward way to predict soil thermal conductivity with reasonable accuracy.

scholarly journals Fractal study in soil spatial variability and thermal conductivity

2019 ◽  
Vol 23 (5 Part A) ◽  
pp. 2849-2856
Author(s):  
Jingfang Shen ◽  
Xu Zhang ◽  
Wenwei Liu ◽  
Ying Zhang
Keyword(s):  
Thermal Conductivity ◽  
Spatial Variability ◽  
Effective Thermal Conductivity ◽  
Multifractal Spectrum ◽  
Coarse Sand ◽  
Soil Thermal Conductivity ◽  
Sierpinski Carpet ◽  
Fractal Method ◽  
Scatter Plots ◽  
Sierpiński Carpet

This paper takes advantage of fractal method to research some soil characteristics through case analysis. The multifractal spectrum and random Sierpinski carpet are used to describe the spatial variability and thermal conductivity of soil quantitatively. On the basis of predecessors, the scatter plots of various types of data have been used to supplement the multifractal results in a more detailed way. It turns out that the content of clay, silt, and coarse sand could reflect the degree of spatial variability of soil. Then based on this case, the effect of porosity on soil thermal conductivity is discussed by using random Sierpinski carpet. The result shows that the effective thermal conductivity of the clay, silt and coarse sand decreases linearly with the increase of porosity, but the degree of reduction is different. Moreover, when the porosity is definite, the effective thermal conductivity of the coarse sand is the largest, that of the clay with the highest thermal conductivity is second, and that of the silt is the smallest.

Predicting the effective thermal conductivity of unfrozen soils with various water contents based on artificial neural network

2021 ◽  
Author(s):  
Chuan-Yong Zhu ◽  
Zhi-Yang He ◽  
Mu Du ◽  
Liang Gong ◽  
Xinyu Wang
Keyword(s):  
Neural Network ◽  
Thermal Conductivity ◽  
Artificial Neural Network ◽  
Water Content ◽  
Effective Thermal Conductivity ◽  
Pearson Correlation ◽  
Complex Structure ◽  
Ann Model ◽  
Input Parameters ◽  
Artificial Neural

Abstract The effective thermal conductivity of soils is a crucial parameter for many applications such as geothermal engineering, environmental science, and agriculture and engineering. However, it is pretty challenging to accurately determine it due to soils’ complex structure and components. In the present study, the influences of different parameters, including silt content (m si), sand content (m sa), clay content (m cl), quartz content (m qu), porosity, and water content on the effective thermal conductivity of soils, were firstly analyzed by the Pearson correlation coefficient. Then different artificial neural network (ANN) models were developed based on the 465 groups of thermal conductivity of unfrozen soils collected from the literature to predict the effective thermal conductivity of soils. Results reveal that the parameters of m si, m sa, m cl, and m qu have a relatively slight influence on the effective thermal conductivity of soils compared to the water content and porosity. Although the ANN model with six parameters has the highest accuracy, the ANN model with two input parameters (porosity and water content) could predict the effective thermal conductivity well with acceptable accuracy and R 2=0.940. Finally, a correlation of the effective thermal conductivity for different soils was proposed based on the large number of results predicted by the two input parameters ANN-based model. This correlation has proved to have a higher accuracy without assumptions and uncertain parameters when compared to several commonly used existing models.

scholarly journals Temperature Changes in the Vicinity of Thermally Loaded Structure Embedded in the Soil: Effect of Sand Content and Saturation Degree

2017 ◽  
Vol 39 (2) ◽  
pp. 61-71
Author(s):  
Adrian Różański
Keyword(s):  
Thermal Conductivity ◽  
Solid Phase ◽  
Rapid Development ◽  
Degree Of Saturation ◽  
Soil Thermal Conductivity ◽  
Soil Medium ◽  
Temperature Changes ◽  
Soil Skeleton ◽  
Soil Conductivity ◽  
Loaded Structure

Abstract Due to the rapid development of geothermal technologies, the problem of efficient and proper evaluation of soil thermal conductivity becomes extremely important. Factors mostly affecting the soil conductivity are the conductivity of solid phase and the degree of saturation. The former one is mainly affected by the mineral composition, in particular, by the content of quartz whose conductivity is the highest one among all the minerals forming soil skeleton. Organic matter, because of its relatively low conductivity, influences the solid conductivity as well. The problem addressed in the paper is the influence of mentioned factors on temperature changes in the vicinity of thermally loaded structure embedded in the soil medium. Numerical simulations are carried out for different values of soil thermal conductivity resulting from various quartz contents and degrees of saturation. In addition, a weak coupled - heat and water transport - problem is considered.

scholarly journals Thermal properties of a tropical unsaturated soil

2021 ◽  
Vol 337 ◽  
pp. 01019
Author(s):  
Thaise da Silva Oliveira Morais ◽  
Cristina de Hollanda Cavalcanti Tsuha ◽  
Orencio Monje Vilar
Keyword(s):  
Thermal Conductivity ◽  
Thermal Properties ◽  
Unsaturated Soil ◽  
Unsaturated Soils ◽  
Thermal Characteristics ◽  
Thermal Response ◽  
Test Site ◽  
Degree Of Saturation ◽  
Ambient Temperatures ◽  
Heating And Cooling

Ground thermal properties, especially the thermal conductivity, are of paramount importance for the design of ground source heat pump systems (GSHP), used for space heating and cooling. However, very little information, if any, are available from the thermal characteristics of tropical unsaturated soils related to the GSHP application. To evaluate the thermal behaviour of a typical Brazilian tropical unsaturated soil, an extensive experimental investigation was conducted at the test site of the University of Sao Paulo at São EESC/USP) comprising Carlos (a detailed soil characterization; field monitoring of the seasonal groundwater table variation; soil and ambient temperatures, and matric suction of the top soil. This paper describes the investigation program and compares the thermal soil properties as measured in laboratory and field thermal response tests. The results were variable depending on the testing techniques; however, all results showed that the soil thermal conductivity is strongly influenced by the degree of saturation of the soil.

scholarly journals Predicting the effective thermal conductivity of geo-materials using artificial neural networks

2020 ◽  
Vol 205 ◽  
pp. 04001
Author(s):  
Dinesh Shrestha ◽  
Frank Wuttke
Keyword(s):  
Thermal Conductivity ◽  
Prediction Models ◽  
Complex Nature ◽  
Ann Model ◽  
Soil Thermal Conductivity ◽  
Energy Applications ◽  
The Past ◽  
Artificial Neural ◽  
Artificial Neural Network Ann ◽  
Semi Empirical

Soil thermal conductivity is an important thermal property used in heat transfer modelling and geo-energy applications. Because of its complex nature and depending on several factors such as porosity, moister content, structure, etc., it is always challenging to predict the thermal conductivity of geo-materials. In the past, many predictions models like theoretical, semi-empirical, empirical models have been proposed based on the experimental data. However, these models are more specific to certain boundary conditions. Therefore, in this study, an artificial neural network (ANN) approach was used to predict the thermal conductivity of geo-materials as a function of porosity, gradation and mineralogy. A comparison between existing prediction models and the developed ANN model for predicting thermal conductivity is also given.

Identification of pipe inner surface in heat conduction problems by deep learning and effective thermal conductivity transform

2020 ◽  
Vol 37 (9) ◽  
pp. 3505-3523
Author(s):  
Haolong Chen ◽  
Zhibo Du ◽  
Xiang Li ◽  
Huanlin Zhou ◽  
Zhanli Liu
Keyword(s):  
Thermal Conductivity ◽  
Deep Learning ◽  
Effective Thermal Conductivity ◽  
Identification Problem ◽  
Learning Model ◽  
Surface Shape ◽  
Transform Method ◽  
Content Type ◽  
Inner Surface ◽  
Deep Learning Model

Purpose The purpose of this paper is to develop a transform method and a deep learning model to identify the inner surface shape based on the measurement temperature at the outer boundary of the pipe. Design/methodology/approach The training process is assisted by the finite element method (FEM) simulation which solves the direct problem for the data preparation. To avoid re-meshing the domain when the inner surface shape varies, a new transform method is proposed to transform the shape identification problem into the effective thermal conductivity identification problem. The deep learning model is established to set up the relationship between the measurement temperature and the effective thermal conductivity. Then the unknown geometry shape is acquired by the mapping between the inner shape and the effective thermal conductivity through the inverse transform method. Findings The new method is successfully applied to identify the internal boundary of a pipe with eccentric circle, ellipse and nephroid inner geometries. The results show that as the measurement points increased and the measurement error decreased, the results became more accurate. The position of the measurement point and mesh density of the FEM model have less effect on the results. Originality/value The deep learning model and the transform method are developed to identify the pipe inner surface shape. There is no need to re-mesh the domain during the computation progress. The results show that the proposed method is a fast and an accurate tool for identifying the pipe inner surface.

scholarly journals Heat Transfer Interface to Graphitic Foam

2019 ◽  
Author(s):  
Fang-Ming Lin ◽  
Eric Anderssen ◽  
Raymond K. Yee
Keyword(s):  
Heat Transfer ◽  
Thermal Conductivity ◽  
Effective Thermal Conductivity ◽  
Heat Dissipation ◽  
Critical Role ◽  
Carbon Foam ◽  
Thin Layers ◽  
Uniform Structure ◽  
Carbon Foams ◽  
Graphitic Foam

Abstract Thermal interface materials (TIMs) used for bonding components are important for creating a thermally conductive path which improves heat dissipation. Low density, porous carbon foams are commonly used for thermal management applications and devices. Their high surface area to volume ratio enables cooling more effectively via different heat transfer methods. Many studies have adopted different methods to analytically or computationally analyze the effective thermal conductivity of carbon foams. Others have studied the participation of TIMs used in composite materials. However, very few studies have analyzed the microscale effects in heat transfer of the interaction between TIM and carbon foams. The amount of contact between a carbon foam and a bonded surface has hardly been reported in the literature. In this study, the carbon foam is deposited with thin layers of graphene until reaching the desired foam density; this type of foam is known as the graphitic foam. Graphene’s highly anisotropic thermal properties result in high thermal conductivity in the planar direction but low in the normal direction. With these anisotropic thermal characteristics, the objective of this study is to determine the effect of TIM thickness on thermal conductivity of the graphitic foam. It was hypothesized that the direction which heat enters the graphitic foam and the size of the cross-sectional area normal to the heat flux direction would affect the overall effective thermal conductivity. As commonly known, a gap created between ligands (foam structure) and the bonded surface would likely reduce the overall effective thermal conductivity. At the gap, heat is transferred via the TIMs or the graphitic foam through conduction, depending on if a direct contact exists between the graphitic foam and the bonded surface. The filler types used for the TIMs are hypothesized to play a critical role in the heat portion transferred via the TIMs. The heat transfer in 2-D becomes extremely complicated while anisotropic materials (graphene coating) and isotropic materials (TIMs) interact. Furthermore, the non-uniform structure of the carbon foam introduces more complexity to the heat transfer at the interface. A computational model using ANSYS finite element program was developed in this study to help the analysis. The results demonstrate that the parameters at the interface can be optimized to improve the overall effective thermal conductivity of the interface.

Music Emotion Recognition

2021 ◽  
Author(s):  
tejaswini kambaiahgari ◽  
Uma Rao K
Keyword(s):  
Deep Learning ◽  
Nearest Neighbor ◽  
Learning Algorithm ◽  
Machine Learning Algorithms ◽  
Training Data ◽  
Ann Model ◽  
K Nearest Neighbor ◽  
Data Set ◽  
Deep Learning Algorithm ◽  
Present World

Abstract In the present world, there are many songs over the internet. But the information retrieval on these songs can be complicated. This paper intends to classify songs based on emotions using deep learning. We propose a strategy to recognize the emotion present in a song by classifying their spectrograms, which contains both time and frequency information. According to human psychology, neurons within a sub pop- ulation of our brain did not react the same way for all the emotions.So only specific neurons need to be triggered for identifying an emotion. Dif- ferent deep learning and machine learning algorithms are implemented to build music emotion recognizer. The main objective of this study is to study about the features which are important for audio file ,to de- velop a music emotion classifier using deep learning algorithm and also to validate the model.The datasets are split into training and testing sets, models are trained with training data set. The accuracy of Artifi- cial Neural Network (ANN) model is 79.7% ,K-Nearest Neighbor (KNN) model is 78.26% and logistic regression for gender classification is 81%.

Sign in / Sign up

Export Citation Format

Share Document