Prediction of thermal conductivity of rock through physico-mechanical properties
Introduction
Thermal conductivity of rock is studied along with different physico-mechanical properties due to its increasing importance in the geotechnical engineering, geothermal engineering, nuclear disposal, etc. Its study is important because it is main characteristic of energy transfer phenomenon. Energy transfer arising from the temperature difference between the adjacent parts of the body is called heat conduction. The amount of heat to be transferred through any body depends upon a number of factors, such as the particle shape, porosity, temperature range, solid constituents, moisture content, uniaxial and/or triaxial pressure exerted on the rock, etc. [1], [2], [3], [4], [5]. It widely influences the energy transfer between adjacent rocks in underground mines and in insulation of the building by providing an energy efficient solution. Energy saving is the important part of any national energy strategy and its conservation for underdeveloped countries with inadequate resources is even more important [5]. Thermal insulation material is most important part of any thermal insulation system and a lower system thermal conductivity can be achieved by combination of more thermal insulation material. Such systems are generally characterized by an effective thermal conductivity. The thermal conductivity is determined by the measurements of temperature gradient in the rock and heat input [6].
In general, the thermal conductivity can be calculated using Fourier's Law as given below:where dQ/dt is the time rate of heat transfer; A the area of the body whose heat is to be transferred; dT/dx the temperature gradient, k the thermal conductivity of the material; k0 the thermal conductivity of the rock under normal conditions, W/(m °C); λ and n are the rock-dependent constant parameters in uniaxial compression; P is the applied uniaxial pressure, Mpa; , ncp and βcp are the rock-dependent constant parameters in triaxial compression, Cp is the confining pressure, MPa. Transport and thermodynamic properties which is referred as thermo-physical properties affect the thermal conductivity of rocks. Properties like k the thermal conductivity of the material comes under transport properties while in thermodynamic analysis properties like density and specific heat are commonly used.
Considering the physical mechanism associated with conduction in general, the thermal conductivity of a solid is larger than that of a liquid, and that of liquid is larger than gas.
Knowing a greater usability of thermal property in the civil engineering, a lot of work has been carried out to find thermal conductivity of rock and to predict by a definite simple model for the judgment the thermal property of rocks. Progress has been made in recent years in the ability to predict the thermal conductivity, but the state of the art is deficient in many ways. On the basis of detailed investigation, a viable approach for the prediction of thermal conductivity is necessary. An artificial intelligence (AI) comes in handy to fulfill this problem. Artificial neural networks (ANNs) and adaptive neuro fuzzy inference system (ANFIS) are used in the present study. ANN can be viewed as an interesting class of statistical pattern recognition algorithm, which provides explicit facilities for modeling non-linear and non-Gaussian statistical regularities and proves to be strong tool to prepare an equivalent model by virtue of its capabilities of function approximation and classification. The potential of modeling the material behavior using ANN was first proposed by Ghaboussi et al. [7]. ANNs have been used to solve a wide variety of application in Geomechanics and Rock Engineering [8]. In the last few years, fuzzy inference systems (FISs) began to be used in the areas of rock mechanics and engineering geology [9], [10], [11], [12]. According to Setnes et al. [13], an interesting and perhaps the most attractive characteristics of fuzzy models compared with other conventional methods commonly used in geosciences. Such as in statistics, they are able to describe complex and non-linear multivariable problems in a transparent way. Fuzzy logic is a logical system, which is an extension of multivalued logic. Fuzzy propositions are statements that posses fuzzy variables. The concept of a fuzzy set is the basis of a fuzzy logic. A fuzzy set is a set without a crisp, clearly defined boundary. ANFIS and ANN can be viewed as strong tools in the statistical pattern recognition algorithm and to prepare an equivalent model by virtue of their capabilities of function approximation and classification. Data sets for the analysis are taken from literature [14] based on the laboratory experiments.
Section snippets
Input parameters
An attempt has been made to predict the thermal conductivity of rock through its physico-mechanical properties. There are various physical factors affecting the thermal conductivity of rocks. Mineral composition and constitution, structural and textural features of rocks, amount of pore water present and the condition at which rocks are tested also affect the thermal conductivity of the rocks. Physical properties like P-wave velocity, porosity, bulk density, uniaxial compressive strength has
Artificial neural network
Neural networks are inspired by biological nervous system existing in the human brain. ANN is popularly known as “neuro computing”, neural network, parallel distributed, processing algorithms and connectionist-network. Neural network consist of many interconnected neurons that are called processing elements with familiar characteristics like inputs, synaptic strength, activation output and bias. Number of artificial neurons in ANN can be representative of neurons of the natural neural network
Neuro-fuzzy model
For inference in a rule-based fuzzy model, the fuzzy propositions need to be represented by an implication function called a fuzzy if-then rule or a fuzzy conditional statement [9]. The use of fuzzy sets to present linguistic terms enables one to represent more accurately and consistently something which is fuzzy [26]. A linguistic variable whose values are words, phrases or sentences are labels of fuzzy sets [27]. In literature, many methods such as intuition, rank ordering, angular fuzzy
The networks
The data was divided into training and testing data sets using sorting methods, to maintain the statistical consistency. In the present case, about 10% of the data formed the testing database for each network. Consequently, data for the testing data sets were extracted at regular intervals from the sorted database and the remaining 90% of the database formed the training database. Same data set are used for all the networks to make a comparable analysis of different architecture. Model used for
Results and discussion
AI modeling has provided some of the interesting results to predict the thermal conductivity of rock using simple rock parameters. ANN and ANFIS are the form of AI used in present study found to be very strong tool in the prediction of non-linear behavior of thermal conductivity. Fig. 7a–f shows the prediction trend of all the networks used in the study.
Among other networks ANFIS captures complete range very accurately with an average absolute percentage error of 0.03% with maximum value of
Conclusion
It is evident from the present study that AI modeling has good prediction capability to determine the very complex rock parameter like thermal conductivity, using simple rock parameter like P-wave velocity, porosity, bulk density and uniaxial compressive strength. Six different models of ANN and ANFIS have been tested and verified to see the suitability. It is found that among all network tried and tested ANFIS has shown better result as compared to other model based on average absolute
References (33)
- et al.
Thermal conductivity of rocks and its variation with uniaxial and triaxial stress
International Journal of Rock Mechanics and Mining Sciences
(2004) - et al.
Knowledge-based fuzzy model for performance prediction of a rock-cutting trencher
International Journal of Approximate Reasoning
(1997) - et al.
A rule based fuzzy model for the prediction of petrophysical rock parameters
Journal of Petroleum Science and Engineering
(2001) A fuzzy triangular chart to predict the uniaxial compressive strength of Ankara agglomerates from their petrographic composition
Engineering Geology
(2002)- et al.
Determination of the thermal conductivity of rock from P-wave velocity
International Journal of Rock Mechanics and Mining Sciences
(2004) Effective thermal conductivity of granular porous materials
International Communications in Heat and Mass Transfer
(1996)Fuzzy sets
IEEE Information and Control
(1965)- et al.(1995)
The variation of thermal conductivity with pressure in rocks and the investigation of its effect in underground mines
(1999)- et al.
Variation of thermal conductivity of rocks with pressure
CIM Bulletin
(2002)
Optimising insulation thickness for building using life cost
Applied Energy
Thermal conductivity of rocks and minerals
American Geophysical Union
Knowledge-based modeling of material behavior with neural networks
Journal of Engineering Mechanics, ASCE
Neuro-fuzzy modeling in engineering geology
Rule-based modeling: precision and transparency
IEEE Transactions on Systems Man and Cybernetics, Part C
Cited by (115)
Research on thermal performance of ground source heat pump based on artificial neural network predictive model
2024, Applied Thermal EngineeringExperimental investigation on rock thermal properties under the influence of temperature
2023, Thermochimica ActaCitation Excerpt :According to Xu et al. [40] and Gasia et al. [41], materials with low thermal conductivity limits heat transfer between working fluid and solid and decrease the thermal performance of material, for example a thermal energy storage, which requires very extensive specific thermal interface to exchange the heat. In general, the thermal conductivity of a solid is larger than that of a liquid which is larger than that of gas [42]. Thermal conductivity can be divided in two types : lattice conductivity produced by the diffusion of thermal vibration in a crystalline lattice and radiative conductivity produced by infrared electromagnetic waves.
Effect of diabase intrusion on the CBM-bearing coalfields of southern Brazil: A review
2022, Journal of South American Earth SciencesPredicting the thermal conductivity of soils using integrated approach of ANN and PSO with adaptive and time-varying acceleration coefficients
2022, International Journal of Thermal SciencesCalculations of wellbore heat loss
2021, Developments in Petroleum Science