Research on axial bearing capacity of rectangular concrete-filled steel tubular columns based on artificial neural networks

Design of rectangular concrete-filled steel tubular (CFT) columns has been a big concern owing to their complex constraint mechanism. Generally, most existing methods are based on simplified mechanical model with limited experimental data, which is not reliable under many conditions, e.g., columns using high strength materials. Artificial neural network (ANN) models have shown the effectiveness to solve complex problems in many areas of civil engineering in recent years. In this paper, ANN models were employed to predict the axial bearing capacity of rectangular CFT columns based on the experimental data. 305 experimental data from articles were collected, and 275 experimental samples were chosen to train the ANN models while 30 experimental samples were used for testing. Based on the comparison among different models, artificial neural network model1 (ANN1) and artificial neural network model2 (ANN2) with a 20-neuron hidden layer were chosen as the fit prediction models. ANN1 has five inputs: the length (D) and width (B) of cross section, the thickness of steel (t), the yield strength of steel (f _y), the cylinder strength of concrete (f′_c). ANN2 has ten inputs: D, B, t, f _y, f′_c, the length to width ratio (D/B), the length to thickness ratio (D/t), the width to thickness ratio (B/t), restraint coefficient (ξ), the steel ratio (α). The axial bearing capacity is the output data for both models.The outputs from ANN1 and ANN2 were verified and compared with those from EC4, ACI, GJB4142 and AISC360-10. The results show that the implemented models have good prediction and generalization capacity. Parametric study was conducted using ANN1 and ANN2 which indicates that effect law of basic parameters of columns on the axial bearing capacity of rectangular CFT columns differs from design codes.The results also provide convincing design reference to rectangular CFT columns.     

A practical ANN model for predicting the PSS of two-way reinforced concrete slabs

This paper aims to develop a practical artificial neural network (ANN) model for predicting the punching shear strength (PSS) of two-way reinforced concrete slabs. In this regard, a total of 218 test results collected from the literature were used to develop the ANN models. Accordingly, the slab thickness, the width of the column section, the effective depth of the slab, the reinforcement ratio, the compressive strength of concrete, and the yield strength of reinforcement were considered as input variables. Meanwhile, the PSS was considered as the output variable. Several ANN models were developed, but the best model with the highest coefficient of determination (R²) and the smallest root mean square errors was retained. The performance of the best ANN model was compared with multiple linear regression and existing design code equations. The comparative results showed that the proposed ANN model was provided the most accurate prediction of PSS of two-way reinforced concrete slabs. The parametric study was carried out using the proposed ANN model to assess the effect of each input parameter on the PSS of two-way reinforced concrete slabs. Finally, a graphical user interface was developed to apply for practical design of PSS of two-way reinforced concrete slabs.

     

Artificial intelligence-based estimation of flushing half-cone geometry

An accurate estimation of half-cone geometry (i.e., volume and length) created by pressure flushing operation in dam reservoirs is required for sediment management in the reservoir storage. In this study, two artificial intelligence techniques namely, Artificial Neural Network (ANN) and Adaptive Neuro-fuzzy Inference System (ANFIS) were utilized to estimate the volume and length of flushing half-cone based on influential variables, i.e., mean flow velocity through bottom outlet (u), water depth in reservoir (H_w), mean grain diameter of deposited sediments (d₅₀), thickness of deposited sediment (H_s) and bottom outlet diameter (D). Experimental data in both dimensional and non-dimensional forms were used to train and test ANN and ANFIS models. The results of the intelligence-based models were also compared with those of existing studies. The outcomes indicated that both ANN and ANFIS models predict the volume and length of flushing half-cone more accurately than existing studies. Also, it was found that the ANN model provides a better estimation of the geometry of flushing half-cone compared to the ANFIS model. Finally, sensitivity analysis was conducted to determine the most and the least influential variables affecting the flushing half-cone geometry. It was found that the sediment characteristics (H_s and d₅₀) and fluids properties (H_w and u) have respectively the most and the least effect on flushing half-cone volume and length.     

ANFIS-based prediction of moment capacity of reinforced concrete slabs exposed to fire

Reinforced concrete slabs, just as the other structural elements, are highly affected by the high temperatures. Due to the decrease in strength of reinforced concrete members under high temperature, bearing moment capacity of reinforced concrete slabs also decreases. In this study, a prediction model is investigated in order to determine the bearing moment capacities of reinforced concrete slabs under high temperature. Pre-calculated moment capacities of slabs exposed to fire are predicted by the implementation of adaptive neuro-fuzzy inference system (ANFIS) and the prediction performance of ANFIS model is investigated. The bending capacities of slabs with different concrete characteristics and different times of exposure are calculated. High temperature resulting from the duration of fire exposure is calculated as a function of time in accordance with ISO 834. The temperature distribution inside the slab is determined by the adoption of a steady-state one-dimensional heat transfer. The slab was separated into slim slices and the heat in each slice is determined depending on the time of exposure. Forces and resistance of materials under fire exposure are calculated by applying the reduction coefficients in Eurocode 2. Results confirm the high prediction capability of ANFIS model.     

Asymptotic behavior and blow up of solutions for semilinear parabolic equations at critical energy level

In this paper we study the initial boundary value problem of semilinear parabolic equations with semilinear term f(u). By using the family of potential wells method we prove that if f(u) satisfies some conditions, J(u₀) ≤ d and I(u₀) > 0, then the solution decays to zero exponentially as t → ∞. On the other hand, if J(u₀) ≤ d, I(u₀) < 0, then the solution blows up in finite time.     

Group path covering and distance two labeling of graphs

For a positive integer d, an L(d,1)-labeling f of a graph G is an assignment of integers to the vertices of G such that |f(u)−f(v)|?d if uv∈E(G), and |f(u)−f(v)|?1 if u and u are at distance two. The span of an L(d,1)-labeling f of a graph is the absolute difference between the maximum and minimum integers used by f. The L(d,1)-labeling number of G, denoted by λd,1(G), is the minimum span over all L(d,1)-labelings of G. An L^′(d,1)-labeling of a graph G is an L(d,1)-labeling of G which assigns different labels to different vertices. Denote by the L^′(d,1)-labeling number of G. Georges et al. [Discrete Math. 135 (1994) 103-111] established relationship between the L(2,1)-labeling number of a graph G and the path covering number of Gc, the complement of G. In this paper we first generalize the concept of the path covering of a graph to the t-group path covering. Then we establish the relationship between the L^′(d,1)-labeling number of a graph G and the (d−1)-group path covering number of Gc. Using this result, we prove that and for bipartite graphs G can be computed in polynomial time.     

Classification of dynamic processes and PID controller tuning in a parameter plane

A quadruplet, defined by the ultimate frequency ω_u, the ultimate gain k_u, the angle φ of the tangent to the Nyquist curve at the ultimate frequency and the gain G_p(0), is sufficient for classification of a large class of stable processes, processes with oscillatory dynamics, integrating and unstable processes G_p(s). From the model defined by the above quadruplet, a two parameter model G_n(s_n) is obtained by the time and amplitude normalizations. Two parameters of G_n(s_n), the normalized gain ρ and the angle φ, are coordinates of the classification ρ-φ parameter plane. Model G_n(s_n) is used to obtain the desired closed-loop system performance/robustness tradeoff in the desired region of the classification plane. Tuning procedures and tuning formulae are derived guaranteeing almost the same performance/robustness tradeoff as obtained by the optimal PID controller, applied to G_p(s) classified to the same region of the classification plane. Validity of the proposed method is demonstrated on a test batch consisting of stable processes, processes with oscillatory dynamics, integrating and unstable processes, including dead-time.     

Prediction of penetration depth in a plunging water jet using soft computing approaches

The flow characteristics of the plunging water jets can be defined as volumetric air entrainment rate, bubble penetration depth, and oxygen transfer efficiency. In this study, the bubble penetration depth is evaluated based on four major parameters that describe air entrainment at the plunge point: the nozzle diameter (D _N), jet length (L _j), jet velocity (V _N), and jet impact angle (θ). This study presents artificial neural network (ANN) and genetic expression programming (GEP) model, which is an extension to genetic programming, as an alternative approach to modeling of the bubble penetration depth by plunging water jets. A new formulation for prediction of penetration depth in a plunging water jets is developed using GEP. The GEP-based formulation and ANN approach are compared with experimental results, multiple linear/nonlinear regressions, and other equations. The results have shown that the both ANN and GEP are found to be able to learn the relation between the bubble penetration depth and basic water jet properties. Additionally, sensitivity analysis is performed for ANN, and it is found that D _N is the most effective parameter on the bubble penetration depth.     

Derivation of empirical equations for neutronic performance in a thorium fusion breeder with various coolants using regression analysis

In this paper, regression analyses (RA) are presented for the neutronic calculation of ThO₂ mixed ²⁴⁴CmO₂ fuel with different neutronic parameters for various coolants, natural lithium, Li₂₀Sn₈₀ and Flinabe, respectively. The tritium breeding ratio (TBR), energy multiplication factor (M), total fission rate (Σ_f) and ²³²Th(n, γ) reaction is computed by XSDRNPM. In addition, this numerical results are estimated by RA depends on neutronic parameters and the empirical equations for neutronic performance are acquired. The results obtained by using XSDRNPM and the results of the RA, obtained empirical equations, are compared. The empirical equations indicate that RA can successfully be used for the prediction of the neutronic performance parameters in the hybrid reactor with a high degree of accuracy. In addition, correlation matrix is calculated to determined statistical relationships between variables TBR, M, Σ_f, and ²³²Th(n, γ).     

Radio number of ladder graphs

Let G be a connected graph with diameter diam(G). The radio number for G, denoted by rn(G), is the smallest integer k such that there exists a function f: V(G)→{0, 1, 2, …, k} with the following satisfied for all vertices u and v:|f(u)?f(v)|≥diam (G)?d _G (u, v)+1, where d _G (u, v) is the distance between u and v in G. In this paper, we determine the radio number of ladder graphs.     

Multivariate adaptive regression spline (MARS) and least squares support vector machine (LSSVM) for OCR prediction

This article investigates the feasibility of multivariate adaptive regression spline (MARS) and least squares support vector machine (LSSVM) for the prediction of over consolidation ratio (OCR) of clay deposits based on Piezocone Penetration Tests (PCPT) data. MARS uses piece-wise linear segments to describe the non-linear relationships between input and output variables. LSSVM is firmly based on the theory of statistical learning, and uses regression technique. The input parameters of the models are corrected cone resistance (q _t ), vertical total stress (σ_v), hydrostatic pore pressure (u ₀), pore pressure at the cone tip (u ₁), and the pore pressure just above the cone base (u ₂). The developed LSSVM model gives error bar of predicted OCR. Equations have also been developed for prediction of OCR. The performance of MARS and LSSVM models has been compared with the traditional methods for OCR prediction. As the results reveal, the proposed MARS and LSSVM models are robust models for determination of OCR.     

More on the controllability of linear time-invariant systems

This study shows that a controllable system [xdot] = Ax + Bu, where x is an n-vector, can be driven from an arbitrary initial condition x(0) = x₀ to an arbitrary final condition x(t_f = x_f by a polynomial control function of degree M = 2r + 1, where r = n ? rank (B), through a polynomial trajectory of degree M. A simple algorithm for finding u by solving a set of linear equations, the solution of which yields the polynomial coefficients, is given.     

Estimation of pressuremeter modulus and limit pressure of clayey soils by various artificial neural network models

The main purpose of the present study is to develop some artificial neural network (ANN) models for the prediction of limit pressure (P _L) and pressuremeter modulus (E _M) for clayey soils. Moisture content, plasticity index, and SPT values are used as inputs in the ANN models. To get plausible results, the number of hidden layer neurons in all models is varied between 1 and 5. In addition, both linear and nonlinear activation functions are considered for the neurons in output layers while a nonlinear activation function is employed for the neurons in the hidden layers of all models. Logistic activation function is used as a nonlinear activation function. During the modeling studies, total eight different ANN models are constructed. The ANN models having two outputs produced the worst results, independent from activation function. However, for P _L, the best results are obtained from the feed-forward neural network with five neurons in the hidden layer, and logistic activation function is employed in the output neuron. For E _M, the best model producing the most acceptable results is Elman recurrent network model, which has 4 neurons in the neurons in the hidden layer, and linear activation function is used for the output neuron. Finally, the results show that the ANN models produce the more accurate results than the regression-based models. In the literature, when empirical equations based on regression analysis were used, the best root mean square error (RMSE) values obtained to date for P _L and E _M have been 0.43 and 5.65, respectively. In this study, RMSE values for P _L and E _M were found to be 0.20 and 2.99, respectively, by using ANN models. It was observed that using ANN approach drastically increases the prediction accuracy in terms of RMSE criterion.     

Investigation of pollution flashover on high voltage insulators using artificial neural network

High voltage insulators form an essential part of the high voltage electric power transmission systems. Any failure in the satisfactory performance of high voltage insulators will result in considerable loss of capital, as there are numerous industries that depend upon the availability of an uninterrupted power supply. The importance of the research on insulator pollution has been increased considerably with the rise of the voltage of transmission lines. In order to determine the flashover behavior of polluted high voltage insulators and to identify to physical mechanisms that govern this phenomenon, the researchers have been brought to establish a modeling. Artificial neural networks (ANN) have been used by various researches for modeling and predictions in the field of energy engineering systems. In this study, model of V_C = f (H, D, L, σ, n, d) based on ANN which compute flashover voltage of the insulators were performed. This model consider height (H), diameter (D), total leakage length (L), surface conductivity (σ) and number of shed (d) of an insulator and number of chain (n) on the insulator.     

Nonlinear eigenvalue problems for quasilinear systems

The paper deals with the existence of positive solutions for the quasilinear system (Φ(u'))' + λh(t)f(u) = 0,0 < t < 1 with the boundary condition u(0) = u(1) = 0. The vector-valued function Φ is defined by Φ(u) = (q(t)(p(t)u₁), …, q(t)(p(t)u_n)), where u = (u₁, …, u_n), andcovers the two important cases (u) = u and (u) = up > 1, h(t) = diag[h₁(t), …, h_n(t)] and f(u) = (f¹(u), …, fⁿ (u)). Assume that fⁱ and h_i are nonnegative continuous. For u = (u₁, …, u_n), let

, f₀ = maxf¹₀, …, fⁿ₀ and f_∞ = maxf¹_∞, …, fⁿ_∞. We prove that the boundary value problem has a positive solution, for certain finite intervals of λ, if one of f₀ and f_∞ is large enough and the other one is small enough. Our methods employ fixed-point theorem in a cone.     

Experiment and multiobjective optimization design of tape-spring hinges

Flexible tape-spring hinges can be folded elastically and are able to self-deploy by releasing stored strain energy with fewer component parts and slight weights. This study presents a detailed investigation of the folding and deployment of single-layer tape-spring (SLTS) hinges and double-layer tape-spring (DLTS) hinges under pure bend loading. The material properties of tape-spring hinges are measured using an INSTRON machine. A DLTS hinge construction is created, and its moment-rotation relationship during quasi-static deployment is measured. An experiment is conducted to verify the validation of the numerical models for the DLTS hinges. The quasi-static deployment behavior of SLTS hinges and DLTS hinges is then analyzed using nonlinear finite element ABAQUS/Explicit solver, starting from the complete folded configuration. The DLTS hinge has good quasi-static deployment performances with regard to maximum stress (S _m ), steady moment (M ^*) and the peak moment (M _d ) during the DLTS hinge quasi-static deployment. In addition, the sampling designs of the DLTS hinges are created based on a three-level full factorial design of experiments (DOE) method. The surrogate models of S _m , M ^* and M _d of the DLTS hinges are derived using response surface method (RSM) to reduce the computational cost of quasi-static folding and deployment of numerical simulations. The Multiobjective optimization design (MOD) of the DLTS hinge is performed using modified non-dominated sorting genetic algorithm (NSGA-II) algorithm to achieve the optimal design. The finite element models for the optimal design based on numerical method are established to validate the optimization results.     

Observational constraints on a hyperbolic potential in brane-world inflation

We focus on the large field of a hyperbolic potential form, which is characterized by a parameter f, in the framework of the brane-world inflation in Randall-Sundrum-II model. From the observed form of the power spectrum P _R (k), the parameter f should be of order 0.1m _p to 0.001m _p , the brane tension must be in the range λ ~ (1?10)×10⁵⁷ GeV⁴, and the energy scale is around V₀ ^1/4 ~ 10¹⁵ GeV. We find that the inflationary parameters (n _s , r, and dn _s /d(ln k) depend only on the number of e-folds N. The compatibility of these parameters with the last Planck measurements is realized with large values of N.     

Ranking numbers of graphs

Given a graph G, a vertex ranking (or simply, ranking) of G is a mapping f from V(G) to the set of all positive integers, such that for any path between two distinct vertices u and v with f(u)=f(v), there is a vertex w in the path with f(w)>f(u). If f is a ranking of G, the ranking number of G under f, denoted γf(G), is defined by , and the ranking number of G, denoted γ(G), is defined by . The vertex ranking problem is to determine the ranking number γ(G) of a given graph G. This problem is a natural model for the manufacturing scheduling problem. We study the ranking numbers of graphs in this paper. We consider the relation between the ranking numbers and the minimal cut sets, and the relation between the ranking numbers and the independent sets. From this, we obtain the ranking numbers of the powers of paths and the powers of cycles, the Cartesian product of P₂ with Pn or Cn, and the caterpilars. And we also find the vertex ranking numbers of the composition of two graphs in this paper.     

Least square support vector machine and multivariate adaptive regression spline for modeling lateral load capacity of piles

This article adopts least square support vector machine (LSSVM) and multivariate adaptive regression spline (MARS) for prediction of lateral load capacity (Q) of pile foundation. LSSVM is firmly based on the theory of statistical learning, uses regression technique. MARS is a nonparametric regression technique that models complex relationships. Diameter of pile (D), depth of pile embedment (L), eccentricity of load (e), and undrained shear strength of soil (S _u) have been used as input parameters of LSSVM and MARS. Equations have been presented from the developed MARS and LSSVM. This study also presents a comparative study between the developed MARS and LSSVM.     

Geometric Properties of the Fractured Tibia Stabilized by Unreamed Interlocking Nail: Development of a Three-Dimensional Finite Element Model

Based upon magnetic resonance scans of five human tibiae a three-dimensional finite element model using eight nodal isoparametric elements was developed to analyze the biomechanical properties of fracture fixation by an unreamed interlocking nail. Tension phenomena and bone implant translations occurring in the borderlines of the fracture zone, bone-implant interface, and the fixation site of the interlocking screws were analyzed with the help of link elements. The proximal fracture segment was fixed with a link element so as to produce exclusively translatory shifts corresponding to the vector of the load applied. Under condition of static loadF= 500 N or axial torsionM_T= 15 Nm the biomechanical properties of a nailed horizontal fracture (42-A3), a three fragment lesion (42-B2), and a comminuted midshaft fracture (42-C3) were evaluated. On condition of axial load maximum dislocations of 0.1549 mm are induced in the direction of the x-axis due to the asymmetric geometry of the human tibia which promotes medially directed translations. Independent from the fracture type present a homogenous tension profile was calculated for the whole tibia diaphysis with a σ_EQVranging from 24.18 to 121.14 MPa due to the relative low elastic modulus of the cortical bone compared to material characteristics of the implant. However, application of a torsional momentM_T= 15 Nm induces significantly increased tension maxima in the nail–interlocking screw interface with a σ_EQV= 7,626 MPa. Maximum translatory movementsu_x= 12.59 mm andu_y= 23.53 mm in the x and y plane indicate that these load conditions bear a high risk of an implant failure.