Prediction of Punching Capacity of Slab-Column Connections without Transverse Reinforcement Based on a Backpropagation Neural Network

Bu, Jie; Zhang, Fanzhen; Zhu, Meng; He, Zhiyang; Hu, Qigao

doi:https://doi.org/10.1155/2019/7904685

Advances in Civil Engineering

On this page

Abstract Introduction Conclusion Appendix Data Availability Disclosure Conflicts of Interest Acknowledgments References Copyright Related Articles

Research Article | Open Access

Volume 2019 | Article ID 7904685 | https://doi.org/10.1155/2019/7904685

Prediction of Punching Capacity of Slab-Column Connections without Transverse Reinforcement Based on a Backpropagation Neural Network

Jie Bu,¹Fanzhen Zhang,¹Meng Zhu,¹Zhiyang He,¹and Qigao Hu²

Academic Editor: Roman Wan-Wendner

Received23 Jul 2019

Revised09 Oct 2019

Accepted21 Oct 2019

Published23 Dec 2019

Abstract

Punching shear failure of slab-column connections can cause the progressive collapse of a structure. In this study, a punching test database is first established. Then, based on the Levenberg–Marquardt (LM) algorithm and using the nonlinear function of the backpropagation neural network (BPNN), a prediction model of the punching capacity of slab-column connections without transverse reinforcement is established. Finally, the proposed model is compared with the formulas of the Chinese, American, and European standards using several methods. The statistical eigenvalue method shows that the BPNN model has the highest accuracy and the lowest dispersion. The defect point counting method shows that the BPNN model had the fewest total number of defects and was the safest and most economical. The influencing factor analysis suggests that factors in the BPNN model had the most reasonable influence on the punching bearing capacity of slab-column connections. Finally, the model is verified using a case study and the Matlab program. The results show that the average error of the formulas in the Chinese, American, and European standards are 21.08%, 30.21%, and 11.47%, respectively, higher than that of the BPNN model.

1. Introduction

Bullock’s Department Store collapsed in 1994, Sanfeng Department Store in South Korea toppled down in 1995, and Morbio Inferior Shopping Center in Switzerland fell down in 2004 [1–3]. The above accidents show that slab-column connections without transverse reinforcement are prone to punching failure when they experience accidental loads, which then triggers a chain reaction and finally leads to the progressive collapse of the entire structure. Therefore, researchers have conducted a large number of trials and theoretical analyses on the mechanism of slab-column connections without transverse reinforcement under punching failure, and this research study has led to a comprehensive cognition of the variables that can trigger punching failure. Some mechanical models have been proposed that are based on the knowledge of the mechanism of slab-column connections to resist shearing. Such models include Mutton’s critical crack punching theory [4], Kinnunen and Nylander’s conical shell model [5], and Alexander and Simmond’s space truss model [6]. However, these theoretical equations are hard to unify and are in complex form; hence, they are not suitable for engineering applications. Currently, the recommended calculation methods for punching capacity in the national standards consist primarily of half-experience and half-theory formulas based on experimental data fitting. These methods include the calculation formulas in the GB 50010-2010 [7], ACI318-14 [8], and EC 2-04 [9] codes. These formulas are concise and clear, making them accessible to engineering designers. However, the theory referred to in these formulas for punching capacity primarily considers one kind of resisting shear mechanism or two, while ignoring other factors. Thus, the applicability of these formulas is limited [10–12]. The accuracy and reliability of the calculations also need to be further improved.

Due to the complexity of the mechanism of slab-column connections without transverse reinforcement under punching shearing failure, it is difficult to predict the punching capacity of slab-column connections by fitting the test data taking all factors into consideration. This is especially the case when it comes to influencing factors with large nonlinearity and uncertainty, as well as discreteness caused by brittle failure. An artificial neural network is a data-processing model enlightened by a biological neural network, the most common of which is called a BPNN. The Kolmogorov theorem has proven that the BPNN has strong nonlinear mapping and generalization abilities. Each continuous function or mapping function can be realized by three levels of networks [13]. The BPNN has been widely used for solving many civil engineering problems, including the shear performance of concrete members. Kumar and Barai established a neural network that can be used to predict the extreme shearing force of fiber concrete beams without transverse reinforcement [14]. Mansour predicted the extreme shearing strength of an RC beam with transverse reinforcement using an artificial neural network [15]. Meanwhile, Cladera and Mari used a neural network to establish a design procedure for a normal/high-strength concrete beam with and without stirrups [16]. Using the nonlinear function of a BPNN, this study established a prediction model for the punching capacity of slab-column connections without transverse reinforcement. In addition, the BPNN model is evaluated using the statistical eigenvalue method, the defect point method, and the influencing factor analysis method. The proposed model provides a new method for the calculation of punching capacity.

2. Establishment of the BPNN Model for Punching Capacity

The BPNN is a forward network based on error back propagation. It is composed of trained artificial neurons and is used to represent the optimal connection between a given input and expected output. The establishment of the BPNN model for punching capacity primarily includes the following steps. The first step is to establish training samples. As the research background for this study, it was necessary to determine the input and output sample parameters and establish the corresponding punching test database. The second step is the design of the BPNN model. It primarily includes the setting of the number of network layers, number of input layer nodes, number of hidden layer nodes, number of output layer nodes, activation function, training method, training parameters, and other factors. The third step is centered on BPNN training. The Levenberg–Marquardt (LM) algorithm is used to iteratively update the weights and thresholds of the network so that the errors between the output value of the network and the expected output are continuously reduced, and thus the optimal neural network is achieved. The fourth step is the evaluation of the training results. The performance of the neural network is then evaluated by cost function and regression analyses.

2.1. Establishment of the Punching Test Database

At the beginning of the 20th century, the progressive collapse of plate structures caused by punching failures of slab-column connections attracted the attention of scholars [17]. Therefore, scholars around the world have conducted numerous studies in the past century on the punching failure of slab-column connections. The research parameters have primarily included concrete strength, longitudinal reinforcement, size effect, column section shape and size, shear span to depth ratio, boundary conditions, punching shear reinforcement, loading mode (axial or partial load), aggregate type and size, and other factors. Many research results have been obtained due to these studies.

In this study, most of the domestic and foreign literatures regarding punching tests of slab-column connections without transverse reinforcement were collected [18–46]. The engineering application practice, the integrity of key data, and the research purpose of this study were all considered. To select the quantifiable influencing parameters of punching capacity as comprehensively as possible, it was determined that concrete strength (), longitudinal reinforcement ratio (), yield strength of longitudinal reinforcement (), effective height of the plate section (), shear span to depth ratio (), and ratio of column side length to plate effective height () would be used as the control variables of punching capacity () of slab-column connections. This was done so as to keep other influencing factors consistent and to screen the data. Finally, a set of BPNN training samples were established using as input values and as the output. The punching test database included 206 groups of slab-column connections without transverse reinforcement (see Table 1).

Due to differences in test designs, the material performance indices, loading modes, and other aspects of the test data in different literatures, there is a need to define a uniform description of key test data. Hence, the database is now explained. First, the database was unified using the international system of units (SI) in the database. Second, the concrete strength was uniformly converted into axial compressive strength , and the conversion relationships of concrete strength (f_c, , f_t, and f_cu) are shown in Table 2. Third, the slab-column connection in the database was all square cylinders, and vertical loads were applied using a steel pad, short column, or along the support boundary. The simulation of the simply supported boundary (the force characteristics of the reverse-bending line) was realized using the simply supported four sides.

2.2. Design of the BPNN Model

A neural network can be multilayered. Existing theories have proven that a network with a single hidden layer can achieve arbitrary nonlinear mapping by appropriately increasing the number of neuron nodes [10]. A single hidden layer can meet the needs of the problem background involved in this study. The number of input and output layer nodes depends on the dimension of the input and output vectors. According to the background of punching capacity of the BPNN model proposed in this study, the number of nodes used for the input layer is six. The input layer nodes are . The number of nodes in the output layer is one, which is the network output . The number of hidden layer nodes has a great influence on the performance of the BPNN model. Generally, more hidden layer nodes can contribute to better performance. It was found that when the node of the hidden layer was 15, the network had the best performance and the smallest error. For the selection of the activation function, the general hidden layer used a tan-sigmoid function (hyperbolic tangent function), while the output layer adopted a linear function. The training algorithm chose the LM algorithm with a fast convergence speed and a small mean square error. The BPNN model used an iterative updating method to determine weights and thresholds. The initial weights and thresholds were defined as small nonzero values that were randomly selected by the computer. The final neural network structure is shown in Figure 1.

2.3. Training of the BPNN Model

The input vector () is constructed using the parameters in the punching database, and is the expected output value. There are 206 groups of inputs and expected outputs. We assume that the input vector of the kth sample is . The corresponding output of the hidden layer is . The output of the output layer is . The expected output is . The connection weight between the input layer and the hidden layer is then set to be . The connection weight between the hidden layer and the output layer is . The threshold vector of neurons in the hidden layer is . The threshold of the output layer neuron is . The activation function of the hidden layer neurons is and the activation function of the output layer neuron is .

Then, the jth output in the hidden layer is as follows:

The output in the output layer is as follows:

The error of the kth sample is as follows:

The cost function (the average error of all samples) is as follows:

All the weights (15 × 6 + 15) and thresholds (15 + 1) were put into a weight matrix (121 × 1). It was assumed that the weight matrix after the nth iteration was . The LM algorithm was then applied to update W(n) iteratively. The Jacobian matrix of the cost function was then defined. The matrix uses the partial derivative of the error with respect to the parameter as the element:

The expression of the iterative update of the weight matrix is as follows:where is a tentative parameter. For a given parameter , if the cost function can be reduced by a change in the threshold ∆W, is reduced. Otherwise, increases.

According to the above calculation results, the training algorithm flow of the BPNN model is shown in Figure 2.

2.4. Result of the BPNN Model

The sample data of 206 groups are divided randomly into three groups: training samples (144), validation samples (31), and test samples (31). Training samples are used for error adjustment in the network training. Test samples are used to measure the network generalization. The training is stopped when the generalization stops improving. Test samples are used to measure the performance of network after training. The training samples are then substituted into the above training algorithm for iterative calculation to obtain an optimized BPNN model, to determine the final weight and threshold values and to obtain the neural network code for the punching capacity prediction model (see Appendix).

Figure 3 shows the variation of the cost function of the training samples, verification samples, and test samples with the number of iterations. It can be seen from the figure that when the number of iterations reaches 20, the cost function value is the minimum, and the training stops at this time. Figure 4 shows the training process of the neural network. Figure 5 shows the linear regression analysis between the output values of the training samples, verification samples, test samples, and population samples and the expected output values. According to this figure, the correlation between the neural network output and the expected output is very high, reaching 0.99663, 0.98419, 0.98922, and 0.99342, respectively, indicating that the neural network has very good performance and a good fitting effect.

(a)

(b)

(c)

(d)

3. Assessment of the BPNN Model

Since the BPNN model for predicting the punching capacity of slab-column connections without transverse reinforcement established in this study was directly based on results of existing test data, the predicted value of the model was given a safety reserve of 5%. This means that the predicted value of the model would be 95% of the output value of the model. Furthermore, the value of a model is determined by its application in engineering practice. Therefore, the present study established a set of relatively perfect evaluation system to evaluate the performance of the model. More specifically, the statistical eigenvalue method was used to evaluate the precision and discrete degree of the model, and the defect point counting method was used to evaluate the safety and economy of the model. In addition, the influencing factor analysis method was used to evaluate whether the model can reasonably reflect the impact of various factors on the punching bearing capacity.

3.1. The Statistical Eigenvalue Method

Based on the punching test database of the slab-column connections without transverse reinforcement, the predicted results of this model were compared with the calculated results of the Chinese concrete structural design code GB 50010-2010, the American concrete code ACI 318-14, and the European model code EC 2-04. For the sake of description, the following variable is defined:where is the value of the punching capacity obtained in the test and is the value of the punching capacity calculated using various methods, as shown in Table 3.

As shown in Table 3, the mean and median of the BPNN model are 1.05834 and 1.05486, which are the minimum in four formulas, followed by EC 2-04 and GB 50010-2010. The American standard is a little conservative. And the mean and median of ACI 318-14 are 1.31155 and 1.32631. Therefore, the BPNN model is the most accurate in four prediction methods.

According to the standard deviation and variable coefficient of X, the discretization degree of the BPNN model is the smallest, followed by EC 2-04, while discretization degrees of GB 50010-2010 and ACI 318-14 are relatively large. Moreover, P5 and P95 represent the 5th and 95th percentiles, respectively. P5 means that 5% of the data are less than this value, and P95 means that 5% data are more than this value. Thus, 90% of the data are within the range of (P5, P95). By comparing the interval of (minimum, maximum) and the interval of (P5, P95), it can be seen that the distribution interval (located near 1) of the BPNN model prediction results is far better than that of the other standards. This also indicates that, compared with the three standards, the dispersion degree of the BPNN model prediction results is smaller.

3.2. The Defect Point Counting Method

Drawing on the ideas of the defect point deduction method [47] and the point counting method [48] in management science, the defect point counting method is proposed to evaluate the safety and economy of the model. The basic idea is as follows. The ratio, X, of the test value () and the predicted value of each punching capacity calculation method () is used to classify the severity of the defects and to determine the weight and number of defect points of each defect grade. Then, the total number of defects is obtained using the weighted sum. The fewer the total number of points, the better the method can predict the punching capacity of slab-column connections. For the ratio of the experimental value and the predicted value, when X is less than 1, the slab-column connection is not safe. When it is greater than 1, it is safe. However, if X is too large, it is too conservative and uneconomical. Based on the severity classification principle of bell system defects and combined with the actual situation, the X value was divided into six severity levels of defects. Based on the test data, the number of defect points in each punching design method was counted. Table 4 shows the number of defect points in the slab-column connections. It can be seen from Table 4 that the total number of defect points in the BPNN model was 129, which is far fewer than the total number of defect points in the other three standards. The number of defect points was 246 in the Chinese standard, 242 in the American standard, and 194 in the European standard; these were 90.69%, 87.6%, and 50.39%, respectively, higher than that of the BPNN model. This shows that the BPNN model had the best comprehensive performance for safety and economy.

3.3. The Influencing Factor Analysis Method

The ratio of the test value and the predicted value is used as the ordinate. The concrete strength (), ratio of longitudinal reinforcement (), yield strength of longitudinal reinforcement (), effective height of plate section (), shear span to depth ratio (), and ratio of column side length to plate effective height () are used as the abscissa. The upper and lower limits of 95% and mean value of each group of data are given, and the influences of various factors on the prediction results of the punching capacity are then analyzed.

Figures 6–8, respectively, depict the influence of the effective height of the plate section (), the ratio of the column side length to the plate effective height (), and the concrete strength () on the ratio of the test value to the predicted values.

(a)

(b)

(c)

(d)

(a)

(b)

(c)

(d)

(a)

(b)

(c)

(d)

It can be seen from Figure 6 that when the effective height of the plate is less than 100 mm, the dispersion of prediction results of each formula is relatively large. When the effective height of the plate is greater than 100 mm, the accuracy and dispersion of the BPNN model prediction results are significantly better than those of the other three formulas. From Figure 7, we can see that when the parameter is less than 2, the prediction results of Chinese and American formulas are not ideal. Meanwhile, the BPNN model and the European formula predict better results over the entire interval. Figure 8 shows that the Chinese and American formulas have an obvious trend distribution with the change in concrete strength, while the BPNN model and the European formula show better prediction results and less dispersion.

Although Chinese, American, and European standards did not consider the influence of the shear span to depth ratio (), the yield strength of the longitudinal reinforcement (), and the ratio of the longitudinal reinforcement () on the punching capacity, the BPNN model was still used to evaluate the influence of these three variables in this study, as shown in Figures 9–11. The calculation results show that, with changes in the three variables, the ratio of the test value to the predicted value of the BPNN model is uniformly distributed on both sides of the mean, and there is no trend distribution or large dispersion degree.

In general, Chinese and American formulas are conservative, and their prediction results are highly dispersed. The European formula predicts better accuracy and has a smaller dispersion. Meanwhile, the BPNN model considers the most comprehensive influencing factors and does not show a trend distribution with changes in , , , , , and . The above results indicate that the BPNN model reasonably reflected the impact of various factors on the punching capacity of slab-column connections without transverse reinforcement.

Based on the above calculation and analysis, it is clear that the BPNN model established in this study is superior to the calculation formulas in the Chinese, American, and European standards.

In order to illustrate the necessity of the parameters considered in the BPNN model, the American formula is used to illustrate the influence of these parameters. It can be seen from Figure 12 that, as the reinforcement ratio increases, the result also increases, which is obviously unreasonable. The main reason for this is that the American formula does not consider the effect of the reinforcement ratio. As shown in Figures 13 and 14, the prediction result of the American formula has a large dispersion with changes in and . Furthermore, there are many unsafe results, which are not allowed in the actual application. Therefore, the parameters selected in this paper have a significant impact on the punching capacity. Empirically, ACI 318-14 uses the shear force of critical section as the punching capacity of slab-column connections. The parameters used in ACI 318-19 to calculate the shear strength include critical section perimeter, effective height of plate section, and concrete strength. From comparison results of this study, parameters used in the paper are perhaps more appropriate than the code. The paper suggests that ACI 318-14 should also take these parameters into account to improve the reliability of the formula. The same advice applies to GB 50010-2010 and EC 2-04.

4. Application Example

To verify the reliability and accuracy of the model presented in this study further, the punching test of slab-column connections without transverse reinforcement [42, 49] completed by Hunan University was selected as the calculation example. The relevant parameters of the punching test of slab-column connections are shown in Table 5.

To run this calculation example, the following actions were performed: first, we ran the Matlab working environment and edited the neural network code in Appendix and opened its root directory. Next, we typed the Neural Network Function (x1) on the command line; x1 is []. The output was the value of the punching capacity of slab-column connections predicted in this study. Finally, predicted results were compared with calculated results of Chinese, American, and European standards in Table 6.

is the value of the punching capacity measured by the test. are the values of the punching capacity calculated by the BPNN model, the Chinese, American, and European standards, respectively. From the table above, we can observe that the maximum of is 1.1208, the minimum is 1.0172, the mean is 1.072253, and the error is within 10%. In addition, the mean values of are 1.298288, 1.396167, and 1.19527, respectively. The calculation errors of the Chinese, American, and European standards are 21.08%, 30.21%, and 11.47% higher than that of the BPNN model, respectively. Thus, it can be seen that, using the Matlab tool and the BPNN model, prediction code established in this study can calculate the punching capacity of slab-column connections more quickly and accurately.

5. Conclusion

In general, shear failure is induced by the transfer between the column and slab of a shearing force combined with a moment. The research considers the transfer of a shearing force (without eccentricity with respect to the centroid of the shear critical section). In this study, a BPNN was used to study the punching capacity calculation of slab-column connections without transverse reinforcement. The main conclusions are as follows.

First, the quantifiable impact parameters of the punching capacity of slab-column connections without transverse reinforcement were considered comprehensively. A punching test database (including 206 groups) of slab-column connections without transverse reinforcement was established. This included influencing factors of concrete strength , the ratio of longitudinal reinforcement , the yield strength of longitudinal reinforcement , the effective height of the plate section , the shear span to depth ratio , and the ratio of column side length to the plate effective height . The BPNN model was designed and trained and then was evaluated by means of mean square error and regression analyses. The BPNN model showed good performance.

Second, the predicted value of the BPNN model of 95% was used as the model output. In this study, the accuracy and discreteness of the BPNN model were evaluated using the statistical eigenvalue method, and the safety and economy of the BPNN model were evaluated using the defect point counting method. Whether the BPNN model could reasonably reflect the impact of various factors on the punching capacity was evaluated using the influencing factor analysis method. Research results suggested that the mean, median, standard deviation, and variation coefficient of of the BPNN model were optimal; the number of defect points were fewest; and the predicted results did not show a trend distribution and large dispersion of relevant factors. This means that the BPNN model can meet relevant requirements well and is superior to the formulas in the Chinese, American, and European standards.

Third, based on the BPNN model established in this study, the code was run in the Matlab working environment. Parameters of the test model of Hunan University were calculated, and they were compared with the corresponding results of the Chinese, American, and European standards. The results indicate that the BPNN model had the best calculation results, with an average error within 10%. Compared with the BPNN model, the calculation errors of the Chinese, American, and European standards were increased by 21.08%, 30.21%, and 11.47%, respectively.

Appendix

Neural Network Code for Prediction Model of Punching Capacity

function [y1] = myNeuralNetworkFunction (x1) %MYNEURALNETWORKFUNCTION neural network simulation function. % % Generated by Neural Network Toolbox function genFunction, 13-Feb-2019 17 : 51 : 35. % % [y1] = myNeuralNetworkFunction (x1) takes these arguments: % x = Qx6 matrix, input #1 % and returns: % y = Qx1 matrix, output #1 % where Q is the number of samples. %#ok< ∗ RPMT0> % =====NEURAL NETWORK CONSTANTS===== % Input 1 x1_step1·xoffset = [75; 0.22; 278; 17.8; 2.926395939; 0.666666667]; x1_step1·gain = [0.00719424460431655; 0.574712643678161; 0.00464037122969838; 0.023121387283237; 0.18823518904255; 0.439710268466749]; x1_step1·ymin = −1; % Layer 1 b1 = [−0.67013086397926890925; 0.20485204467667655903; −3.9823333846859974017; 0.26809837709864853261; 1.7519871170795724424; 0.99641617199102761049; 4.9763998448198938362; 1.1368201646791966652; −0.025928389261043835456; −0.92100364806924983618; 0.36880965470930515693; 11.19473168509247607; −5.7906209524835876579; 1.8210861550491890259; 1.0562373148061163786]; IW1_1 = [0.54241403693654410834 0.24796025994322995478 −0.014337576347544853453 0.18764574836693678761 −0.02829727644609779727 0.14145204455730814308; −2.4509908541198388576 2.8901071801540454409 −2.0586515897176820289 1.068335537227783183 −4.6183794460269416149 −0.02484542256670946303; −7.6917611610029394953 3.0974401276965424223 −3.7294875430272114158 4.4642135026415905585 7.3171434926831198098 −12.328913326533490036; 3.5595775453552365164 3.3699076853018046229 1.5200070719384131124 −3.4388910985329763648 −6.2360139697241718792 −2.6537507383974756614; −2.0904525084619258735 4.3392922147544492617 5.9324277695856784121 −8.5047866210874421 −2.7523798326730455344 4.0482637507758116868; −0.22774737124199373461 −0.76951597973573482303 6.9372813682084002451 −0.16830700683789390215 5.8457813380652119406 3.4576020408617522683; −11.252702180792377717 −2.2694352690532371142 1.564784156023274253 −4.9174176477441013944 −4.5068636359880498432 −5.6545914419692682173; 10.059197750593041221 −0.17002386664310031872 −8.9848474105867879302 1.0203632176534829235 4.9221652171394971731 −7.5710047392480142037; −1.4840366841073464599 3.8623959556322895459 1.6833086970154664819 1.4067932842560260109 1.2210393313963610051 −1.001875039735422801; 1.0548272447130120355 1.7632488982764233931 −0.32313056811567220095 −1.3903358650695212262 1.0460118017996697937 2.5325861994828038348; 7.8613465153517045891 7.4271278087830125969 −2.8222326515948368275 −1.7772430280884681242 −3.905950647510644469 −17.387776097206195658; 6.9442041861601406794 0.22091386915732519336 5.89654429623693499 1.9608851775534088535 8.0650553137584175545 1.7641288972052406869; −6.4259520951425530555 2.1257615458185741275 0.63700368732926271331 0.47411663304245349471 0.76026839039380778029 −6.1951688429695117577; 3.4323263734923310508 −1.2974701439316240759 2.757336565240562809 −2.9415561788931592346 −4.7208935670603473511 7.4539269787059039274; 0.32595830157754457357 3.3624573492982667844 1.4011897034149485286 0.85463835267573085019 2.8748323421137191858 −1.9927818384202813373]; % Layer 2 b2 = 0.78597773687780803087; LW2_1 = [3.4772906528603062526 0.12639460740666358385 −0.23439286264789302439 0.020693346676863687977 −0.0060410169541254875661 0.080236891899916409909 1.2792025383667153804 −0.029240579066094837118 −0.21752104710756975381 −0.040404470314744492243 0.04108162773976927612 0.050369066295788737786 −0.035981188002320835251 −0.24956065236877369995 0.12526282041160077818]; % Output 1 y1_step1·ymin = −1; y1_step1·gain = 0.000841750841750842; y1_step1·xoffset = 115; % =====SIMULATION======== % Dimensions Q = size(x1, 1); % samples % Input 1 x1 = x1′; xp1 = mapminmax_apply (x1, x1_step1); % Layer 1 a1 = tansig_apply (repmat (b1, 1, Q) + IW1_1 ∗ xp1); % Layer 2 a2 = repmat (b2, 1, Q) + LW2_1 ∗ a1; % Output 1 y1 = mapminmax_reverse (a2, y1_step1); y1 = y1′; end % =====MODULE FUNCTIONS======== % Map Minimum and Maximum Input Processing Function function y = mapminmax_apply (x, settings) y = bsxfun (@minus, x, settings·xoffset); y = bsxfun (@times, y, settings·gain); y = bsxfun (@plus, y, settings·ymin); end % Sigmoid Symmetric Transfer Function function a = tansig_apply(n, ∼) a = 2./(1 + exp(−2 ∗ n)) − 1; end % Map Minimum and Maximum Output Reverse-Processing Function function x = mapminmax_reverse (y, settings) x = bsxfun (@minus, y, settings·ymin); x = bsxfun (@rdivide, x, settings·gain); x = bsxfun (@plus, x, settings·xoffset); end

Data Availability

The punching test data used to support the findings of this study have been included in Table 1, and the data can also be obtained from the papers in “References”. The neural network codes for predicting punching capacity of slab-column connections without transverse reinforcement are listed in Appendix.

Disclosure

Qigao Hu is the co-author.

Conflicts of Interest

The authors declare that they have no conflicts of interest.

Acknowledgments

The work presented in this study was funded by the National Natural Science Foundation of China, “Research on progressive collapse mechanism of reinforced concrete flat plate structure under blast loading (Grant no. 51608525).” The authors thank LetPub (http://www.letpub.com) for its linguistic assistance during the preparation of this manuscript.

References

D. Mitchell, R. H. DeVall, M. Saatcioglu, R. Simpson, R. Tinawi, and R. Tremblay, “Damage to concrete structures due to the 1994 northridge earthquake,” Canadian Journal of Civil Engineering, vol. 22, no. 4, pp. 361–377, 1995.
View at: Publisher Site | Google Scholar
T. W. Park, “Inspection of collapse cause of sampoong department Store,” Forensic Science International, vol. 217, no. 1–3, pp. 119–121, 2012.
View at: Publisher Site | Google Scholar
M. Yaser, Post-Punching Behavior of Reinforced Concrete Slabs, EPFL, Lausanne, Switzerland, 2010.
A. Muttoni, “Punching shear strength of reinforced concrete slabs without transverse reinforcement,” ACI Structural Journal, vol. 105, no. 42, pp. 440–445, 2008.
View at: Publisher Site | Google Scholar
S. Kinnunen and H. Nylander, Punching of Concrete Slabs Without Shear Reinforcement, Transactions of the Royal Institute of Technology, Stockholm, Sweden, 1960.
S. D. B. Alexander and S. H. Simmonds, “Bond model for concentric punching shear,” ACI Structural Journal, vol. 89, no. 3, pp. 325–328, 1992.
View at: Publisher Site | Google Scholar
China Architecture & Building Press, Ministry of Housing and Urban-Rural Development of the People’s Republic of China. Code for Design of Concrete Structures GB 50010-2010, China Architecture & Building Press, Beijing, China, 2010.
American Concrete Institute, Building code requirements for structural concrete (ACI 318-14), American Concrete Institute, Farmington Hills, MI, USA, 2014.
British Standards Institution, Eurocode 2: Design of Concrete Structures: Part 1–1: General Rules and Rules for Buildings, British Standards Institution, London, UK, 2004.
N. Venkata Ramana, “Review on punching shear strength of slabs,” International Journal of Engineering Research and Development, vol. 13, no. 10, pp. 1–25, 2017.
View at: Google Scholar
M. Lapi, M. Orlando, F. Angotti, and P. Spinelli, “Comparison of recent code provisions for punching shear capacity of R/C slabs without shear reinforcement,” Lecture Notes in Civil Engineering, vol. 10, pp. 113–132, 2018.
View at: Publisher Site | Google Scholar
L. Dang, R. Pang, S. Liang et al., “Ultimate bearing capacity calculation of slab-column connections and comparative study on different codes at home and abroad,” Architecture Science, vol. 35, no. 1, pp. 32–37, 2019.
View at: Google Scholar
H. Wang and J. Sun, “Classification method based on BP neural network and SVM,” Software, vol. 36, no. 11, pp. 96–99, 2015.
View at: Google Scholar
S. Kumar and S. V. Barai, “Neural networks modeling of shear strength of SFRC corbels without stirrups,” Applied Soft Computing, vol. 10, no. 1, pp. 135–148, 2010.
View at: Publisher Site | Google Scholar
M. Y. Mansour, M. Dicleli, J. Y. Lee, and J. Zhang, “Predicting the shear strength of reinforced concrete beams using artificial neural networks,” Engineering Structures, vol. 26, no. 6, pp. 781–799, 2004.
View at: Publisher Site | Google Scholar
A. Cladera and A. R. Marí, “Shear design procedure for reinforced normal and high-strength concrete beams using artificial neural networks. Part I: beams without stirrups,” Engineering Structures, vol. 26, no. 7, pp. 917–926, 2004.
View at: Publisher Site | Google Scholar
A. N. Talbot, Reinforced Concrete Wall Footings and Column Footings, University of Illinois at Urbana Champaign, Urbana, IL, USA, 1925.
R. C. Elstner and E. Hognestad, “Shearing strength of reinforced concrete slabs,” ACI Journal Proceedings, vol. 53, no. 7, pp. 51–53, 1956.
View at: Publisher Site | Google Scholar
J. Moe, Shearing Strength of Reinforced Concrete Slabs and Footings under Concentrated Loads, Portland Cement Association, Research and Development Laboratories, Skokie, IL, USA, 1961.
M. Manterola, Poinçonnement de Dalles Sans Armature d’effort Trenchant. Dalles, Structures Planes, CEB-Bull, Paris, France, 1966.
W. G. Corley and N. M. Hawkins, “Shearhead reinforcement for slabs,” ACI Journal Proceedings, vol. 65, no. 10, pp. 811–̶815, 1968.
View at: Publisher Site | Google Scholar
N. M. Hawkins, M. E. Criswell, and F. Roll, Shear Strength of Slabs without Shear Reinforcement, vol. 42, ACI Special Publication, Naples, FL, USA, 1974.
Y. Kakuta, A. Itoh, and Y. Fujita, “Experimental study on punching strength of reinforced concrete slabs,” Proceedings of the Japan Society of Civil Engineers, vol. 1974, no. 229, pp. 105–115, 1974.
View at: Publisher Site | Google Scholar
P. E. Regan and M. W. Braestrup, Punching Shear in Reinforced Concrete a State of Art Report, CEB, Secretariat Permanent, Arlington, VI, USA, 1985.
J. Zheng and Z. Zheng, “Experimental study on punching strength of reinforced concrete slabs,” Journal of Fuzhou University (Natural Science Edition), vol. 20, no. 2, pp. 65–69, 1992.
View at: Google Scholar
A. Tomaszewicz, High Strength Concrete, SP2 Plates and Shells, Report 2.3 Punching Shear Capacity of Reinforced Concrete Slabs, SINTEF Structures and Concrete, Trondheim, Norway, 1993.
D. D. Theodorakopoulos and N. Swamy, “Contribution of steel fibers to the strength characteristics of lightweight concrete slab–column connections failing in punching shear,” ACI Structural Journal, vol. 90, no. 4, pp. 342–350, 1993.
View at: Publisher Site | Google Scholar
Y. An and G. Zhao, “Experimental study on punching resistance of reinforced concrete slab mixed with steel fibers,” Journal of Building Structures, vol. 15, no. 2, pp. 11–14, 1994.
View at: Google Scholar
E. Sistonen, M. Lydman, and S. Huovinen, The Geometrical Model of the Calculation Formula of the Punching Hear Capasity of the Reinforced Concrete Slab, Helsinki University of Technology. Laboratory of Structural Engineering and Building Physics, Espoo, Finland, 1997.
C. M. Ghannoum, Effect of High–Strength Concrete on the Performance of Slab-Column Specimens, MC Gill University, Montreal, Canada, 1998.
G. Krueger, Resistance au Poinconnement Excentre des Plancers Dalles, École Polytechnique Fédérale de Lausann, Lausanne, Switzerland, 1999.
R. R. K. Beutel, Durchstanzen Schubbewehrter Flachdecken im Bereich von Innenstützen, RWTH Aachen University, Aachen, Germany, 2002.
C. E. Ospina, S. D. B. Alexander, and J. J. R. Cheng, “Punching of two–way concrete slabs with fiber–reinforced polymer reinforcing bars or grids,” ACI Structural Journal, vol. 100, no. 61, pp. 589–595, 2001.
View at: Google Scholar
H. G. Park, K. K. Choi, and J. K. Wight, “Strain-based shear strength model for slender beams without web reinforcement,” ACI Structural Journal, vol. 103, no. 6, pp. 783–793, 2006.
View at: Google Scholar
G. Birkle and W. H. Dilger, “Influence of slab thickness on punching shear strength,” ACI Structural Journal, vol. 105, no. 2, pp. 180–185, 2008.
View at: Google Scholar
X. Huang, L. Liu, and X. Tao, “Considering the influence of longitudinal reinforcement ratio and the length of side loading surface than plate punching by experimental research,” Journal of Civil Engineering, vol. 41, no. 7, pp. 21–25, 2008.
View at: Google Scholar
Y. Zhang, “Research on impact shear test of reinforced concrete slab,” College of Civil Engineering, Hunan University, Changsha, China, 2009, M.S. thesis.
View at: Google Scholar
S. Guandalini, O. L. Burdet, and A. Muttoni, “Punching tests of slabs with low reinforcement ratios,” ACI Structural Journal, vol. 106, no. 1, pp. 87–93, 2009.
View at: Publisher Site | Google Scholar
R. Guidotti, Poinçonnement des Planchers-dalles Avec Colonnes Superposées Fortement Sollicitées, École Polytechnique Fédérale de Lausann, Lausanne, Switzerland, 2010.
E. Rizk, H. Marzouk, A. Hussein et al., “Effect of reinforcement ratio on punching capacity of RC plates,” Canadian Journal of Civil Engineering, vol. 38, no. 7, pp. 729–735, 2011.
View at: Google Scholar
S. Lips, Punching of Flat Slabs with Large Amounts of Shear Reinforcement, École Polytechnique Fédérale de Lausann, Lausanne, Switzerland, 2012.
W. Yi, F. Hong, and J. Peng, “Experimental study on punching shear failure of reinforced concrete slab-column connections,” Building Structure, vol. 46, no. 15, pp. 11–18, 2016.
View at: Google Scholar
A. P. Caldentey, P. P. Lavaselli, H. G. Peiretti et al., “Influence of stirrup detailing on punching shear strength of flat slabs,” Engineering Structures, vol. 49, pp. 855–860, 2013.
View at: Google Scholar
M. Inacio, A. Ramos, V. Lucio, and D. Faria, “Punching of high strength concrete flat slabs–experimental investigation,” in Proceedings of the Fib Symposium, pp. 1–5, Tel–Aviv, Israel, April 2013.
View at: Google Scholar
M. Bartolac, D. Damjanović, and I. Duvnjak, “Punching strength of flat slabs with and without shear reinforcement,” Građevinar, vol. 67, no. 8, pp. 771–779, 2015.
View at: Google Scholar
J. Einpaul, J. Bujnak, M. F. Ruiz et al., “Study on influence of column size and slab slenderness on punching strength,” ACI Structural Journal, vol. 113, no. 1, pp. 135–138, 2016.
View at: Publisher Site | Google Scholar
S. Hu and H. Wang, “Comparison of GIS product quality evaluation based on fuzzy set and defect deduction method,” Journal of Earth Science and Environment, vol. 28, no. 2, pp. 96–99, 2006.
View at: Google Scholar
G. Liu, Quality Management, Tsinghua University Press, Beijing, China, 2003.
J. Zhao, W. Yi, and Z. Zhu, “Experimental research on post-punching behavior of slab-column connections,” Journal of Building Structures, vol. 36, no. 7, pp. 35–42, 2015.
View at: Google Scholar

Copyright

Copyright © 2019 Jie Bu et al. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

PDF Download Citation

Download other formats

Order printed copies

Views

735

Downloads

1191

Citations