A reasonable prediction for the peak strength of reinforced concrete (RC) columns is paramount for the seismic performance evaluation of RC structures. The available prediction models are commonly dependent on the failure mode, and each of them is only applicable to the columns with a particular one. However, the failure mode of RC columns is difficult to be identified accurately in prior, leading to the inconvenience of predicting its peak strength. To overcome this shortcoming, a probabilistic approach was proposed using Bayesian neural network (BNN) to develop a failure-mode–independent model for predicting the peak strength of RC columns directly. The results indicated that the developed model produces reasonable prediction for the peak strength of RC columns failing in different modes. For the training subset, the mean prediction accuracy of the flexure-dominated, flexure-shear-dominated, and shear-dominated columns is 0.997, 0.997, and 0.998, respectively. For the testing subset, the corresponding mean prediction accuracy is 0.957, 0.952, and 0.943. Compared to existing probabilistic models, the developed model exhibits better performance in reducing the uncertainties in peak strength prediction. Compared to existing deterministic models, the developed model could predict the peak strength of RC columns in terms of the confidence interval. In particular, if the confidence interval of peak strength is defined as the mean plus and minus two times standard deviation, 98.9% and 98.4% of the training subset and testing subset are covered. Therefore, the developed model is beneficial for engineers to address the confusion, namely, which peak prediction is the most probable one, when several deterministic models exist for a specific specimen.
Keywords: Experimental database; modeling; peak strength; prediction; reinforced concrete column
Reinforced concrete (RC) columns are probably one of the most critical components of existing RC structures to resist vertical and lateral loads. The post-earthquake observation revealed that RC columns may suffer three different failure modes, namely, flexure failure (FF) mode, shear failure (SF) mode, and flexure-shear (FS) failure mode ([
The peak strength of RC columns, which represents the maximum bearing capacity to resist the vertical and lateral load, is an important indicator in seismic capacity assessment of RC structures. Due to the complexity of failure mode evolution, predicting the peak strength of RC columns is generally associated with a particular failure mode. During the past years, numerous models have been proposed for predicting this quantity of importance accurately. For example, the conventional fiber-section numerical model was developed to predict the peak strength of flexure-dominated RC columns ([
Following the two types of peak strength models, identifying the failure mode of RC columns accurately in prior is also important. If a wrong failure mode is identified, it is difficult to predict the peak strength of RC columns accurately. In order to identify the failure mode of RC columns accurately, two indictors, namely, shear aspect ratio and shear demand to capacity ratio were developed over the past decades. Unfortunately, the two indictors show poor performance ([
The failure mode identification accuracy using the advanced techniques has attained great success. For example, the model generated by the AdaBoost learning algorithm gets a high identification accuracy by 0.96 ([
Toward this end, the data-driven approach is selected to develop the failure-mode–independent peak strength model for its capability of relating the peak strength of RC columns with the important design variables directly. In the recent years, different data-driven approaches, for example, artificial neural network (ANN), support vector machines (SVM), and decision tree (DT) have been employed in this field. For example, [
The contents of this study are organized as follows. First, the experimental data of RC columns failing in different modes was collected from literatures. Then, the Bayesian neural network (BNN) was introduced to develop the probabilistic failure-mode–independent model, including the back propagation (BP) neural network and the Bayesian inference theory. Furthermore, the advantages of the developed model were demonstrated by comparing with the experimental data and existing deterministic predictions. Finally, a comprehensive parameter sensitivity analysis was conducted to examine the influence of column design parameters on the confidence interval of peak strength.
The experimental database used to develop the probabilistic model was collected from the PEER center, which consists of 251 specimens ([
- 1. Column width:
- 2. Column depth:
- 3. Equivalent cantilever length:
- 4. Compressive strength of concrete:
- 5. Yield strength of longitudinal reinforcement:
- 6. Yield strength of transverse reinforcement:
- 7. Longitudinal reinforcement ratio:
- 8. Transverse reinforcement ratio:
- 9. Axial load:
Graph
Table 1. Experimental database considered in this study.
No References Number of specimens Pattern 1 Aboutaha and Machado (1999) 3 305 508 1829 83.0 0 0 0.0253 0.0137 0–2058 FF 2 Aboutaha et al. (1999) 2 457–914 457–914 1219 16.0–21.9 400 434 0.0188 0.001–0.001 0 SF 3 Amitsu et al. (1991) 1 278 278 323 46.3 414 441 0.0412 0.009 2632 FS 4 Ang et al. (1981) 2 400 400 1200 23.6–25.0 280–320 427 0.0151 0.009–0.011 840–1435 FF 5 Arakawa et al. (1982) 1 250 250 375 20.6 323 393 0.0068 0.0089 429 FF 6 Arakawa et al. (1989) 2 180 180 225 31.8–33.0 249 340 0.0313 0.002 190–476 SF 7 Atalay and Penzien (1975) 10 305 305 1676 27.6–33.3 363–392 363–429 0.0163 0.004–0.006 267–801 FF 8 Azizinamini et al. (1988) 2 457 457 1372 39.3–39.8 454–616 439 0.0194 0.005–0.009 1690–2580 FF 9 Bayrak and Sheikh (1996) 8 305 305 1842 71.7–102.2 463–542 454 0.0258 0.012–0.030 2401–4468 FF 10 Bechtoula et al. (2002) 5 250–600 250–600 625–1200 32.2–39.2 485–524 388–461 0.017–0.024 0.005–0.009 705–8000 FF 11 Bett et al. (1985) 1 305 305 457 29.9 414 462 0.0244 0.0009 288 SF 12 Galeota et al. (1996) 24 250 250 1140 80.0 430 430 0.015–0.060 0.005–0.018 1000–1500 FF 13 Gill et al. (1979) 4 550 550 1200 21.4–41.4 294–375 316–375 0.0179 0.007–0.013 1815–4265 FF 14 Imai and Yamamoto (1986) 1 400 500 825 27.1 336 318 0.0266 0.0032 392 SF 15 Kanda et al. (1988) 6 250 250 750 24.8–27.9 352–506 374 0.0162 0.004 184 FF 16 Lynn et al. (1996) 6 457 457 1473 25.5–33.1 400 331 0.019–0.030 0.001–0.002 503–1512 FS 17 Lynn et al. (1998) 2 457 457 1473 25.5–33.1 400 331 0.0194 0.0007 503–1512 FS 18 Matamoros et al. (1999) 12 203 203 610 37.9–69.6 407–515 572–587 0.0193 0.01 0–569 FF 19 Mo and Wang (2000) 9 400 400 1400 24.9–27.5 460 497 0.0214 0.006–0.006 450–900 FF 20 Muguruma et al. (1989) 8 200 200 500 85.7–115.8 328–792 400 0.038 0.016 1176–2156 FF 21 Nagasaka (1982) 2 200 200 300 21.0–21.6 344 371 0.0127 0.008–0.014 147–294 FS 22 Nosho et al. (1996) 1 279 279 2134 40.6 351 407 0.0101 0.001 1076 FF 23 Ohno and Nishioka (1984) 3 400 400 1600 24.8 325 362 0.0142 0.003 127 FF 24 2 200 200 400 29.9–32.0 316 369–370 0.020–0.027 0.0048 183 FS 25 Ono et al. (1989) 2 200 200 300 25.8 426 361 0.0213 0.009 265–636 FS 26 Park and Paulay (1990) 1 400 600 1784 26.9 305 432 0.0188 0.0106 646 FF 27 Paultre and Legeron (2000) 6 305 305 2000 92.4–104.3 391–418 430–451 0.0215 0.009–0.019 1200–3600 FF 28 Paultre et al. (2001) 6 305 305 2000 92.4–109.5 391–825 446–451 0.0215 0.014–0.020 1200–5150 FF 29 Pujol (2002) 14 152 305 686 27.4–36.5 411 453 0.0245 0.005–0.011 133–267 FF 30 Saatcioglu and Grira (1999) 10 350 350 1645 34.0 570–580 428–478 0.020–0.033 0.004–0.011 831–1923 FF 31 Saatcioglu and Ozcebe (1989) 5 350 350 1000 32.0–43.6 425–470 430–438 0.0321 0.003–0.009 0–600 FF 32 Sakai et al. (1990) 7 250 250 500 99.5 344–1126 379 0.018–0.024 0.005–0.007 2176 FF 33 Sezen and Moehle (2002) 3 457 457 1473 21.1–21.8 476 434 0.0247 0.002 667–2669 FS 34 Soesianawati et al. (1986) 4 400 400 1600 40.0–46.5 255–364 446 0.0151 0.003–0.006 744–2112 FF 35 Sugano (1996) 5 225 225 450 118.0 1415–1424 393 0.0186 0.008–0.016 2089–3579 FF 36 Takemura and Kawashima (1997) 6 400 400 1245 33.2–36.8 368 363 0.0158 0.002 157 FF 37 Tanaka and Park (1990) 8 400–550 400–550 1600–1650 25.6–32.1 325–333 474–511 0.013–0.016 0.008–0.011 819–2913 FF 38 Thomsen and Wallace (1994) 11 152 152 597 67.5–102.7 793–1262 455–517 0.0245 0.004–0.007 0–418 FF 39 Umehara and Jirsa (1982) 3 230–410 230–410 455 34.9–42.0 414 441 0.0301 0.002–0.006 534–1068 SF 40 Watson and Park (1989) 5 400 400 1600 39.0–42.0 308–388 474 0.0151 0.003–0.023 3200–4704 FF 41 Wehbe et al. (1998) 4 380 610 2335 27.2–28.1 428 448 0.0222 0.003–0.004 601–1514 FF 42 Wight and Sozen (1973) 14 152 305 876 26.1–34.7 317–345 496 0.0245 0.003–0.015 111–189 FS 43 Xiao and Martirossyan (1998) 6 254 254 508 76.0–86.0 449–510 510 0.025–0.036 0.008–0.016 489–1068 FS 44 Zahn et al. (1986) 2 400 400 1600 28.3–40.1 466 440 0.0151 0.007–0.009 1010–2502 FF 45 Zhou et al. (1985) 3 80 80 80 32.3–34.0 341 336 0.0177 0.0039 124–189 FS 46 Zhou et al. (1987) 9 160 160 160–480 19.8–28.8 559 341 0.0222 0.007–0.010 406–517 FF/FS/SF Mean 251 289.7 314.7 1091 51.9 483.7 429.2 0.0237 0.0082 1234.6 Standard deviation 118.3 117.7 545.6 29.3 227.7 75.8 0.0101 0.0051 1379.6 Coefficient of variation 0.408 0.374 0.500 0.563 0.471 0.177 0.425 0.626 1.117 Minimum 80 80 80 16 0 0 0.0068 0.0007 0 Maximum 914 914 2335 118 1424 587 0.0603 0.0295 8000
1 Note: FF, SF, and FS represent the flexure-dominated, shear-dominated, and flexure-shear-dominated failure modes, respectively.
Graph: Figure 1.Statistical distribution of column design parameters in the complied experimental database.
In the experimental database, noted that the "actual" failure modes of RC columns were identified by [
Given the peak strength of RC columns is unavailable in the experimental database, each column is first standardized in an equivalent cantilever to reduce the influence of the testing configuration. Then, the envelop curves are extracted from the hysteresis curves in terms of the force-displacement relationship. Based on the obtained envelop curves, the maximum strength of RC columns along the positive and negative directions is identified. As shown in Figure 2, the identified maximum strength is not identical along the two directions, despite the specimen is designed and tested symmetrically. This demonstrates well that the prevailing uncertainties induced by experimental testing, concrete material properties, and measurement error are inevitable. To average such discrepancy along the two directions, the peak strength of RC columns is defined as the average values of the identified maximum strength.
Graph: Figure 2.Maximum strengths along the positive and negative directions for RC columns failing in different modes.
Based on the compiled experimental database, the hold-out method is adopted to categorize the experimental data into two subsets, namely, training subset and testing subset. The training subset is categorized to develop the model, whereas the testing subset is categorized to test the generalization capacity of the developed model. For the validation subset, it is not further separated from the training subset to avoid over-fitting because the BNN is advantageous in this problem by penalizing the highly complex model automatically. In the traditional ML algorithm, the validation subset is defined to validate the model as an early stop technique. This technique trains the model until the prediction error starts to increase for the validation subset. This is tedious and computationally expensive. In particular, separating the validation subset from the training subset is impractical if there are only limited experimental data, resulting in the model training has insufficient data. In this regard, the BNN is extremely applicable for the problem with limited experimental data. For the detailed description about the BNN to avoid over-fitting, interested readers can direct to [
For the optimal size between the training subset and the testing subset, there is no widely accepted criterion at present ([
Graph: Figure 3.Comparison of PDF for the whole dataset and both subsets.
Normalizing the input and output parameters is paramount because it can reduce the influence of model parameter magnitude. The normalization is generally dependent on the activation function used in BNN. Specifically, the input parameters are normalized with the following expression
Graph
where x
Graph
where t
The BNN was originally proposed by [
In the BNN, the BP neural network is the core element. Following the classical ANN algorithm, the BP neural network is composed of an input layer, several hidden layers and an output layer. In this study, the input layers are the main design parameters of RC columns. The hidden layer includes several neurons which receives the inputs from the previous layer, and then provides an output for the next layer by processing the input data. The output layer contains one or more processing units that produce the output of the network. Obviously, the structure of the hidden layer is unknown and it is dependent on the complexity of the target problem. If the structure of the hidden layer is too simple, the underlying trend of the experimental data cannot be adequately captured. Then, the generalization ability of the developed model is damaged. However, if the structure of the hidden layer is too complicated, the over-fitting may occur and the generalization ability of the developed model is also poor. Therefore, the trial-and-error method is commonly employed for the BP neural network to search for an optimal structure of the hidden layer by changing the number of hidden layers, the number of neurons and the type of activation functions, respectively.
Figure 4 shows the typical BP neural network used in this study. As observed, the established network includes nine neurons in the input layer, ten neurons in the hidden layer and one neuron in the output layer to predict the peak strength of RC columns. In mathematics, the established network relates the input parameters with the output parameter with the following expression
Graph
where x
Graph: Figure 4.Architecture of the typical BP neural network used in this study.
Following the BP algorithm, an optimization algorithm is applied to adjust the magnitude of w in iteration by minimizing the error of the network. For the procedures of adjusting the magnitude of w, interested readers can refer to [
Graph
where t
Graph
where α is the regularization coefficient, and
Graph
where m is the number of the weight parameters. For equation (
In the BNN, the Bayesian inference theory is introduced to treat w as a random variable rather than a deterministic one. In introducing the Bayesian inference theory for the established network, the objective function of the network should be modified by adding another regularization parameter, yielding
Graph
where β is the regularization coefficient to express the noise of the experimental data and α is the regularization coefficient to control the weight distribution of the developed model. Then, the posterior distribution of w can be determined by the Bayesian inference theory as
Graph
where D is the experimental database; p(w|a, β) is the prior distribution of w describing the knowledge of the weight before observing the experimental database; p(D|w, a, β) is the likelihood function of the network; and p(D|a, β) is a normalized factor to assure that the total probability of p(w|D, a, β) is equal to the unity. In the Bayesian inference theory, the normalized factor is also known as the evidence, having
Graph
It is obvious that evaluating the posterior distribution of w is to determine the prior distribution of w and the likelihood function of the network. According to the investigation by [
Graph
For the likelihood function of the network, the model prediction is expressed in PDF, so the probabilistic distribution of the prediction error is defined. Similar to the prior distribution of w, the probabilistic distribution of the prediction error can be described by a normal distribution with a zero mean and a standard deviation of 1/β ([
Graph
Substituting equations (
Graph
Then the next step is to find the maximization of equation (
Graph
where Δw=w-w
Graph
Submitting equation (
Graph
According to [
Graph
Comparing equation (
Graph
Differentiating the maximum of equation (
Figure 5 shows the flowchart of the above stated BNN to develop the probabilistic model for predicting the peak strength of RC columns. As observed, the first step is to draw samples from the prior distribution of w and determine the initial values of a and β randomly. The second step is to train the BP neural network by minimizing S(w) to find the most optimal w
Graph: Figure 5.Flowchart of incorporating the Bayesian inference theory with the BP neural network.
Following the above stated flowchart, a probabilistic model is developed in this study to predict the peak strength of RC columns failing in different modes. Table 2 enlists the most optimal value of w
Graph
Graph
Table 2. Weights and biases between the input and output layers.
Weights and biases Neurons in hidden layer 1 2 3 4 5 6 7 8 9 10 Input layer −0.120 0.253 −0.066 −0.120 −0.408 −0.097 0.032 −0.020 −0.071 −0.231 0.139 0.300 −0.025 −0.277 −0.181 −0.002 0.187 0.028 0.094 −0.323 0.008 −0.209 −0.104 0.014 0.444 0.349 −0.323 −0.339 0.130 0.381 −0.062 0.339 −0.237 −0.462 −0.061 0.072 −0.309 −0.523 −0.127 0.171 −0.237 −0.169 −0.217 −0.064 −0.093 0.009 0.128 −0.069 −0.022 0.225 −0.124 0.054 0.042 0.104 −0.201 0.348 −0.049 −0.041 −0.009 0.350 −0.097 −0.179 −0.042 0.149 −0.129 0.003 0.040 −0.233 −0.125 0.153 0.444 0.074 0.583 0.129 −0.124 0.097 −0.564 −0.131 0.065 0.160 0.182 −0.516 −0.209 −0.137 −0.052 −0.101 −0.053 −0.206 0.172 −0.106 0.187 0.354 −0.168 −0.371 0.541 0.553 −0.015 −0.219 −0.310 0.301 Output layer 0.629 0.543 −0.515 0.505 −0.583 −0.546 0.493 −0.459 0.705 0.394 −0.331 –– –– –– –– –– –– –– –– ––
Obviously, equation (
Graph
where y
Graph
where A is the established network and
Figure 6 shows the mean prediction against the experimental data of RC columns for the training subset and testing subset, respectively. As observed, the coefficients of determination R-squared (R
Graph: Figure 6.Comparison of mean prediction and experimental data for (a) training subset and (b) testing subset.
Graph: Figure 7.Comparison of mean prediction and experimental data for RC columns failing in different modes.
Graph: Figure 8.Standard deviation of peak strength for the training subset and testing subset.
Based on the mean and SD of peak strength predicted by the developed model, the confidence interval of peak strength can be defined accordingly. As shown in Figure 9, the confidence interval of peak strength is narrow because the SD of peak strength is less. In spite of this, almost all the experimental data can be covered by the confidence interval of peak strength. In particular, 98.9% and 87.3% of the training subset and testing subset are covered by the confidence interval in terms of the mean ±1 × SD, respectively. If the confidence interval of peak strength is defined by the mean ±2 × SD, 98.9% and 98.4% of the training subset and testing subset are covered, respectively. Compared to existing probabilistic models ([
Graph: Figure 9.Confidence interval of peak strength for the training subset and testing subset.
Based on the developed model, it is easy to achieve a balance of economic and safety for structural engineers to design RC columns. For example, the peak strength of RC columns can be defined at the mean −2 × SD if the specimen requires a significant conservative design, where the exact value will have a 98% probability to exceed the defined peak strength. If the specimen requires a moderate conservative design, the peak strength of RC columns can be defined at the mean −1 × SD, indicating that the exact value has an 84% probability to exceed the defined peak strength. If engineers wants to have an economic design but with less safety for the specimen, the peak strength of RC columns can be defined at the mean +1 × SD. In this case, the exact value only has 16% probability to exceed the defined peak strength.
To demonstrate the capability of the developed model, the commonly used deterministic peak strength models, e.g., the flexural strength model recommended by, and the shear strength model provided by [
Graph: Figure 10.Probabilistic calibration of deterministic prediction models.
Finally, a parameter sensitivity analysis is conducted to examine the influence of important design parameters on the confidence interval of peak strength. In parameter variation, the magnitude of column design parameters is varied individually one after another within the distribution ranges of the testing subset; while the magnitude of other column design parameters are fixed at the reference values. Without loss of generality, the median of the column design parameters in the testing subset is defined as the reference values, resulting in:
Figure 11 shows the variation of the confidence interval of peak strength in terms of the mean ±1× SD when the magnitude of column design parameters varies. As observed, the confidence interval of peak strength increases with the increase of B and H. The maximum increase amplitude of B and H is 5.6 and 29.1, respectively, for the mean prediction. This is reasonable because a larger cross-section commonly resists larger external force. For the increase of L, it is interesting to note that the confidence interval of peak strength deceases. The maximum decrease amplitude of the mean prediction is 8.4. This is also acceptable because L is an important parameter affecting the seismic behaviors of RC columns. The variation of L is related to the shear aspect ratio, which affects the relationship between the normal stress and the shear stress. In general, columns with a larger L tend to fail in flexure mode and columns with smaller L tend to fail in shear mode. Compared to the flexural-dominated columns, the shear-dominated columns have larger peak strength and lesser deformation ductility when the other parameters are maintained. For the increase of f
Graph: Figure 11.Parameter sensitivity analysis of column design parameters.
According to the above sensitivity analysis results, each of the considered column design parameters is ranked in a descending order. Figure 12 shows the tornado diagram in terms of the mean and SD of peak strength, respectively. As observed, H, L, and B are the most important parameters affecting the mean prediction, and the other design parameters affect the mean prediction slightly. Among them, the least sensitive design parameters are
Graph: Figure 12.Tornado diagrams of column design parameters for the mean and standard deviation prediction of peak strength.
A probabilistic approach was proposed in this study to develop a probabilistic model for predicting the peak strength of RC columns failing in different modes. According to the investigations, the following conclusions are drawn:
- (
1 ) The developed model can predict the peak strength of RC columns in terms of the confidence interval. If the confidence interval is defined as the mean ±1× SD, 98.9% and 87.3% of the experimental database in the training subset and testing subset are covered, respectively. If the confidence interval is defined by the mean ±2× SD, 98.9% and 98.4% of the experimental database in the training subset and testing subset are covered. Compared to existing probabilistic model, the developed model exhibits better performance to reduce the uncertainties in peak strength prediction. - (
2 ) The developed model can predict well the mean peak strength of RC columns. For the training subset, the mean prediction accuracy is 0.997, 0.997, and 0.998 for the flexure-dominated, flexure-shear-dominated, and shear-dominated columns, respectively. For the testing subset, the corresponding mean prediction accuracy is 0.957, 0.952, and 0.943, respectively. Therefore, the failure mode has less effect on the mean peak strength prediction of RC columns. - (
3 ) The developed model can be used to evaluate the prediction accuracy of existing deterministic models in probability. The peak strength of RC columns predicted by the deterministic models becomes a quantile of the PDF of peak strength. This is beneficial for engineers to solve the confusion, namely, which prediction is the most probable one in practice when several deterministic models exist for a specific specimen. - (
4 ) The increase of B, H, fc, and P leads to a growth of peak strength with a maximum increase amplitude of the mean prediction by 5.6, 29.1, 1.39, and 1.16, respectively. A shorter column specimen with smaller L leads to a larger peak strength, and the maximum decrease amplitude of the mean prediction is 8.4. For the increase of fy , fv ,v , H, and
Though the developed model shows great potentialities for the peak strength prediction of RC columns failing in different modes. There are also some limitations and future research directions. First, the problem itself is mainly concentrated on the peak strength of RC columns. There can be more potential possibilities for the problem without clear mechanical interpretation and the case with a large scatter prediction, for example, biaxial stiffness, deformation ductility, and torsional strength. Second, the number of the experimental data is limited due to the experimental testing cost. How to improve the generalization capacity of the developed model using the limited experimental data is still a universal issue in this field. Third, the developed model remains a black box in the context of data-driven approach. For the problem that has not been well solved, how to help the development of mechanical-based model will increase the persuasiveness of the developed model for professional structural engineers.
Chao-Lie Ning https://orcid.org/0000-0001-5643-1414
• B
- = Column sectional width
• H
- = Depth of cross-section
• L
- = Equivalent cantilever length
-
f
c - = Concrete compressive strength
-
f
v - = Yield strength of transverse reinforcement
-
f
y - = Yield strength of longitudinal reinforcement
-
ρ
v - = Transverse reinforcement ratio
- ρ
- = Longitudinal reinforcement ratio
• P
- = Applied axial load
-
F
e,max - = Absolute maximum effective force
-
F
0.004 - = Strength at the maximum strain of 0.004
-
x
i - = Input parameters
-
x
i,n - = Normalized input parameters
-
x
m - = mean of x
i -
σ
i - = Standard deviation of x
i -
t
i - = Experimental peak strength
-
t
i,n - = Normalized experimental peak strength
-
t
i,max - = Maximum value of t
i -
t
i,min - = Minimum value of t
i -
y
i - = Output of the network
-
y
m - = Mean peak strength prediction
- σ
- = Predicted variation of peak strength
• A
- = Established network
-
f
1 - = Activation functions of the hidden neurons
-
f
2 - = Activation functions of the output neurons
• b
- = Biases of the network
- ω
- = Weights of the network
• w
- = Parameter space including _Ii_ and ω
• N
- = The number of the experimental data
• m
- = The number of weight parameters
- α
- = Regularization coefficient to control the weight distribution of the developed model
- β
- = Regularization coefficient to express the noise of the experimental data
- p(w | a, β)
- = Prior distribution of w
- p(D | w, a, β)
- = Likelihood function of the network
- p(D | a, β)
- = Normalized factor
• D
- = Experimental database
• S(w)
- = Objective function
-
H
m - = Hessian matrix of S(w)
• FF
- = Flexural failure
• FS
- = Flexural-shear failure
• SF
- = Shear failure
• SD
- = Standard deviation
By Chao-Lie Ning; Meng Wang and Xiaohui Yu
Reported by Author; Author; Author