Limits...
Re-evaluation of the AASHTO-flexible pavement design equation with neural network modeling.

Tiğdemir M - PLoS ONE (2014)

Bottom Line: The existing AASHTO flexible pavement design equation does not currently predict the pavement performance of the strategic highway research program (Long Term Pavement Performance studies) test sections very accurately, and typically over-estimates the number of equivalent single axle loads needed to cause a measured loss of the present serviceability index.Here we aimed to demonstrate that the proposed neural network model can more accurately represent the loads values data, compared against the performance of the AASHTO formula.It is concluded that the neural network may be an appropriate tool for the development of databased-nonparametric models of pavement performance.

View Article: PubMed Central - PubMed

Affiliation: Department of Civil Engineering, Süleyman Demirel University, Engineering Faculty, Isparta, Turkey.

ABSTRACT
Here we establish that equivalent single-axle loads values can be estimated using artificial neural networks without the complex design equality of American Association of State Highway and Transportation Officials (AASHTO). More importantly, we find that the neural network model gives the coefficients to be able to obtain the actual load values using the AASHTO design values. Thus, those design traffic values that might result in deterioration can be better calculated using the neural networks model than with the AASHTO design equation. The artificial neural network method is used for this purpose. The existing AASHTO flexible pavement design equation does not currently predict the pavement performance of the strategic highway research program (Long Term Pavement Performance studies) test sections very accurately, and typically over-estimates the number of equivalent single axle loads needed to cause a measured loss of the present serviceability index. Here we aimed to demonstrate that the proposed neural network model can more accurately represent the loads values data, compared against the performance of the AASHTO formula. It is concluded that the neural network may be an appropriate tool for the development of databased-nonparametric models of pavement performance.

Show MeSH

Related in: MedlinePlus

Regression plot of KESALs predictions for target (AASHTO Equation produced) with model output of ANN (7 inputs).
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4232605&req=5

pone-0113226-g004: Regression plot of KESALs predictions for target (AASHTO Equation produced) with model output of ANN (7 inputs).

Mentions: Because of an absence of rain data for some sections, 234 of a total of 244 sections were employed for modeling. The training data-set, comprising 164 random sections of 234 available (70%), was initially chosen for the learning stage. The NN model produced excellent results, as illustrated in Figure 4, which shows the training targets (predicted KESALs by AASHTO equation) and the network outputs (computed KESALs values). The correlation coefficient for the training stage was high (R2 = 0.999). Of the remaining 30% of the data-set, 15% of the sections were used to validate the model and another 15% were used to test the model. Predictions were good despite a higher dispersion than in the learning stage. The correlation coefficient for the validation stage was R2 = 0.990.


Re-evaluation of the AASHTO-flexible pavement design equation with neural network modeling.

Tiğdemir M - PLoS ONE (2014)

Regression plot of KESALs predictions for target (AASHTO Equation produced) with model output of ANN (7 inputs).
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4232605&req=5

pone-0113226-g004: Regression plot of KESALs predictions for target (AASHTO Equation produced) with model output of ANN (7 inputs).
Mentions: Because of an absence of rain data for some sections, 234 of a total of 244 sections were employed for modeling. The training data-set, comprising 164 random sections of 234 available (70%), was initially chosen for the learning stage. The NN model produced excellent results, as illustrated in Figure 4, which shows the training targets (predicted KESALs by AASHTO equation) and the network outputs (computed KESALs values). The correlation coefficient for the training stage was high (R2 = 0.999). Of the remaining 30% of the data-set, 15% of the sections were used to validate the model and another 15% were used to test the model. Predictions were good despite a higher dispersion than in the learning stage. The correlation coefficient for the validation stage was R2 = 0.990.

Bottom Line: The existing AASHTO flexible pavement design equation does not currently predict the pavement performance of the strategic highway research program (Long Term Pavement Performance studies) test sections very accurately, and typically over-estimates the number of equivalent single axle loads needed to cause a measured loss of the present serviceability index.Here we aimed to demonstrate that the proposed neural network model can more accurately represent the loads values data, compared against the performance of the AASHTO formula.It is concluded that the neural network may be an appropriate tool for the development of databased-nonparametric models of pavement performance.

View Article: PubMed Central - PubMed

Affiliation: Department of Civil Engineering, Süleyman Demirel University, Engineering Faculty, Isparta, Turkey.

ABSTRACT
Here we establish that equivalent single-axle loads values can be estimated using artificial neural networks without the complex design equality of American Association of State Highway and Transportation Officials (AASHTO). More importantly, we find that the neural network model gives the coefficients to be able to obtain the actual load values using the AASHTO design values. Thus, those design traffic values that might result in deterioration can be better calculated using the neural networks model than with the AASHTO design equation. The artificial neural network method is used for this purpose. The existing AASHTO flexible pavement design equation does not currently predict the pavement performance of the strategic highway research program (Long Term Pavement Performance studies) test sections very accurately, and typically over-estimates the number of equivalent single axle loads needed to cause a measured loss of the present serviceability index. Here we aimed to demonstrate that the proposed neural network model can more accurately represent the loads values data, compared against the performance of the AASHTO formula. It is concluded that the neural network may be an appropriate tool for the development of databased-nonparametric models of pavement performance.

Show MeSH
Related in: MedlinePlus