Prediction of falling weight deflectometer parameters using hybrid model of genetic algorithm and adaptive neuro-fuzzy inference system

A falling weight deflectometer is a testing device used in civil engineering to measure and evaluate the physical properties of pavements,such as the modulus of the subgrade reaction(Y1)and the elastic modulus of the slab(Y2),which are crucial for assessing the structural strength of pavements.In this study,we developed a novel hybrid artificial intelligence model,i.e.,a genetic algorithm(GA)-optimized adaptive neuro-fuzzy inference system(ANFIS-GA),to predict Y1 and Y2 based on easily determined 13 parameters of rigid pavements.The performance of the novel ANFIS-GA model was compared to that of other benchmark models,namely logistic regression(LR)and radial basis function regression(RBFR)algorithms.These models were validated using standard statistical measures,namely,the coefficient of correlation(R),mean absolute error(MAE),and root mean square error(RMSE).The results indicated that the ANFIS-GA model was the best at predicting Y1(R=0.945)and Y2(R=0.887)compared to the LR and RBFR models.Therefore,the ANFIS-GA model can be used to accurately predict Y1 and Y2 based on easily measured parameters for the appropriate and rapid assessment of the quality and strength of pavements.

Dynamic analysis of falling weight deflectometer

Falling weight deflectometer （FWD） testing has been used to evaluate structural condition of pavements to predict the layer moduli using backcalculation process. However, the predicted pavement layer moduli sometimes may not be accurate even if computed and measured deflection basin has fulfilled the standard and is in concurrence with certain tolerable limits. The characteristics of pavement structure, including pavement layer thickness condition and temperature variation, affect the predicted pavement structural capacity and back calculated layer modulus. The main objective of this study is to analyze the FVc＇D test results of flexible pavement in Western Australia to predict the pavement structural capacity. Collected data includes, in addition to FWD measurements, core data and pavement distress surveys. Results showed that the dynamic analysis of falling weight deflectometer test and prediction for the strength of character of flexible pavement layer moduli have been achieved, and algorithms for interpretation of the deflection basin have been improved. The variations of moduli of all layers along the length of sections for majority of the projects are accurate and consistent with measured and computed pre- diction. However, some of the projects had some inconsistent with modulus values along the length of the sections. Results are reasonable but consideration should be taken to fix varied pavement layers moduli sections.

Deterioration mechanism and rapid detection of performances of an existing subgrade in southern China

To relieve the increasing traffic load, many early built highways need to be widened or reconstructed. The rapid performance detection to existing subgrades is important to their reasonable evaluation and maximized utilization. Based on five kinds of soils taken from an existing highway in southern China, three commonly detecting methods were used to determine their moisture contents, compaction degrees and resilient moduli. The results showed that the measured moisture contents were greater than the design value, and the compaction degrees decreased sharply compared to the original ones. The moisture and heat exchange produced a decrease in the resilient modulus of plate loading test(PLT) from the standard 60 MPa down to 40 MPa. Afterwards, the portable falling weight deflectometer(PFWD) and dynamic cone penetrometer(DCP) were used to evaluate the subgrade performances. The measured PFWD moduli and the DCP penetration rates were correlated with the resilient moduli of PLT, deflections of the Beckman beam test, compaction degrees and moisture contents. The correlation analysis indicates that both of two methods are suitable in rapid detecting subgrade performances, but PFWD method is more recommended for it has higher accuracy and efficiency.

Effects of Temperature on the Dynamic Properties of Asphalt Mixtures

By using the falling weight deflectometer（FWD）,the dynamic loading tests on different thickness of asphalt mixture pavement in different temperature were performed.The experimental results show that the effects of temperature on dynamic properties of asphalt mixture are significant,and the thickness of asphalt mixture is also another important influence factor.The comparisons indicate that effect of temperature on the behaviors of dynamic loading properties and static loading properties of asphalt mixture were quite different.

Dynamic Response Solution of Multi-Layered Pavement Structure Under FWD Load Appling the Precise Integration Algorithm

The pavement layered structures are composed of surface layer,road base and multi-layered soil foundation.They can be undermined over time by repeated vehicle loads.In this study,a hybrid numerical method which can evaluate the displacement responses of pavement structures under dynamic falling weight deflectometer(FWD)loads.The proposed method consists of two parts:(a)the dynamic stiffness matrices of the points at the surface in the frequency domain which is based on the domain-transformation and dual vector form equation,and(b)interpolates the dynamic stiffness matrices by a continues rational function of frequency.The mixed variables formulation(MVF)can treat multiple degree of freedom systems with considering the coupling term between degree of freedoms.The accuracy of the developed method has been demonstrated by comparison between the proposed method and published results from the other method.Then the proposed method can be applied as a forward calculation technique to emulate the falling weight deflectometer test for multi-layered pavement structures.

Analysis of Road Base Uniformity via the Deviation of Modulus of Asphalt Mixtures

The modulus deviation of base material calculated from the data of falling weight deflectometer （FWD） was used to evaluate the uniformity of road base so as to reflect the construction quality. Four parameters,the repeatability standard deviation of the data in the same driveway, the reproducibility standard deviation of the data in the different driveway, the consistency statistics value of the data in the different driveway, and the consistency statistics value of the data in the same driveway, were introduced for the construction uniformity analysis. The experimental result shows that the materials modulus calculated from FWD has a highly correlative relationship with the uniformity of road base.

Structural Evaluation for Maputo Airport Pavement

Maputo Airport was initially constructed to serve mixed traffic of light and medium aircrafts. With its opening to heavier aircrafts such as B727, DC10, Airbus 340, etc. , structural improvements have become necessary. For this purpose, structural evaluation were described and performed using falling weight deflectometer. Results show that while subgrade response to loads appears more consistent with depth, surface layer of the pavement is significantly influenced by the layer thickness as well as mechanical properties of pavement materials. Load magnitude also affects pavement performance. But loading conditions show an equivalent or even greater influence on pavement performance.