Comparative Analysis of Machine Learning Models for Prediction of Remaining Service Life of Flexible Pavement

Evaluating Rutting Resistance of Rejuvenated Recycled Hot-Mix Asphalt Mixtures Using Different Types of Recycling Agents

Growing environmental pollution worldwide is mostly caused by the accumulation of different types of liquid and solid wastes. Therefore, policies in developed countries seek to support the concept of waste recycling due to its significant impact on the environmental footprint. Hot-mix asphalt mixtures (HMA) with reclaimed asphalt pavement (RAP) have shown great performance under rutting. However, incorporating a high percentage of RAP (>25%) is a challenging issue due to the increased stiffness of the resulting mixture. The stiffness problem is resolved by employing different types of commercial and noncommercial rejuvenators. In this study, three types of noncommercial rejuvenators (waste cooking oil (WCO), waste engine oil (WEO), and date seed oil (DSO)) were used, in addition to one type of commercial rejuvenator. Three percentages of RAP (20%, 40%, and 60%) were utilized. Mixing proportions for the noncommercial additives were set as 0−10% for mixtures with 20% RAP, 12.5−17.5% for mixtures with 40% RAP, and 17.5−20% for mixtures with 60% RAP. In addition, mixing proportions for the commercial additive were set as 0.5−1.0% for mixtures with 20% RAP, 1.0−1.5% for mixtures with 40% RAP, and 1.5−2.0% for mixtures with 60% RAP. The rutting performance of the generated mixtures was indicated first by using the rutting index (G*/sin δ) for the combined binders and then evaluated using the Hamburg wheel-track test. The results showed that the rejuvenated mixtures with the commercial additive at 20 and 60% RAP performed well compared to the control mixture, whereas the rejuvenated ones at 40% RAP performed well with noncommercial additives in comparison to the control mixture. Furthermore, the optimum percentages for each type of the used additives were obtained, depending on their respective performance, as 10%, 12.5%, and 17.5% of WCO, 10%, 12.5−17.5%, and 17.5% of WEO, <10%, 12.5%, and 17.5% of DSO, and 0.5−1.0%, 1.0%, and 1.5−2.0% of the commercial rejuvenator, corresponding to the three adopted percentages of RAP.

Prediction of International Roughness Index Based on Stacking Fusion Model

Pavement performance prediction is necessary for road maintenance and repair (M&R) management and plans. The accuracy of performance prediction affects the allocation of maintenance funds. The international roughness index (IRI) is essential for evaluating pavement performance. In this study, using the road pavement data of LTPP (Long-Term Pavement Performance), we screened the feature parameters used for IRI prediction using the mean decrease impurity (MDI) based on random forest (RF). The effectiveness of this feature selection method was proven suitable. The prediction accuracies of four promising prediction models were compared, including Gradient Boosting Decision Tree (GBDT), eXtreme Gradient Boosting (XGBoost), support vector machine (SVM), and multiple linear regression (MLR). The two integrated learning algorithms, GBDT and XGBoost, performed well in prediction. GBDT performs best with the lowest root mean square error (RMSE) of 0.096 and the lowest mean absolute error (MAE) of 6.2% and the coefficient of determination (R2) reaching 0.974. However, the prediction accuracy varies in numerical intervals, with some deviations. The stacking fusion model with a powerful generalization capability is proposed to build a new prediction model using GBDT and XGBoost as the base learners and bagging as the meta-learners. The R2, RMSE, and MAE of the stacking fusion model are 0.996, 0.040, and 1.3%, which further improves the prediction accuracy and verifies the superiority of this fusion model in pavement performance prediction. Besides, the prediction accuracy is generally consistent across different numerical intervals.

Nonlinear Regression-Based GNSS Multipath Modelling in Deep Urban Area

As the necessity of location information closely related to everyday life has increased, the use of global navigation satellite systems (GNSS) has gradually increased in populated urban areas. Contrary to the high necessity and expectation of GNSS in urban areas, GNSS performance is easily degraded by multipath errors due to high-rise buildings and is very difficult to guarantee. Errors in the signals reflected by the buildings, i.e., multipath and non-line-of-sight (NLOS) errors, are the major cause of the poor accuracy in urban areas. Unlike other GNSS major error sources, the reflected signal error, which is a user-dependent error, is difficult to differentiate or model. This paper suggests training a multipath prediction model based on support vector regression to obtain a function of the elevation and azimuth angle of each satellite. To extract an unbiased multipath from the GNSS measurements, the clock error of high-elevation QZSS was estimated, and the clock offset with other constellations was also calculated. A nonlinear multipath map was generated, as a result of training with the extracted multipaths, by a Support Vector Machine, which appropriately reflected the geometry of the building near the user. The model was effective at improving the urban area positioning accuracy by 58.4% horizontally and 77.7% vertically, allowing us to achieve a 20 m accuracy level in a deep urban area, Teheran-ro, Seoul, Korea.

Application of Analytical Hierarchy Process for Structural Health Monitoring and Prioritizing Concrete Bridges in Iran

This paper proposes a method for monitoring the structural health of concrete bridges in Iran. In this method, the bridge condition index (BCI) of bridges is determined by the analytical hierarchy process (AHP). BCI constitutes eight indices that are scored based on the experts’ views, including structural, hydrology and climate, safety, load impact, geotechnical and seismicity, strategic importance, facilities, and traffic and pavement. Experts’ views were analyzed by Expert Choice software, and the relative importance (weight) of all eight indices were determined using AHP. Moreover, the scores of indices for various conditions were extracted from experts’ standpoints. BCI defines as the sum of weighted scores of indices. Bridge inspectors can examine the bridge, determine the scores of indices, and compute BCI. Higher values of BCI indicate better conditions. Therefore, bridges with lower BCI take priority in maintenance activities. As the case studies, the authors selected five bridges in Iran. Successful implementation of the proposed method for these case studies verified that this method can be applied as an easy-to-use optimization tool in health monitoring and prioritizing programs.

The Effect of Incorporating Industrials Wastewater on Durability and Long-Term Strength of Concrete

Concrete, as one of the essential construction materials, is responsible for a vast amount of emissions. Using recycled materials and gray water can considerably contribute to the sustainability aspect of concrete production. Thus, finding a proper replacement for fresh water in the production of concrete is significant. The usage of industrial wastewater instead of water in concrete is considered in this paper. In this study, 450 concrete samples are produced with different amounts of wastewater. The mechanical parameters, such as slump, compressive strength, water absorption, tensile strength, electrical resistivity, rapid freezing, half-cell potential and appearance, are investigated, and a specific concentration and impurities of wastewater that cause a 10% compressive strength reduction were found. The results showed that the usage of industrial wastewater does not significantly change the main characteristics of concrete. Although increasing the concentration of wastewater can decrease the durability and strength features of concrete nonlinearly, the negative effects on durability tests are more conspicuous, as utilizing concentrated wastewaters disrupt the formation of appropriate air voids, pore connectivity and pore-size distribution in the concrete.

Waterlogging Resistance Evaluation Index and Photosynthesis Characteristics Selection: Using Machine Learning Methods to Judge Poplar’s Waterlogging Resistance

Flood disasters are the major natural disaster that affects the growth of agriculture and forestry crops. Due to rapid growth and strong waterlogging resistance characteristics, many studies have explained the waterlogging resistance mechanism of poplar from different perspectives. However, there is no accurate method to define the evaluation index of waterlogging resistance. In addition, there is also a lack of research on predicting the waterlogging resistance of poplars. Based on the changes of poplar biomass and seedling height, the evaluation index of poplar resistance to waterlogging was well determined, and the characteristics of photosynthesis were used to predict the waterlogging resistance of poplars. First, four methods of hierarchical clustering, lasso, stepwise regression and all-subsets regression were used to extract the photosynthesis characteristics. After that, the support vector regression model of poplar resistance to waterlogging was established by using the characteristic parameters of photosynthesis. Finally, the results show that the SVR model based on Stepwise regression and Lasso method has high precision. On the test set, the coefficient of determination (R2) was 0.8581 and 0.8492, the mean square error (MSE) was 0.0104 and 0.0341, and the mean relative error (MRE) was 9.78% and 9.85%, respectively. Therefore, using the characteristic parameters of photosynthesis to predict the waterlogging resistance of poplars is feasible.

A Novel Life Prediction Model Based on Monitoring Electrical Properties of Self-Sensing Cement-Based Materials

Assessing the damage level in concrete infrastructures over time is a critical issue to plan their timely maintenance with proper actions. Self-sensing concretes offer new opportunities for damage assessment by monitoring their electrical properties and relating their variations to damage levels. In this research, fatigue tests were conducted to study the response of a self-sensing concrete under high-cycle dynamic loading. The concept of G-value was defined as the slope of the voltage response baseline of the self-sensing concrete over time that reflects the damage created under the fatigue-loading test. Based on this definition, log (G)–log (N) curves were obtained using a linear regression approach, with N representing the number of cycles during the fatigue tests. While traditional fatigue curves S-log (N) are used to estimate the remaining life under fatigue loading, log (G)–log (N) diagrams can be used to determine the damage level based on the voltage response of the self-sensing concrete as a function of the loading history. This finding can be useful for the estimation of the lifetime and remaining life of self-sensing concrete structures and infrastructure, eventually helping to optimize the related maintenance operations.

Smart Structural Health Monitoring of Flexible Pavements Using Machine Learning Methods

The pavement is a complex structure that is influenced by various environmental and loading conditions. The regular assessment of pavement performance is essential for road network maintenance. International roughness index (IRI) and pavement condition index (PCI) are well-known indices used for smoothness and surface condition assessment, respectively. Machine learning techniques have recently made significant advancements in pavement engineering. This paper presents a novel roughness-distress study using random forest (RF). After determining the PCI and IRI values for the sample units, the PCI prediction process is advanced using RF and random forest trained with a genetic algorithm (RF-GA). The models are validated using correlation coefficient (CC), scatter index (SI), and Willmott’s index of agreement (WI) criteria. For the RF method, the values of the three parameters mentioned were −0.177, 0.296, and 0.281, respectively, whereas in the RF-GA method, −0.031, 0.238, and 0.297 values were obtained for these parameters. This paper aims to fulfill the literature’s identified gaps and help pavement engineers overcome the challenges with the conventional pavement maintenance systems.

Classification-Based Regression Models for Prediction of the Mechanical Properties of Roller-Compacted Concrete Pavement

In the field of pavement engineering, the determination of the mechanical characteristics is one of the essential processes for reliable material design and highway sustainability. Early determination of the mechanical characteristics of pavement is essential for road and highway construction and maintenance. Tensile strength (TS), compressive strength (CS), and flexural strength (FS) of roller-compacted concrete pavement (RCCP) are crucial characteristics. In this research, the classification-based regression models random forest (RF), M5rule model tree (M5rule), M5prime model tree (M5p), and chi-square automatic interaction detection (CHAID) are used for simulation of the mechanical characteristics of RCCP. A comprehensive and reliable dataset comprising 621, 326, and 290 data records for CS, TS, and FS experimental cases was extracted from several open sources in the literature. The mechanical properties are determined based on influential input combinations that are processed using principle component analysis (PCA). The PCA method specifies that volumetric/weighted content forms of experimental variables (e.g., coarse aggregate, fine aggregate, supplementary cementitious materials, water, and binder) and specimens’ age are the most effective inputs to generate better performance. Several statistical metrics were used to evaluate the proposed classification-based regression models. The RF model revealed an optimistic classification capacity of the CS, TS, and FS prediction of the RCCP in comparison with the CHAID, M5rule, and M5p models. Monte-Carlo simulation was used to verify the results in terms of the uncertainty and sensitivity of variables. Overall, the proposed methodology formed a reliable soft computing model that can be implemented for material engineering, construction, and design.

Intelligent Road Inspection with Advanced Machine Learning; Hybrid Prediction Models for Smart Mobility and Transportation Maintenance Systems

Prediction models in mobility and transportation maintenance systems have been dramatically improved by using machine learning methods. This paper proposes novel machine learning models for an intelligent road inspection. The traditional road inspection systems based on the pavement condition index (PCI) are often associated with the critical safety, energy and cost issues. Alternatively, the proposed models utilize surface deflection data from falling weight deflectometer (FWD) tests to predict the PCI. Machine learning methods are the single multi-layer perceptron (MLP) and radial basis function (RBF) neural networks as well as their hybrids, i.e., Levenberg–Marquardt (MLP-LM), scaled conjugate gradient (MLP-SCG), imperialist competitive (RBF-ICA), and genetic algorithms (RBF-GA). Furthermore, the committee machine intelligent systems (CMIS) method was adopted to combine the results and improve the accuracy of the modeling. The results of the analysis have been verified through using four criteria of average percent relative error (APRE), average absolute percent relative error (AAPRE), root mean square error (RMSE) and standard error (SE). The CMIS model outperforms other models with the promising results of APRE = 2.3303, AAPRE = 11.6768, RMSE = 12.0056 and SD = 0.0210.