scholarly journals A weighted multi-output neural network model for the prediction of rigid pavement deterioration

2020 ◽  
Author(s):  
Fengdi Guo ◽  
Xingang Zhao ◽  
Jeremy Gregory ◽  
Randolph Kirchain
Keyword(s):  
Neural Network ◽  
Longitudinal Crack ◽  
Condition Index ◽  
Prediction Performance ◽  
Pavement Management ◽  
Pavement Condition ◽  
Single Output ◽  
Rigid Pavements ◽  
Model Training ◽  
Condition Metric

A novel weighted multi-output neural network (NN) model is proposed for predicting the deterioration of rigid pavements based on Iowa pavement management system data. This first-of-a-kind model simultaneously predicts four pavement condition metrics concerning rigid pavements, including IRI, faulting, longitudinal crack and transverse crack. It provides an opportunity to efficiently evaluate pavement conditions and to make treatment decisions based on multi-condition metrics, such as the pavement condition index (PCI) for budget allocation models. Compared to traditional single-output NN models, this multi-output model is capable of incorporating correlations among different condition metrics. During model training, each condition metric is assigned a weight to reflect its relative importance. When the weights equal to those in the formula for the multi-condition metric, the prediction performance for PCI is optimal (13% lower MSE than optimal, single-output models). The multi-output model improves on the prediction performance for three of the four individual condition metrics compared to optimal single-output models. Results show that the consideration of correlations could improve the prediction performance for single and multi-condition metrics. Finally, variable weighting is critical for achieving the optimal balance of prediction performance among the various metrics as dictated by the needs of the decisionmaker.

Pavement management with dynamic traffic and artificial neural network: a case study of Montreal

2016 ◽  
Vol 43 (3) ◽  
pp. 241-251 ◽  
Author(s):  
Md. Shohel Reza Amin ◽  
Luis E. Amador-Jiménez
Keyword(s):  
Neural Network ◽  
Linear Programming ◽  
Travel Demand ◽  
Learning Algorithm ◽  
Good Condition ◽  
Condition Index ◽  
Pavement Management ◽  
Pavement Performance ◽  
Pavement Condition ◽  
Demand Models

This study improves the pavement management system by developing a linear programming optimization for the road network of the City of Montreal with simulated traffic for a period of 50 years and deals with the uncertainty of pavement performance modeling. Travel demand models are applied to simulate annual average daily traffic (AADT) every 5 years. A backpropagation neural network (BPN) with a generalized delta rule learning algorithm is applied to develop pavement performance models without uncertainties. Linear programming of life-cycle optimization is applied to develop maintenance and rehabilitation strategies to ensure the achievement of good levels of pavement condition subject to a given maintenance budget. The BPN network estimated that PCI values were predominantly determined by the differences in pavement condition index, AADT, and equivalent single axle loads. Dynamic linear programming optimization estimated that CAD$150 million is the minimum annual budget required to keep most of the arterial and local roads in good condition in Montreal.

scholarly journals Proposal and Implementation of a Heliport Pavement Management System: Technical and Economic Comparison of Maintenance Strategies

2021 ◽  
Vol 13 (16) ◽  
pp. 9201 ◽  
Author(s):  
Paola Di Mascio ◽  
Alessio Antonini ◽  
Piero Narciso ◽  
Antonio Greto ◽  
Marco Cipriani ◽  
...  
Keyword(s):  
Management System ◽  
Condition Index ◽  
Pavement Management ◽  
Pavement Management System ◽  
Pavement Condition ◽  
Airport Pavement ◽  
Maintenance And Rehabilitation ◽  
Pavement Condition Index ◽  
Rotary Wing ◽  
Economic Comparison

Maintenance and rehabilitation (M&R) scheduling for airport pavement is supported by the scientific literature, while a specific tool for heliport pavements lacks. A heliport pavement management system (HPMS) allows the infrastructure manager to obtain benefits in technical and economic terms, as well as safety and efficiency, during the analyzed period. Structure and rationale of the APSM could be replicated and simplified to implement a HPMS because movements of rotary-wing aircrafts have less complexity than fixed-wing ones and have lower mechanical effects on the pavement. In this study, an innovative pavement condition index-based HPMS has been proposed and implemented to rigid and flexible surfaces of the airport of Vergiate (province of Varese, Italy), and two twenty-year M&R plans have been developed, where the results from reactive and proactive approaches have been compared to identify the best strategy in terms of costs and pavement level of service. The result obtained shows that although the loads and traffic of rotary-wing aircrafts are limited, the adoption of PMS is also necessary in the heliport environment.

Estimation of Pavement Serviceability Index Through Android-Based Smartphone Application for Local Roads

2017 ◽  
Vol 2639 (1) ◽  
pp. 129-135 ◽  
Author(s):  
Waleed Aleadelat ◽  
Khaled Ksaibati
Keyword(s):  
Smartphone Application ◽  
Condition Index ◽  
Pavement Management ◽  
Pavement Condition ◽  
Explanatory Variables ◽  
Pavement Condition Index ◽  
Local Roads ◽  
Series Acceleration ◽  
The Difference ◽  
The Cost

The Wyoming Technology Transfer Center is in the process of developing a pavement management system (PMS) for county paved roads in Wyoming. This PMS uses the present serviceability index (PSI) as a main pavement performance parameter. This PMS depends on pavement condition index, international roughness index, and pavement rutting as explanatory variables to estimate PSI. This study researched new explanatory variables measured by using smartphones’ sensors to estimate PSI. It was found that the variance of the signals (time series acceleration data) acquired by smartphones’ accelerometers could work as a very good explanatory variable to estimate PSI. Two models were developed with high significance ( R2 higher than .9) to predict PSI using the variance of smartphone signals. The initial validation results suggested that using these models could predict, with high certainty, the actual PSI values. The difference between the predicted and the actual PSI values was not statistically different. The study was performed on 20 roadway segments extracted from the Wyoming county roads’ PMS database. In addition, the selected segments had various lengths and geometric features reflecting various roadway segments under any PMS. The proposed methodology is intended to lower the cost of measuring county roads’ pavement conditions by estimating PSI directly without the reliance on the direct measurement of pavement condition parameters.

scholarly journals Comparison of Pavement Performance Models for Urban Road Management System

2020 ◽  
Vol 15 (3) ◽  
pp. 111-129
Author(s):  
Igoris Kravcovas ◽  
Audrius Vaitkus ◽  
Rita Kleizienė
Keyword(s):  
Bearing Capacity ◽  
Management System ◽  
Condition Index ◽  
Performance Model ◽  
Pavement Management ◽  
Pavement Performance ◽  
Performance Models ◽  
Climate Conditions ◽  
Pavement Condition ◽  
Pavement Performance Model

The key factors for effective pavement management system (PMS) are timely preservation and rehabilitation activities, which provide benefit in terms of drivers’ safety, comfort, budget and impact on the environment. In order to reasonably plan the preservation and rehabilitation activities, the pavement performance models are used. The pavement performance models are usually based on damage and distress observations of rural roads, and can be applied to forecast the performance of urban roads. However, the adjustment of the parameters related to traffic volume, speed and load, climate conditions, and maintenance has to be made before adding them to PMS for urban roads. The main objective of this study is to identify the performance indicators and to suggest pavement condition establishment methodology of urban roads in Vilnius. To achieve the objective, the distresses (rut depth and cracks), bearing capacity, and international roughness index (IRI) were measured for fifteen urban roads in service within a two-year period. The distresses, rut depth and IRI were collected with the Road Surface Tester (RST) and bearing capacity of pavement structures were measured with a Falling Weight Deflectometer (FWD). The measured distresses were compared to the threshold values identified in the research. According to the measured data, the combined pavement condition indices using two methodologies were determined, as well as a global condition index for each road. The analysed roads were prioritized for maintenance and rehabilitation in respect to these criteria. Based on the research findings, the recommendations for further pavement condition monitoring and pavement performance model implementation to PMS were highlighted.

scholarly journals Assessment of Al-Amarah street within the Al-kut city using pavement condition index (PCI) and GIS technique

2018 ◽  
Vol 162 ◽  
pp. 01033
Author(s):  
Mohammed Al-Neami ◽  
Rasha Al-Rubaee ◽  
Zainab Kareem
Keyword(s):  
Condition Index ◽  
Pavement Management ◽  
Pavement Condition ◽  
The Road ◽  
Gis Technique ◽  
Gis Data ◽  
Pavement Condition Index ◽  
Specific Sign ◽  
Maintenance Process

The capabilities of geographical system and their spatial analysis is considered the most appropriate tools to enhance pavement management operations, with features such as graphical display of pavement condition. In Iraq, most of transportation agencies do not have a tool that is used as a database for road deteriorations, so there is a need for road surveying and storing the collected information in GIS to know the condition of every road with details. Furthermore, these data can be used for maintenance process and estimation of prior cost. This research has been carried out to estimate of flexible pavement condition through visual surveys using the Pavement Condition Index (PCI) method; so it can provide an easy way to calculate the PCI based on GIS data with Micro PAVER software 5.2. Al-Amarah Street, which is internal road in Al-Kut city in the eastern part of Iraq, is used as a case study. The average pavement condition index of the selected case study is found to be “64” using Micro PAVER 5.2 software which mean “Fair” pavement condition. Arc Map 9.3 has been applied in this study to make an integrated maintenance system for each road in the region demonstrating the annual road deteriorations and the resulting change in the PCI values which occurs every year. The study provides an easy and simplified way of presentation the details of deteriorations on the satellite or the geographical map of the road in which each type of distress has been symbolized with specific sign and each PCI value has been represented with specific color.

scholarly journals Evaluation of Asphalt Concrete Airport Pavement Conditions Based on the Airfield Pavement Condition Index (APCI) in Scope of Flight Safety

Aerospace ◽  
2020 ◽  
Vol 7 (6) ◽  
pp. 78
Author(s):  
Mariusz Wesołowski ◽  
Paweł Iwanowski
Keyword(s):  
Quality Management System ◽  
Condition Index ◽  
Assessment Method ◽  
Technical Condition ◽  
Pavement Management ◽  
Infrastructure Development ◽  
Pavement Condition ◽  
Airport Pavement ◽  
Pavement Condition Index ◽  
High Level

Airoport infrastructure development requires care to maintain it in proper technical condition. Due to this, airport pavements should be constantly monitored, and, above all, correctly managed. High-level airport pavement management requires access to reliable information about their current technical condition as well as proper forecasting of this condition in the future. Obtaining good quality information about the technical condition of airport pavement should be based on a proven methodology, taking into account the introduced quality management system. The authors propose a method of technical pavement condition assessment based on the Airfield Pavement Condition Index (APCI), taking into account not only the results of the surface deterioration inventory, but also repair overviews, load bearing capacity, evenness and roughness of the surface, as well as the surface tensile bond strength. The method was developed during long-term work financed by the Ministry of Science and Higher Education. At the beginning of the article, the authors focus on reviewing the currently available methods of assessing the technical condition of the pavement. Then they briefly present the most popular surface assessment method based on the PCI indicator. Afterwards, a proprietary asphalt pavement assessment method based on the APCI indicator is proposed and an example of how to use the method is presented. Finally, they discuss the results and summarize the work done, and present further directions of work.

scholarly journals Use of Deep Learning to Study Modeling Deterioration of Pavements a Case Study in Iowa

2020 ◽  
Vol 5 (11) ◽  
pp. 95
Author(s):  
Seyed Amirhossein Hosseini ◽  
Ahmad Alhasan ◽  
Omar Smadi
Keyword(s):  
Short Term Memory ◽  
Weighted Average ◽  
Condition Index ◽  
The State ◽  
Pavement Management ◽  
Department Of Transportation ◽  
Pavement Condition ◽  
Process And Outcome ◽  
Pavement Condition Index

This paper describes the process and outcome of deterioration modeling for three different pavement types (asphalt, concrete, and composite) in the state of Iowa. Pavement condition data is collected by the Iowa Department of Transportation (DOT) and stored in a Pavement-Management Information System (PMIS). In the state of Iowa, the overall pavement condition is quantified using the Pavement Condition Index (PCI), which is a weighted average of indices representing different types of distress, roughness, and deflection. Deterioration models of PCI as a function of time were developed for the different pavement types using two modeling approaches. The first approach is the long/short-term memory (LSTM), a subset of a recurrent neural network. The second approach, used by the Iowa DOT, is developing individual regression models for each section of the different pavement types. A comparison is made between the two approaches to assess the accuracy of each model. The results show that the LSTM model achieved a higher prediction accuracy over time for all different pavement types.

Development of Adaptive Performance Models for Oklahoma Airfield Pavement Management System

2003 ◽  
Vol 1853 (1) ◽  
pp. 44-54 ◽  
Author(s):  
Jie Yuan ◽  
Michael A. Mooney
Keyword(s):  
Management System ◽  
Condition Index ◽  
Pavement Management ◽  
General Aviation ◽  
Portland Cement Concrete ◽  
Performance Models ◽  
Pavement Management System ◽  
Pavement Condition ◽  
Maintenance And Rehabilitation ◽  
The Family

The Oklahoma airfield pavement management system (APMS) is a set of pavement management tools that can assist with pavement condition evaluation, as well as prioritization and scheduling of pavement maintenance and rehabilitation activities. Pavement performance models were developed to support the APMS for more than 70 Oklahoma general aviation airports. The family modeling method based on the pavement condition index was tailored to fit the deterioration characteristics of these airfield pavements. The statistical and engineering significance of seven levels of pavement factors was investigated, and pavement factors that affect pavement deterioration significantly were identified as family variables. Asphalt concrete pavement families were formed by sorting pavement function, distress cause, and pavement thickness, while portland cement concrete pavements were divided into families according to pavement function and climate zone. The family polynomial curves were able to reveal the expected deterioration patterns and are logical in engineering principle. Rooted by an adaptive database, the system accepts expert opinion and automatically integrates effects of major maintenance and rehabilitation activities into modeling. From the up-to-date database, the performance models update forecasts automatically.

scholarly journals EVALUASI KONDISI PERKERASAN JALAN DENGAN MENGGUNAKAN METODE PAVEMENT CONDITION INDEX (PCI) (STUDI KASUS RUAS JALAN BEUREUNUEN – BATAS KEUMALA)

2018 ◽  
Vol 1 (3) ◽  
pp. 761-768
Author(s):  
Yuswardi Ramli ◽  
Muhammad Isya ◽  
Sofyan M. Saleh
Keyword(s):  
Longitudinal Crack ◽  
Condition Index ◽  
Functional Condition ◽  
Primary Data ◽  
Pavement Condition ◽  
The Road ◽  
Periodic Maintenance ◽  
Pavement Condition Index ◽  
Length Width ◽  
Actual Field

Abstract: In order to accommodate the needs of movement with a certain level of service, it is necessary to make an effort to maintain the quality of road services, where one of these efforts is to evaluate the condition of the road surface. Based on the above condition, a research is needed in order to evaluate the condition of pavement in accordance with the type and level of damage by using PCI method.This research was aimed to know the functional condition of pavement on road of Beureunuen - Keumala Border. This research took place on the Beureunuen - Keumala road border which was divided into 2 segments; segment I (Km 7 + 000 s / d Km 9 + 000) and segment II (Km.13 + 000 s / d Km.15+ 000). The primary data collection was done with actual field survey data in the form of length, width, area, and depth of each type of damage that indicates the condition of the roads surface both minor and severe damages. This research was conducted by using Pavement Condition Index (PCI) methods. The results shows that the most common types of damage that occur on road of Beureunuen - Keumala Border are alligator crack, block crack, depression, corrugations, edge crack, rutting, longitudinal crack, patching, potholes, and raveling. Evaluation of damage on segment I of the road on Beureunuen - Keumala border gives result of the average PCI value on segment I of the road on Beureunuen - Keumala is 39,6 with bad condition. The average PCI value of Segment II is 24.7 with very bad condition. The type of maintenance required on road of Beureunuen-Keumala border is periodic maintenance on segment I and reconstruction on segment II.Abstrak: Agar dapat tetap mengakomodasi kebutuhan pergerakan dengan tingkat layanan tertentu maka perlu dilakukan suatu usaha untuk menjaga kualitas layanan jalan, dimana salah satu usaha tersebut adalah mengevaluasi kondisi permukaan jalan. Berdasarkan keadaan tersebut di atas, maka diperlukan penelitian untuk mengevaluasi kondisi perkerasan jalan sesuai dengan jenis dan tingkat kerusakan dengan menggunakan metode PCI. Tujuan penelitian ini adalah untuk mengetahui kondisi fungsional perkerasan pada ruas jalan Beureunuen – Batas Keumala. Penelitian ini mengambil lokasi di ruas jalan Beureunuen – Batas Keumala yang terbagi atas 2 segmen dengan segmen I (Km. 7+000 s/d Km. 9+000) dan segmen II (Km.13+000 s/d Km. 15+000). Pengumpulan data primer dilakukan dengan survei aktual lapangan yaitu berupa data panjang, lebar, luasan, serta kedalaman tiap jenis kerusakan yang menunjukan skala kondisi permukaan jalan dari keadaan rusak ringan sampai rusak berat. Penelitian ini dilakukan dengan Pavement Condition Index (PCI). Hasil penelitian menunjukkan bahwa jenis kerusakan yang umum terjadi pada ruas jalan Beureunuen – Batas Keumala adalah retak kulit buaya, retak blok, keriting, retak pinggir, alur, retak memanjang, tambalan, lubang dan pelepasan butir. Evaluasi kerusakan pada segmen I ruas jalan Beureunuen – Batas Keumala memberikan hasil berupa nilai PCI rata-rata pada segmen I ruas jalan Beureunuen – Batas Keumala adalah 39,6 dengan kondisi buruk. Nilai PCI rata-rata Segmen II sebesar 24,7 dengan kondisi sangat buruk. Jenis penanganan yang diperlukan pada ruas jalan Beureunuen – Batas Keumala, adalah pemeliharaan berkala pada segmen I dan rekonstruksi pada segmen II.

Sign in / Sign up

Export Citation Format

Share Document