A machine learning methodology to predict alerts and maintenance interventions in roads

Morales, Francisco J.; Reyes, Antonio; Cáceres, Noelia; Romero, Luis; Benítez, Francisco G.; Morgado, João; Duarte, Emanuel Felipe

doi:10.1080/14680629.2020.1753098

Cited by 8 publications

(5 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This is in line with other studies, which have used different forms of artificial intelligence to predict maintenance intervention timelines and metrics. This is validated in recent studies which have achieved accuracies of: 87% when predicting the infrastructure's condition using a neural network with embedding [77], 86% for predicting road surface milling and overlays interventions [78], 85% when using combinations of gradient boosting trees to predict the PCI [79] and 87% predicting global road performance indicators [29]. Other studies have achieved higher accuracies when using the LTPP database [80] and other studies showing that the majority of research using ANN for predictions is done using this database [41].…”

Section: Fastai Model Resultssupporting

confidence: 58%

Exploiting Data Analytics and Deep Learning Systems to Support Pavement Maintenance Decisions

2021

View full text Add to dashboard Cite

Road networks are critical infrastructures within any region and it is imperative to maintain their conditions for safe and effective movement of goods and services. Road Management, therefore, plays a key role to ensure consistent efficient operation. However, significant resources are required to perform necessary maintenance activities to achieve and maintain high levels of service. Pavement maintenance can typically be very expensive and decisions are needed concerning planning and prioritizing interventions. Data are key towards enabling adequate maintenance planning but in many instances, there is limited available information especially in small or under-resourced urban road authorities. This study develops a roadmap to help these authorities by using flexible data analysis and deep learning computational systems to highlight important factors within road networks, which are used to construct models that can help predict future intervention timelines. A case study in Palermo, Italy was successfully developed to demonstrate how the techniques could be applied to perform appropriate feature selection and prediction models based on limited data sources. The workflow provides a pathway towards more effective pavement maintenance management practices using techniques that can be readily adapted based on different environments. This takes another step towards automating these practices within the pavement management system.

show abstract

Section: Fastai Model Resultssupporting

confidence: 58%

Exploiting Data Analytics and Deep Learning Systems to Support Pavement Maintenance Decisions

2021

View full text Add to dashboard Cite

show abstract

“…It is a technique that helps in decision-making theoretically and frugally that includes techniques of sound management for conserving the best imaginable national of the airport asphalts for a convinced quantity of period while following current legal needs. On the other side, the deployment of an APMS entails charges for inventory management procedures, database creation and upkeep, the creation or purchase of management software, and data analysis [17]. However, the advantages of APMS are widely acknowledged, and APMS practices are included in the airport handbook which help to keep the airport certified.…”

Section: Literature Reviewmentioning

confidence: 99%

Empirical Models Investigation of Pavement Management for Advancing the Road's Planning Using Predictive Maintenance

Aldabbas¹

2023

cea

View full text Add to dashboard Cite

“…According to Statistics Norway, there are a total of 54,899 km of county and national roadways in Norway that the Norwegian Public Road Administration (NPRA) is responsible for monitoring and ensuring are well-maintained. Predictive maintenance (PdM) techniques are designed to determine the conditions of roadways in order to estimate when maintenance should be performed [ 1 ]. Compared to traditional maintenance activities, such as time-based preventative maintenance, PdM is conditions-based, where maintenance is carried out based on real-time estimations of the degradation state of the roadway infrastructure fostering safety and cost-savings [ 2 ].…”

Section: Introductionmentioning

confidence: 99%

“…Each collected image is labeled with geolocation. Only a limited number of the collected images are manually analyzed based on reports from road users because the manual inspection is a very tedious, time-consuming, and inefficient process [ 1 ].…”

Section: Introductionmentioning

confidence: 99%

Predictive Maintenance of Norwegian Road Network Using Deep Learning Models

Hassan

Steinnes

Gustafsson

et al. 2023

Sensors

View full text Add to dashboard Cite

Industry 4.0 has revolutionized the use of physical and digital systems while playing a vital role in the digitalization of maintenance plans for physical assets in an optimal way. Road network conditions and timely maintenance plans are essential in the predictive maintenance (PdM) of a road. We developed a PdM-based approach that uses pre-trained deep learning models to recognize and detect the road crack types effectively and efficiently. We, in this work, explore the use of deep neural networks to classify roads based on the amount of deterioration. This is done by training the network to identify various types of cracks, corrugation, upheaval, potholes, and other types of road damage. Based on the amount and severity of the damage, we can determine the degradation percentage and have a PdM framework where we can identify the intensity of damage occurrence and, thus, prioritize the maintenance decisions. The inspection authorities and stakeholders can make maintenance decisions for certain types of damages using our deep learning-based road predictive maintenance framework. We evaluated our approach using precision, recall, F1-score, intersection-over-union, structural similarity index, and mean average precision measures, and found that our proposed framework achieved significant performance.

show abstract

A machine learning methodology to predict alerts and maintenance interventions in roads

Cited by 8 publications

References 25 publications

Exploiting Data Analytics and Deep Learning Systems to Support Pavement Maintenance Decisions

Exploiting Data Analytics and Deep Learning Systems to Support Pavement Maintenance Decisions

Empirical Models Investigation of Pavement Management for Advancing the Road's Planning Using Predictive Maintenance

Predictive Maintenance of Norwegian Road Network Using Deep Learning Models

Contact Info

Product

Resources

About