scholarly journals Secure and Accurate Road Weather Services - The Belgian SARWS project

2021 ◽  
Author(s):  
Sylvain Watelet ◽  
Joris Van den Bergh ◽  
Maarten Reyniers ◽  
Wim Casteels ◽  
Toon Bogaerts ◽  
...  
Keyword(s):  
Surface Temperature ◽  
Real Time ◽  
Air Temperature ◽  
Vehicle Dynamics ◽  
Large Scale ◽  
Road Surface ◽  
Sensor Data ◽  
Weather Forecasts ◽  
Road Surface Temperature ◽  
Weather Stations

<p>For the generation of accurate warnings for dangerous road conditions, road weather models typically depend on observations from road weather stations (RWS) at fixed locations along roads and highways. Observations at higher resolution in space and time have the potential to provide more localized, real-time weather warnings. The rise of connected vehicles with onboard sensing capabilities opens up exciting new opportunities in this field. For this purpose, a heterogeneous group of industrial stakeholders and researchers consisting of more than thirty partners from seven countries including Belgium, initiated the CELTIC-NEXT project "Secure and Accurate Road Weather Services" (SARWS). The goal of SARWS is to provide real-time weather services by expanding observational data from traditional RWS sources with data from large-scale vehicle fleets. The Belgian consortium consists of Verhaert New Products & Services, Be-Mobile, Inuits, bpost, imec - IDLab (University of Antwerp) and the Royal Meteorological Institute of Belgium (RMI). Within the Belgian consortium, the focus is on the use of vehicle data to enable real-time warning services for potentially dangerous local weather and road surface conditions. The vehicle fleet consists of cars of the Belgian Post Group (bpost) in the region around Antwerp, and will consist of 15 cars by the end of summer 2021. Data on vehicle dynamics, such as wheel speed, are gathered from the vehicle's CAN bus, while an additional installed sensor box collects air temperature, relative humidity and road surface temperature observations. Data on wipers and fog light activation, and camera images are also collected.</p><p>We present the Belgian SARWS setup, data flow, and the developed data distribution platform. We discuss validation results for 2021, comparing car sensor observations to close RWS and weather stations, focusing mainly on air temperature, humidity and road surface temperature, and show the need for calibration and bias correction. We also demonstrate an experimental version of the RMI road weather model that provides short-term road weather forecasts for 50-meter road segments, using car sensor data for initialization, and compare with road weather forecasts at nearby station locations. We also demonstrate machine learning approaches that are explored to detect weather information from the vehicle dynamics.</p>

scholarly journals Modeling Road Surface Temperature from Air Temperature and Geographical Parameters—Implication for the Application of Floating Car Data in a Road Weather Forecast Model

2019 ◽  
Vol 58 (5) ◽  
pp. 1023-1038 ◽  
Author(s):  
Yumei Hu ◽  
Esben Almkvist ◽  
Torbjörn Gustavsson ◽  
Jörgen Bogren
Keyword(s):  
Surface Temperature ◽  
Air Temperature ◽  
Winter Season ◽  
Road Surface ◽  
View Factor ◽  
Traffic Intensity ◽  
Weather Patterns ◽  
Floating Car Data ◽  
Thermal Mapping ◽  
Road Surface Temperature

AbstractPrecise forecasts of road surface temperature (RST) and road conditions allow winter roads to be maintained efficiently. The upcoming “big data” application known as “floating car data” (FCD) provides the opportunity to improve road weather forecasts with measurements of air temperature Ta from in-car sensors. The research thus far with regard to thermal mapping has mainly focused on clear and calm nights, which occur rarely and during low traffic intensity. It is expected that more than 99% of the FCD will be collected during conditions other than clear and calm nights. Utilizing 32 runs of thermal mapping and controlled Ta surveys carried out on mostly busy roads over one winter season, it was possible to simulate the use of Ta and geographical parameters to reflect the variation of RST. The results show that the examined route had several repeatable thermal fingerprints during times of relatively high traffic intensity and with different weather patterns. The measurement time, real-time weather pattern, and previous weather patterns influenced the spatial pattern of thermal fingerprints. The influence of urban density and altitude on RST can be partly seen in their relationship with Ta, whereas the influence of shading and sky-view factor was only seen for RST. The regression models with Ta included explained up to 82% of the RST distribution and outperformed models that are based only on the geographical parameters by as much as 30%. The performance of the models denotes the possible utility of Ta from FCD, but further investigation is needed before moving from controlled Ta measurements to Ta from FCD.

scholarly journals Effects of Speeds and Weights of Travelling Vehicles on the Road Surface Temperature

2021 ◽  
pp. 100077
Author(s):  
Samim Mustafa ◽  
Hidehiko Sekiya ◽  
Aya Hamajima ◽  
Iwao Maeda ◽  
Shuichi Hirano
Keyword(s):  
Surface Temperature ◽  
Road Surface ◽  
The Road ◽  
Road Surface Temperature ◽  
On The Road

A Novel Real-Time Thermal Analysis and Layer Time Control Framework for Large Scale Additive Manufacturing

2020 ◽  
Author(s):  
Sepehr Fathizadan ◽  
Feng Ju ◽  
Kyle Rowe ◽  
Alex Fiechter ◽  
Nils Hofmann
Keyword(s):  
Additive Manufacturing ◽  
Surface Temperature ◽  
Real Time ◽  
Large Scale ◽  
Production Efficiency ◽  
Control Method ◽  
Data Extraction ◽  
Critical Role ◽  
Imaging Data ◽  
Time Data

Abstract Production efficiency and product quality need to be addressed simultaneously to ensure the reliability of large scale additive manufacturing. Specifically, print surface temperature plays a critical role in determining the quality characteristics of the product. Moreover, heat transfer via conduction as a result of spatial correlation between locations on the surface of large and complex geometries necessitates the employment of more robust methodologies to extract and monitor the data. In this paper, we propose a framework for real-time data extraction from thermal images as well as a novel method for controlling layer time during the printing process. A FLIR™ thermal camera captures and stores the stream of images from the print surface temperature while the Thermwood Large Scale Additive Manufacturing (LSAM™) machine is printing components. A set of digital image processing tasks were performed to extract the thermal data. Separate regression models based on real-time thermal imaging data are built on each location on the surface to predict the associated temperatures. Subsequently, a control method is proposed to find the best time for printing the next layer given the predictions. Finally, several scenarios based on the cooling dynamics of surface structure were defined and analyzed, and the results were compared to the current fixed layer time policy. It was concluded that the proposed method can significantly increase the efficiency by reducing the overall printing time while preserving the quality.

Machine-Learning for the Prediction of Lost Circulation Events - Time Series Analysis and Model Evaluation

2021 ◽  
Author(s):  
Arturo Magana-Mora ◽  
Mohammad AlJubran ◽  
Jothibasu Ramasamy ◽  
Mohammed AlBassam ◽  
Chinthaka Gooneratne ◽  
...  
Keyword(s):  
Machine Learning ◽  
Time Series ◽  
Real Time ◽  
Large Scale ◽  
Model Comparison ◽  
Drilling Fluid ◽  
Sensor Data ◽  
False Alarms ◽  
Suitable Model ◽  
Lost Circulation

Abstract Objective/Scope. Lost circulation events (LCEs) are among the top causes for drilling nonproductive time (NPT). The presence of natural fractures and vugular formations causes loss of drilling fluid circulation. Drilling depleted zones with incorrect mud weights can also lead to drilling induced losses. LCEs can also develop into additional drilling hazards, such as stuck pipe incidents, kicks, and blowouts. An LCE is traditionally diagnosed only when there is a reduction in mud volume in mud pits in the case of moderate losses or reduction of mud column in the annulus in total losses. Using machine learning (ML) for predicting the presence of a loss zone and the estimation of fracture parameters ahead is very beneficial as it can immediately alert the drilling crew in order for them to take the required actions to mitigate or cure LCEs. Methods, Procedures, Process. Although different computational methods have been proposed for the prediction of LCEs, there is a need to further improve the models and reduce the number of false alarms. Robust and generalizable ML models require a sufficiently large amount of data that captures the different parameters and scenarios representing an LCE. For this, we derived a framework that automatically searches through historical data, locates LCEs, and extracts the surface drilling and rheology parameters surrounding such events. Results, Observations, and Conclusions. We derived different ML models utilizing various algorithms and evaluated them using the data-split technique at the level of wells to find the most suitable model for the prediction of an LCE. From the model comparison, random forest classifier achieved the best results and successfully predicted LCEs before they occurred. The developed LCE model is designed to be implemented in the real-time drilling portal as an aid to the drilling engineers and the rig crew to minimize or avoid NPT. Novel/Additive Information. The main contribution of this study is the analysis of real-time surface drilling parameters and sensor data to predict an LCE from a statistically representative number of wells. The large-scale analysis of several wells that appropriately describe the different conditions before an LCE is critical for avoiding model undertraining or lack of model generalization. Finally, we formulated the prediction of LCEs as a time-series problem and considered parameter trends to accurately determine the early signs of LCEs.

scholarly journals Applying the METRo model for road-condition forecasting in Norway 

2021 ◽  
Author(s):  
Stephanie Mayer ◽  
Fabio Andrade ◽  
Torge Lorenz ◽  
Luciano de Lima ◽  
Anthony Hovenburg ◽  
...  
Keyword(s):  
Surface Temperature ◽  
Heat Dissipation ◽  
Road Traffic ◽  
Weather Forecast ◽  
Road Surface ◽  
Balance Model ◽  
Weather Station ◽  
The Road ◽  
Road Surface Temperature ◽  
Road Condition

<p>According to the 14<sup>th</sup> Annual Road Safety Performance Index Report by the European Transport Safety Council, annually more than 100,000 accidents occur on European roads, of which 22,660 people lost their lives in 2019. The factors contributing to road traffic accidents are commonly grouped into three categories: environment, vehicle or driver. The European accident research and safety report 2013 by Volvo states in about 30% of accidents contributing factors could be attributed to weather and environment leading for example to unexpected changes in road friction, such as black ice. In this work, we are developing a solution to forecast road conditions in Norway by applying the <em>Model of the Environment and Temperature of Roads – METRo</em>, which is a surface energy balance model to predict the road surface temperature. In addition, METRo includes modules for water accumulation at the surface (liquid and frozen) and vertical heat dissipation (Crevier and Delage, 2001). The road condition is forecasted for a given pair of latitude, longitude and desired forecast time. Data from the closest road weather station and postprocessed weather forecast are used to initialize METRo and provide boundary conditions to the road weather forecast. The weather forecasts are obtained from the THREDDS service and the road weather station data from the FROST service, both provided by MET Norway. We develop algorithms to obtain the data from these services, process them to match the METRo model input requirements and send them to METRo’s pre-processing algorithms, which combine observations and forecast data to initialize the model. In a case study, we will compare short-term METRo forecasts with observations obtained by road weather stations and with observations retrieved by car-mounted environmental sensors (e.g., road surface temperature). This work is part of the project <em>AutonoWeather - Enabling autonomous driving in winter conditions through optimized road weather interpretation and forecast</em> financed by the Research Council of Norway in 2020. </p>

Sign in / Sign up

Export Citation Format

Share Document