A Real- Time Vessel- Buoy Collision Risk Estimation Model for Inland Waterway Navigation

Author(s):  
Tingxuan Li ◽  
Shan Liang ◽  
Tong Liu
2021 ◽  
Vol 9 (5) ◽  
pp. 538
Author(s):  
Jinwan Park ◽  
Jung-Sik Jeong

According to the statistics of maritime collision accidents over the last five years (2016–2020), 95% of the total maritime collision accidents are caused by human factors. Machine learning algorithms are an emerging approach in judging the risk of collision among vessels and supporting reliable decision-making prior to any behaviors for collision avoidance. As the result, it can be a good method to reduce errors caused by navigators’ carelessness. This article aims to propose an enhanced machine learning method to estimate ship collision risk and to support more reliable decision-making for ship collision risk. In order to estimate the ship collision risk, the conventional support vector machine (SVM) was applied. Regardless of the advantage of the SVM to resolve the uncertainty problem by using the collected ships’ parameters, it has inherent weak points. In this study, the relevance vector machine (RVM), which can present reliable probabilistic results based on Bayesian theory, was applied to estimate the collision risk. The proposed method was compared with the results of applying the SVM. It showed that the estimation model using RVM is more accurate and efficient than the model using SVM. We expect to support the reasonable decision-making of the navigator through more accurate risk estimation, thus allowing early evasive actions.


2021 ◽  
Author(s):  
Unmesh Patil ◽  
Alessandro Renzaglia ◽  
Anshul Paigwar ◽  
Christian Laugier

2021 ◽  
Author(s):  
Tongkum Tossapol ◽  
Khamawat Siritheerasas ◽  
Feras Abu Jafar ◽  
Trinh Dinh Phu ◽  
Pham Nam Hieu

Abstract The Well X in Nong Yao field, is an infill-well designed for the Gulf of Thailand which presented several interesting challenges due to its complexity, tortuosity, and potential collision risks with other wells. This paper demonstrates the application of a Real-time Advanced Survey Correction (RASC) with Multi Station Analysis (MSA) to correct the Measurement While Drilling (MWD)'s azimuth. The Well X is a 3D Complex design with a high drilling difficulty index (DDI) at 6.9, high tortuosity of 316 degree, and which has an aggressive build on inclination and azimuthal U-turning well path. The well also creates difficult doglegs severity (DLS) up to 5.5deg/100ft, which is near the limit of the flexibility required to achieve the horizontal landing point. The conventional MWD survey, with proximity scanning with the nearby Well A, demonstrates high risk with a calculated Oriented Separation Factor (OSF) of 1.01. The RASC-MSA method is applied with a clearly defined workflow during execution in real-time and provide significant improvement in calculated OSF. RASC-MSA is applied for every 1,000 ft interval drilling below the 9.625in casing shoe. The workflow ensures that the directional driller follows the corrected survey along the well path and especially in the last 300 ft before reaching the electrical submersible pump (ESP) tangent section. The result from RASC-MSA, indicated a 29 ft lateral shift on the left side of the MWD standard surveys. Without this technique, Well X has a high potential to collide with Well A and Well B (Figure 1) as the actual OSF may less than 1 while drilling. The final 3D Least Distance proximity scanning with Well A shows a minimum OSF = 1.35, which is a 30% improvement compared to the conventional MWD survey. Another nearby well, Well B, indicates a minimum OSF=1.66 and passed the anti-collision OSF rule. In consideration of the drilling efficiency, availability, cost effectiveness and time saving, the RASC-MSA analysis to correct the MWD's azimuth are applied and the separation factor can be improved by 30%. In conclusion, the collision risk management technique applied successfully met the complex challenges of Well X, which was successfully drilled and safely delivered. Figure 1 3D visualization to exhibit the collision issue between Well X and nearby existing Wells A and Well B.


Sign in / Sign up

Export Citation Format

Share Document