scholarly journals Analysis of the Influence of Waves in the Occurrence of Accidents in the Portuguese Coast Using Bayesian Belief Networks

2010 ◽  
Vol 13 (1) ◽  
pp. 105-116 ◽  
Author(s):  
Pedro Antão ◽  
C. Soares
Keyword(s):  
Weather Conditions ◽  
Bayesian Belief Network ◽  
Bayesian Belief Networks ◽  
Belief Networks ◽  
Large Wave ◽  
Simple Modification ◽  
Portuguese Coast ◽  
Lack Of Information ◽  
Wave Heights ◽  
Height Data

Analysis of the Influence of Waves in the Occurrence of Accidents in the Portuguese Coast Using Bayesian Belief NetworksSea and weather conditions are the second most frequent cause of accidents in Portuguese waters accounting for 23% of the occurrences. However due to lack of information in the Portuguese maritime accident database it is difficult to assess what this cause consists specifically, i.e., fog, large wave heights or other events. In the present study significant wave height data was introduced in a Bayesian Belief Network (BBN) model in order assess the correlation between their amplitude and certain accident typologies and related consequences (human injuries or fatalities). The results of different inferences of the BBN model show that through a simple modification of an accident model the influence of weather pattern can be assessed and specific risk factors can be identified.

Integration of weather conditions for predicting microbial water quality using Bayesian Belief Networks

2020 ◽  
Vol 170 ◽  
pp. 115349 ◽  
Author(s):  
Anjaneyulu Panidhapu ◽  
Ziyu Li ◽  
Atefeh Aliashrafi ◽  
Nicolás M. Peleato
Keyword(s):  
Water Quality ◽  
Weather Conditions ◽  
Bayesian Belief Networks ◽  
Belief Networks ◽  
Microbial Water Quality

scholarly journals Applying Bayesian Belief Networks to Assess Alpine Grassland Degradation Risks: A Case Study in Northwest Sichuan, China

2021 ◽  
Vol 12 ◽  
Author(s):  
Shuang Zhou ◽  
Li Peng
Keyword(s):  
Potential Evapotranspiration ◽  
Confusion Matrix ◽  
Bayesian Belief Networks ◽  
Alpine Grassland ◽  
Vegetation Coverage ◽  
Grassland Degradation ◽  
Belief Networks ◽  
Lack Of Information ◽  
The Status ◽  
Accuracy Of Results

Grasslands are crucial components of ecosystems. In recent years, owing to certain natural and socio-economic factors, alpine grassland ecosystems have experienced significant degradation. This study integrated the frequency ratio model (FR) and Bayesian belief networks (BBN) for grassland degradation risk assessment to mitigate several issues found in previous studies. Firstly, the identification of non-encroached degraded grasslands and shrub-encroached grasslands could help stakeholders more accurately understand the status of different types of alpine grassland degradation. In addition, the index discretization method based on the FR model can more accurately ascertain the relationship between grassland degradation and driving factors to improve the accuracy of results. On this basis, the application of BBN not only effectively expresses the complex causal relationships among various variables in the process of grassland degradation, but also solves the problem of identifying key factors and assessing grassland degradation risks under uncertain conditions caused by a lack of information. The obtained result showed that the accuracies based on the confusion matrix of the slope of NDVI change (NDVIs), shrub-encroached grasslands, and grassland degradation indicators in the BBN model were 85.27, 88.99, and 74.37%, respectively. The areas under the curve based on the ROC curve of NDVIs, shrub-encroached grasslands, and grassland degradation were 75.39% (P < 0.05), 66.57% (P < 0.05), and 66.11% (P < 0.05), respectively. Therefore, this model could be used to infer the probability of grassland degradation risk. The results obtained using the model showed that the area with a higher probability of degradation (P > 30%) was 2.22 million ha (15.94%), with 1.742 million ha (78.46%) based on NDVIs and 0.478 million ha (21.54%) based on shrub-encroached grasslands. Moreover, the higher probability of grassland degradation risk was mainly distributed in regions with lower vegetation coverage, lower temperatures, less potential evapotranspiration, and higher soil sand content. Our research can provide guidance for decision-makers when formulating scientific measures for alpine grassland restoration.

Algorithms for Bayesian Belief-Network Precomputation

1991 ◽  
Vol 30 (02) ◽  
pp. 81-89 ◽  
Author(s):  
E. H. Herskovits ◽  
G. F. Cooper
Keyword(s):  
Computational Complexity ◽  
Expert Systems ◽  
Expected Utility ◽  
Bayesian Belief Network ◽  
Bayesian Belief Networks ◽  
Future Research ◽  
Belief Networks ◽  
Major Drawback ◽  
Belief Network ◽  
General Method

AbstractBayesian belief networks provide an intuitive and concise means of representing probabilistic relationships among the variables in expert systems. A major drawback to this methodology is its computational complexity. We present an introduction to belief networks, and describe methods for precomputing, or caching, part of a belief network based on metrics of probability and expected utility. These algorithms are examples of a general method for decreasing expected running time for probabilistic inference.We first present the necessary background, and then present algorithms for producing caches based on metrics of expected probability and expected utility. We show how these algorithms can be applied to a moderately complex belief network, and present directions for future research.

A Degradation Diagnosis Method for Gas Turbine - Fuel Cell Hybrid Systems Using Bayesian Networks

2021 ◽  
Author(s):  
Luca Mantelli ◽  
Valentina Zaccaria ◽  
Mario L. Ferrari ◽  
Konstantinos G. Kyprianidis
Keyword(s):  
Fuel Cell ◽  
Gas Turbine ◽  
Hybrid Systems ◽  
Hybrid System ◽  
Bayesian Belief Network ◽  
Bayesian Belief Networks ◽  
Belief Networks ◽  
Essential Information ◽  
Belief Network ◽  
Starting Point

Abstract This paper aims to develop and test Bayesian belief network based diagnosis methods, which can be used to predict the most likely degradation levels of turbine, compressor and fuel cell in a hybrid system on the basis of different sensors measurements. The capability of the diagnosis systems to understand if an abnormal measurement is caused by a component degradation or by a sensor fault is also investigated. The data used both to train and to test the networks is generated from a deterministic model and later modified to consider noise or bias in the sensors. The application of Bayesian belief networks to fuel cell - gas turbine hybrid systems is novel, thus the results obtained from this analysis could be a significant starting point to understand their potential. The diagnosis systems developed for this work provide essential information regarding levels of degradation and presence of faults in gas turbine, fuel cell and sensors in a fuel cell - gas turbine hybrid system. The Bayesian belief networks proved to have a good level of accuracy for all the scenarios considered, regarding both steady state and transient operations. This analysis also suggests that in the future a Bayesian belief network could be integrated with the control system to achieve safer and more efficient operations of these plants.

A Degradation Diagnosis Method for Gas Turbine – Fuel Cell Hybrid Systems Using Bayesian Networks

2020 ◽  
Author(s):  
L. Mantelli ◽  
V. Zaccaria ◽  
K. Kyprianidis ◽  
M. L. Ferrari
Keyword(s):  
Fuel Cell ◽  
Gas Turbine ◽  
Hybrid Systems ◽  
Hybrid System ◽  
Cell Hybrid ◽  
Bayesian Belief Network ◽  
Bayesian Belief Networks ◽  
Belief Networks ◽  
Sensor Fault ◽  
Belief Network

Abstract During the last decades there has been a rise of awareness regarding the necessity to increase energy systems efficiency and reduce carbon emissions. These goals could be partially achieved through a greater use of gas turbine - solid oxide fuel cell hybrid systems to generate both electric power and heat. However, this kind of systems are known to be delicate, especially due to the fragility of the cell, which could be permanently damaged if its temperature and pressure levels exceed their operative limits. This could be caused by degradation of a component in the system (e.g. the turbomachinery), but also by some sensor fault which leads to a wrong control action. To be considered commercially competitive, these systems must guarantee high reliability and their maintenance costs must be minimized. Thus, it is necessary to integrate these plants with an automated diagnosis system capable to detect degradation levels of the many components (e.g. turbomachinery and fuel cell stack) in order to plan properly the maintenance operations, and also to recognize a sensor fault. This task can be very challenging due to the high complexity of the system and the interactions between its components. Another difficulty is related to the lack of sensors, which is common on commercial power plants, and makes harder the identification of faults in the system. This paper aims to develop and test Bayesian belief network based diagnosis methods, which can be used to predict the most likely degradation levels of turbine, compressor and fuel cell in a hybrid system on the basis of different sensors measurements. The capability of the diagnosis systems to understand if an abnormal measurement is caused by a component degradation or by a sensor fault is also investigated. The data used both to train and to test the networks is generated from a deterministic model and later modified to consider noise or bias in the sensors. The application of Bayesian belief networks to fuel cell - gas turbine hybrid systems is novel, thus the results obtained from this analysis could be a significant starting point to understand their potential. The diagnosis systems developed for this work provide essential information regarding levels of degradation and presence of faults in gas turbine, fuel cell and sensors in a fuel cell – gas turbine hybrid system. The Bayesian belief networks proved to have a good level of accuracy for all the scenarios considered, regarding both steady state and transient operations. This analysis also suggests that in the future a Bayesian belief network could be integrated with the control system to achieve safer and more efficient operations of these plants.

Using Bayesian network models to incorporate uncertainty in the economic analysis of pollution abatement measures under the water framework directive

2005 ◽  
Vol 5 (6) ◽  
pp. 95-104 ◽  
Author(s):  
D.N. Barton ◽  
T. Saloranta ◽  
T.H. Bakken ◽  
A. Lyche Solheim ◽  
J. Moe ◽  
...  
Keyword(s):  
Water Quality ◽  
At Risk ◽  
Economic Valuation ◽  
Pollution Abatement ◽  
Network Models ◽  
Cost Effective ◽  
Bayesian Belief Networks ◽  
Probabilistic Interpretation ◽  
Belief Networks ◽  
Benefit Cost Analysis

The evaluation of water bodies “at risk” of not achieving the Water Framework Directive's (WFD) goal of “good status” begs the question of how big a risk is acceptable before a programme of measures should be implemented. Documentation of expert judgement and statistical uncertainty in pollution budgets and water quality modelling, combined with Monte Carlo simulation and Bayesian belief networks, make it possible to give a probabilistic interpretation of “at risk”. Combined with information on abatement costs, a cost-effective ranking of measures based on expected costs and effect can be undertaken. Combined with economic valuation of water quality, the definition of “disproportionate cost” of abatement measures compared to benefits of achieving “good status” can also be given a probabilistic interpretation. Explicit modelling of uncertainty helps visualize where research and consulting efforts are most critical for reducing uncertainty. Based on data from the Morsa catchment in South-Eastern Norway, this paper discusses the relative merits of using Bayesian belief networks when integrating biophysical modelling results in the benefit-cost analysis of derogations and cost-effectiveness ranking of abatement measures under the WFD.

scholarly journals Using Bayesian Belief Networks to assess the influence of landscape connectivity on ecosystem service trade-offs and synergies in urban landscapes in the UK

2021 ◽  
Author(s):  
James D. Karimi ◽  
Jim A. Harris ◽  
Ron Corstanje
Keyword(s):  
Functional Connectivity ◽  
Ecosystem Service ◽  
Urban Areas ◽  
Landscape Connectivity ◽  
Structural Characteristics ◽  
Bird Species ◽  
Bayesian Belief Networks ◽  
Belief Networks ◽  
Patch Area ◽  
Trade Offs

Abstract Context Landscape connectivity is assumed to influence ecosystem service (ES) trade-offs and synergies. However, empirical studies of the effect of landscape connectivity on ES trade-offs and synergies are limited, especially in urban areas where the interactions between patterns and processes are complex. Objectives The objectives of this study were to use a Bayesian Belief Network approach to (1) assess whether functional connectivity drives ES trade-offs and synergies in urban areas and (2) assess the influence of connectivity on the supply of ESs. Methods We used circuit theory to model urban bird flow of P. major and C. caeruleus at a 2 m spatial resolution in Bedford, Luton and Milton Keynes, UK, and Bayesian Belief Networks (BBNs) to assess the sensitivity of ES trade-offs and synergies model outputs to landscape and patch structural characteristics (patch area, connectivity and bird species abundance). Results We found that functional connectivity was the most influential variable in determining two of three ES trade-offs and synergies. Patch area and connectivity exerted a strong influence on ES trade-offs and synergies. Low patch area and low to moderately low connectivity were associated with high levels of ES trade-offs and synergies. Conclusions This study demonstrates that landscape connectivity is an influential determinant of ES trade-offs and synergies and supports the conviction that larger and better-connected habitat patches increase ES provision. A BBN approach is proposed as a feasible method of ES trade-off and synergy prediction in complex landscapes. Our findings can prove to be informative for urban ES management.

scholarly journals Evaluation of the Impact of Weather-Related Limitations on the Installation of Offshore Wind Turbine Towers

Energies ◽  
2021 ◽  
Vol 14 (13) ◽  
pp. 3778
Author(s):  
Stephan Oelker ◽  
Aljoscha Sander ◽  
Markus Kreutz ◽  
Abderrahim Ait-Alla ◽  
Michael Freitag
Keyword(s):  
Discrete Event Simulation ◽  
Discrete Event ◽  
Weather Conditions ◽  
Tuned Mass Damper ◽  
Offshore Wind ◽  
Offshore Wind Turbine ◽  
Measurement Campaign ◽  
Event Simulation ◽  
Mass Damper ◽  
Wave Heights

Weather conditions have a significant impact on the installation of offshore wind turbines. The rules for installation set clear limits. These limits are usually based on estimations of various experts and not on real assumptions and measurements on-site. When wind speeds and wave heights are too high, work cannot be carried out, and this leads to delays and additional costs. Therefore, we have carried out a measurement campaign during the installation of rotor blades to investigate to which extent the limits can be adjusted by using a tuned mass damper. The results from the measurement campaign—specifically empirically derived significant wave height limits—are used in a discrete event simulation. This study simulates delays resulting from weather conditions. Based on this, the total installation costs are considered. The results of the measurement campaign show that a safe installation with the use of a damper is possible at wave heights of up to 1.6 m. With the discrete event simulation, it is possible to prove that 17.9% can be saved for the costs of the installation vessel. In addition, the wind farm could be erected 32 days faster. Thus, it can be stated that the use of a tuned mass damper simplifies the installation from a technical point of view and is economical.

Sign in / Sign up

Export Citation Format

Share Document