Object-oriented Bayesian Networks Research Articles

From frequented environments to the crime scene: Evaluating findings of fibre comparisons in complex transfer scenarios.

The evaluation of the results from a fibre comparison given activity level propositions is well established when considering only a single group of potential primary transfers. However, secondary transfers are less prevalent in the literature despite their potential value, especially in cases where the primary transfers are not sufficiently informative. In particular, one can consider the fibres from frequented environments of the person of interest (POI) identified in a struggle. If the POI did struggle with the complainant, these fibres can potentially be recovered in small quantities on the surface of the complainant as a result of secondary or higher order transfers. Therefore, these fibres may provide useful information that can resolve competing propositions involving struggles, as well as forensic intelligence in the form of linkages or investigative leads. If a non-differentiation is indeed found between recovered fibres and fibres from the frequented environments of the POI, these results need to be properly interpreted. In this paper, a model, based on an object oriented Bayesian network (OOBN), for evaluating such findings along with its implementation is proposed. Using available data from the literature and other sources, the model was then used to assess a few hypothetical scenarios involving secondary transfers. The results provided useful insights into secondary transfer that help to validate the model and demonstrate the potential utility that can be gained by considering transfers beyond the primary order. Moreover, these results can be used to help guide future research by identifying gaps in the literature. Finally, the direct application to a case study was conducted to demonstrate the practical aspects of such a model.

Development of a probabilistic risk model for pharmaceuticals in the environment under population and wastewater treatment scenarios.

Preparing for future environmental pressures requires projections of how relevant risks will change over time. Current regulatory models of environmental risk assessment (ERA) of pollutants such as pharmaceuticals could be improved by considering the influence of global change factors (e.g., population growth) and by presenting uncertainty more transparently. In this article, we present the development of a prototype object-oriented Bayesian network (BN) for the prediction of environmental risk for six high-priority pharmaceuticals across 36 scenarios: current and three future population scenarios, combined with infrastructure scenarios, in three Norwegian counties. We compare the risk, characterized by probability distributions of risk quotients (RQs), across scenarios and pharmaceuticals. Our results suggest that RQs would be greatest in rural counties, due to the lower development of current wastewater treatment facilities, but that these areas consequently have the most potential for risk mitigation. This pattern intensifies under higher population growth scenarios. With this prototype, we developed a hierarchical probabilistic model and demonstrated its potential in forecasting the environmental risk of chemical stressors under plausible demographic and management scenarios, contributing to the further development of BNs for ERA. Integr Environ Assess Manag 2024;20:1715-1735. © 2024 The Authors. Integrated Environmental Assessment and Management published by Wiley Periodicals LLC on behalf of Society of Environmental Toxicology & Chemistry (SETAC).

Improving Fault Diagnosis of the Drilling Permanent Magnet Synchronous Motor (DPMSM) in Harsh Environments: A Novel Approach Using Object-Oriented Bayesian Network (OOBN)

The drilling permanent magnet synchronous motor (DPMSM) contains multiple subsystems with identical structures and has a high probability of failure because the downhole working conditions are harsh. Therefore, the quick localization of faults is difficult to determine although the fault type may be identified in time. The system diagnostic model based on the Bayesian network (BN) can be used for fault diagnosis and localization for components in subsystems, but it is difficult to build and modify due to the complex system in practice. New methods are necessary to reduce the difficulty of building and modifying models. In this study, object-oriented ideas are introduced into the BN to establish a system diagnostic model based on an Object-oriented Bayesian network (OOBN) for the DPMSM. First, the fault diagnostic models for subsystems based on BN are established, respectively. Then, submodels of forward and backward based on BN are instantiated as instance nodes. Next, instance nodes are connected through input nodes and output nodes to establish the OOBN-based system diagnosis model. Finally, the system diagnosis model is validated by sensitivity analysis and the effectiveness is discussed in Cases. The system diagnosis model can effectively reduce the difficulties of modeling and modifying.

A novel object-oriented Bayesian network on risk assessment of sea lanes of communication

The maritime transportation system heavily depends on sea lanes of communication. Unfortunately, the surge in shipping activities has also resulted in an increase in maritime incidents, encompassing both conventional accidents and piracy-related events. This paper presents a novel object-oriented Bayesian network framework for assessing the risk of traditional maritime accidents and piracy-related incidents. Furthermore, an enhanced machine-learning-based Tree augmented naïve learning approach is proposed to address the correlation relationships among the influential factors and the distinctions between mathematical and practical meanings. The paper also introduces mutual information theory and an improved scenario construction approach to identify the key influential factors on maritime risks and unveil the non-linear relationships among them. The findings indicate that both the degraded natural environment and social environment contribute to the risk levels of maritime accidents. Furthermore, the type of ship is recognized as the most significant factor contributing to unsafe conditions. The research results will offer valuable insights to the maritime industry, specifically aiding ship owners, ship crew, and shipping companies in understanding the key influential factors in multiple types of maritime accidents and assessing potential risks.

Safety analysis of blended hydrogen pipelines using dynamic object-oriented bayesian network

Energy demand is increasing rapidly while traditional fossil fuel resources are depleting. Hydrogen is considered a promising alternate fuel. The safety of hydrogen transportation is a key issue that warrants greater attention, primarily to determine how existing pipelines of natural gas transportation can be used for hydrogen transportation. This study has proposed a safety analysis model using the physics and mechanistic approach of hydrogen-associated degradation. A dynamic Object-Oriented Bayesian network (OOBN) model is proposed to study the mechanisms and physics of failure with hydrogen-associated degradation. The proposed model is explained using an industrial case study. Results show low-strength steel is less susceptible to hydrogen-associated degradation than high-strength steel pipes. Moisture, internal stress, and loss of metal ductility are key parameters that require detailed attention. The results of dynamic OOBN also indicate that hydrogen release probability follows a non-linear behavior dependent on the type of metal and operating conditions. The study identifies that controlling the corrosion rate can help ensure the safety of blended hydrogen pipelines.

Human health risk model for microplastic exposure in the Arctic region

Microplastics enriched with carcinogens like heavy metals, polycyclic aromatic hydrocarbons (PAHs), and their derivatives are ubiquitous in Arctic waters. They contaminate the local land and sea-based food sources, which is a significant health hazard. It is thus imperative to assess the risk posed by them to the nearby communities, which primarily rely on locally available food sources to meet their energy requirements. This paper proposes a novel ecotoxicity model to assess the human health risk posed by microplastics. The region's geophysical and environmental conditions affecting human microplastic intake, along with the human physiological parameters influencing biotransformation, are incorporated into the developed causation model. It investigates the carcinogenic risk associated with microplastic intake in humans via ingestion in terms of incremental excess lifetime cancer risk (IELCR). The model first evaluates microplastic intake and then uses reactive metabolites produced due to the interaction of microplastics with xenobiotic metabolizing enzymes to assess cellular mutations that result in cancer. All these conditions are mapped in an Object-Oriented Bayesian Network (OOBN) framework to evaluate IELCR. The study will provide a vital tool for formulating better risk management strategies and policies in the Arctic region, especially concerning Arctic Indigenous peoples.

An object-oriented Bayesian network model for the quantitative risk assessment of navigational accidents in ice-covered Arctic waters

Merchant ship operations in the ice-covered Arctic waters may encounter traditional navigational accident risks (i.e., grounding, collision, etc.) and risks from sea ice, such as ship besetting in ice. However, describing, modeling, and quantifying the multiple risks in ice navigation are challenges from maritime risk assessment perspective. This paper proposes an object-oriented Bayesian network (OOBN) model for the quantitative risk assessment of multiple navigational accidents in ice-covered Arctic waters. The OOBN model makes use of the accident database from Lloyd's intelligence and maritime accident investigation reports. The proposed model decomposes navigational accidents into five levels based on accident causation theory: environment, unsafe condition, unsafe act, probability of navigational accident, and consequence of the navigational accident. Consequently, collision, grounding, ship besetting in ice, and ship–ice collision accidents are selected as the cases to interpret the quantitative risk assessment for navigational risk factors identification, risk analysis, and evaluation. The results demonstrate that (1) the risk is the highest in grounding accidents, followed by besetting in ice, collision, and ship–ice collision in ice-covered Arctic waters; (2) unsafe speed and unsafe condition are the critical mutual factors of these four accident scenarios; (3) and the critical risk influencing factors for the specific navigational accidents are identified to propose corresponding risk control options. The proposed OOBN model can be used for quantitative risk assessment of navigational accidents in ice-covered Arctic waters.

Modelling socio-technical risks of industrial megaprojects using Bayesian Networks and reference classes

Current processes in definition, estimation, and financing of large resource projects often exclude relevant sources of socio-technical risks with overarching effects. This paper proposes an expandable Object-Oriented Bayesian Network (OOBN) to incorporate the effects and dependencies of project risk factors and outcome variables as related to cost. The model can be trained based on collected data, expert knowledge for previously unmeasured sources of socio-technical risks, or some combinations thereof. The model is linked to a reference class of mining projects to position the project at hand within the reference class and to distinguish various extents of cost overrun. Three rounds of interviews were conducted with project expert cohorts to identify socio-technical risk factors, establish their influence weights, and verify specific projects' results. The methodology helps overcome various biases within project estimation processes by combining both singular-evidence of the project at hand (i.e., inside view) and distributional-evidence of the peer reference class (i.e., outside view).

Research on aging-related degradation of control rod drive system based on dynamic object-oriented Bayesian network and hidden Markov model

The control rod drive system is critical to the reactor's reliable operation. The performance of its control system and mechanical system will gradually deteriorate because of operational and environmental stresses, thus increasing the reactor's operational risk. Currently there are few researches on the aging-related degradation of the entire control rod drive system. Because it is difficult to quantify the effect of various environmental stresses and establish an accurate physical model when multiple mechanisms superimposed in the degradation process. Therefore, this paper investigates the aging-related degradation of a control rod drive system by integrating Dynamic Object-Oriented Bayesian Network and Hidden Markov Model. Uncertainties in the degradation of the control system and mechanical system are addressed by using fuzzy theory and the Hidden Markov Model respectively. A system which consists of eight control rod drive mechanisms divided into two groups is used to demonstrate the method. The aging-related degradation of the control rod drive system is analyzed by the Bayesian inference algorithm based on the accelerated life test data, and the impact of different operating schemes on the system performance is also investigated. Meanwhile, the components or units that have major impact on the system's performance are identified at different operational phases. Finally, several essential safety measures are suggested to mitigate the risk caused by the system degradation.

Aligning the achievement of SDGs with long-term sustainability and resilience: An OOBN modelling approach

This research utilizes an Object-Oriented Bayesian Network (OOBN) to model the relationships between the Sustainable Development Goal (SDGs) and resilience and sustainability at national, regional, and global levels. The ability of the OOBN to learn the parameters, i.e., the conditional probability distributions between the variables included in the network, was exploited to explore the impacts of progress of SDGs on the sustainability and resilience of nations. The resulting OOBN is used to examine different situations pertinent to policy analysis and design at the times of disasters, particularly in the wake of the COVID-19 pandemic. Three case studies are used to illustrate the step by step process of using the proposed OOBN as well as the expected results of its application in policy analysis and evaluation contexts. The proposed is able to provide insight regarding which SDGs will have more significant impacts on both resilience and sustainability as well as their constituent components. The results of this research indicate how data induced OOBNs can be utilised by policy makers to prioritize new policies and evaluate the impacts of existing policies on both the resilience and sustainability of societies.

Early warning method for overseas natural gas pipeline accidents based on FDOOBN under severe environmental conditions

The completion and operation of transnational long-distance oil and gas pipelines will not only alleviate shortages of oil and gas resources in China, but also lead to new development opportunities in the countries along their routes. However, the frequent occurrence of severe environmental disasters has led to several uncertainties regarding the long-term safe and stable operation of overseas pipelines, including pipeline fracture, fire, explosions, etc. In this paper, the fuzzy dynamic object-oriented Bayesian network (FDOOBN) theory was introduced to establish an early warning method for overseas natural gas pipeline accidents under harsh environmental conditions. Firstly, for the harsh environmental conditions (lightning, rain, and wind) at pipeline laying stations, accident scenarios under a single harsh environmental condition and the combination of multiple harsh environmental conditions were constructed. The object-oriented concept was adopted to modularize the station system and equipment, and the dynamic Bayesian network (DBN) model of each subsystem of the station was established. Then, the conditional probability parameters in the model were determined by the fuzzy mathematical method. The DBN model of each subsystem and the dynamic object-oriented Bayesian network (DOOBN) model of the entire station system based on the process flow of the station and the object-oriented concept were introduced in turn to establish the fuzzy dynamic Bayesian network (FDBN) model and the FDOOBN model respectively. The dynamic early warning system for station risk under harsh environmental conditions was finally realized. Finally, the prediction errors of environmental parameters, such as meteorological conditions, were introduced to modify the reliability of the model. The results show that compared with the traditional model, the error-corrected FDOOBN model not only has a better performance in simplifying the modelling process and fully integrating expert experience, but also has an increase in dynamic warning range, further improving the reliability of accident warnings.

Research on modeling method of power system network security risk assessment based on object-oriented Bayesian network

A modeling method of security risk assessment for power system network is presented in this paper. The modeling method is divided into three steps. Firstly, Object-oriented Bayesian network(OOBN) is used for structural modeling to avoid the state explosion caused by the large scale of the network. Secondly, Combined with expert knowledge, an effective parameter modeling method is proposed. Based on the OOBN model, the parallel computing reasoning method of OOBN subnet is studied to reduce the complexity of joint probability calculation and improve the calculation timeliness. Finally, the prototype of power information test system is designed to verify the effectiveness of the model. The results show that the method can be used in the security risk assessment for power system network efficiently.

Capsizing accident scenario model for small fishing trawler

Fishing is considered one of the most dangerous occupations globally. Small-scale fisheries, which make up about 90% of the entire industry worldwide, are done using small boats with little onboard shelter and limited navigation and safety equipment. Small-scale fishing uses small fishing vessels such as small trawlers, which are prone to accidents, such as capsize. This paper proposes applying the Object-Oriented Bayesian Network (OOBN) to capture the risk influencing factors of the capsizing accident scenario under different operating conditions for a small fishing trawler, a sub-class of fishing vessels. The model dynamically assesses the probability of capsizing occurrence, considering the complex interaction among critical influencing parameters. The application of the proposed model is demonstrated on a small fishing trawler. To enhance the applicability of the model, uncertainty analysis was also conducted. The probability of capsize is estimated as 0.092±0.003. A study considering the most critical contributing factors was also performed to identify key risk-reducing measures. The most critical measure identified are the human elements (training and experience). The proposed model would serve as a tool for the maritime industry and governmental regulatory bodies for decision making.

Spatio-temporal Object-Oriented Bayesian Network modelling of the COVID-19 Italian outbreak data

The spatial epidemic dynamics of COVID-19 outbreak in Italy were modelled by means of an Object-Oriented Bayesian Network in order to explore the dependence relationships, in a static and a dynamic way, among the weekly incidence rate, the intensive care units occupancy rate and that of deaths. Following an autoregressive approach, both spatial and time components have been embedded in the model by means of spatial and time lagged variables. The model could be a valid instrument to support or validate policy makers’ decisions strategies.

The importance of considering common sources of unknown DNA when evaluating findings given activity level propositions

Evaluating forensic biological evidence considering activity level propositions is becoming more prominent around the world. In such evaluations it is common to combine results from multiple items associated with the alleged activities. The results from these items may not be conditionally independent, depending on the mechanism of cell/DNA transfer being considered and it is important that the evaluation takes these dependencies into account. Part of this consideration is to incorporate our understanding of prevalent DNA and of background DNA on objects and people, and how activities can lead to common sources of unknown DNA being deposited on items. We demonstrate a framework for evaluation of DNA evidence in such a scenario using Object-Oriented Bayesian Networks and apply it to a motivating case from South Australia.

Schedule Risk Assessments Using a Precedence Network: An Object-Oriented Bayesian Approach

Uncertainties affect the scheduling of construction projects. They are among the main causes of delays in construction projects, which increase project costs and reduce project quality. Uncertainties in scheduling affect the duration of activities. Under such conditions, the duration of each activity is influenced by several risk factors; however, previous Bayesian scheduling models considered the effects of one or no factor on the duration of tasks. Also, all parameters of the scheduling network were not considered in those models. In this study, given the causal relationships between uncertainties and their multiple effects on the task duration, a duration model is presented. Next, the effects of uncertainties on all scheduling parameters are applied to Bayesian object-oriented networks through mapping precedence networks. Object-oriented Bayesian networks are a new project management approach to risk assessment and uncertainties in decision-making. This approach is quite effective in considering the causal structure of risk variables and assessing the repetitive structure of precedence networks in large-scale scheduling networks. The project completion time, total slack, delays, as well as other scheduling parameters are estimated using the model proposed, which is titled the Bayesian Precedence Network.

Dynamic ecological risk modelling of hydrocarbon release scenarios in Arctic waters

The Arctic is an ecologically diverse area that is increasingly vulnerable to damages from oil spills associated with commercial vessels traversing newly open shipping lanes. The significance of such accidents on Arctic marine habitats and the potential for recovery can be examined using ecological risk assessment (ERA) coupled with a dynamic object-oriented Bayesian network (DOOBN). A DOOBN approach is useful to represent the probabilistic relationships inherent in the interactions between key events associated with an oil spill, including oil dispersion from the source, ice-oil slick interactions, seawater-oil slick formation, sedimentation, and exposures to different aquatic life. From such analysis, a probabilistic cost analysis can be performed to examine the theoretical cost of habitat services lost and restored. The application of an ERA-DOOBN model to assess oil spills in the Arctic is demonstrated using a case study. The utility of the model output for determining habitat restoration costs and developing policy guidelines for ecological response measures in the Arctic is also discussed.

Multi-criteria decision analysis in Bayesian networks - Diagnosing ecosystem service trade-offs in a hydropower regulated river

The paper demonstrates the use of Bayesian networks in multicriteria decision analysis (MCDA) of environmental design alternatives for environmental flows (eflows) and physical habitat remediation measures in the Mandalselva River in Norway. We demonstrate how MCDA using multi-attribute value functions can be implemented in a Bayesian network with decision and utility nodes. An object-oriented Bayesian network is used to integrate impacts computed in quantitative sub-models of hydropower revenues and Atlantic salmon smolt production and qualitative judgement models of mesohabitat fishability and riverscape aesthetics. We show how conditional probability tables are useful for modelling uncertainty in value scaling functions, and variance in criteria weights due to different stakeholder preferences. While the paper demonstrates the technical feasibility of MCDA in a BN, we also discuss the challenges of providing decision-support to a real-world habitat remediation process.

An explorative object-oriented Bayesian network model for oil spill response in the Arctic Ocean

This paper proposes an Object-Oriented Bayesian Network model to study oil spill mitigative measures using cost-effectiveness as a decision-making factor. The cost-effectiveness is defined as the ratio of dollar spent to the efficiency of oil removal in the spill area. The proposed model considers the complexity, lack of data, and uncertainties in an oil spill and response modelling scenario for Arctic shipping accident occurrence. The crude oil release, slick formation, weathering and transport, ecological impact, and response scenarios are modelled using Bayesian Network. Application of the model is demonstrated using a hypothetical scenario of an oil spill involving a ship in the Arctic region. The results show that a combination of in-situ burning, mechanical and manual recovery, and use of dispersants would cost the highest, while the use of in-situ burning, and dispersants gives the cheapest option. The study provides a deeper understanding of oil spill dynamics and effectiveness of the response techniques. The proposed model could serve as a useful tool for oil spill response decision-making.

Assessment of flood risk in Mediterranean catchments: an approach based on Bayesian networks

National and international technical reports have demonstrated the increase of extreme event occurrences which becomes more dangerous in coastal areas due to their higher population density. In Spain, flood and storm events are the main reasons for compensation according to the National Insurance Consortium. The aim of this paper is to model the risk of flooding in a Mediterranean catchment in the South of Spain. A hybrid dynamic object-oriented Bayesian network (OOBN) was learnt based on mixture of truncated exponential models, a scenario of rainfall event was included, and the final model was validated. OOBN structure allows the catchment to be divided into five different units and models each of them independently. It transforms a complex problem into a simple and easily interpretable model. Results show that the model is able to accurately watch the evolution of river level, by predicting its increase and the time the river needs to recover normality, which can be defined as the river resilience.