Bayesian Network Method Research Articles

A novel approach for reliability assessment of residual heat removal system for HPR1000 based on failure mode and effect analysis, fault tree analysis, and fuzzy Bayesian network methods

Residual heat removal system (RHRS) is one of the important and complicated safety systems for Hualong Pressurized Reactor 1000 (HPR1000). Therefore, it is essential to carry out the reliability assessment of the RHRS for HPR1000. In order to fill the gap of how to assess the reliability of the RHRS with uncertainty, the failure mode and effect analysis (FMEA), fault tree (FT) analysis (FTA), and fuzzy Bayesian network (BN) (FBN) methods were applied to establish a novel approach for assessing its reliability. The proposed approach included: (1) identifying the events containing failure modes, failure causes, and resulted failures for the RHRS by FMEA; (2) analyzing the deterministic logical relationship among events, and establishing the FT for the RHRS by FTA; and (3) establishing the FBN model for reliability assessment of the RHRS by FBN according to the transformation process from FT to FBN model, and modifying the conditional probability tables (CPTs) so as to express the event polymorphism and non-deterministic logical relationship between events. The applicability of the approach was validated in East China.

Analysis of Demand Disruption on Product Availability in the Retail Industry

The customer behavior in shopping were changing the demand disruptions when the COVID-19 pandemic attacked the countries. Retail industries are one of business sectors which were directly impacted the availability of item products. The purpose of this study is to understand the level of demand disruptions of COVID-19 pandemic using Bayesian Network (BN). BN method is powerful method to assess and decide the uncertainly of demand and risk. Based on relevant literature and interviews, the hierarchy of BN were developed and stock out data to represent the product of availability in 5 case study were collected in case study. Finally, the analysis to understand the level of demand disruptions each item products, product family and categories have been performed. This paper provides a new evidence by changing of shopping behavior when the COVID-19 pandemic attached in Indonesia and presents the BN application could be used to handle risk assessment based on stock out data systematically and comprehensively.

Prediction Models of Infrastructure Resilience as a Decision Support System Based on Bayesian Network

The impact of climate change is the implication of global warming that affects people around the world, including Indonesia, which is causing more the intensity and type of natural disaster that causes a decrease or malfunction of a city. To reduce the impact of climate change is needed for the application of the concept of resilience. Resilience is the ability to withstand disturbances caused by external factors and the ability to recover if damage occurs. One of the natural disasters is an earthquake is a natural disaster that often occurs in Indonesia and generally causes significant damage to the physical condition of buildings and infrastructure. This study aims to create a prediction model to measure the impact of a disaster as a decision support system such as a mitigation strategy and responses to identify measures that can improve performance infrastructure to meet resilience goals. One of probabilistic methods is the Bayesian Network method. It is a graphical model probabilistic that represents a set of variables and freedom probabilistic using conditional-probability-table. This research expects as a proposed method of assessing resilience infrastructure to cities in Indonesia when natural disasters occur, especially earthquakes.

The effect of nonconformities encountered in the use of technology on the occurrence of collision, contact and grounding accidents

Technology and its innovative applications make life easier and reduce the workload on seafarers. Today's ship bridges have much more modern and integrated navigation systems than before, and the ship's handling and management have become much easier. However, nonconformities encountered in the use of technological devices may cause accidents. In this study, the effect of human factor related errors associated with the use of the bridge's electronic navigational devices on grounding and collision-contact accidents was investigated. Nonconformities obtained from 175 collision-contact and 115 grounding accident reports were qualitatively analysed by means of human factor analysis and a classification system. Afterwards, relationships between nonconformities and their probabilities were evaluated quantitatively via a Bayesian network method. As a result of the study, the accident network was revealed. This accident network summarizes how operating errors in the use of technological equipment cause accidents. Recommendations on the prevention of accidents caused by operating errors associated with the use of new technologies are finally given.

An Interaction-Based Bayesian Network Framework for Surgical Workflow Segmentation.

Recognizing and segmenting surgical workflow is important for assessing surgical skills as well as hospital effectiveness, and plays a crucial role in maintaining and improving surgical and healthcare systems. Most evidence supporting this remains signal-, video-, and/or image-based. Furthermore, casual evidence of the interaction between surgical staff remains challenging to gather and is largely absent. Here, we collected the real-time movement data of the surgical staff during a neurosurgery to explore cooperation networks among different surgical roles, namely surgeon, assistant nurse, scrub nurse, and anesthetist, and to segment surgical workflows to further assess surgical effectiveness. We installed a zone position system (ZPS) in an operating room (OR) to effectively record high-frequency high-resolution movements of all surgical staff. Measuring individual interactions in a closed, small area is difficult, and surgical workflow classification has uncertainties associated with the surgical staff in terms of their varied training and operation skills, patients in terms of their initial states and biological differences, and surgical procedures in terms of their complexities. We proposed an interaction-based framework to recognize the surgical workflow and integrated a Bayesian network (BN) to solve the uncertainty issues. Our results suggest that the proposed BN method demonstrates good performance with a high accuracy of 70%. Furthermore, it semantically explains the interaction and cooperation among surgical staff.

Pedestrians’ Injury Severity in Traffic Accidents in Spain: A Pedestrian Actions Approach

Road traffic accidents are currently between the seventh and tenth leading cause of death in the world, with approximately 1.35 million people killed per year. Despite extensive efforts by governments, according to the World Health Organization, road accidents still cause far too many deaths, especially among pedestrians, cyclists and two-wheel motor vehicle riders, who together account for almost 50% of road traffic fatalities. In particular, Spain had 410,974 traffic accidents between 2016 and 2019, involving 722,516 vehicles and 61,177 pedestrians with varying degrees of injury. This study uses the Bayesian network method to understand how the pedestrians’ responsibility and actions at the time of the traffic accident affect the injury suffered by said pedestrian, also considering the variables of the road infrastructure and vehicles at the accident site. The results confirm that the variables linked to the unsafe behavior of pedestrians, and their responsibility in traffic accidents, increase the risk of suffering serious or fatal injuries during an accident; for example, if a pedestrian is distracted this increases his/her probability of suffering a severe injury (27.86%) with respect to not being distracted (20.73%). Conditions related to traffic in high-speed areas, areas with no or poor lighting, and areas lacking sidewalks, also record increases in pedestrian injury, as is the case in the age group of pedestrians over 60 years of age.

Early warning of water quality degradation: A copula-based Bayesian network model for highly efficient water quality risk assessment

In the context of global climate change and increasingly severe environmental pollution, drinking water quality risk assessments to provide crucial early warnings have become essential routine work. At present, traditional water quality assessment methods are commonly used without considering the correlation among different indicators and the substantial uncertainty from multiple sources, which limit their applications. To address this issue, a copula-based Bayesian network (CBN) method was proposed in this study to concretely evaluate the water quality risk with multiple environmental risk indicators in a large drinking water reservoir in Tianjin city, China. Taking rainfall and water temperature (WT) as external environmental risk indicators and pH, ammonia nitrogen (NH3–N), total nitrogen (TN), total phosphorus (TP), and permanganate index (CODMn) as internal environmental risk indicators, the CBN model was constructed to investigate the interaction between the indicators and water quality state and assess the contingent risk. Our results showed that TN and NH3–N should be considered key risk indicators. Additionally, we performed forward and backward risk analyses to assess water quality risk during different seasons and determined the distributions of key indicators under different water quality risk grades. From a time perspective, the reservoir's water quality risk is much higher in winter and spring than in other seasons affected by winter snowfall. From a spatial perspective, the water quality risk is much higher at the reservoir's entrance than at other locations affected by water diversion. Furthermore, we found that the probability of water quality risk events may be relatively high when the TN concentration is 3.6 mg/L to 6.4 mg/L at the reservoir's entrance. The results reveal that the CBN method could be an invaluable decision-support tool for reservoir managers and scientists, which could provide an early warning of water quality degradation by only inputting monitoring data.

Validation of risk analysis for ship collision in narrow waters by using fuzzy Bayesian networks approach

Risk analysis is regarded as one of the most critical research topics in maritime industry due to the nature of work. Validation of risk analysis is a significant challenge for safety researchers. This paper aims to address the gap by utilising the power of Bayesian Network method under fuzzy logic environment. While Bayesian Network provides a compact representation of a joint probability distribution, fuzzy logic tackles with vagueness and ambiguity in PRA (Probabilistic Risk Assessment). The validation and sensitivity analyses are performed under various conditions to improve the accuracy of findings. Three different axioms are tested to validate the results. The proposed method is applied for the risk modelling of ship collision in narrow waters. Besides its theoretical background, the paper is expected to help safety researchers validate their results. The maritime safety professionals (safety inspectors, DPAs, superintendents and ship owners) can also benefit from the paper to identify and minimise the potential risks for ship collision in narrow waters.

Ontology knowledge base combined with Bayesian networks for integrated corridor risk warning

With the accelerated urbanization process, the emergence of urban underground integrated pipeline corridors is the trend for cities, especially large and medium-sized cities. However, due to the complexity of the internal system of the integrated corridor, there are various risks in the process of its construction and operation and maintenance, and the risk factors are complex and diverse. In this paper, we introduce ontology technology and knowledge base construction into the risk management of integrated pipeline corridor, build an ontology-based knowledge base of integrated pipeline corridor risk, and construct a Bayesian network based on the established risk knowledge base for risk evaluation of identified risk factors. The combination of ontology knowledge base construction and Bayesian network method of integrated pipeline corridor risk makes the risk identification system completer and more effective, and the method can effectively evaluate the disaster risk level of integrated pipeline corridor operation and maintenance, which can meet the practical needs of integrated pipeline corridor operation and maintenance risk management and disaster prevention and mitigation work.

High Expression of Caspase-8 Associated with Improved Survival in Diffuse Large B-Cell Lymphoma: Machine Learning and Artificial Neural Networks Analyses

High expression of the anti-apoptotic TNFAIP8 is associated with poor survival of the patients with diffuse large B-cell lymphoma (DLBCL), and one of the functions of TNFAIP8 is to inhibit the pro-apoptosis Caspase-8. We aimed to analyze the immunohistochemical expression of Caspase-8 (active subunit p18; CASP8) in a series of 97 cases of DLBCL from Tokai University Hospital, and to correlate with other Caspase-8 pathway-related markers, including cleaved Caspase-3, cleaved PARP, BCL2, TP53, MDM2, MYC, Ki67, E2F1, CDK6, MYB and LMO2. After digital image quantification, the correlation with several clinicopathological characteristics of the patients showed that high protein expression of Caspase-8 was associated with a favorable overall and progression-free survival (Hazard Risks = 0.3; p = 0.005 and 0.03, respectively). Caspase-8 also positively correlated with cCASP3, MDM2, E2F1, TNFAIP8, BCL2 and Ki67. Next, the Caspase-8 protein expression was modeled using predictive analytics, and a high overall predictive accuracy (>80%) was obtained with CHAID decision tree, Bayesian network, discriminant analysis, C5 tree, logistic regression, and Artificial Intelligence Neural Network methods (both Multilayer perceptron and Radial basis function); the most relevant markers were cCASP3, E2F1, TP53, cPARP, MDM2, BCL2 and TNFAIP8. Finally, the CASP8 gene expression was also successfully modeled in an independent DLBCL series of 414 cases from the Lymphoma/Leukemia Molecular Profiling Project (LLMPP). In conclusion, high protein expression of Caspase-8 is associated with a favorable prognosis of DLBCL. Predictive modeling is a feasible analytic strategy that results in a solution that can be understood (i.e., explainable artificial intelligence, “white-box” algorithms).

Process system failure evaluation method based on a Noisy-OR gate intuitionistic fuzzy Bayesian network in an uncertain environment

In the system reliability evaluation of the process industries, it is sometimes difficult to get precise and sufficient failure data of system components utilized to calculate the failure probability. In this study, a Noisy-OR gate Bayesian network method based on intuitionistic fuzzy theory is proposed in cases of imprecise and insufficient historical data. The main contributes of this method include: a set of triangular intuitionistic fuzzy numbers considering uncertainty and hesitation is defined based on the standards and industry practices, meanwhile, a corresponding probability conversion method is also proposed; an improved similarity aggregation method is employed for less uncertainty accumulation and reducing the deviation caused by individual differences during the aggregation; the uncertain causal relationship among the relevant nodes is determined by applying the Noisy-OR gate in the Bayesian network. Furthermore, a case study of the crude oil tank fire and explosion accident is performed to illustrate the applicability of proposed approach. The comparison between the obtained results and that from pre-existing methods shows that the proposed method can provide a more suitable result in an uncertain environment. The weak links of the crude oil tank system are identified through Bayesian reasoning and sensitivity analysis, which can aid decision-making and improve the security execution of the crude oil tank system.

Reliabilities analysis of evacuation on offshore platforms: A dynamic Bayesian Network model

An offshore platform is naturally vulnerable to accidents, such as the leakage of dangerous chemicals, fire and explosion. Oil and gas are explosive and all the equipment and pipes are squeezed into a limited area on a platform. Escape, Evacuation, and Rescue (EER) plans play a vital role as the last barrier to ensure the safety of personnel in the event of a major accident. As a result, the main contributors leading to evacuation failure need to be analyzed to prioritize technology development and select a robust EER strategy. This research aims to undertake the quantitative reliability analysis of various EER strategies on offshore platforms. First, a reliability prediction model of emergency evacuation is established for offshore platforms based on the K2 structure learning algorithm and a Bayesian network parameter learning method. The conditional probability table of each node is determined by combining the Bayesian estimation method and a junction tree reasoning engine. The reliability of emergency evacuation on a platform is predicted using a dynamic Bayesian network model. The transition probability is determined through a Markov method. The main factors leading to evacuation failure are investigated using the diagnostic reasoning method of Bayesian Network. The findings can provide insights for the development of cost effective EER strategies for an offshore platform.

Anaplastic lymphoma kinase tyrosine kinase inhibitor‐induced hepatic failure in lung cancer patients: A study of signal mining and analysis of the FDA adverse event reporting system database

Anaplastic Lymphoma Kinase Tyrosine Kinase Inhibitors (ALK TKIs) are standard first-line therapy for non-small cell lung cancer patients with ALK rearrangement. Although some cases of hepatotoxicity related to these drugs have been reported, there is still a lack of investigation on severe hepatotoxicity, such as hepatic failure, with ALK TKIs. We evaluated ALK TKI (crizotinib, alectinib, brigatinib, ceritinib and lorlatinib)-induced hepatic failure events (AIHFEs), by using the Reporting Odds Ratio (ROR) and Bayesian Confidence Propagation Neural Network method for mining the adverse event report signals in the FDA Adverse Event Reporting System (FAERS) database from Jan 2013 to Dec 2019. The AIHFEs of "Hepatic failure," "hepatitis fulminant" and "hepatic necrosis" were defined as exposure event signals caused by ALK TKIs. The RORs of "Hepatic failure" were 4.95 (2.36-10.42) in alectinib, 3.77 (1.69-8.40) in ceritinib and 2.45 (1.60-3.76) in crizotinib, respectively. The ROR of "hepatitis fulminant" was 7.86 (3.52-17.54) in crizotinib. The Information Component value of "hepatic necrosis" was 1.97 (0.15) in alectinib. In reports of exposure-event signals, the clinical outcome of eventual death was common and could occur within 3months. In the reports of "hepatic failure," there was no significant difference in the number of reports between men and women [OR=1.86 (0.94-3.67), p=0.09]. By mining the adverse event report signals in the FAERS database, we found the exposure event signals of AIHFEs in ALK TKIs were "hepatic failure," "hepatitis fulminant" and "hepatic necrosis". AIHFEs were more likely to appear in the reports of ceritinib, crizotinib and alectinib.

Reliability Analysis of Flexible Multiple State Switch Based on Bayesian Network Method

In order to accurately establish the reliability model of flexible multiple state(FMSS) switch and excavate the weaknesses of component reliability, a method of reliability modeling of FMSS based on Bayesian network is proposed in this paper. Firstly, a multi-state reliability model is established by Markov process. Then, the Bayesian network of MMC is established. The correctness of the model is verified by examples. The reliability of SM, MMC and FMSS is calculated. The influence of submodule redundancy on FMSS is analyzed. The weak link of FMSS is analyzed. The research results in this paper can provide support for the application of FMSS in distribution network.

Analysis of oceanaut operating performance using an integrated Bayesian network aided by the fuzzy logic theory

Because the oceanaut plays a significant role in safety and capability during manned deep-diving scientific tasks, preventing oceanaut performance decline is of paramount importance. However, the factors responsible for oceanaut performance are almost entirely unexplored. To address the preceding issues, a quantitative method of fuzzy integrated Bayesian network (FIBN) was modeled within the limits of oceanaut operating procedures. To quantify the probabilities of the influencing factors, the probability of each node in the FIBN was calculated using integrated expert judgement, fuzzy logic theory, and Bayesian network. By considering a total of 28 factors related to oceanaut performance in the “Jiaolong” manned submersible, this study found that difficult sampling, long sampling times, cabin equipment failure, oceanaut physical decline, and declining decision-making ability are important factors that affect oceanaut performance. The FIBN proposed in our study fused the qualitative and quantitative methods and can be developed into a versatile tool for analysis of comprehensive systems that contain both static and dynamic factors. Relevance to industryThe results provide a powerful basis for the design of manned submersible and assignment of tasks to oceanauts, while the fuzzy integrated Bayesian network (FIBN) method proposed can be effectively applied to various quantitative assessment fields which direct researchers to deal with analysis problems of complex systems.

The prediction of aquifer groundwater level based on spatial clustering approach using machine learning.

Water resources management requires a proper understanding of the status of available and exploitable water. One of the useful management tools is the use of simulation models that are highly efficient in spite of the complex problems in the groundwater sector. In the present study, three data-based models, namely, group method of data handling (GMDH), Bayesian network (BN), and artificial neural network (ANN), have been investigated to simulate the groundwater levels and assess the quantitative status of aquifers. Five observation wells were selected in Birjand aquifer using spatial clustering to analyze and evaluate the aquifer. To determine the effective variables in predicting groundwater level, 10 scenarios were developed by combining several variables, including groundwater level in the previous month, aquifer exploitation, surface recharge, precipitation, temperature, and evaporation. Results showed that the GMDH model with three input variables, i.e., the groundwater level in the previous month, aquifer exploitation, and precipitation, had the highest prediction performance, RMSE, NASH, MAPE, and R2 of which were obtained equal to 0.074, 0.97, 0.0037, and 0.97, respectively. Furthermore, Taylor's diagram showed that the predicted values using the GMDH model had the highest correlation with the observational data. Hydrograph simulation was performed for 6 years to analyze the condition of the aquifer. The results showed that the groundwater level is in critical condition in this aquifer, and a 1.2-m groundwater loss was predicted for this aquifer. The findings of this study show that the management of the studied aquifer is necessary to improve its current situation.

Reliability analysis on the train control system in the CTCS-3 operating mode

Purpose This paper aims to study the reliability of the high-speed train operation control system in the Chinese Train Control System Level 3 (CTCS-3) operating mode. Design/methodology/approach Dynamic fault tree and Bayesian network method are adopted to analyze the reliability and weakness of the CTCS-3 system. Findings First, a physical architecture and data flow diagram of the CTCS-3 system are established according to the typical structure and functions of the CTCS-3 system. Second, the dynamic fault tree of the CTCS-3 system is constructed. Considering the prior probability of the bottom event and the existence of dynamic redundancy, the dynamic fault tree is transformed into a Bayesian net. The reliability of the CTCS-3 system is carried out based on the prior probability and the weakness that affects the reliability of the system based on the posterior probability is also analyzed by the Bayesian network. Finally, it is disclosed that the impact of the on-board subsystem on the reliability of the CTCS-3 system is generally greater than that of the ground subsystem. The two weakest modules in the onboard subsystem are the driver-machine interface (DMI) and balise transmission module (BTM) and the weakest one in the ground subsystem is Balise. The analysis results are generally consistent with the malfunctions in the field operation of China’s high-speed railway. Originality/value (1) By reasoning, the reliability of the train operation control system in the CTCS-3 operating mode meets the standard requirements. (2) Through backward reasoning, it is found that the failure of the onboard subsystem leads to a greater probability of failure of the train control system. (3) The DMI, BTM and automatic train protection computer unit modules are weak components in the onboard subsystem. Vital digit input&output, train interface unit and train security gateway are rarely involved in previous research, the result in this paper shows that these three modules are also weak components in the subsystem, which requires attention.

System level reliability assessment for high power light-emitting diode lamp based on a Bayesian network method

The increased system complexity in electronic products brings challenges in a system level reliability assessment and lifetime estimation. Traditionally, the graph model-based reliability block diagrams (RBD) and fault tree analysis (FTA) have been used to assess the reliability of products and systems. However, these methods are based on deterministic relationships between components that introduce prediction inaccuracy. To fill the gap, a Bayesian Network (BN) method is introduced that considers the intricacies of the high-power light-emitting diode (LED) lamp system and the functional interaction among components for reliability assessment and lifetime prediction. An accelerated degradation test was conducted to analyze the evolution of the degradation and failure of components that influence the system level lifetime and performance of LED lamps. The Gamma process and Weibull distribution are used for component level lifetime prediction. The junction tree algorithm was deployed in the BN structure to estimate the joint probability distributions of the lifetime states. The degradation and prediction results showed that LED modules contribute a major part for lumen degradation of LED lamps followed by drivers and the least effect is from diffuser and reflector. The BN based lifetime estimation results also exhibited an accurate prediction as validated with the Gamma process and such improved reliability assessment outcomes are beneficial to LED manufacturers and customers. Thus, the proposed approach is effective to evaluate and address the long-term reliability assessment concerns of high-reliability LED lamps and fulfill the guarantee of high prediction accuracy in less time and cost-effective manner.

Quality function deployment based failure mode and effect analysis approach for risk evaluation

The traditional failure mode and effect analysis (FMEA) aims to define the risk priority number of each failure mode by multiplying occurrence, severity and detection parameters of each failure mode. Many studies in the literature commented the traditional FMEA due to its limitations such as equal importance degrees, discrete ordinal scales and multiplication of O, S and D criteria. This study suggests coping with these drawbacks a new method, which combines the quality function deployment (QFD) method under interval type-2 fuzzy set, Bayesian network and VIKOR method. The previous studies generally handle to rank the failure modes as only goal. This paper investigates concurrently the failure modes and the reasons of failure modes. QFD method provides us this benefit by employing customer requirements (CRs) and design requirements (DRs). CRs are the reasons of failure modes while DRs are failure modes. This study presents a new perspective to examine the correlations of CRs and DRs as linguistic terms by using Bayesian network. The VIKOR method deals with ranking the failure modes by aggregating the weights of O, S and D criteria. The developed method is utilized for risk evaluation of tile and marble works in building construction. The result shows that the most significant design requirement or failure mode is DR14 (unsuitable plug-socket utilization).

Using improved dynamic Bayesian networks in reliability evaluation for flexible test system of aerospace pyromechanical device products

The flexible test system (FTS) for aerospace pyromechanical device products (PDPs) is an important mean to accurately assess the quality of aerospace-grade PDPs. Since PDPs are disposable products produced in small batch and multi-batch, only a limited number of samples can be tested for each batch to evaluate the quality level of whole batch of products. Therefore, the reliability of ignition FTS is concerned to ensure the reliability of limited test samples. To meet the test requirements of PDPs, the ignition FTS adopts a flexible method to adapt to the different batch types and models. Besides, the reliability of ignition FTS is related to time and product batch task, the reliability evaluation method based on traditional Bayesian network can't describe the dynamic process of product batch. Therefore, this paper proposes a dynamic Bayesian network method based on the combination of time and batch factors to overcome the limitations of product batch change, and a channel configuration optimization method is introduced to meet the reliability requirements, which provides an effective mean for evaluating the FTS reliability. Numerical experiments show that the method can accurately reflect the reliability change of FTS for aerospace PDPs.