An integrated safety prognosis model for complex system based on dynamic Bayesian network and ant colony algorithm

Hu, Jinqiu; Zhang, Laibin; Ma, Lin; Liang, Wei

doi:10.1016/j.eswa.2010.07.050

Cited by 70 publications

(28 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Markov chains) or approximate methods such as meta-heuristics or techniques of artificial intelligence (Hu et al [49]). In all cases, the qualitative characterization of a model will necessarily involve elicitation of experts (Knegtering and Pasman [48], Zahra et al [41]). The advantage of using a decision aid is to be able to use a model repeatedly to make decisions, choose options or set diagnostics where consequences are major and possibly spread out over time and past experience is of little help, all while minimizing the introduction of bias.…”

Section: Integrated Risk Management a Promising Avenuementioning

confidence: 99%

“…et al [41], Tixier et al [42]) in laboratory experiments (Dempsey et al [43]) or using digital human modeling (Illmann et al [44], Demirel and Duffy [3], Fritzsche et al [45], Neumann and Medbo [46], Cimino et al [47]) have been used to complete the comprehension, formalizing and modeling of the decisional subsystem of the system under study. Quantitative or qualitative characterization of such a model can be achieved using Bayesian methods (Knegtering and Pasman [48], Hu et al [49]) or multi-criteria methods such as AHP (analytical hierarchy process) (Saaty, [98]) or ELECTRE, when specific events can be associated with risks and probabilities of their occurrence can be estimated. When probabilities of occurrence cannot be estimated, consideration must be given to using combinatory or continuous optimization algorithms, depending on the nature of the system under study.…”

Section: Integrated Risk Management a Promising Avenuementioning

confidence: 99%

See 1 more Smart Citation

De-Icing of aircraft: Incorporating business risks and occupational health and safety

Nadeau¹,

Morency²

2017

Int. J. SAFE

View full text Add to dashboard Cite

Airliner maintenance is a high-risk sector from an occupational health and safety perspective. In the current context of increasing air traffic worldwide and in view of the economic and safety issues associated with aircraft maintenance, it is imperative that companies providing this service receive support in their quest to reconcile operational performance with OHS. A survey of interdisciplinary research published from 2004 to 2014 allowed analysis of current thought in industrial engineering, human factors engineering and aeronautical de-icing, thus revealing a need for the design of aircraft de-icing activities that are sustainable, holistic and integrated. In response to market evolution, aeronautics will have to offer aircrafts that are greener, meaning safe for all users (including maintenance workers) and the environment throughout the product lifecycle.

show abstract

Section: Integrated Risk Management a Promising Avenuementioning

confidence: 99%

Section: Integrated Risk Management a Promising Avenuementioning

confidence: 99%

De-Icing of aircraft: Incorporating business risks and occupational health and safety

Nadeau¹,

Morency²

2017

Int. J. SAFE

View full text Add to dashboard Cite

show abstract

“…A DBN is a type of BN which is used to model time-series data by introducing relevant temporal dependencies, so as to describe the dynamic behavior of random variables (Hu et al, 2011). A DBN consists of a sequence of time slices and temporal links.…”

Section: Dynamic Bayesian Networkmentioning

confidence: 99%

“…Both of these are relevant in situations where experience is limited and the causal relationship is not well understood. In addition, current DBN based models assume that parameters of conditional probability and failure rates are time-invariant (Cai et al, 2013;Hu et al, 2011) , but in practices many failures in mechanical equipment follow other probability distribution, e.g. Weibull.…”

Section: Introductionmentioning

confidence: 99%

A DBN-based risk assessment model for prediction and diagnosis of offshore drilling incidents

Zhang

Zheng

et al. 2016

Journal of Natural Gas Science and Engineering

Self Cite

View full text Add to dashboard Cite

Abstract:Drilling operations of offshore oil and gas fields are characterized by high reliance on advanced technology, high risk, and high costs due to operating in harsh ocean environments, under complicated geological factors, and extreme operating condition. Lost circulation or well "kick" are examples of hazardous events that may occur while drilling wells and such events may develop into a blowout accident if not handled. Identification and analysis of root causes and consequences are effective measures to prevent serious accidents from happening. The risk of having a blowout may change with time, depending on the stage of the drilling operation, and such kind of dynamics should be captured in risk assessment. This paper presents an approach for determining the conditional probabilities of hazardous events and their consequences. The approach includes models that take into account the influence of degradation and (if used in operation) new real-time information which represents the change in a state of a model parameter (such as state change of mud density) that can be captured while the drilling operation is ongoing.The approach presents a newly-developed model based on the basic theory of Dynamic Bayesian network (DBN) and this proposed model can incorporate some additional nodes to handle the uncertainty issues involving the model uncertainty and relevant parameters' uncertainty and also consider the effect of degradation, which are missed in other papers when using the DBN method for risk assessment of similar systems and operations. The main objective of this newly-developed model is to demonstrate how dynamic risk assessments can be used for incident prediction evolution as well as root cause reasoning during offshore drilling operation, given that a specific event has occurred. A bowtie model is established firstly to link the potential incident scenarios with pressure regimes and formation load capacity, and then the model is translated into a DBN. DBN inference is adapted to perform predictive and diagnostic analysis in different time slices for risk assessment and root cause reasoning. A sensitivity analysis is carried out to find the relative importance of each root cause in generating the potential drilling incidents. A case study with focusing on lost circulation during three drilling scenarios is used to illustrate and verify the feasibility of the proposed approach.Key words: Dynamic Bayesian network (DBN); drilling incidents; dynamic risk assessment; prediction of incident evolution; root cause reasoning Highlights: Potential incident scenarios with pressure regimes and weak formation are presented.  A newly-developed model based on Dynamic Bayesian Network is proposed for offshore drilling incidents.  Effects of model and parameter uncertainty are taken into account.  Prediction of risk evolution and root cause reasoning are performed based on the influence of degradation and occurred events.

show abstract

“…16,17 The dynamic problem is represented with DBNs and the outcome of the analysis is how system or component reliability behaves in time. 18,19 The impact of maintenance of an element at a specific time on this behavior is also reported in some of them. 20,21 However optimization of maintenance activities (i.e., finding a minimum cost plan) 22 using DBNs is rarely considered which is another main motivation for this study.…”

Section: Introductionmentioning

confidence: 99%

Replacement policies for a complex system with unobservable components using dynamic Bayesian networks

Özgür-Ünlüakın¹,

Bi̇lgi̇ç²

2014

IJCIS

View full text Add to dashboard Cite

We study maintenance of a complex dynamic system consisting of ageing and unobservable components under a predetermined threshold reliability level. Our aim is to construct an optimum replacement policy for the components of the system by minimizing total number of replacements or total replacement cost. We represent the problem with dynamic Bayesian networks (DBNs). We prove that under the existence of a predetermined threshold reliability, performing replacements at periods when the system reliability just falls below the threshold assures optimum replacement times. Four component selection approaches and their cost focused versions are proposed to choose the component to replace and are tested on a complex dynamic problem. Their performances are analyzed under various threshold and cost levels.

show abstract

An integrated safety prognosis model for complex system based on dynamic Bayesian network and ant colony algorithm

Cited by 70 publications

References 24 publications

De-Icing of aircraft: Incorporating business risks and occupational health and safety

De-Icing of aircraft: Incorporating business risks and occupational health and safety

A DBN-based risk assessment model for prediction and diagnosis of offshore drilling incidents

Replacement policies for a complex system with unobservable components using dynamic Bayesian networks

Contact Info

Product

Resources

About