Bayesian risk-based decision method for model validation under uncertainty

This paper develops a decision-making methodology for computational model validation, considering the risk of using the current model, data support for the current model, and cost of acquiring new information to improve the model. A Bayesian decision theory-based method is developed for this purpose, using a likelihood ratio as the validation metric for model assessment. An expected risk or cost function is defined as a function of the decision costs, and the likelihood and prior of each hypothesis. The risk is minimized through correctly assigning experimental data to two decision regions based on the comparison of the likelihood ratio with a decision threshold. A Bayesian validation metric is derived based on the risk minimization criterion. Two types of validation tests are considered: pass/fail tests and system response value measurement tests. The methodology is illustrated for the validation of reliability prediction models in a tension bar and an engine blade subjected to high cycle fatigue. The proposed method can effectively integrate optimal experimental design into model validation to simultaneously reduce the cost and improve the accuracy of reliability model assessment.     

Application of risk assessment and decision analysis to the evaluation, ranking and selection of environmental remediation alternatives

A single framework integrating risk assessment and decision analysis methods for evaluating, ranking and selecting preferred remediation alternatives at a contaminated site was developed and demonstrated. The methodology used relies on stakeholder inputs throughout the entire process and employs those inputs to combine the results of multiple risk assessments to arrive at a total impact for each remediation alternative. The total impact values allow the ranking of the alternatives, which in turn, serves as the basis for deliberations among the stakeholders in order to identify the preferred alternative. Six major risk or impact categories were considered in the evaluation of the alternatives: human health and safety, environmental protection, life cycle cost, socio-economics, cultural, archeological and historical resources, and programmatic assumptions.     

Uncertainty quantification in dynamic system risk assessment: a new approach with randomness and fuzzy theory

Quantifying uncertainty during risk analysis has become an important part of effective decision-making and health risk assessment. However, most risk assessment studies struggle with uncertainty analysis and yet uncertainty with respect to model parameter values is of primary importance. Capturing uncertainty in risk assessment is vital in order to perform a sound risk analysis. In this paper, an approach to uncertainty analysis based on the fuzzy set theory and the Monte Carlo simulation is proposed. The question then arises as to how these two modes of representation of uncertainty can be combined for the purpose of estimating risk. The proposed method is applied to a propylene oxide polymerisation reactor. It takes into account both stochastic and epistemic uncertainties in the risk calculation. This study explores areas where random and fuzzy logic models may be applied to improve risk assessment in industrial plants with a dynamic system (change over time). It discusses the methodology and the process involved when using random and fuzzy logic systems for risk management.     

A probabilistic methodology for the design of radiological confinement of tokamak reactors

A methodology using probabilistic risk assessment techniques is proposed for evaluating the design of multiple confinement barriers for a fusion plant within the context of a limited allowable risk. The methodology was applied to the reference design of the International Thermonuclear Experimental Reactor (ITER). Accident sequence models were developed to determine the probability of radioactive releases from each confinement barrier. The current ITER design requirements, that set environmental radioactive release limits for individual event sequences grouped in categories by frequency, is extended to derive a limit on the plant overall risk. This avoids detailed accounting for event uncertainties in both frequency and consequence. Thus, an analytical form for a limit line is derived as a complementary cumulative frequency of permissible radioactive releases to the environment. The line can be derived using risk aversion of the designer's own choice. By comparing the releases from each confinement barrier against this limit line, a decision can be made about the number of barriers required to comply with the design requirements. A decision model using multi-attribute utility function theory was constructed to help the designer in choosing the type of the tokamak building while considering preferences for attributes such as construction cost, project completion time, technical feasibility and public attitude. Sensitivity analysis on some of the relevant parameters in the model was performed.     

Reliability-based assessment of ageing bridges using risk ranking and life cycle cost decision analyses

Information about present and anticipated bridge reliabilities, in conjunction with decision models, provides a rational and powerful decision-making tool for the structural assessment of bridges. For assessment purposes, an updated reliability (after an inspection) may be used for comparative or relative risk purposes. This may include the prioritisation of risk management measures (risk ranking) for inspection, maintenance, repair or replacement. A life-cycle cost analysis may also be used to quantify the expected cost of a decision. The present paper will present a broad overview of the concepts, methodology and immediate applications of risk-based assessments of bridges. In particular, two practical applications of reliability-based bridge assessment are considered — risk ranking and life-cycle cost analysis.     

Uncertainties on predicted concentrations of radionuclides in terrestrial foods and ingestion doses

Models are routinely used to calculate doses following routine releases and potential accidental releases of radionuclides. These models contain a number of parameters. Values for many of these are not accurately known. The primary aim of this study was to determine the level of uncertainty on predicted concentrations of radionuclides in foods, and doses to individuals consuming those foods, arising from uncertainties on the model input parameter values. A secondary objective was to identify those input parameters whose uncertainty makes a major contribution to the overall uncertainty on the predicted endpoints. The methodology adopted and results obtained are presented for the following radionuclides: 90Sr, 131I, 137Cs and 239Pu. The estimated uncertainty ratios (the ratio of the 95th to the 5th percentile) are frequently very large, often two to three orders of magnitude. The results of this study may be used to identify areas where further research could improve assessment capabilities.     

Implementation and evaluation of nonparametric regression procedures for sensitivity analysis of computationally demanding models

The analysis of many physical and engineering problems involves running complex computational models (simulation models, computer codes). With problems of this type, it is important to understand the relationships between the input variables (whose values are often imprecisely known) and the output. The goal of sensitivity analysis (SA) is to study this relationship and identify the most significant factors or variables affecting the results of the model. In this presentation, an improvement on existing methods for SA of complex computer models is described for use when the model is too computationally expensive for a standard Monte-Carlo analysis. In these situations, a meta-model or surrogate model can be used to estimate the necessary sensitivity index for each input. A sensitivity index is a measure of the variance in the response that is due to the uncertainty in an input. Most existing approaches to this problem either do not work well with a large number of input variables and/or they ignore the error involved in estimating a sensitivity index. Here, a new approach to sensitivity index estimation using meta-models and bootstrap confidence intervals is described that provides solutions to these drawbacks. Further, an efficient yet effective approach to incorporate this methodology into an actual SA is presented. Several simulated and real examples illustrate the utility of this approach. This framework can be extended to uncertainty analysis as well.     

基于成本的职能型组织决策体制模型选择

一个企业的组织是由若干个职能部门组成的。为了降低组织的决策成本,建立了度量决策成本的模型,该模型的成本与用来进行决策的信息振荡相关。该模型给出了在不同的情况下选择决策模式的方法。该模型显示：在系统振荡比个别振荡大得多的情况下,如果对部门之间的协调要求比较高,则适宜采用同化信息体制,如部门之间的竞争关系大于协调要求,则采用信息异化体制;相反,在个别振荡比系统振荡大得多的情况下,采用分权体制成本更低。在系统振荡与个别振荡相差不大的情况下,如对部门之间的协调要求比较高,则适宜采用水平体制,反之信息分散化体制成本较低。     

Assessing Performance Risk for Complex Product Development: A Simulation‐Based Model

Assessing and managing performance risk is important for complex product development projects. The performance risk of complex product development can be defined as the probability failing to achieve desired performance level subject to cost and time constraints. This article presents a simulation model based on the graphical evaluation and review technique (GERT) and analyzes the complex product development project using simulation data. The model computes the probability distribution of project duration and cost in a GERT network with multifeedback branches considering activities rework that is caused by probabilistic failure to meet the planned design objective. A simulation strategy is designed to assess the performance risk in both subsystems and system development. With the performance risk assessment methodology, project managers can make a better decision and then minimize the performance risk of product development project. Finally, an obstacle clearance armored vehicle development project is used to illustrate the effectiveness of the proposed model. Copyright © 2012 John Wiley & Sons, Ltd.     

Assessment of the mineral industry NORM/TENORM disposal in hazardous landfills

The main objective of this paper is to describe the assessment methodology utilised in Brazil, to foresee the performance of industrial landfills to disposal solid wastes containing natural radionuclides arising from milling and metallurgical installations that process ores containing NORM. An integrated methodology is utilized and issues as risk, exposure pathways and the plausible scenarios in which the contaminant can migrate and reach the environment and human beings are addressed. A specific example of the procedure is described and results are presented for actual situations. The model consists of an engineered depository constructed of earthen materials which minimise costs and maintain integrity over long-term. In order to define the landfill characteristics and the potential consequences to the environment, an impact analysis is carried out, considering the engineering aspects of the waste deposit and the exposure pathways by which the contaminant can migrate and reach the environment and human beings. Analytical solutions are used in the computer program in order to obtain fast results.     

On uncertainty in remediation analysis: variance propagation from subsurface transport to exposure modeling

Addressing long-term potential human exposures to, and health risks from contaminants in the subsurface environment requires the use of models. Because these models must project contaminant behavior into the future, and make use of highly variable landscape properties, there is uncertainty associated with predictions of long-term exposure. Many parameters used in both subsurface contaminant transport simulation and health risk assessment have variance owing to uncertainty and/or variability. These parameters are best represented by ranges or probability distributions rather than single values. Based on a case study with information from an actual site contaminated with trichloroethylene (TCE), we demonstrate the propagation of variance in the simulation of risk using a complex subsurface contaminant transport simulation model integrated with a multi-pathway human health risk model. Ranges of subsurface contaminant concentrations are calculated with the subsurface transport simulator T2VOC (using the associated code ITOUGH2 for uncertainty analysis) for a three-dimensional system in which TCE migrates in both the vadose and saturated zones over extended distances and time scales. The subsurface TCE concentration distributions are passed to CalTOX, a multimedia, multi-pathway exposure model, which is used to calculate risk through multiple exposure pathways based on inhalation, ingestion and dermal contact. Monte Carlo and linear methods are used for the propagation of uncertainty owing to parameter variance. We demonstrate how rank correlation can be used to evaluate contributions to overall uncertainty from each model system. In this sample TCE case study, we find that although exposure model uncertainties are significant, subsurface transport uncertainties are dominant.     

Multivariate sensitivity analysis to measure global contribution of input factors in dynamic models

Many dynamic models are used for risk assessment and decision support in ecology and crop science. Such models generate time-dependent model predictions, with time either discretised or continuous. Their global sensitivity analysis is usually applied separately on each time output, but Campbell et al. (2006 [1]) advocated global sensitivity analyses on the expansion of the dynamics in a well-chosen functional basis. This paper focuses on the particular case when principal components analysis is combined with analysis of variance. In addition to the indices associated with the principal components, generalised sensitivity indices are proposed to synthesize the influence of each parameter on the whole time series output. Index definitions are given when the uncertainty on the input factors is either discrete or continuous and when the dynamic model is either discrete or functional. A general estimation algorithm is proposed, based on classical methods of global sensitivity analysis.The method is applied to a dynamic wheat crop model with 13 uncertain parameters. Three methods of global sensitivity analysis are compared: the Sobol'-Saltelli method, the extended FAST method, and the fractional factorial design of resolution 6.     

基于概率的高层建筑地震需求模型与风险评估EI北大核心CSCD

提出了基于贝叶斯理论的地震风险评估方法,综合考虑了地震危险性模型、输入地震动记录、结构参数和需求模型的不确定性,并以云南大理地区1970年-2017年间的地震数据为研究基础进行了详细讨论。在传统基于概率地震危险性分析方法的基础上,提出了基于贝叶斯理论的地震危险性分析方法,通过贝叶斯更新准则,确定了地震概率模型中未知参数的后验概率分布;通过贝叶斯理论建立了基于概率的地震需求模型,并在易损性中考虑了需求模型认知不确定性的影响;以42层钢框架-RC核心筒建筑为例,开展了地震作用下的风险评估。研究表明:基于贝叶斯理论的地震危险性分析方法,能够获得更为合理的危险性模型;忽略需求模型中参数不确定性的影响,将错误估计结构的地震易损性;不同加载工况将对高层建筑的地震风险产生显著影响。提出的概率风险评估方法,提供了可以考虑固有不确定性和认知不确定性的有效途径,有助于推动高性能结构地震韧性评价和设计理论的发展。     

Addressing imperfect maintenance modelling uncertainty in unavailability and cost based optimization

Optimization of testing and maintenance activities performed in the different systems of a complex industrial plant is of great interest as the plant availability and economy strongly depend on the maintenance activities planned. Traditionally, two types of models, i.e. deterministic and probabilistic, have been considered to simulate the impact of testing and maintenance activities on equipment unavailability and the cost involved. Both models present uncertainties that are often categorized as either aleatory or epistemic uncertainties. The second group applies when there is limited knowledge on the proper model to represent a problem, and/or the values associated to the model parameters, so the results of the calculation performed with them incorporate uncertainty. This paper addresses the problem of testing and maintenance optimization based on unavailability and cost criteria and considering epistemic uncertainty in the imperfect maintenance modelling. It is framed as a multiple criteria decision making problem where unavailability and cost act as uncertain and conflicting decision criteria. A tolerance interval based approach is used to address uncertainty with regard to effectiveness parameter and imperfect maintenance model embedded within a multiple-objective genetic algorithm. A case of application for a stand-by safety related system of a nuclear power plant is presented. The results obtained in this application show the importance of considering uncertainties in the modelling of imperfect maintenance, as the optimal solutions found are associated with a large uncertainty that influences the final decision making depending on, for example, if the decision maker is risk averse or risk neutral.     

Stress test optimization using an integrated production test and field reliability model

Numerous papers and texts have been written in the reliability literature regarding the determination of the optimum test duration for a production stress or a burn‐in test. The techniques presented have largely been based on the identification of the change point at which infant mortality has largely been removed from the units. The time‐on‐test is typically the only factor that influences this decision. Few of these models have attempted to integrate the field performance or the influence of warranty costs into this decision. This paper proposes and validates a methodology that integrates the influence of the production test failures and the field performance including their respective costs into a single unified model. The objective is to identify a production test duration that minimizes the overall cost. A Weibull model is initially developed for the production test that incorporates the failure observations in different time segments of the test based on the ability to detect latent defects in the product. A separate Weibull model is then developed for the product's performance in the field that includes the lifetime of the unit. This paper identifies how both these Weibull models can be combined into a single model including both test and field costs with the objective of minimizing the overall cost. The advantage of the proposed technique is that it does not require one to track individual units from production through to the field in order to develop an integrated test and field cost model. Copyright © 2009 John Wiley & Sons, Ltd.     

On using residual risk to assess the cost effectiveness and health protectiveness of remedy selection at superfund sites

This article examines the importance of determining residual risk and its impact on remedy selection at Superfund Sites. Within this examination, risks are assessed using probabilistic models that incorporate the uncertainty and variability of the input parameters, and utilize parameter distributions based on current and applicable site-specific data. Monte Carlo methods are used to propagate these uncertainties and variabilities through the risk calculations resulting in a distribution for the estimate of both risk and residual risk. Such an approach permits an informed decision based on a broad information base which involves considering the entire uncertainty distribution of risk rather than a point estimate for each exposure scenario. Using the probabilistic risk estimates, with current and applicable site-specific data, alternative decisions regarding cleanup are obtained for two Superfund Sites.     

Data assimilation in the decision support system rodos

Model predictions for a rapid assessment and prognosis of possible radiological consequences after an accidental release of radionuclides play an important role in nuclear emergency management. Radiological observations, e.g. dose rate measurements, can be used to improve such model predictions. The process of combining model predictions and observations, usually referred to as data assimilation, is described in this article within the framework of the real time on-line decision support system (RODOS) for off-site nuclear emergency management in Europe. Data assimilation capabilities, based on Kalman filters, are under development for several modules of the RODOS system, including the atmospheric dispersion, deposition, food chain and hydrological models. The use of such a generic data assimilation methodology enables the propagation of uncertainties throughout the various modules of the system. This would in turn provide decision makers with uncertainty estimates taking into account both model and observation errors. This paper describes the methodology employed as well as results of some preliminary studies based on simulated data.     

Closed loop supply chain network design and optimisation using fuzzy mixed integer linear programming model

Owing to the revolution in sustainable and green manufacturing the production planning and network design of closed loop supply chain concept has got the attention of researchers and managers. In this paper, a multi-product, multi-facility capacitated closed-loop supply chain framework is proposed in an uncertain environment including reuse, refurbish, recycle and disposal of parts. The uncertainty related to demand, fraction of parts recovered for different product recovery processes, product acquisition cost, purchasing cost, transportation cost, processing, and set-up cost is handled with fuzzy numbers. A fuzzy mixed integer linear programming model is proposed to decide optimally the location and allocation of parts at each facility and number of parts to be purchased from external suppliers in order to maximise the profit of organisation. The proposed solution methodology is able to generate a balanced solution between the feasibility degree and degree of satisfaction of the decision maker. The proposed model has been tested with an illustrative example.     

Decisions with uncertain alternatives

This paper analyses decision models with an uncertain set of alternatives defined by a deterministic objective function and constraints with uncertain coefficients. Here, in contrast to decisions under risk, the stochastic distribution of uncertain coefficients is not known. On the basis of an uncertain multiobjective decision model, we define efficient alternatives and formulate deterministic surrogate models. Uncertain decision models with recourse are introduced, and we present solution concepts that combine approaches from both multiobjective decision making and decision models with uncertain objective functions. These approaches are discussed in relation to stochastic and fuzzy programming and to models with linear partial information. In addition, ramifications of this particular approach are explored.