储气库注采管柱螺纹失效动态风险评估*

为解决储气库注采管柱螺纹失效问题,识别注采管柱螺纹失效致因与后果,基于蝴蝶结和贝叶斯网络方法构建注采管柱螺纹动态失效风险分析模型,采用模糊集理论计算模型变量先验概率,并评估注采管柱失效后果概率,从而推断注采管柱螺纹失效关键致因因素;引入先兆数据,评估注采管柱螺纹动态失效风险态势。结果表明:气体中携带固体颗粒、上螺纹速度过快、注采温度高、地层断裂等13个因素对螺纹失效风险影响较大;螺纹失效概率逐渐增大,螺纹失效后果也越来越严重,需要监控螺纹失效关键致因以降低螺纹失效的风险。     

基于贝叶斯估计的多探测器火警判定方法研究*

为应对感烟探测器的大量误报对消防应急响应带来的挑战,考虑目前以感烟探测器为主的火警设施误报率高且短期内难以全部更换的特点,提出基于贝叶斯估计的多探测器火警判定方法,通过多个探测器的报警时间间隔计算火源位置的后验概率分布,并提出火警真实度概念,为火警判定提供依据。结果表明:使用多探测器耦合模型时每增加1个探测器可将误报率降低约4个数量级,该方法在探测器正常、部分失效、误报的情景下均能有效判别火警。     

Modelling Replicated Weed Growth Data using Spatially-varying Growth Curves

Weed growth in agricultural fields constitutes a major deterrent to the growth of crops, often resulting in low productivity and huge losses for the farmers. Therefore, proper understanding of patterns in weed growth is vital to agricultural research. Recent advances in Geographical Information Systems (GIS) now allow geocoding of agricultural data, which enable more sophisticated spatial analysis. Our current application concerns the development of statistical models for conducting spatial analysis of growth patterns in weeds. Our data comes from an experiment conducted in Waseca, Minnesota, that recorded growth of the weed Setariaspp. We capture the spatial variation in Setaria spp. growth using spatially-varying growth curves. An added challenge is that these designs are spatially replicated, with each plot being a lattice of sub-plots. Therefore, spatial variation may exist at different resolutions – a macro level variation between the plots and micro level variation between the sub-plots nested within each plot. We develop a Bayesian hierarchical framework for this setting. Flexible classes of models result which are fitted using simulation-based methods.     

Habitat selection models to account for seasonal persistence in radio telemetry data

Models for the analysis of habitat selection data incorporate covariates in an independent multinomial selections model (McCracken et al. 1998) Ramsey and Usner 2003 and an extension of that model to include a persistence parameter (2003). In both cases, all parameters are assumed to be fixed through time. Radio telemetry data collected for habitat selection studies typically consist of animal relocations through time, suggesting the need for an extension to these models. We use a Bayesian approach that allows for the habitat selection probabilities, persistence parameter, or both, to change with season. These extensions are particularly important when movement patterns are expected to differ seasonally and/or when availabilities of habitats change throughout the study period due to weather or migration. We implement and compare the models using radio telemetry data for westslope cutthroat trout in two streams in eastern Oregon.     

Interpolation performance of a spatio-temporal model with spatially varying coefficients: application to PM<Subscript>10</Subscript> concentrations in Rio de Janeiro

In this work we present a Bayesian analysis in linear regression models with spatially varying coefficients for modeling and inference in spatio-temporal processes. This kind of model is particularly appealing in situations where the effect of one or more explanatory processes on the response present substantial spatial heterogeneity. We describe for this model how to make inference about the regression coefficients and response processes under two scenarios: when the explanatory processes are known throughout the study region, and when they are known only at the sampling locations. Using a simulation experiment we investigate how parameter inference and interpolation performance are affected by some features of the data and prior distribution that is used. The proposed methodology is used to model the dataset on PM₁₀ levels in the metropolitan region of Rio de Janeiro presented in Paez and Gamerman (2003).     

基于贝叶斯网络的城市地下燃气管网动态风险分析

为研究城市燃气管网风险的动态性,针对传统风险分析方法的局限性,提出基于贝叶斯网络的燃气管网动态风险分析方法。构建燃气管网失效蝴蝶结模型并将其转化为贝叶斯网络模型;在事故发生状态下更新事件失效概率,识别出关键因素;根据异常事件数据和贝叶斯理论,对基本事件失效概率进行实时动态改变;随之更新管网失效及各后果发生的概率,从而实现管网的动态风险分析。研究结果表明:该方法克服了传统风险分析方法的不足,可动态反映燃气管网失效和事故后果发生概率随时间变化的特征,能够为城市地下燃气管网的风险分析与事故预防提供参考。     

Resilience-based optimal firefighting to prevent domino effects in process plants

Domino effects triggered by fire can cause extremely severe damages to the chemical and process plants. In the need of a more effective prevention of fire domino effects, the present study focuses on firefighting which has received less attention compared to passive and active fire protection systems. Considering both the vulnerability and recoverability phases during fire domino effects, we have introduced a methodology for optimal identification of firefighting strategies so as to increase the resiliency of process plants in dealing with fire escalation scenarios. The area above the resilience curve (AARC), which is equal to the accumulation of loss of resilience over time, was considered as the metric to identify the optimal firefighting strategies. In other words, the strategy leading to the lowest AARC can be selected as the optimal strategy from a resiliency perspective.     

Developing a risk-based maintenance model for a Natural Gas Regulating and Metering Station using Bayesian Network

During the last decades, the vital role of maintenance activities in industries including natural gas distribution system has cleared up progressively. High costs may induce to reduced maintenance and, in turn, lead to a lower availability and high risk of undesired events. Therefore, a probabilistic model, based on an acceptable level of risk, is required to avoid under and over estimation of maintenance time interval. This paper presents an advanced Risk-based Maintenance (RBM) methodology to optimize maintenance time schedule. Bayesian Network (BN) is applied to model the risk and the associated uncertainty. The developed method can assist the asset managers to work out the exact maintenance time for each component according to the risk level. To demonstrate and discuss the applicability of the methodology, a case study of Natural Gas Reduction and Measuring Station in Italy is considered. Results prove that the most critical components are the calculator and pilots, while the most reliable one is the odorization. Furthermore, the pressure and temperature gauge (PTG), the remote control system (RCS) and the meter are predicted as the components that require less time to transit from minor risk to catastrophic risk.     

An integrated model for vent area design of hydrocarbon-air mixture explosion inside cubic enclosures with obstacles

This study aims to develop an integrated model - NFPA-68-BRANN model, which can be used to calculate the vent areas of cubic enclosures with obstacles. Seven experiments regarding vented explosion inside the obstructed enclosure are reviewed and applied to check the accuracy of two existing standards, i.e. the NFPA-68 2018 and the BS EN 14994:2007. Accordingly, the parameters to describe the flame development in the NFPA-68 2018 are amended by adopting the Bauwens model. Bayesian Regularization Artificial Neuron Network (BRANN) model presenting the non-linear relationship between the turbulent flame enhancement factor X and its affecting factors is subsequently developed. Eventually, the NFPA-68-BRANN model is generated by incorporating the BRANN model into the modified NFAP-68 2018. The accuracy of the NFPA-68-BRANN model is validated by using a series of the New Baker Test data.