中国石油大学学报（自然科学版）
中國石油大學學報（自然科學版）
중국석유대학학보（자연과학판）
JOURNAL OF CHINA UNIVERSITY OF PETROLEUM(EDITION OF NATURAL SCIENCE)
2015年
3期
149-155
,共7页
长输管道%腐蚀%泄漏%蒸气云爆炸%贝叶斯网络
長輸管道%腐蝕%洩漏%蒸氣雲爆炸%貝葉斯網絡
장수관도%부식%설루%증기운폭작%패협사망락
long-distance oil and gas pipeline%corrosion%leak%vapor cloud explosion%Bayesian network
为了研究长输管道腐蚀泄漏及蒸气云爆炸事故的演化规律，通过对埋地管道内(外)壁腐蚀失效、燃气泄漏、气体云团扩散及蒸气云爆炸等4阶段事件进行分析，构建埋地管线腐蚀泄漏火灾的贝叶斯网络模型。研究网络结构中节点变量的取值范围及离散化方法，并基于对事故统计和专家分析判断，设定节点变量的先验概率，量化节点关联的条件概率分布。在对贝叶斯网络推理策略研究的基础上，考察节点变量对推理结果的敏感性，验证模型的合理性。结果表明，长输管道腐蚀泄漏及次生灾害事件过程具有较大的不确定性，主要体现在中间事件均具有多种状态，事故演化路径概率受模型输入条件影响较大。贝叶斯网络方法用于描述事故过程中间节点事件间的依赖关系有较大的优势，可以定量衡量事故风险的不确定性。
為瞭研究長輸管道腐蝕洩漏及蒸氣雲爆炸事故的縯化規律，通過對埋地管道內(外)壁腐蝕失效、燃氣洩漏、氣體雲糰擴散及蒸氣雲爆炸等4階段事件進行分析，構建埋地管線腐蝕洩漏火災的貝葉斯網絡模型。研究網絡結構中節點變量的取值範圍及離散化方法，併基于對事故統計和專傢分析判斷，設定節點變量的先驗概率，量化節點關聯的條件概率分佈。在對貝葉斯網絡推理策略研究的基礎上，攷察節點變量對推理結果的敏感性，驗證模型的閤理性。結果錶明，長輸管道腐蝕洩漏及次生災害事件過程具有較大的不確定性，主要體現在中間事件均具有多種狀態，事故縯化路徑概率受模型輸入條件影響較大。貝葉斯網絡方法用于描述事故過程中間節點事件間的依賴關繫有較大的優勢，可以定量衡量事故風險的不確定性。
위료연구장수관도부식설루급증기운폭작사고적연화규률，통과대매지관도내(외)벽부식실효、연기설루、기체운단확산급증기운폭작등4계단사건진행분석，구건매지관선부식설루화재적패협사망락모형。연구망락결구중절점변량적취치범위급리산화방법，병기우대사고통계화전가분석판단，설정절점변량적선험개솔，양화절점관련적조건개솔분포。재대패협사망락추리책략연구적기출상，고찰절점변량대추리결과적민감성，험증모형적합이성。결과표명，장수관도부식설루급차생재해사건과정구유교대적불학정성，주요체현재중간사건균구유다충상태，사고연화로경개솔수모형수입조건영향교대。패협사망락방법용우묘술사고과정중간절점사건간적의뢰관계유교대적우세，가이정량형량사고풍험적불학정성。
In order to research evolutionary laws of unconfined vapor cloud explosion ( UVCE) induced by combustible gas leak in long-distance oil and gas pipelines, Bayesian networks on buried pipelines corrosion leak fire were built by analyzing event nodes on inner and outer wall corrosion failure, combustible gas leak, the gas cloud diffusion and UVCE. The state ranges and discrete methods of node variables were studied. Priori probability and conditional probability distribution of the node variables were set by analyzing on accident statistics data and expert judgements. Bayesian network inference strategy was developed, the sensitivities of each network node variable on inference results were analyzed by researching on evolution mechanism of corrosion leak fire, and the rationality of the model was verified. The results show that there are greater uncer-tainty in the process of pipeline corrosion leaks and secondary disaster. The uncertainty presents in diverse intermediate event status value and probability of accident evolutionary path is influenced by the model input conditions. Bayesian network ap-proach has a greater advantage to describe the dependency relations of accident intermediate nodes, and it can be used to measure uncertainties of accidents risk quantitatively.
