| 基于时序片段的油气管道运行工况识别方法* |
| |
| 引用本文： | 张丽,苏怀,范霖,江璐鑫,张劲军.基于时序片段的油气管道运行工况识别方法*[J].中国安全生产科学技术,2022,18(11):99-104. |
| |
| 作者姓名： | 张丽 苏怀 范霖 江璐鑫 张劲军 |
| |
| 作者单位： | （1.中国石油大学（北京） 油气管道输送安全国家工程实验室，北京 102249；2.中国石油大学（北京） 城市油气输配技术北京市重点实验室，北京 102249） |
| |
| 基金项目： | * 基金项目: 国家自然科学基金项目(51904316)；中国石油大学（北京）科学基金项目(2462021YJRC013,2462020YXZZ045) |
| |
| 摘 要： | 为准确识别管道系统运行工况，提高对油气管道突发事故的响应速度，综合提升管网安全管理水平，提出1种基于时序片段的油气管道运行工况识别方法。首先，构建基于概率分布的状态变化识别模型，提取油气管道中不同运行状态点；其次，建立基于时间序列片段的工况识别模型，快速识别不同时间长度内油气管道运行工况；最后，以国内某成品油管道为例进行方法验证。研究结果表明:该方法可有效识别成品油管道阀门开关状态、泵异常停机和阀门内漏3种运行工况。对比传统的识别方法，该方法可降低状态变化点的漏报率，提升管道运行工况识别的准确率。研究结果可为油气管道系统运行工况识别提供新的借鉴方法。
|
| 关 键 词： | 油气管道 时序片段 工况识别 智能化 |
Recognition method on operating conditions of oil and gas pipelines based on sequential segment |
| |
| ZHANG Li,SU Huai,FAN Lin,JIANG Luxin,ZHANG Jinjun.Recognition method on operating conditions of oil and gas pipelines based on sequential segment[J].Journal of Safety Science and Technology,2022,18(11):99-104. |
| |
| Authors: | ZHANG Li SU Huai FAN Lin JIANG Luxin ZHANG Jinjun |
| |
| Affiliation: | (1.National Engineering Laboratory for Oil and Gas Pipeline Transportation Safety,China University of Petroleum,Beijing 102249,China;2.Beijing Key Laboratory of Urban Oil and Gas Transmission and Distribution Technology,China University of Petroleum,Beijing 102249,China) |
| |
| Abstract: | In order to accurately identify the operating conditions of pipeline system,improve the response speed to unexpected accidents,and comprehensively enhance the safety management level of pipeline network,a recognition method on the operating conditions of oil and gas pipelines based on the sequential segment was proposed.Firstly,a recognition model of state change based on probability distribution was constructed to extract the points with different operating states in the oil and gas pipeline.Then,a condition recognition method based on the sequential segment was established,which could quickly identify the operating conditions of oil and gas pipeline in different time intervals.Finally,the proposed method was validated by taking a domestic product oil pipeline as an example.The results showed that the method could effectively identify the operating conditions of oil and gas pipeline such as the valve opening state,valve internal leakage and pump abnormal shutdown.Compared with the traditional recognition methods,the recognition method of state change point had lower missing report rate,and the accuracy of condition recognition method based on the sequential segment was improved.The results can provide a new methodological reference for the recognition of operating conditions of the oil and gas pipeline systems. |
| |
| Keywords: | oil and gas pipeline sequential segment operating condition recognition intelligence |
|
| 点击此处可从《中国安全生产科学技术》浏览原始摘要信息 |
|
点击此处可从《中国安全生产科学技术》下载全文 |
|
