基于南水北调工程巡检专报结合专家经验构建巡检知识图谱概念模型,在此基础上利用实体关系联合抽取框架进行巡检知识抽取,并以Neo4j图数据库为载体进行巡检知识图谱可视化。基于巡检知识图谱进行南水北调工程巡检信息推荐,利用BERT(Bi-d...基于南水北调工程巡检专报结合专家经验构建巡检知识图谱概念模型,在此基础上利用实体关系联合抽取框架进行巡检知识抽取,并以Neo4j图数据库为载体进行巡检知识图谱可视化。基于巡检知识图谱进行南水北调工程巡检信息推荐,利用BERT(Bi-directional encoder representation from transformers)预训练模型设计BERT孪生网络,通过知识检索及字符串相似度计算等技术,实现关联工程风险信息推荐,以辅助巡检人员进行工程风险等级诊断。通过实验评估了知识抽取及字符串相似度计算模型的准确性,知识抽取F1值达到88.42%,字符串相似度计算F1值为86.00%。该方法可提高南水北调工程风险管理能力、推动工程运维的数字化发展。展开更多
In order to understand how the uncertainties in the output can be apportioned to different sources of uncertainties in its inputs, it is critical to investigate the sensitivity of MOVES model. The MOVES model sensitiv...In order to understand how the uncertainties in the output can be apportioned to different sources of uncertainties in its inputs, it is critical to investigate the sensitivity of MOVES model. The MOVES model sensitivity for regional level has been well studied. However, the uncertainty analysis for project level running emissions has not been well understood. In this research, the MOVES model project level sensitivity tests on running emissions were conducted thru the analysis of vehicle specific power （VSP）, scaled tractive power （STP）, and MOVES emission rates versus speed curves. This study tested the speed, acceleration, and grade-three most critical variables for vehicle specific power for light duty vehicles and scaled tractive power for heavy duty vehicles. For the testing of STP, four regulatory classes of heavy duty vehicles including light heavy duty （LHD）, medium heavy duty （MHD）, heavy heavy duty （HHD） and bus were selected. MOVES project running emission rates were also tested for CO, PM2.5, NOx, and VOC versus the operating speeds. A Latin Hypercube （LH） sampling based on method for estimation of the ＂Sobal＂ sensitivity indices shows that the speed is the most critical variable among the three inputs for both VSP and STP. Acceleration and grades show lower response to the main effects and sensitivity indices. MOVES emission rates versus speeds curves for light duty vehicles show that highest emission occurs at lower speed range. No significant differences on emission rates among the regulatory classes of heavy duty vehicles are identified.展开更多
文摘基于南水北调工程巡检专报结合专家经验构建巡检知识图谱概念模型,在此基础上利用实体关系联合抽取框架进行巡检知识抽取,并以Neo4j图数据库为载体进行巡检知识图谱可视化。基于巡检知识图谱进行南水北调工程巡检信息推荐,利用BERT(Bi-directional encoder representation from transformers)预训练模型设计BERT孪生网络,通过知识检索及字符串相似度计算等技术,实现关联工程风险信息推荐,以辅助巡检人员进行工程风险等级诊断。通过实验评估了知识抽取及字符串相似度计算模型的准确性,知识抽取F1值达到88.42%,字符串相似度计算F1值为86.00%。该方法可提高南水北调工程风险管理能力、推动工程运维的数字化发展。
基金support by U.S.Environmental Protection AgencyOhio Department of Transportation
文摘In order to understand how the uncertainties in the output can be apportioned to different sources of uncertainties in its inputs, it is critical to investigate the sensitivity of MOVES model. The MOVES model sensitivity for regional level has been well studied. However, the uncertainty analysis for project level running emissions has not been well understood. In this research, the MOVES model project level sensitivity tests on running emissions were conducted thru the analysis of vehicle specific power （VSP）, scaled tractive power （STP）, and MOVES emission rates versus speed curves. This study tested the speed, acceleration, and grade-three most critical variables for vehicle specific power for light duty vehicles and scaled tractive power for heavy duty vehicles. For the testing of STP, four regulatory classes of heavy duty vehicles including light heavy duty （LHD）, medium heavy duty （MHD）, heavy heavy duty （HHD） and bus were selected. MOVES project running emission rates were also tested for CO, PM2.5, NOx, and VOC versus the operating speeds. A Latin Hypercube （LH） sampling based on method for estimation of the ＂Sobal＂ sensitivity indices shows that the speed is the most critical variable among the three inputs for both VSP and STP. Acceleration and grades show lower response to the main effects and sensitivity indices. MOVES emission rates versus speeds curves for light duty vehicles show that highest emission occurs at lower speed range. No significant differences on emission rates among the regulatory classes of heavy duty vehicles are identified.
