The water distribution network is an important part of the plain water environment improvement system. To make efficient use of the regional water diversion source, scientifically distribute the water diversion flow a...The water distribution network is an important part of the plain water environment improvement system. To make efficient use of the regional water diversion source, scientifically distribute the water diversion flow and improve the water environment carrying capacity of Haishu Plain, the river network hydrodynamic model is used in this paper to simulate the water intake location, reasonable water quantity and influence range of water transfer in Haishu Plain. The simulation results have high accuracy, which can provide a scientific basis for the scale, water transfer mechanism and project layout of water transfer construction in Haishu Plain and show a strong reference value for the study of water diversion and distribution scheme of coastal plain river network.展开更多
水利工程传统应急方案存在数字化程度低、内容关联性差、智能辅助决策不足等问题。本文利用知识图谱和深度学习技术,创建一种水利工程应急方案智能生成模式。首先基于风险防控手册及险情抢险应急方案等文本,提出应急方案知识图谱本体模...水利工程传统应急方案存在数字化程度低、内容关联性差、智能辅助决策不足等问题。本文利用知识图谱和深度学习技术,创建一种水利工程应急方案智能生成模式。首先基于风险防控手册及险情抢险应急方案等文本,提出应急方案知识图谱本体模型,构建应急方案知识图谱,实现应急方案文本中非结构信息的结构化表达。其次,基于水利工程巡检文本,利用BERT(Bi-directional Encoder Representation from Transformers)+BiLSTM+CRF(Bi-directional Long Short Term Memory with Conditional Random Fields)实体识别模型,智能识别巡检文本中的风险事件、工程等实体。最后,设计应急方案智能生成模板,通过多特征融合的实体对齐技术、知识检索与推理技术,实现应急方案的智能生成与推送。通过模型准确性分析以及“渠道渗漏”等实例验证,本文方法识别准确率高(F 1值为96.21%),生成的应急方案可靠,可推广到水利工程应急抢险以及应急预案智能生成等应急管理工作中。展开更多
文摘The water distribution network is an important part of the plain water environment improvement system. To make efficient use of the regional water diversion source, scientifically distribute the water diversion flow and improve the water environment carrying capacity of Haishu Plain, the river network hydrodynamic model is used in this paper to simulate the water intake location, reasonable water quantity and influence range of water transfer in Haishu Plain. The simulation results have high accuracy, which can provide a scientific basis for the scale, water transfer mechanism and project layout of water transfer construction in Haishu Plain and show a strong reference value for the study of water diversion and distribution scheme of coastal plain river network.
文摘水利工程传统应急方案存在数字化程度低、内容关联性差、智能辅助决策不足等问题。本文利用知识图谱和深度学习技术,创建一种水利工程应急方案智能生成模式。首先基于风险防控手册及险情抢险应急方案等文本,提出应急方案知识图谱本体模型,构建应急方案知识图谱,实现应急方案文本中非结构信息的结构化表达。其次,基于水利工程巡检文本,利用BERT(Bi-directional Encoder Representation from Transformers)+BiLSTM+CRF(Bi-directional Long Short Term Memory with Conditional Random Fields)实体识别模型,智能识别巡检文本中的风险事件、工程等实体。最后,设计应急方案智能生成模板,通过多特征融合的实体对齐技术、知识检索与推理技术,实现应急方案的智能生成与推送。通过模型准确性分析以及“渠道渗漏”等实例验证,本文方法识别准确率高(F 1值为96.21%),生成的应急方案可靠,可推广到水利工程应急抢险以及应急预案智能生成等应急管理工作中。
