论文部分内容阅读
应用人工智能技术产生高速公路事件响应预案,提出了基于规则推理、案例推理和贝叶斯网络推理3种方法的事件响应框架.首先,建立了基于规则推理的高速公路事件管理系统(RK-IMS),并应用于宁连高速公路北段事件管理过程中.然后,通过分析RK-IMS系统2年的运营数据,确定了事件案例的结构表示与事件响应的贝叶斯网络结构.最后,应用k近邻算法计算相似性案例,并研究了基于该算法的预案产生和控制策略.利用2006年RK-IMS事件管理系统的实际数据对模型进行了验证.对比分析结果表明,该方法是有效可信的.
The application of artificial intelligence (AI) technology to generate highway incident response plans, an incident response framework based on rule reasoning, case reasoning and Bayesian network reasoning is proposed.Firstly, a rule-based in-highway incident management system (RK-IMS ) And applied to the event management of the northern section of Ning-Lian Freeway.Then, by analyzing the operating data of RK-IMS for 2 years, the structure of event case and the Bayesian network structure of event response were determined.Finally, k nearest neighbor algorithm is used to calculate the similarity case and the plan generation and control strategy based on this algorithm are studied.The model is validated by the actual data of RK-IMS event management system in 2006. The comparative analysis shows that this method is effective and credible of.