内河船舶航行实时风险辨识及路径规划研究——以灌河为例

    Study on real-time risk identification and route planning of inland vessel navigation: a case study of Guanhe River

    • 摘要: 随着内河航运规模和交通流量的持续增长,船舶在狭窄航道、多障碍物航道及复杂水文条件下的航行风险不断增加,对航行安全保障与路径规划精度提出了更高要求。现有船舶路径规划方法多面向海洋或开阔水域,针对内河复杂通航环境的研究相对不足。此外,多源外部环境因素考虑不充分,且在多障碍或狭窄水域中易出现收敛速度慢、规划效率低等问题,难以满足内河船舶安全性与实时性的航行需求。针对上述问题,以江苏灌河为研究对象,提出一种面向内河水域的船舶航行实时风险辨识与路径规划方法。基于RFRM机理,从静态特征、动态特征、自然环境、通航环境和人为因素等5个方面构建航行风险指标体系。采用AHP-Critic融合赋权法与客观赋权方法相结合的策略确定指标权重,将研究水域划分为规则网格单元,实现航行风险等级的空间量化。在此基础上,将风险评估结果引入人工势场模型,通过改进势场函数并引入航道规则与障碍物约束,实现风险规避与通航可行性的统一。仿真结果表明:所提方法能够有效规避高风险水域,并具备一定的动态响应能力,生成路径符合《内河避碰规则》等相关规范。研究可为内河船舶航行实时决策支持与水上交通安全管理提供技术支撑,具有较好的工程应用价值。

       

      Abstract: With the continuous expansion of inland waterway transportation and increasing traffic density,vessels navigating in narrow channels with multiple obstacles and complex hydrological conditions are exposed to growing navigation risks,posing higher requirements for navigation safety assurance and path planning accuracy. Existing ship path planning methods are mainly developed for marine or open waters,while studies focusing on complex inland navigation environments remain limited. Moreover,external environmental factors are often insufficiently considered,leading to slow convergence and low planning efficiency in narrow or obstacle-dense waterways,which makes it difficult to satisfy the requirements for safety and real-time navigation of inland vessels. To address these issues,this study takes the Guanhe River in Jiangsu Province as the study area and proposes a real-time navigation risk identification and path planning method for inland waterways. Based on the RFRM, a navigation risk indicator system is established from five aspects: static characteristics, dynamic characteristics, natural environment, navigation environment, and human factors. An integrated weighting strategy combining the Analytic Hierarchy Process and the CRITIC method is employed to determine indicator weights,and the study area is discretized into regular grid cells to achieve spatial quantification of navigation risk levels. On this basis,the risk assessment results are incorporated into an artificial potential field model. By improving the potential field functions and introducing navigation rules and obstacle constraints,a unified framework for risk avoidance and navigational feasibility is achieved. Simulation results demonstrate that the proposed method can effectively avoid high-risk areas and exhibits a certain level of dynamic responsiveness. The generated paths comply with the Inland Collision Avoidance Regulations. The proposed approach provides technical support for real-time decision-making in inland vessel navigation and waterway traffic safety management,showing good engineering applicability.

       

    /

    返回文章
    返回