文章设计了一种智能型航海避碰系统，即航海智能避碰专家系统。该系统具有多元分层知识库体系结构，采用框架、产生式规则、过程及神经网络等多种知识表示形式，实现了航海避碰知识的表示、存储。建立了基于演绎推理、类比推理、换位推理、神经网络复合推理及元级推理的多路推理机制，克服单一推理的不足。分别建立了碰撞危险度、避让时机及会遇态势分类g型。提出基于层次分析法的多船会遇避让方案选取策略，建立了最优化数学模型。仿真试验表明：系统能对各种避碰情况给出正确的避让方案。

The purpose of this thesis is to developing and exploiting an intelligent system for collision prevention, namely “Intelligent Collision Prevention Expert System for Navigation”(NICPES). The NICPES has a multi-unit and layering Knowledge Base systematic structure and a multi-unit Knowledge Representation (KR) which based on frame KR, production rule KR, procedure KR and neural network KR, to represent and store all kinds of knowledge for navigation collision prevention. The NICPES also builds a multi-inference system, which based on analogy inference, forward illation inference, conversion inference, neural network inference and meta-rule inference, to overcome the shortcoming of unitary inference. For-some problems in collision prevention region, the NICPES builds a set of models to solve them. These models comprise the models of judging collision risk, the model of determining collision prevention time and the model of classifying encounter situation. For multi-ship encounter situation, the NICPES puts forward a tactics to choose optimal collision prevention scheme based on Analytic Hierarchy Process (AHP) and builds a mathematical model that will be used to determine the optimal angle and sailing time during ship's turning for multi and single ship encounter situation. The simulation experiments show that the NICPES can analyze and judge various sailing cases and encounter situation ,and offer a reasonable scheme, which settle the collision problem effectively and ensure the sailing safety.