基于TS算法的FPN鱼雷电子系统故障诊断方法

Torpedo electronic system fault diagnosis with fuzzy Petri net based on tabu search algorithm

针对鱼雷电子系统故障传播的连续性,以及故障征兆与故障原因之间的模糊不确定性特点,提出一种基于禁忌搜索算法的模糊Petri网的鱼雷电子系统故障诊断方法。该方法定义了一个十元组的模糊Petri网,给出了表示模糊产生式规则的三种基本的模糊Petri网模型,在此基础上采用禁忌搜索算法对模糊Petri网模型参数进行优化。当模糊Petri网模型参数得到优化后,根据库所信度的大小通过故障推理进行故障定位。将其应用到某型鱼雷电子系统的故障诊断系统中,结果表明,该方法能够有效的提高模型故障诊断能力,具有较强的实用性。

According to the characteristics of torpedo electronic system fault propagation continuities, uncertainties and fuzziness between fault symptoms and fault causes, a method of torpedo electronic system fault diagnosis with fuzzy Petri net based on tabu search algorithm is proposed to solve the problem. The paper defines 10-tuples as the fuzzy Petri net structure and gives 3 basic kinds of fuzzy Petri net models for the representation of fuzzy production rules. Then the parameters of fuzzy Petri net models are optimized by tabu search algorithm. When the parameters of fuzzy Petri nets are optimized, the fault cause can be found through fault inference. The proposed method is applied in the fault diagnosis system of a torpedo electronic system. Results show that the method can improve the ability of model fault diagnosis with very strong practicality.